Search Results

V8 Diagnostic Ultrasound System; cV8 Diagnostic Ultrasound System; V7 Diagnostic Ultrasound System; cV7 Diagnostic Ultrasound System; V6 Diagnostic Ultrasound System; cV6 Diagnostic Ultrasound System:

The diagnostic ultrasound system and probes are designed to obtain ultrasound images and analyze body fluids. The clinical applications include: Fetal/Obstetrics, Abdominal, Gynecology, Intra-operative, Pediatric, Small Organ, Neonatal Cephalic, Adult Cephalic, Trans-rectal, Trans-vaginal, Muscular-Skeletal (Conventional, Superficial), Urology, Cardiac Adult, Cardiac Pediatric, Thoracic, Trans-esophageal (Cardiac) and Peripheral vessel. It is intended for use by, or by the order of, and under the supervision of, an appropriately trained healthcare professional who is qualified for direct use of medical devices. It can be used in hospitals, private practices, clinics and similar care environment for clinical diagnosis of patients. Modes of Operation: 2D mode, Color Doppler mode, Power Doppler (PD) mode, M mode, Pulsed Wave (PW) Doppler mode, Continuous Wave (CW) Doppler mode, Tissue Doppler Imaging (TDI) mode, Tissue Doppler Wave (TDW) mode, ElastoScan Mode, Combined modes, Multi-Image mode(Dual, Quad), 3D/4D mode.

V5 Diagnostic Ultrasound System; cV5 Diagnostic Ultrasound System; V4 Diagnostic Ultrasound System; cV4 Diagnostic Ultrasound System:

The diagnostic ultrasound system and probes are designed to obtain ultrasound images and analyze body fluids. The clinical applications include: Fetal/Obstetrics, Abdominal, Gynecology, Intra-operative, Pediatric, Small Organ, Neonatal Cephalic, Adult Cephalic, Trans-rectal, Trans-vaginal, Muscular-Skeletal (Conventional, Superficial), Urology, Cardiac Adult, Cardiac Pediatric, Thoracic, Trans-esophageal (Cardiac), Peripheral vessel and Dermatology. It is intended for use by, or by the order of, and under the supervision of, an appropriately trained healthcare professional who is qualified for direct use of medical devices. It can be used in hospitals, private practices, clinics and similar care environment for clinical diagnosis of patients. Modes of Operation: 2D mode, Color Doppler mode, Power Doppler (PD) mode, M mode, Pulsed Wave (PW) Doppler mode, Continuous Wave (CW) Doppler mode, Tissue Doppler Imaging (TDI) mode, Tissue Doppler Wave (TDW) mode, ElastoScan Mode, Combined modes, Multi-Image mode(Dual, Quad), 3D/4D mode, MV-Flow Mode.

■ V8/cV8, V7/cV7, V6/cV6
The V8/cV8, V7/cV7, V6/cV6 Diagnostic Ultrasound Systems are general purpose, mobile, software controlled, diagnostic ultrasound systems. Its function is to acquire ultrasound data and to display the data as 2D mode, Color Doppler mode, Power Doppler (PD) mode, M mode, Pulsed Wave (PW) Doppler mode, Continuous Wave (CW) Doppler mode, Tissue Doppler Imaging (TDI) mode, Tissue Doppler Wave (TDW) mode, ElastoScan Mode, Combined modes, Multi-Image mode(Dual, Quad), 3D/4D mode. The V8/cV8, V7/cV7, V6/cV6 also give the operator the ability to measure anatomical structures and offers analysis packages that provide information that is used to make a diagnosis by competent health care professionals. The V8/cV8, V7/cV7, V6/cV6 have real time acoustic output display with two basic indices, a mechanical index and a thermal index, which are both automatically displayed.

■ V5/cV5, V4/cV4
The V5/cV5, V4/cV4 Diagnostic Ultrasound Systems are general purpose, mobile, software controlled, diagnostic ultrasound systems. Its function is to acquire ultrasound data and to display the data as B-mode, M-mode, Pulsed wave (PW) Doppler, Continuous wave (CW) Doppler, Color Doppler, Tissue Doppler Imaging (TDI), Tissue Doppler Wave (TDW), Power Amplitude Doppler, Pulse Inversion Harmonic Imaging (S-Harmonic), Directional Power Doppler (S-Flow), Color M-Mode, 3D Imaging Mode, 4D Imaging Mode, Elastoscan+ Mode, Tissue Harmonic Imaging, MV-Flow Mode or as a combination of these modes. The V5/cV5, V4/cV4 diagnostic ultrasound systems also give the operator the ability to measure anatomical structures and offer analysis packages that provide information that is used to make a diagnosis by competent health care professionals. The V5/cV5, V4/cV4 diagnostic ultrasound systems have a real time acoustic output display with two basic indices, a mechanical index and a thermal index, which are both automatically displayed.

The provided FDA 510(k) clearance letter describes the Samsung Medison Ultrasound Systems (V8/cV8, V7/cV7, V6/cV6, V5/cV5, V4/cV4) and their AI-powered features: BiometryAssist, ViewAssist, HeartAssist (fetus), and EzNerveMeasure of NerveTrack.

Below is a breakdown of the acceptance criteria and study details for each AI feature, based on the provided text.

BiometryAssist

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size for Test Set and Data Provenance

• Individual Patients: 52 (17 from South Korea, 35 from the US)
• Images: 320 static images
• Data Provenance: Mix of retrospective and prospective data collection from hospitals in South Korea and the United States.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: 3 (one obstetrician, two sonographers) + 1 senior obstetrician for supervision.
• Qualifications:
  • One obstetrician with over 20 years of experience in fetal cardiology.
  • Two sonographers, each with more than 10 years of experience.
  • One senior obstetrician with over 25 years of clinical experience (supervised and corrected annotations).

4. Adjudication Method for Test Set

• Expert reviewers manually performed view classification and measurements following the same protocol as used during actual device operation. The entire process was supervised by a senior obstetrician who reviewed and corrected all annotations to ensure consistency and accuracy. This implies an expert consensus-based adjudication, likely 3+1 or similar, though not explicitly stated as a formal (X+Y) method.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• Not explicitly mentioned. The study focuses on standalone algorithm performance against expert ground truth.

6. Standalone Performance (Algorithm Only)

• Yes, performance metrics (Dice-score, error rates) are reported for the algorithm's output compared to established ground truth.

7. Type of Ground Truth Used

• Expert Consensus: Ground truth was established by expert reviewers manually classifying views and performing measurements, supervised and corrected by a senior obstetrician. This closely reflects the clinical use environment.

8. Sample Size for Training Set

• Not specified. The document only states that data used for training, tuning, and validation were completely separated.

9. How Ground Truth for Training Set Was Established

• All images used for training and tuning were first classified into the correct ultrasound views by three participating experts. Following view classification, the corresponding anatomical structures were manually annotated for each image.

ViewAssist

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size for Test Set and Data Provenance

• Individual Patients: 102 (42 from South Korea, 60 from the US)
• Images: 680 static images
• Data Provenance: Mix of retrospective and prospective data collection from hospitals in South Korea and the United States.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: 3 (one obstetrician, two sonographers) + 1 senior obstetrician for supervision.
• Qualifications:
  • One obstetrician with over 20 years of experience in fetal cardiology.
  • Two sonographers, each with more than 10 years of experience.
  • One senior obstetrician with over 25 years of clinical experience (supervised and corrected annotations).

4. Adjudication Method for Test Set

• Expert reviewers manually performed view classification and measurements following the same protocol as used during actual device operation. The entire process was supervised by a senior obstetrician who reviewed and corrected all annotations to ensure consistency and accuracy. This implies an expert consensus-based adjudication, likely 3+1 or similar.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• Not explicitly mentioned. The study focuses on standalone algorithm performance against expert ground truth.

6. Standalone Performance (Algorithm Only)

• Yes, performance metrics (sensitivity, specificity, Dice-score) are reported for the algorithm's output compared to established ground truth.

7. Type of Ground Truth Used

• Expert Consensus: Ground truth was established by expert reviewers manually classifying views and performing measurements, supervised and corrected by a senior obstetrician. This closely reflects the clinical use environment.

8. Sample Size for Training Set

• Not specified. The document only states that data used for training, tuning, and validation were completely separated.

9. How Ground Truth for Training Set Was Established

• All images used for training and tuning were first classified into the correct ultrasound views by three participating experts. Following view classification, the corresponding anatomical structures were manually annotated for each image.

HeartAssist (fetus)

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size for Test Set and Data Provenance

• Individual Patients: 70 (26 from South Korea, 44 from the US)
• Images: 280 static images
• Data Provenance: Mix of retrospective and prospective data collection from hospitals in South Korea and the United States.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: 3 (one obstetrician, two sonographers) + 1 senior obstetrician for supervision.
• Qualifications:
  • One obstetrician with over 20 years of experience in fetal cardiology.
  • Two sonographers, each with more than 10 years of experience.
  • One senior obstetrician with over 25 years of clinical experience (supervised and corrected annotations).

4. Adjudication Method for Test Set

• Expert reviewers manually performed view classification and measurements following the same protocol as used during actual device operation. The entire process was supervised by a senior obstetrician who reviewed and corrected all annotations to ensure consistency and accuracy. This implies an expert consensus-based adjudication, likely 3+1 or similar.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• Not explicitly mentioned. The study focuses on standalone algorithm performance against expert ground truth.

6. Standalone Performance (Algorithm Only)

• Yes, performance metrics (sensitivity, specificity, Dice-score, error rates) are reported for the algorithm's output compared to established ground truth.

7. Type of Ground Truth Used

• Expert Consensus: Ground truth was established by expert reviewers manually classifying views and performing measurements, supervised and corrected by a senior obstetrician. This closely reflects the clinical use environment.

8. Sample Size for Training Set

• Not specified. The document only states that data used for training, tuning, and validation were completely separated.

9. How Ground Truth for Training Set Was Established

• All images used for training and tuning were first classified into the correct ultrasound views by three participating experts. Following view classification, the corresponding anatomical structures were manually annotated for each image.

EzNerveMeasure of NerveTrack

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size for Test Set and Data Provenance

• Individual Patients: 20 (10 from South Korea, 10 from the US)
• Images: 200 static images (10 static images per patient from a 2D sequence)
• Data Provenance: Prospective data collected in clinical practice using Samsung ultrasound systems (RS80A and V8) from South Korea and the United States.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: 3 anesthesiologists + 1 senior anesthesiologist for resolution.
• Qualifications: All three anesthesiologists had over 10 years of experience. The senior anesthesiologist had over 10 years of extensive clinical experience in regional anesthesia and ultrasound-guided procedures.

4. Adjudication Method for Test Set

• The ground truth (GT) for median nerve locations was initially drawn by one anesthesiologist performing the ultrasound scans, then verified by the other two anesthesiologists. Disagreements were resolved by a senior anesthesiologist. This is a consensus-based adjudication process, effectively a 3+1 method for resolving disagreements.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• Not explicitly mentioned. The study focuses on standalone algorithm performance against expert ground truth.

6. Standalone Performance (Algorithm Only)

• Yes, performance metrics (average error rate, confidence interval, standard deviation) are reported for the algorithm's output compared to established ground truth.

7. Type of Ground Truth Used

• Expert Consensus: Ground truth (median nerve locations, FR, CSA measurements) was established by three anesthesiologists, with disagreements resolved by a senior anesthesiologist. A clinical evaluation was also conducted by experienced doctors to assess clinical significance.

8. Sample Size for Training Set

• Not specified. The document only states that data used for training, tuning, and validation were completely separated.

9. How Ground Truth for Training Set Was Established

• Not explicitly detailed for the training set itself, but it implies a similar expert annotation process as described for validation, with clear separation between data sets.

Ask a specific question about this device

The diagnostic ultrasound system and probes are designed to obtain ultrasound images and analyze body fluids. The clinical applications include: Fetal/Obstetrics, Abdominal, Gynecology, Intraoperative. Pediatric, Small Organ, Neonatal Cephalic, Trans-rectal, Trans-rectal, Trans-vaginal, Muscular-Skeletal (Conventional, Superficial), Urology, Cardiac Adult, Cardiac Pediatric, Thoracic, Trans-esophageal (Cardiac) and Peripheral vessel. It is intended for use by, or by the order of, and under the supervision of, an appropriately trained healthcare professional who is qualified for direct use of medical devices. It can be used in hospitals, private practices, clinics and similar care environment for clinical diagnosis of patients. Modes of Operation: 2D mode. Color Doppler mode, Power Doppler (PD) mode, M mode, Pulsed Wave (PW) Doppler mode, Continuous Wave (CW) Doppler mode. Tissue Doppler Imaging (TDI) mode. Tissue Doppler Wave (TDW) mode, ElastoScan Mode, Combined modes, Multi-Image mode(Dual, Quad), 3D/4D mode.

The V8/cV8, V7/cV7, V6/cV6 are a general purpose, mobile, software controlled, diagnostic ultrasound system. Their function is to acquire ultrasound data and to display the data as 2D mode, Color Doppler mode, Power Doppler (PD) mode, M mode, Pulsed Wave (PW) Doppler mode, Continuous Wave (CW) Doppler mode, Tissue Doppler Imaging (TDI) mode, Tissue Doppler Wave (TDW) mode, ElastoScan Mode, Combined modes, Multi-Image mode(Dual, Quad), 3D/4D mode. The V8/cV8, V7/cV7, V6/cV6 also give the operator the ability to measure anatomical structures and offer analysis packages that provide information that is used to make a diagnosis by competent health care professionals. The V8/cV8, V7/cV7, V6/cV6 have a real time acoustic output display with two basic indices, a mechanical index and a thermal index, which are both automatically displayed.

The provided text describes the acceptance criteria and study proving the device meets those criteria, specifically for the 'EzNerveMeasure' functionality of the V8/cV8, V7/cV7, V6/cV6 Diagnostic Ultrasound System.

Here's a breakdown of the requested information:

1. A table of acceptance criteria and the reported device performance

Note: The document states, "We tested on the flattening ratio (FR) and cross-sectional area (CSA) of NerveTrack EzNerveMeasure." and then presents the average error rates. While explicit acceptance criteria values are not given (e.g., "FR error

Ask a specific question about this device

The diagnostic ultrasound system and probes are designed to obtain ultrasound images and analyze body fluids.

The clinical applications include: Fetal/Obstetrics, Abdominal, Gynecology, Intra-operative, Pediatric, Small Organ, Neonatal Cephalic, Adult Cephalic, Trans-vaginal, Muscular-Skeletal (Conventional, Superficial), Urology, Cardiac Adult, Cardiac Pediatric, Thoracic, Peripheral vessel and Dermatology.

It is intended for use by, or by the order of, and under the supervision of, an appropriately trained healthcare professional who is qualified for direct use of medical devices. It can be used in hospitals, private practices, clinics and similar care environment for clinical diagnosis of patients.

Modes of Operation: 2D mode, Color Doppler mode, Power Doppler (PD) mode, M mode, Pulsed Wave (PW) Doppler mode, Continuous Wave (CW) Doppler mode, Tissue Doppler Imaging (TDI) mode, Tissue Doppler Wave (TDW) mode, ElastoScan Mode, Combined modes, Multi-Image mode(Dual, Quad), 3D/4D mode, MV-Flow Mode.

V5 Diagnostic Ultrasound System; H5 Diagnostic Ultrasound System; XV5 Diagnostic Ultrasound System: XH5 Diagnostic Ultrasound System; V4 Diagnostic Ultrasound System; H4 Diagnostic Ultrasound System: XV4 Diagnostic Ultrasound System; XH4 Diagnostic Ultrasound System are a general purpose, mobile, software controlled, diagnostic ultrasound system. Their function is to acquire ultrasound data and to display the data as 2D mode, Color Doppler mode, Power Doppler (PD) mode, M mode, Pulsed Wave (PW) Doppler mode, Continuous Wave (CW) Doppler mode, Tissue Doppler Imaging (TDI) mode, Tissue Doppler Wave (TDW) mode, ElastoScan Mode, Combined modes, MV-Flow mode, Multi-Image mode(Dual, Quad), 3D/4D mode. The V5/H5/XV5/XH5, V4/H4/XV4/XH4 diagnostic ultrasound system also give the operator the ability to measure anatomical structures and offer analysis packages that provide information that is used to make a diagnosis by competent health care professionals. The V5/H5/XV5/XH5, V4/H4/XV4/XH4 diagnostic ultrasound system have a real time acoustic output display with two basic indices, a mechanical index and a thermal index, which are both automatically displayed.

Here's a breakdown of the acceptance criteria and supporting study details for each AI-powered feature of the V5/H5/XV5/XH5 and V4/H4/XV4/XH4 Diagnostic Ultrasound Systems, as provided in the document:

HeartAssist (Fetal and Adult)

1. Table of Acceptance Criteria and Reported Device Performance:

2. Sample Sizes and Data Provenance:

• Test Set (Fetal):

  • Number of individuals: 80
  • Number of static images: 280
  • Provenance: Mix of retrospective and prospective data collection in clinical practice from five hospitals.
  • Country of Origin: Not explicitly stated, but clinical experts are from multiple countries including US and Korea, suggesting data could be from these regions.

• Test Set (Adult):

  • Number of individuals: 30
  • Number of static images: 540
  • Provenance: Mix of retrospective and prospective data collection in clinical practice from five hospitals.
  • Country of Origin: Not explicitly stated, but clinical experts are from multiple countries including US and Korea, suggesting data could be from these regions.

3. Number of Experts and Qualifications for Ground Truth:

• Fetal:

  • 3 participating experts:
    • 1 obstetrician with >20 years of experience (in fetal cardiology)
    • 2 sonographers with >10 years of experience (in fetal cardiology)
  • Supervised by: 1 obstetrician with >25 years of experience.

• Adult:

  • 4 experts:
    • 2 cardiologists with at least 10 years of experience
    • 2 sonographers with at least 10 years of experience.

4. Adjudication Method:

• Fetal: All acquired images were first classified into correct views by three participating experts. Afterwards, corresponding anatomy areas were manually drawn. The entire process was supervised by another obstetrician.
• Adult: Experts manually traced the contours of the heart and the signal outline on the images. (Implicitly, this suggests an expert consensus or expert-defined ground truth, but a specific adjudication method like "2+1" is not detailed.)

5. MRMC Comparative Effectiveness Study:

• No MRMC comparative effectiveness study was explicitly mentioned for evaluating human readers with and without AI assistance for HeartAssist. The study focused on standalone performance metrics against ground truth.

6. Standalone Performance Study:

• Yes, a standalone study was performed. The reported performance metrics (recognition accuracy, Dice-score, error rates, PCC values) are direct measurements of the algorithm's performance against expert-defined ground truth.

7. Type of Ground Truth Used:

• Expert consensus / Expert-defined outlines. For fetal images, experts classified views and manually drew anatomy areas. For adult images, cardiologists and sonographers manually traced contours. The PCC for adult size measurement was calculated against "the cardiologist's measurements."

8. Sample Size for Training Set:

• Not explicitly stated ("Data used for training, tuning and validation purpose are completely separated").

9. How Ground Truth for Training Set Was Established:

• Not explicitly stated, but it can be inferred that a similar expert-based process was used for generating ground truth for training data, as noted for the validation data: "All acquired images for training, tuning and validation were first classified into the correct views by three participating experts. Afterwards, corresponding anatomy areas were manually drawn..."

BiometryAssist (Fetal)

1. Table of Acceptance Criteria and Reported Device Performance:

2. Sample Sizes and Data Provenance:

• Test Set:
  • Number of individuals: 77
  • Number of static images: 320
  • Provenance: Mix of retrospective and prospective data collection in clinical practice from two hospitals.
  • Country of Origin: Americans and Koreans, suggesting data could be from these regions.

3. Number of Experts and Qualifications for Ground Truth:

• 3 participating experts:
  • 1 obstetrician with >20 years of experience (in fetal cardiology)
  • 2 sonographers with >10 years of experience (in fetal cardiology)
• Supervised by: 1 obstetrician with >25 years of experience.

4. Adjudication Method:

• All acquired images were first classified into the correct views by three participating experts. Afterwards, corresponding anatomy areas were manually drawn for each image. The entire process was supervised by another obstetrician.

5. MRMC Comparative Effectiveness Study:

• No MRMC comparative effectiveness study was explicitly mentioned.

6. Standalone Performance Study:

• Yes, a standalone study was performed. The reported performance metrics (Dice-score, error rates) are direct measurements of the algorithm's performance against expert-defined ground truth.

7. Type of Ground Truth Used:

• Expert consensus / Expert-defined outlines. Experts classified views and manually drew anatomy areas.

8. Sample Size for Training Set:

• Not explicitly stated ("Data used for training, tuning and validation purpose are completely separated").

9. How Ground Truth for Training Set Was Established:

• It's inferred that a similar expert-based process was used as for validation data: "All acquired images for training, tuning and validation were first classified into the correct views by three participating experts. Afterwards, corresponding anatomy areas were manually drawn..."

ViewAssist (Fetal)

1. Table of Acceptance Criteria and Reported Device Performance:

2. Sample Sizes and Data Provenance:

• Test Set:
  • Number of individuals: 77
  • Number of static images: 680
  • Provenance: Mix of retrospective and prospective data collection in clinical practice from two hospitals.
  • Country of Origin: Americans and Koreans, suggesting data could be from these regions.

3. Number of Experts and Qualifications for Ground Truth:

• 3 participating experts:
  • 1 obstetrician with >20 years of experience (in fetal cardiology)
  • 2 sonographers with >10 years of experience (in fetal cardiology)
• Supervised by: 1 obstetrician with >25 years of experience.

4. Adjudication Method:

• All acquired images were first classified into the correct views by three participating experts. Afterwards, corresponding anatomy areas were manually drawn for each image. The entire process was supervised by another obstetrician.

5. MRMC Comparative Effectiveness Study:

• No MRMC comparative effectiveness study was explicitly mentioned.

6. Standalone Performance Study:

• Yes, a standalone study was performed. The reported performance metrics (recognition accuracy, Dice-score) are direct measurements of the algorithm's performance against expert-defined ground truth.

7. Type of Ground Truth Used:

• Expert consensus / Expert-defined outlines. Experts classified views and manually drew anatomy areas.

8. Sample Size for Training Set:

• Not explicitly stated ("Data used for training, tuning and validation purpose are completely separated").

9. How Ground Truth for Training Set Was Established:

• It's inferred that a similar expert-based process was used as for validation data: "All acquired images for training, tuning and validation were first classified into the correct views by three participating experts. Afterwards, corresponding anatomy areas were manually drawn..."

UterineAssist

1. Table of Acceptance Criteria and Reported Device Performance:

2. Sample Sizes and Data Provenance:

• Test Set (Segmentation):

  • Number of static images: 450 sagittal uterus images and 150 transverse uterus images (total 600 images).
  • Number of individuals: 60 contributed to the validation dataset (for segmentation AND feature points/size measurement)
  • Provenance: Mix of retrospective and prospective data collection in clinical practice from three hospitals.
  • Country of Origin: All Koreans.

• Test Set (Feature Points Extraction & Size Measurement):

  • Number of static images: 48 sagittal and 44 transverse plane images of the uterus (total 92 images).
  • Number of individuals: 60 individuals contributed to the validation dataset (same as segmentation).
  • Provenance: Mix of retrospective and prospective data collection in clinical practice from three hospitals.
  • Country of Origin: All Koreans.

3. Number of Experts and Qualifications for Ground Truth:

• 3 participating OB/GYN experts with >10 years' experience.

4. Adjudication Method:

• Segmentation of the ground truth was generated by three participating OB/GYN experts. The image set was divided into three subsets, and each expert drew ground truths for one subset. Ground truths drawn by one expert were cross-checked by the other two experts. Any images not meeting inclusion/exclusion criteria were excluded.

5. MRMC Comparative Effectiveness Study:

• No MRMC comparative effectiveness study was explicitly mentioned.

6. Standalone Performance Study:

• Yes, a standalone study was performed. The reported performance metrics (Dice-score, error rates) are direct measurements of the algorithm's performance against expert-defined ground truth.

7. Type of Ground Truth Used:

• Expert consensus / Expert-drawn contours and measurements.

8. Sample Size for Training Set:

• Not explicitly stated ("Data used for test/training validation purpose are completely separated").

9. How Ground Truth for Training Set Was Established:

• It's inferred that a similar expert-based process was used as for validation data: "Segmentation of the ground truth was generated by three participating OB/GYN experts with more than 10 years' experience." This process for ground truth establishment is also applicable to training data generation.

NerveTrack (Nerve Detection)

1. Table of Acceptance Criteria and Reported Device Performance:

2. Sample Sizes and Data Provenance:

• Test Set:
  • Number of individuals: 22
  • Number of images: 3,999 (extracted from 2D sequences, with each individual contributing at least ten images per sequence).
  • Provenance: Prospective data collected in clinical practice from eight hospitals.
  • Country of Origin: Koreans.

3. Number of Experts and Qualifications for Ground Truth:

• 3 participating experts:
  • 1 anesthesiologist with >10 years of experience in pain management (for drawing GT).
  • "Other doctors" with >10 years of experience (for GT verification).
  • Doctors who scanned the ultrasound were directly involved in GT construction.

4. Adjudication Method:

• Manual drawing of nerve areas by an anesthesiologist. For verification of GT, "other doctors" checked every frame. If they disagreed, corrections were made to finalize the GT.

5. MRMC Comparative Effectiveness Study:

• No MRMC comparative effectiveness study was explicitly mentioned.

6. Standalone Performance Study:

• Yes, a standalone study was performed. The reported accuracy and speed are direct measurements of the algorithm's performance against expert-defined ground truth.

7. Type of Ground Truth Used:

• Expert consensus / Expert-annotated rectangular regions for nerve locations.

8. Sample Size for Training Set:

• Not explicitly stated ("Data used for training, tuning and validation purpose are completely separated").

9. How Ground Truth for Training Set Was Established:

• It's inferred that a similar expert-based process was used as for validation data: "The GT data were built by three participating experts. Nerve areas in all acquired images for training, tuning and validation were manually drawn by an anesthesiologist... For verification of GT, other doctors with more than 10 years of experience checked every frame... corrections were made to make the final GT."

NerveTrack (Nerve Segmentation)

1. Table of Acceptance Criteria and Reported Device Performance:

2. Sample Sizes and Data Provenance:

• Test Set:
  • Number of individuals: 20
  • Number of images: 1,675 (extracted from 2D sequences, with each individual contributing at least ten images per sequence).
  • Provenance: Prospective data collected in clinical practice from ten hospitals.
  • Country of Origin: Koreans.

3. Number of Experts and Qualifications for Ground Truth:

• 3 participating experts:
  • 1 anesthesiologist with >10 years of experience in pain management (for drawing GT).
  • "Other doctors" with >10 years of experience (for GT verification).
  • Doctors who scanned the ultrasound were directly involved in GT construction.

4. Adjudication Method:

• Manual drawing of nerve areas (contours) by an anesthesiologist. For verification of GT, "other doctors" checked every frame. If they disagreed on nerve and other organ contours, corrections were made to finalize the GT.

5. MRMC Comparative Effectiveness Study:

• No MRMC comparative effectiveness study was explicitly mentioned.

6. Standalone Performance Study:

• Yes, a standalone study was performed. The reported accuracy and speed are direct measurements of the algorithm's performance against expert-defined ground truth.

7. Type of Ground Truth Used:

• Expert consensus / Expert-annotated contours for nerve regions.

8. Sample Size for Training Set:

• Not explicitly stated ("Data used for training, tuning and validation purpose are completely separated").

9. How Ground Truth for Training Set Was Established:

• It's inferred that a similar expert-based process was used as for validation data: "The GT data were built by three participating experts. Nerve areas in all acquired images for training, tuning and validation were manually drawn by an anesthesiologist... For verification of GT, other doctors with more than 10 years of experience checked every frame... corrections were made to make the final GT."

Ask a specific question about this device

The Diagnostic Ultrasound System and transducers are intended for diagnostic ultrasound imaging and fluid analysis of the human body.

The clinical applications include: Fetal/Obstetrics, Abdominal, Gynecology, Pediatric, Small Organ, Neonatal Cephalic, Adult Cephalic, Trans-rectal, Trans-vaginal, Muscular-Skeletal (Conventional, Superficial), Urology, Cardiac Adult, Cardiac Pediatric and Peripheral vessel.

It is intended for use by, or by the order of, and under the supervision of, an appropriately trained healthcare professional who is qualified for direct use of medical devices. It can be used in hospitals, private practices, clinics and similar care environment for clinical diagnosis of patients.

Modes of Operation: 2D mode, Color Doppler mode, Power Doppler (PD) mode, M mode, Pulsed Wave (PW) Doppler mode, Continuous Wave (CW) Doppler mode, Tissue Doppler Imaging (TDI) mode, Tissue Doppler Wave (TDW) mode, ElastoScan+™ Mode, Combined modes, Multi-Image modes (Dual, Quad), 3D/4D modes.

The HERA W9/ HERA W10 are general purpose, mobile, software controlled, diagnostic ultrasound system. Its function is to acquire ultrasound data and to display the data as Bmode, M-mode, Pulsed wave (PW) Doppler, Continuous wave (CW) Doppler, Color Doppler, Tissue Doppler Imaging (TDI), Tissue Doppler Wave (TDW), Power Amplitude Doppler, Pulse Inversion Harmonic Imaging (S- Harmonic), Directional Power Doppler (S-Flow), Color M-Mode, 3D Imaging Mode, 4D Imaging Mode, Elastoscan+ Mode, Tissue Harmonic Imaging, MV-Flow Mode or as a combination of these modes.

The HERA W9/HERA W10 also give the operator the ability to measure anatomical structures and offers analysis packages that provide information that is used to make a diagnosis by competent health care professionals. The HERA W9/HERA W10 have real time acoustic output display with two basic indices, a mechanical index and a thermal index, which are both automatically displayed.

The provided FDA 510(k) summary (K242444) describes the acceptance criteria and study proving the device meets these criteria for three AI-powered features: HeartAssist, BiometryAssist, and ViewAssist, as well as a non-AI feature, SonoSync.

Here's a breakdown of the requested information for each AI feature:

HeartAssist

1. Acceptance Criteria and Reported Device Performance

2. Sample size used for the test set and data provenance

• Individuals: 69
• Static Images: 315 (at least 1 static image per view location per individual)
• Provenance: Data collected at two hospitals in the United States and South Korea. Mixed retrospective and prospective data collection.

3. Number of experts used to establish the ground truth for the test set and their qualifications

• Number of Experts: Three active participating experts for initial classification and manual drawing, supervised by one additional expert.
• Qualifications:
  • One obstetrician with more than 20 years of experience (primary classification/drawing).
  • Two sonographers with more than 10 years of experience in fetal cardiology (primary classification/drawing).
  • One obstetrician with more than 25 years of experience (supervising the entire process).

4. Adjudication method for the test set

Not explicitly stated. The process mentions "All acquired images for training, tuning and validation were first classified into the correct views by three participating experts. Afterwards, corresponding anatomy areas were manually drawn for each of the images." It doesn't specify if there was a consensus mechanism or independent review and adjudication if the experts disagreed.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done

No, an MRMC comparative effectiveness study was not done. This study focuses on the standalone performance of the AI algorithm.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done

Yes, the provided data describes the standalone performance of the HeartAssist algorithm against established ground truth.

7. The type of ground truth used

Expert consensus based on manual classification of views and manual drawing of corresponding anatomy areas.

8. The sample size for the training set

Not explicitly stated for HeartAssist, but it is mentioned that "Data used for training, tuning and validation purpose are completely separated from the ones during training process and there is no overlap among the three."

9. How the ground truth for the training set was established

Not explicitly detailed for the training set, but it is implied to be the same method as for the validation set: "All acquired images for training, tuning and validation were first classified into the correct views by three participating experts. Afterwards, corresponding anatomy areas were manually drawn for each of the images."

BiometryAssist

1. Acceptance Criteria and Reported Device Performance

2. Sample size used for the test set and data provenance

• Individuals: 33
• Static Images: 360 (at least 1 static image per view location per individual)
• Provenance: Data collected at two hospitals in South Korea and the United States. Mixed retrospective and prospective data collection.

3. Number of experts used to establish the ground truth for the test set and their qualifications

• Number of Experts: Three active participating experts for initial classification and manual drawing, supervised by one additional expert.
• Qualifications:
  • One obstetrician with more than 20 years of experience (primary classification/drawing).
  • Two sonographers with more than 10 years of experience in fetal cardiology (primary classification/drawing).
  • One obstetrician with more than 25 years of experience (supervising the entire process).

4. Adjudication method for the test set

Not explicitly stated. The process mentions "All acquired images for training, tuning and validation were first classified into the correct views by three participating experts. Afterwards, corresponding anatomy areas were manually drawn for each of the image." It doesn't specify if there was a consensus mechanism or independent review and adjudication if the experts disagreed.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done

No, an MRMC comparative effectiveness study was not done. This study focuses on the standalone performance of the AI algorithm.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done

Yes, the provided data describes the standalone performance of the BiometryAssist algorithm against established ground truth.

7. The type of ground truth used

Expert consensus based on manual classification of views and manual drawing of corresponding anatomy areas.

8. The sample size for the training set

Not explicitly stated for BiometryAssist, but it is mentioned that "Data used for training, tuning and validation purpose are completely separated from the ones during training process and there is no overlap between the three."

9. How the ground truth for the training set was established

Not explicitly detailed for the training set, but it is implied to be the same method as for the validation set: "All acquired images for training, tuning and validation were first classified into the correct views by three participating experts. Afterwards, corresponding anatomy areas were manually drawn for each of the image."

ViewAssist

1. Acceptance Criteria and Reported Device Performance

2. Sample size used for the test set and data provenance

• Individuals: 98
• Static Images: 1,485 (at least 1 static image per view location per individual)
• Provenance: Data collected at two hospitals in South Korea and the United States. Mixed retrospective and prospective data collection.

3. Number of experts used to establish the ground truth for the test set and their qualifications

• Number of Experts: Three active participating experts for initial classification and manual drawing, supervised by one additional expert.
• Qualifications:
  • One obstetrician with more than 20 years of experience (primary classification/drawing).
  • Two sonographers with more than 10 years of experience in fetal cardiology (primary classification/drawing).
  • One obstetrician with more than 25 years of experience (supervising the entire process).

4. Adjudication method for the test set

Not explicitly stated. The process mentions "All acquired images for training, tuning and validation were first classified into the correct views by three participating experts. Afterwards, corresponding anatomy areas were manually drawn for each of the image." It doesn't specify if there was a consensus mechanism or independent review and adjudication if the experts disagreed.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done

No, an MRMC comparative effectiveness study was not done. This study focuses on the standalone performance of the AI algorithm.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done

Yes, the provided data describes the standalone performance of the ViewAssist algorithm against established ground truth.

7. The type of ground truth used

Expert consensus based on manual classification of views and manual drawing of corresponding anatomy areas.

8. The sample size for the training set

Not explicitly stated for ViewAssist, but it is mentioned that "Data used for training, tuning and validation purpose are completely separated from the ones during training process and there is no overlap between the three."

9. How the ground truth for the training set was established

Not explicitly detailed for the training set, but it is implied to be the same method as for the validation set: "All acquired images for training, tuning and validation were first classified into the correct views by three participating experts. Afterwards, corresponding anatomy areas were manually drawn for each of the image."

General Notes applicable to all AI features:

• No Multi-Reader Multi-Case (MRMC) Study: The document explicitly states that "The subject of this premarket submission, HERA W9/ HERA W10, did not require clinical studies to demonstrate the substantial equivalence." The studies described are technical performance evaluations of the AI algorithms, not comparative effectiveness studies with human readers.
• Ground Truth Consistency: For all three AI features, the ground truth establishment process is described identically, relying on a small panel of experienced experts.
• Independence of Data: For all three AI features, it is stated that "Data used for training, tuning and validation purpose are completely separated from the ones during training process and there is no overlap among the three."
• Demographics: For all three AI features, the demographic distribution of the validation dataset indicates Female Gender, Reproductive age (specific age not collected), and Ethnicity/Country as Not Available / United States and South Korea. ICUOG and AIUM guidelines were used to divide fetal ultrasound images into views. BMI and Gestational Age distributions are also provided.
• Equipment: Data was acquired with SAMSUNG MEDISON's ultrasound systems (HERA W9/HERA W10) to secure diversity.

Ask a specific question about this device

The diagnostic ultrasound system and probes are designed to obtain ultrasound images and analyze body fluids.

The clinical applications include: Fetal/Obstetrics, Abdominal, Gynecology, Intra-operative, Pediatric, Small Organ, Neonatal Cephalic, Adult Cephalic, Trans-vaginal, Muscular-Skeletal (Conventional, Superficial), Urology, Cardiac Adult, Cardiac Pediatric, Thoracic, Trans-esophageal (Cardiac) and Peripheral vessel.

It is intended for use by, or by the order of, and under the supervision of, an appropriately trained healthcare professional who is qualified for direct use of medical devices. It can be used in hospitals, private practices, clinics and similar care environment for clinical diagnosis of patients.

Modes of Operation: 2D mode. Color Doppler mode. Pulsed Wave (PW) Doppler mode. Continuous Wave (CW) Doppler mode, Tissue Doppler Imaging (TDI) mode, Tissue Doppler Wave (TDW) mode, Power Doppler (PD) mode, ElastoScan™ Mode, MV-Flow Mode, Multi Image mode (Dual Quad) Combined modes 3D/AD model

The HERA Z20, R20, HERA Z30, R30 diagnostic ultrasound system are a general purpose, mobile, software controlled, diagnostic ultrasound system. Their function is to acquire ultrasound data and to display the data as 2D mode, Color Doppler mode, Power Doppler (PD) mode, M mode, Pulsed Wave (PW) Doppler mode, Continuous Wave (CW) Doppler mode, Tissue Doppler Imaging (TDI) mode, Tissue Doppler Wave (TDW) mode, ElastoScan Mode, Combined modes, MV-Flow mode, Multi-Image mode(Dual, Quad), 3D/4D mode.

The HERA Z20, R20, HERA Z30, R30 diagnostic ultrasound system also give the operator the ability to measure anatomical structures and offer analysis packages that provide information that is used to make a diagnosis by competent health care professionals. The HERA Z20, R20, HERA Z30, R30 diagnostic ultrasound system have a real time acoustic output display with two basic indices, a mechanical index and a thermal index, which are both automatically displayed.

Here's a summary of the acceptance criteria and the studies conducted for the AI-powered features of the HERA Z20, R20, HERA Z30, R30 Diagnostic Ultrasound System, based on the provided text.

This document describes several AI-powered features: Live ViewAssist, EzVolume, UterineContour, ViewAssist, HeartAssist, and BiometryAssist. Each feature has its own acceptance criteria and study findings.

1. A table of acceptance criteria and the reported device performance

Note: Some performance metrics were not explicitly stated as "acceptance criteria" but rather as "summary test statistics or other test results," indicating the device's measured performance against implicit or internal targets.

2nd/3rd Tri (Accepted): Fluid 0.78, Head 0.94, Body 0.68, Umbilical-cord 0.67, Limbs 0.66, Placenta 0.75, Uterus 0.80
2nd/3rd Tri (Rejected): Fluid 0.25, Head 0.46, Body 0.29, Umbilical-cord 0.38, Limbs 0.39, Placenta 0.32, Uterus 0.30 |
| UterineContour| Segmentation (uterus Dice-score) | Not explicitly stated as acceptance criteria | Average dice-score of uterus: 96% |
| | Segmentation (endometrium Dice-score) | Not explicitly stated as acceptance criteria | Average dice-score of endometrium: 92% |
| | 3D coronal view adaptation | Proportion of appropriateness evaluated as clinically diagnosable, with over 90% of all cases | Over 90% of all cases |
| ViewAssist | View recognition accuracy | Threshold 89% | Average recognition accuracy: 94.50% |
| | Anatomy annotation (Dice-score) | Threshold 0.8 | Average Dice-score: 0.892 |
| HeartAssist | View recognition accuracy | Threshold 89% | Average recognition accuracy: 95.00% |
| | Segmentation (Dice-score) | Threshold 0.8 | Average Dice-score: 0.876 |
| | Size measurement (Area error rate) | Not explicitly stated as acceptance criteria | 8% or less |
| | Size measurement (Angle error rate) | Not explicitly stated as acceptance criteria | 4% or less |
| | Size measurement (Circumference error rate) | Not explicitly stated as acceptance criteria | 11% or less |
| | Size measurement (Diameter error rate) | Not explicitly stated as acceptance criteria | 11% or less |
| BiometryAssist| Segmentation (Dice-score) | Threshold 0.8 | Average Dice-score: 0.928 |
| | Size measurement (Circumference error rate) | Not explicitly stated as acceptance criteria | 8% or less |
| | Size measurement (Distance error rate) | Not explicitly stated as acceptance criteria | 4% or less |
| | Size measurement (NT, NB, IT error rate)| Not explicitly stated as acceptance criteria | 1mm or less |

2. Sample size used for the test set and the data provenance

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

4. Adjudication method for the test set

5. If a multi-reader, multi-case (MRMC) comparative effectiveness study was done

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly stated as performed to compare human readers with and without AI assistance. The studies described focus on the standalone performance of the AI algorithms.

6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done

Yes, standalone performance studies of the AI algorithms were done for all the described features: Live ViewAssist, EzVolume, UterineContour, ViewAssist, HeartAssist, and BiometryAssist. The reported metrics like Cohen's kappa, FPS, acceptance rates, Dice scores, and error rates are all measures of the algorithm's performance without human intervention during the assessment phase (though human experts were used to establish ground truth).

7. The type of ground truth used

For all features, the ground truth was established by expert consensus based on manual classification, delineation, or drawing by qualified clinical experts (obstetricians, sonographers, and examiners).

8. The sample size for the training set

The document explicitly states that "Data used for training, tuning and validation purpose are completely separated from the ones during training process and there is no overlap among the three." However, the exact sample size for the training set itself is not provided for any of the features. The sample sizes listed in Section 2 are for the test/validation sets.

9. How the ground truth for the training set was established

For all features, the ground truth for the training set (and validation/evaluation sets) was established through manual classification, delineation, or drawing by the same groups of qualified clinical experts mentioned in section 3, following similar expert consensus processes as described for the test sets. For UterineContour, initial delineations by 3 experts were then reviewed and fixed with consensus for unmatched results.

Ask a specific question about this device

SonoSync is a software solution for live streaming images acquired through ultrasound systems to healthcare professionals for diagnostic image viewing, remote access, review, consultation, quidance, support and education in real time.

It is required to follow the technical and operator requirements in the User Manual.

As users of this remote solution, the healthcare professionals take responsibility for ensuring that image quality, display contrast and ambient light conditions meet the generally accepted practices of the ultrasound imaging.

SonoSync is a software solution that allows medical professionals to stream ultrasound images live, providing real-time access to diagnostic imaging, remote viewing, reviewing, consulting, guiding, supporting, and educating.

SonoSync supports four main features: remote diagnostic viewing and guiding, remote clinical training and education, collaboration, and remote service support.

With permission from the person operating the ultrasound equipment, a remote user can control the ultrasound equipment using a virtual remote touch panel and remote control panel.

Furthermore, under the technical, operational, and environmental conditions described in the manual, healthcare professionals can provide clinical diagnostics at a remote location as if directly using the ultrasound equipment.

The provided text does not contain detailed information about a study that proves the device meets specific acceptance criteria in the format requested. The document is an FDA 510(k) submission summary for SonoSync, a software solution for live streaming ultrasound images.

While it mentions "Pre-set criteria were utilized in validation tests to assess whether remote viewing and reviewing with SonoSync matched the performance of local ultrasound systems," it does not provide the specific acceptance criteria, the reported device performance against those criteria, the sample size or provenance of data, the number or qualifications of experts, adjudication methods, or other detailed study information.

It states:

• "10. Summary of Non-Clinical Testing: Pre-set criteria were utilized in validation tests to assess whether remote viewing and reviewing with SonoSync matched the performance of local ultrasound systems. Specifications for remote displays and required network bandwidth to ensure diagnostic image quality were identified. Labeling materials have been prepared to inform users about the necessary specifications for safely and effectively conducting remote diagnostic reviews and viewing."

This indicates that some testing was performed, but the results, methodology, and specific criteria are not elaborated in this summary. Therefore, I cannot generate the requested table or answer the specific questions about the study design.

Ask a specific question about this device

The diagnostic ultrasound system and transducers are designed to obtain ultrasound images and analyze body fluids.

The clinical applications include: Fetal/Obstetrics, Abdominal, Gynecology, Intra-operative, Pediatric, Small Organ, Neonatal Cephalic, Adult Cephalic, Trans-vaginal, Muscular-Skeletal (Conventional, Superficial), Urology, Cardiac Adult, Cardiac Pediatric, Thoracic, Trans-esophageal (Cardiac) and Peripheral vessel.

It is intended for use by, or by the order of, and under the supervision of, an appropriately trained healthcare professional who is qualified for direct use of medical devices. It can be used in hospitals, private practices, clinics and similar care environment for clinical diagnosis of patients. Modes of Operation: 2D mode, Color Doppler mode, Power Doppler (PD) mode, M mode, Pulsed Wave (PW) Doppler mode, Continuous Wave (CW) Doppler mode, Tissue Doppler Imaging (TDI) mode, Tissue Doppler Wave (TDW) mode, ElastoScan Mode, Combined modes, Multi-Image mode(Dual, Quad), 3D/4D mode

The V8/XV8/XH8, V7/XV7/XH7, V6/XV6/XH6 diagnostic ultrasound system are a general purpose, mobile, software controlled, diagnostic ultrasound system. Their function is to acquire ultrasound data and to display the data as 2D mode, Color Doppler mode, Power Doppler (PD) mode, M mode, Pulsed Wave (PW) Doppler mode, Continuous Wave (CW) Doppler mode, Tissue Doppler Imaging (TDI) mode, Tissue Doppler Wave (TDW) mode, ElastoScan Mode, Combined modes, Multi-Image mode(Dual, Quad), 3D/4D mode. The V8/XV8/XH8, V7/XV7/XH7, V6/XV6/XH6 diagnostic ultrasound system also give the operator the ability to measure anatomical structures and offer analysis packages that provide information that is used to make a diagnosis by competent health care professionals. The V8/XV8/XH8, V7/XV7/XH7, V6/XV6/XH6 diagnostic ultrasound system have a real time acoustic output display with two basic indices, a mechanical index and a thermal index, which are both automatically displayed.

Here's a breakdown of the acceptance criteria and study details for the AI-based NerveTrack feature, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance (NerveTrack - Detection)

1. Table of Acceptance Criteria and Reported Device Performance (NerveTrack - Segmentation)

2. Sample Size Used for the Test Set and Data Provenance:

The document does not explicitly state the numerical sample size for the test set (number of frames or cases). It only mentions that the "test images" were used and that evaluation included "BMI subgroups" (underweight, healthy weight, overweight, and obesity) to assess generalizability.

• Sample Size: Not explicitly quantified.
• Data Provenance:
  • Country of Origin: Not explicitly stated, though Samsung Medison Co., Ltd. is based in the Republic of Korea. The document mentions "All the nerve data were acquired on Samsung ultrasound devices including V8."
  • Retrospective or Prospective: Not explicitly stated, however, the description of "collecting scan data" and the involvement of experts in "establishing the ground truth" suggests these were real-world scans that were then annotated.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications:

• Number of Experts: 12 anesthesiologists and 5 sonographers (total of 17 experts).
• Qualifications: Over ten years' experience.

4. Adjudication Method for the Test Set:

• Adjudication Method: For each dataset, the doctors who performed the ultrasound scans directly drew the ground truth (GT) of the nerve locations. These were then reviewed and verified as accurate by at least two additional anesthesiologists and sonographers. Any errors or discrepancies were corrected until satisfactory results were achieved. This effectively describes a form of expert consensus and review process.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

• No, a multi-reader, multi-case (MRMC) comparative effectiveness study was not reported. The study focused on the standalone performance of the AI algorithm.

6. Standalone Performance (Algorithm Only without Human-in-the-Loop Performance):

• Yes, a standalone performance study was done. The reported accuracy and speed metrics are for the NerveTrack algorithm itself, without human intervention or assistance during the test. The document states, "The standalone performance of NerveTrack was evaluated..."

7. Type of Ground Truth Used:

• Type of Ground Truth: Expert consensus. Specifically, "The ground truth made by anesthesiologists" and established by the manual drawing/delineation of nerve locations by doctors who performed the scans, followed by review and verification by at least two additional experts.

8. Sample Size for the Training Set:

• Sample Size: Not explicitly stated. The document only mentions "The training data used for the training of the NerveTrack algorithm are independent of the data used to test the NerveTrack algorithm."

9. How the Ground Truth for the Training Set Was Established:

• Ground Truth Establishment: The document does not explicitly describe how the ground truth for the training set was established. It only states that the training data and test data are independent. However, given the robust process described for the test set's ground truth (expert drawing and multi-expert review/verification), it is highly probable that a similar, if not identical, expert-driven ground truth establishment method was used for the training data as well.

Ask a specific question about this device

The diagnostic ultrasound system and probes are designed to obtain ultrasound images and analyze body fluids.

The clinical applications include: Fetal/Obstetrics, Abdominal, Gynecology, Intraoperative, Pediatric, Small Organ, Neonatal Cephalic, Adult Cephalic, Trans vaginal, Muscular Skeletal (Conventional, Superficial), Urology, Cardiac Adult, Cardiac Pediatric, Trans esophageal(Cardiac) and Peripheral vessel.

It is intended for use by, or by the order of, and under the supervision of, an appropriately trained healthcare professional who is qualified for direct use of medical devices. It can be used in hospitals, private practices, clinics and similar care environment for clinical diagnosis of patients.

Modes of Operation: 2D mode, Color Doppler mode, Pulsed Wave (PW) Doppler mode, Continuous Wave (CW) Doppler mode, Tissue Doppler Imaging (TDI) mode, Tissue Doppler Wave (TDW) mode, Power Doppler (PD) mode, ElastoScan™ Mode, Multi Image mode(Dual, Quad), Combined modes. 3D/4D mode.

The RS85 is a general purpose, mobile, software controlled, diagnostic ultrasound system. Its function is to acquire ultrasound data and to display the data as 2D mode, Color Doppler imaging, Power Doppler imaging (including Directional Power Doppler mode; S-Flow), PW Spectral Doppler mode, CW Spectral Doppler mode, Harmonic imaging, Tissue Dopler imaging, Tissue Doppler Wave, 3D imaging mode (real-time 4D imaging mode), Elastoscan* Mode, MV-Flow Mode or as a combination of these modes. The RS85 also gives the operator the ability to measure anatomical structures and offers analysis packages that provide information that may aid in making a diagnosis by competent health care professionals. the RS85 has real time acoustic output display with two basic indices, a mechanical index, which are both automatically displayed.

This document describes the validation of AI-based features for the Samsung Medison RS85 Diagnostic Ultrasound System, specifically focusing on NerveTrack's detection, segmentation, and EzNerveMeasure functionalities, as well as SonoSync.

Here's a breakdown of the requested information:

Acceptance Criteria and Reported Device Performance

Study Details

1. Sample Sizes and Data Provenance

2. Number of Experts and Qualifications for Ground Truth

• Number of Experts: Three participating experts.
• Qualifications of Experts:
  • One anesthesiologist with more than 10 years of experience in pain management performed the initial manual drawing of nerve areas.
  • Other doctors with more than 10 years of experience performed verification of the ground truth.

3. Adjudication Method for the Test Set

The adjudication method appears to be a 2+1 process:

1. Initial ground truth (GT) data was manually drawn by one anesthesiologist.
2. Other doctors (presumably at least two distinct individuals to form a consensus if needed, though the document only states "other doctors") with more than 10 years of experience checked every frame.
3. If discrepancies ("did not agree on nerve locations/contours") arose, necessary corrections were made to finalize the GT. This indicates a consensus-based approach for disagreement resolution, but the specific number for resolving disagreements is not explicitly 2+1; it just states "other doctors."

4. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not performed according to the provided text. The studies focus on the standalone performance of the AI algorithms.

5. Standalone Performance Study

Yes, standalone (algorithm only without human-in-the-loop) performance studies were done for NerveTrack's detection, segmentation, and EzNerveMeasure functionalities. The reported results (accuracy, speed, Dice coefficient, Hausdorff distance, and error rates) are direct measurements of the algorithm's performance against established ground truth.

6. Type of Ground Truth Used

The ground truth used was expert consensus. It was established by manual delineation (drawing of nerve areas/contours) by an anesthesiologist with over 10 years of experience, followed by verification and correction (if needed) by other doctors also with over 10 years of experience.

7. Sample Size for the Training Set

The document explicitly states: "Data used for training, tuning and validation purpose are completely separated from the ones during training process, and there is no overlap among the three." However, the exact sample size for the training set is not provided in this document. It only gives the test set sizes.

8. How Ground Truth for the Training Set Was Established

While the exact size of the training set is not given, the method for establishing its ground truth is described similarly to the validation set:

• The GT data for training, tuning, and validation were built by three participating experts.
• Nerve areas were manually drawn by an anesthesiologist with more than 10 years of experience in pain management.
• The doctors who scanned the ultrasound were directly involved in the construction of GT data.
• For verification, other doctors with more than 10 years of experience checked every frame.
• If they did not agree on nerve locations/contours, necessary corrections were made to create the final GT.

This suggests that the ground truth for the training set was also established through expert consensus and manual delineation, following the same "Truthing" process as the test set.

Ask a specific question about this device

The diagnostic ultrasound system and probes are designed to obtain ultrasound images and analyze body fluids.

The clinical applications include: Fetal/Obstetrics, Abdominal, Gynecology, Pediatric, Small Organ, Neonatal Cephalic, Adult Cephalic, Trans-rectal, Muscular-Skeletal (Conventional, Superficial), Urology, Cardiac Adult, Cardiac Pediatric, Trans-esophageal (Cardiac), Peripheral vessel, Lung and Dermatology.

It is intended for use by, or by the order of, and under the supervision of, an appropriately trained healthcare professional who is qualified for direct use of medical devices. It can be used in hospitals (includes emergency room), private practices, clinics and similar care environment for clinical diagnosis of patients.

Modes of Operation: 2D mode, Color Doppler mode, Power Doppler (PD) mode, M mode, Pulsed Wave (PW) Doppler mode, Continuous Wave (CW) Doppler mode, Tissue Doppler Imaging (TDI) mode, Tissue Doppler Wave (TDW) mode, ElastoScan Mode, Combined modes, Multi-Image mode(Dual, Quad), 3D/4D mode.

The HM70 EVO is a general purpose, mobile, software controlled, diagnostic ultrasound system. Its function is to acquire ultrasound data and to display the data as 2D mode. M mode, Color Doppler imaging, Power Doppler imaging (including Directional Power Doppler mode; S-Flow), PW Spectral Doppler mode, CW Spectral Doppler mode, Harmonic imaging(S-Harmonic), Tissue Doppler imaging, Tissue Doppler Wave, Panoramic Imaging, Freehand 3D, 3D imaging mode (real-time 4D imaging mode), Elastoscan Mode or as a combination of these modes. The HM70 EVO also gives the operator the ability to measure anatomical structures and offers analysis packages that provide information that is used to make a diagnosis by competent health care professionals. The HM70 EVO has real time acoustic output display with two basic indices, a mechanical index and a thermal index. which are both automatically displayed.

The provided text describes two AI-based features of the HM70 EVO Diagnostic Ultrasound System: UterineAssist and NerveTrack. The acceptance criteria and performance studies for each are detailed below.

UterineAssist

1. Table of Acceptance Criteria and Reported Device Performance

For UterineAssist, the document details performance for three areas: image segmentation, feature points extraction, and size measurement. While explicit acceptance criteria values (like a minimum percentage or maximum error) are not stated in a direct acceptance criteria table, the reported device performance serves as the evidence of meeting internal acceptance.

2. Sample Sizes Used for the Test Set and Data Provenance

• Segmentation Test:

  • Sample Size: 450 sagittal uterus images and 150 transverse uterus images (total 600 images).
  • Data Provenance: Collected at three hospitals. Mix of retrospective and prospective data collection in clinical practice.
  • Country of Origin: All Koreans (implies South Korea).

• Feature Points Extraction Test & Size Measurement Test:

  • Sample Size: 45 sagittal and 41 transverse plane images of uterus (total 86 images).
  • Data Provenance: Collected at three hospitals. Mix of retrospective and prospective data collection in clinical practice.
  • Country of Origin: All Koreans (implies South Korea).

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications

• Number of Experts: Three participating OB/GYN experts.
• Qualifications: Each had more than 10 years' experience.

4. Adjudication Method for the Test Set

• Method: The set of images (uterus and endometrium) were divided into 3 subsets. Each of the three OB/GYN experts drew the ground truths for one of the subsets. The ground truths drawn by one expert were then cross-checked by the other two experts. Any images not meeting inclusion/exclusion criteria were excluded. This can be described as a 1+2 cross-check adjudication method.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

• No MRMC comparative effectiveness study is reported for UterineAssist, as this section only describes the standalone performance metrics.

6. If a Standalone (algorithm only without human-in-the-loop performance) was done

• Yes, the reported performance metrics (Dice-score, error measurements) reflect the "standalone" performance of the algorithm.

7. The Type of Ground Truth Used

• The ground truth for both segmentation and feature points/size measurements was established by expert consensus/adjudication from three experienced OB/GYN experts.

8. The Sample Size for the Training Set

• The training data details (specific sample size) are not provided, but it is stated that it is independent of the test data.

9. How the Ground Truth for the Training Set was Established

• Not explicitly stated, but implicitly, similar expert labeling or other reliable methods would have been used, consistent with the independent test data approach. It is only mentioned that the training and test data sets are "completely separated" and there is "no overlap."

NerveTrack

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Sizes Used for the Test Set and Data Provenance

• Number of Subjects: 18 (13 Females, 5 Males)
• Number of Images: 2,146
• Age Range: 22-68 years
• BMI Range: 16-31.5
• Data Provenance: Not explicitly stated as retrospective or prospective, but the description of gathering scan data and expert involvement suggests a prospective collection or a specifically designed retrospective collection process for validation.
• Country of Origin: All Koreans (implies South Korea).

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications

• Number of Experts: Ten anesthesiologists and five sonographers (total 15 experts) for review and confirmation.
• Qualifications: All had more than 10 years of experience.
• Initial Ground Truth Drawing: One anesthesiologist who scanned the ultrasound directly drew the GT.

4. Adjudication Method for the Test Set

• Method: One anesthesiologist who directly scanned the ultrasound drew the initial ground truth (GT) for the nerve location. Then, "two or more other anesthesiologists and sonographers reviewed and confirmed that it was correct." If any mistake was identified during the review, it was revised. This indicates a 1 + (2 or more) consensus/adjudication method.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

• No, the document describes "standalone performance" validation of the NerveTrack algorithm, specifically focusing on accuracy and speed. It does not mention any MRMC study comparing human readers with and without AI assistance.

6. If a Standalone (algorithm only without human-in-the-loop performance) was done

• Yes, the validation clearly states, "The standalone performance of NerveTrack was evaluated..." and provides performance metrics (accuracy and speed) for the algorithm itself.

7. The Type of Ground Truth Used

• The ground truth for the location of 10 different kinds of nerves was established by expert consensus/adjudication involving anesthesiologists and sonographers with significant experience.

8. The Sample Size for the Training Set

• The training data details (specific sample size) are not provided, but it is stated that it is independent of the test data.

9. How the Ground Truth for the Training Set was Established

• Not explicitly stated, but it is mentioned that the "training data used for the training of the NerveTrack algorithm are independent of the data used to test the NerveTrack algorithm." This implies a separate, established ground truth for the training set, likely using similar expert labeling methods.

Ask a specific question about this device

The diagnostic ultrasound system and transducers are designed to obtain ultrasound images and analyze body fluids.

The clinical applications include: Fetal/Obstetrics, Abdominal, Gynecology, Intra-operative, Small Organ, Neonatal Cephalic, Adult Cephalic, Trans-vaginal, Muscular-Skeletal (Conventional, Superficial), Urology, Cardiac Adult, Cardiac Pediatric, Thoracic, Trans-esophageal (Cardiac) and Peripheral vessel.

It is intended for use by, or by the order of, and under the supervision of, an appropriately trained healthcare professional who is qualified for direct use of medical devices. It can be used in hospitals, private practices, clinics and similar care environment for clinical diagnosis of patients.

Modes of Operation: 2D mode, Color Doppler mode, Power Doppler (PD) mode, M mode, Pulsed Wave (PW) Doppler mode, Continuous Wave (CW) Doppler mode, Tissue Doppler Imaging (TDI) mode, Tissue Doppler Wave (TDW) mode, ElastoScan Mode, Combined modes, Multi-Image mode(Dual, Quad), 3D/4D mode

The V8 / V7 / V6 / H8 / H7 / H6 are a general purpose, mobile, software controlled, diagnostic ultrasound system. Their function is to acquire ultrasound data and to display the data as 2D mode, Color Doppler mode, Power Doppler (PD) mode, M mode, Pulsed Wave (PW) Doppler mode, Continuous Wave (CW) Doppler mode, Tissue Doppler Imaging (TDI) mode, Tissue Doppler Wave (TDW) mode, ElastoScan Mode, Combined modes, Multi-Image mode(Dual, Quad), 3D/4D mode. The V8 / V7 / V6 / H8 / H7 / H6 also give the operator the ability to measure anatomical structures and offer analysis packages that provide information that is used to make a diagnosis by competent health care professionals. The V8 / V7 / V6 / H8 / H7 / H6 have a real time acoustic output display with two basic indices, a mechanical index and a thermal index, which are both automatically displayed.

Here's an analysis of the acceptance criteria and the study proving the device meets those criteria, based on the provided document:

Device: Samsung Medison V8/H8, V7/H7, V6/H6 Diagnostic Ultrasound System with NerveTrack AI

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size Used for the Test Set and Data Provenance

• Nerve Detection Test Set:

  • Number of Subjects: 18 (13 females, 5 males)
  • Number of Images/Frames: 2,146
  • Data Provenance: All Koreans. The document does not explicitly state if the data was retrospective or prospective. However, the description of data collection (sliding transducer at specific speeds) suggests it was collected for the purpose of this study, indicating a prospective component or at least an intentionally collected dataset.

• Nerve Segmentation Test Set:

  • Number of Subjects: 11 (8 females, 3 males)
  • Number of Images/Frames: 3,836
  • Data Provenance: All Koreans. Similar to the detection dataset, the provenance is Korean, and the collection method description points towards intentionally collected data.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications

• Number of Experts: 15 experts were involved (10 anesthesiologists and 5 sonographers).
• Qualifications of Experts: All experts had "more than 10 years of experience."

4. Adjudication Method for the Test Set

The ground truth establishment method was as follows:

• One anesthesiologist who scanned the ultrasound directly drew the initial ground truth (GT) of the nerve location.
• "Two or more other anesthesiologists and sonographers reviewed and confirmed that it was correct."
• "If there was any mistake during the review, it was revised again."

This describes a form of consensus-based adjudication with an initial ground truth creator and subsequent confirmation/revision by multiple independent experts. It's not a strict N+M or sequential read, but rather a collaborative review and refinement process.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

No, the document does not indicate that a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done to compare human readers with vs. without AI assistance. The study focuses solely on the standalone performance of the AI algorithm (NerveTrack).

6. If a Standalone (algorithm only without human-in-the-loop performance) was done

Yes, the document explicitly states: "The standalone performance of NerveTrack was evaluated..." The "Summary Performance data" tables provided are for the algorithm's performance without a human in the loop.

7. The Type of Ground Truth Used

The ground truth used was expert consensus. It was established by a team of experienced anesthesiologists and sonographers who reviewed and confirmed the actual nerve locations in the ultrasound images.

8. The Sample Size for the Training Set

The document states: "The training data used for the training of the NerveTrack algorithm are independent of the data used to test the NerveTrack algorithm." However, the exact sample size for the training set is not provided in the given text.

9. How the Ground Truth for the Training Set was Established

The document mentions that the training data is independent of the test data. While it does not explicitly detail the ground truth establishment method for the training set, it is highly probable that a similar expert-based annotation process (as described for the test set) was used to establish the ground truth for the training data. This is a common practice in AI development to ensure consistency in data labeling.

Ask a specific question about this device