Search Results
Found 5 results
510(k) Data Aggregation
(124 days)
LOGIQ E10 is intended for use by a qualified physician for ultrasound evaluation of Fetal/Obstetrics; Abdominal (including Renal, Gynecology/Pelvic); Pediatric; Small Organ (Breast, Testes, Thyroid); Neonatal Cephalic, Adult Cephalic; Cardiac (Adult and Pediatric); Peripheral Vascular; Musculo-skeletal Conventional and Superficial; Urology (including Prostate); Transrectal; Transvaginal; Tranesophageal and Intraoperative (Abdominal and Vascular).
Modes of operation include: B, M, PW Doppler, CW Doppler, Color Doppler, Color M Doppler, Power Doppler, Harmonic Imaging, Coded Pulse, 3D/4D Imaging mode, Elastography, Shear Wave Elastography, Attenuation Imaging and combined modes: B/M, B/Color, B/PWD, B/Color/PWD, B/Power/PWD.
The LOGIQ E10 is intended to be used in a hospital or medical clinic.
The LOGIQ E10 is a full featured, Track 3, general purpose diagnostic ultrasound system which consists of a mobile console approximately 585 mm wide (keyboard), 991 mm deep and 1300 mm high that provides digital acquisition, processing and display capability. The user interface includes a computer keyboard, specialized controls, 12-inch high-resolution color touch screen and 23.8-inch High Contrast LED LCD monitor.
Here's an analysis of the acceptance criteria and supporting studies for the LOGIQ E10 ultrasound system, derived from the provided FDA 510(k) Clearance Letter:
1. Table of Acceptance Criteria and Reported Device Performance
| Feature/Metric | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| Auto Abdominal Color Assistant 2.0 | ||
| Overall Model Detection Accuracy | $\ge 80%$ | $94.8%$ |
| Sensitivity (True Positive Rate) | $\ge 80%$ | $0.91$ |
| Specificity (True Negative Rate) | $\ge 80%$ | $0.98$ |
| DICE Similarity Coefficient (Segmentation Accuracy) | $\ge 0.80$ | $0.82$ |
| Auto Aorta Measure Assistant (Long View AP Measurement) | ||
| Average Accuracy | Not explicitly stated as a target percentage, but implied by strong performance metrics | $87.2%$ (95% CI of $\pm 1.98%$) |
| Average Absolute Error | Not explicitly stated as a target | $0.253$ cm (95% CI of $0.049$ cm) |
| Limits of Agreement | Not explicitly stated as a target range | $(-0.15, 0.60)$ cm (95% CI of $(-0.26, 0.71)$) |
| Auto Aorta Measure Assistant (Short View AP Measurement) | ||
| Average Accuracy | Not explicitly stated as a target percentage, but implied by strong performance metrics | $92.9%$ (95% CI of $\pm 2.02%$) |
| Average Absolute Error | Not explicitly stated as a target | $0.128$ cm (95% CI of $0.037$ cm) |
| Limits of Agreement | Not explicitly stated as a target range | $(-0.21, 0.36)$ cm (95% CI of $(-0.29, 0.45)$) |
| Auto Aorta Measure Assistant (Short View Trans Measurement) | ||
| Average Accuracy | Not explicitly stated as a target percentage, but implied by strong performance metrics | $86.9%$ (95% CI of $\pm 6.25%$) |
| Average Absolute Error | Not explicitly stated as a target | $0.235$ cm (95% CI of $0.110$ cm) |
| Limits of Agreement | Not explicitly stated as a target range | $(-0.86, 0.69)$ cm (95% CI of $(-1.06, 0.92)$) |
| Auto Common Bile Duct (CBD) Measure Assistant (Porta Hepatis measurement accuracy without segmentation scroll edit) | ||
| Average Accuracy | Not explicitly stated as a target percentage, but implied by strong performance metrics | $59.85%$ (95% CI of $\pm 17.86%$) |
| Average Absolute Error | Not explicitly stated as a target | $1.66$ mm (95% CI of $1.02$ mm) |
| Limits of Agreement | Not explicitly stated as a target range | $(-4.75, 4.37)$ mm (95% CI of $(-6.17, 5.79)$) |
| Auto Common Bile Duct (CBD) Measure Assistant (Porta Hepatis measurement accuracy with segmentation scroll edit) | ||
| Average Accuracy | Not explicitly stated as a target percentage, but implied by strong performance metrics | $80.56%$ (95% CI of $\pm 8.83%$) |
| Average Absolute Error | Not explicitly stated as a target | $0.91$ mm (95% CI of $0.45$ mm) |
| Limits of Agreement | Not explicitly stated as a target range | $(-1.96, 3.25)$ mm (95% CI of $(-2.85, 4.14)$) |
| Ultrasound Guided Fat Fraction (UGFF) | ||
| Correlation Coefficient with MRI-PDFF (Japan Cohort) | Strong correlation confirmed | $0.87$ |
| Offset (UGFF vs MRI-PDFF, Japan Cohort) | Not explicitly stated as a target | $-0.32%$ |
| Limits of Agreement (UGFF vs MRI-PDFF, Japan Cohort) | Not explicitly stated as a target range | $-6.0%$ to $5.4%$ |
| % Patients within $\pm 8.4%$ difference (Japan Cohort) | Not explicitly stated as a target | $91.6%$ |
| Correlation Coefficient with MRI-PDFF (US/EU Cohort) | Strong correlation confirmed | $0.90$ |
| Offset (UGFF vs MRI-PDFF, US/EU Cohort) | Not explicitly stated as a target | $-0.1%$ |
| Limits of Agreement (UGFF vs MRI-PDFF, US/EU Cohort) | Not explicitly stated as a target range | $-3.6%$ to $3.4%$ |
| % Patients within $\pm 4.6%$ difference (US/EU Cohort) | Not explicitly stated as a target | $95.0%$ |
| Correlation Coefficient with UDFF (EU Cohort) | Strong correlation confirmed | $0.88$ |
| Offset (UGFF vs UDFF, EU Cohort) | Not explicitly stated as a target | $-1.2%$ |
| Limits of Agreement (UGFF vs UDFF, EU Cohort) | Not explicitly stated as a target range | $-5.0%$ to $2.6%$ |
| % Patients within $\pm 4.7%$ difference (EU Cohort) | Not explicitly stated as a target | All patients |
2. Sample Size for Test Set and Data Provenance
- Auto Abdominal Color Assistant 2.0:
- Test Set Sample Size: 49 individual subjects, 1186 annotation images.
- Data Provenance: Retrospective, all data from the USA.
- Auto Aorta Measure Assistant:
- Test Set Sample Size:
- Long View Aorta: 36 subjects (11 Male, 25 Female).
- Short View Aorta: 35 subjects (11 Male, 24 Female).
- Data Provenance: Retrospective, from Japan (15-16 subjects) and USA (20 subjects).
- Test Set Sample Size:
- Auto Common Bile Duct (CBD) Measure Assistant:
- Test Set Sample Size: 25 subjects (11 Male, 14 Female).
- Data Provenance: Retrospective, from USA (40%) and Japan (60%).
- Ultrasound Guided Fat Fraction (UGFF):
- Test Set Sample Size (Primary Study): 582 participants.
- Data Provenance (Primary Study): Retrospective, Japan.
- Test Set Sample Size (Confirmatory Study 1): 15 US patients + 5 EU patients (total 20).
- Data Provenance (Confirmatory Study 1): Retrospective, USA and EU.
- Test Set Sample Size (Confirmatory Study 2): 24 EU patients.
- Data Provenance (Confirmatory Study 2): Retrospective, EU.
3. Number of Experts and Qualifications for Ground Truth
- Auto Abdominal Color Assistant 2.0: Not explicitly stated, but implies multiple "readers" to ground truth anatomical visibility. No specific qualifications are mentioned beyond "readers."
- Auto Aorta Measure Assistant: Not explicitly stated, but implies multiple "readers" for measurements and an "arbitrator" to select the most accurate measurement. No specific qualifications are mentioned beyond "readers" and "arbitrator."
- Auto Common Bile Duct (CBD) Measure Assistant: Not explicitly stated, but implies multiple "readers" for measurements and an "arbitrator" to select the most accurate measurement. No specific qualifications are mentioned beyond "readers" and "arbitrator."
- Ultrasound Guided Fat Fraction (UGFF): Ground truth for the primary study was MRI Proton Density Fat Fraction (MRI-PDFF %). No human experts were involved in establishing the ground truth for UGFF, as it relies on MRI-PDFF as the reference. The correlation between UGFF and UDFF also used UDFF as a reference, not human experts.
4. Adjudication Method for the Test Set
- Auto Abdominal Color Assistant 2.0: Not explicitly mentioned, however, the process described as "Readers to ground truth the 'anatomy' visible in static B-Mode image. (Before running AI)" and then comparing to AI predictions does not suggest an adjudication process for the ground truth generation itself beyond initial reader input. Confusion matrices were generated later.
- Auto Aorta Measure Assistant: An "Arbitrator" was used to "select most accurate measurement among all readers" for the initial ground truth, which was then compared to AI baseline. This implies a 1 (arbitrator) + N (readers) adjudication method for measurement accuracy. For keystroke comparison, readers measured with and without AI.
- Auto Common Bile Duct (CBD) Measure Assistant: An "Arbitrator" was used to "select most accurate measurement among all readers" for the initial ground truth, which was then compared to AI baseline. This implies a 1 (arbitrator) + N (readers) adjudication method for measurement accuracy. For keystroke comparison, readers measured with and without AI.
- Ultrasound Guided Fat Fraction (UGFF): Ground truth was established by MRI-PDFF or comparison to UDFF. No human adjudication method was described for these.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- Auto Aorta Measure Assistant: Yes, a comparative study was performed by comparing keystroke counts with and without AI assistance for human readers.
- Effect Size:
- Long View Aorta AP Measurement: Average reduction from $4.132 \pm 0.291$ keystrokes (without AI) to $1.236 \pm 0.340$ keystrokes (with AI).
- Short View Aorta AP and Trans Measurement: Average reduction from $7.05 \pm 0.158$ keystrokes (without AI) to $2.307 \pm 1.0678$ keystrokes (with AI).
- Effect Size:
- Auto Common Bile Duct (CBD) Measure Assistant: Yes, a comparative study was performed by comparing keystroke counts with and without AI assistance for human readers.
- Effect Size: Average reduction of $1.62 \pm 0.375$ keystrokes (mean and standard deviation) from manual to AI-assisted measurements.
- Other features (Auto Abdominal Color Assistant 2.0, UGFF): The documentation does not describe a MRMC study for improved human reader performance with AI assistance for these features.
6. Standalone (Algorithm Only) Performance Study
- Auto Abdominal Color Assistant 2.0: Yes, the model's accuracy (detection accuracy, sensitivity, specificity, DICE score) was evaluated in a standalone manner against the human-annotated ground truth.
- Ultrasound Guided Fat Fraction (UGFF): Yes, the correlation and agreement of the UGFF algorithm's values were tested directly against an established reference standard (MRI-PDFF) and another device's derived fat fraction (UDFF).
7. Type of Ground Truth Used
- Auto Abdominal Color Assistant 2.0: Expert consensus/annotations on B-Mode images, followed by comparison to AI predictions.
- Auto Aorta Measure Assistant: Expert consensus on measurements (human readers with arbitrator selection) and keystroke counts from these manual measurements and AI-assisted measurements.
- Auto Common Bile Duct (CBD) Measure Assistant: Expert consensus on measurements (human readers with arbitrator selection) and keystroke counts from these manual measurements and AI-assisted measurements.
- Ultrasound Guided Fat Fraction (UGFF): Established clinical reference standard: MRI Proton Density Fat Fraction (MRI-PDFF %). For one confirmatory study, another cleared device's derived fat fraction (UDFF) was used as a comparative reference.
8. Sample Size for the Training Set
- The document states that "The exams used for test/training validation purpose are separated from the ones used during training process" but does not provide the sample size for the training set itself for any of the AI features.
9. How the Ground Truth for the Training Set was Established
- The document implies that the ground truth for training data would have been established similarly to the test data ground truth (e.g., expert annotation for Auto Abdominal Color Assistant, expert measurements for Auto Aorta/CBD Measure Assistants). However, the specific methodology for the training set's ground truth establishment (e.g., number of experts, adjudication, qualifications) is not detailed in the provided text. It only explicitly states that "Before the process of data annotation, all information displayed on the device is removed and performed on information extracted purely from Ultrasound B-mode images" for annotation. Independence of test and training data by exam site origin or overall separation is mentioned, but not the process for creating the training set ground truth.
Ask a specific question about this device
(125 days)
The LOGIQ E10s is intended for use by a qualified physician for ultrasound evaluation.
Specific clinical applications and exam types include: Fetal / Obstetrics; Abdominal (including Renal, Gynecology / Pelvic); Pediatric; Small Organ (Breast, Testes, Thyroid); Neonatal Cephalic; Adult Cephalic; Cardiac (Adult and Pediatric); Peripheral Vascular; Musculo-skeletal Conventional and Superficial; Urology (including Prostate); Transrectal; Transvaginal; Transesophageal and Intraoperative (Abdominal and Vascular).
Modes of operation include: B, M, PW Doppler, CW Doppler, Color Doppler, Color M Doppler, Power Doppler, Harmonic Imaging, Coded Pulse, 3D/4D Imaging mode, Elastography, Shear Wave Elastography, Attenuation Imaging and Combined modes: B/M, B/Color, B/PWD, B/Color/PWD, B/Power/PWD.
The LOGIQ E10s is intended to be used in a hospital or medical clinic.
The LOGIQ E10s is a full featured, Track 3, general purpose diagnostic ultrasound system which consists of a mobile console approximately 585 mm wide (keyboard), 991 mm deep and 1300 mm high that provides digital acquisition, processing and display capability. The user interface includes a computer keyboard, specialized controls, 12-inch high-resolution color touch screen and 23.8-inch High Contrast LED LCD monitor.
The provided text describes three AI features: Auto Abdominal Color Assistant 2.0, Auto Aorta Measure Assistant, and Auto Common Bile Duct (CBD) Measure Assistant, along with a UGFF Clinical Study.
Here's an analysis of the acceptance criteria and study details for each, where available:
1. Table of Acceptance Criteria and Reported Device Performance
For Auto Abdominal Color Assistant 2.0
| Acceptance Criteria | Reported Device Performance | Meets Criteria? |
|---|---|---|
| Overall model detection accuracy (sensitivity and specificity): $\ge 80%$ (0.80) | Accuracy: 94.8% | Yes |
| Sensitivity (True Positive Rate): $\ge 80%$ (0.80) | Sensitivity: 0.91 | Yes |
| Specificity (True Negative Rate): $\ge 80%$ (0.80) | Specificity: 0.98 | Yes |
| DICE Similarity Coefficient (Segmentation Accuracy): $\ge 0.80$ | DICE score: 0.82 | Yes |
For Auto Aorta Measure Assistant
| Acceptance Criteria | Reported Device Performance | Meets Criteria? |
|---|---|---|
| No explicit numerical acceptance criteria were provided for keystrokes or measurement accuracy. The study aims to demonstrate improvement in keystrokes and acceptable accuracy. The provided results are the performance reported without specific targets for acceptance. | Long View Aorta:- Average keystrokes: 4.132 (without AI) vs. 1.236 (with AI)- Average accuracy: 87.2% with 95% CI of +/- 1.98%- Average absolute error: 0.253 cm with 95% CI of 0.049 cm- Limits of Agreement: (-0.15, 0.60) with 95% CI of (-0.26, 0.71)Short View AP Measurement:- Average accuracy: 92.9% with 95% CI of +/- 2.02%- Average absolute error: 0.128 cm with 95% CI of 0.037 cm- Limits of Agreement: (-0.21, 0.36) with 95% CI of (-0.29, 0.45)Short View Trans Measurement:- Average accuracy: 86.9% with 95% CI of +/- 6.25%- Average absolute error: 0.235 cm with 95% CI of 0.110 cm- Limits of Agreement: (-0.86, 0.69) with 95% CI (-1.06, 0.92) | N/A |
For Auto Common Bile Duct (CBD) Measure Assistant
| Acceptance Criteria | Reported Device Performance | Meets Criteria? |
|---|---|---|
| No explicit numerical acceptance criteria were provided for keystrokes or measurement accuracy. The study aims to demonstrate reduction in keystrokes and acceptable accuracy. The provided results are the performance reported without specific targets for acceptance. | - Average reduction in keystrokes (manual vs. AI): 1.62 +/- 0.375Keystrokes for Porta Hepatis measurement with segmentation scroll edit- Average accuracy: 80.56% with 95% CI of +/- 8.83%- Average absolute error: 0.91 mm with 95% CI of 0.45 mm- Limits of Agreement: (-1.96, 3.25) with 95% CI of (-2.85, 4.14)Porta Hepatis measurement accuracy without segmentation scroll edit- Average accuracy: 59.85% with 95% CI of +/- 17.86%- Average absolute error: 1.66 mm with 95% CI of 1.02 mm- Limits of Agreement: (-4.75, 4.37) with 95% CI of (-6.17, 5.79) | N/A |
For UGFF Clinical Study
| Acceptance Criteria (Implied by intent to demonstrate strong correlation) | Reported Device Performance | Meets Criteria? |
|---|---|---|
| Strong correlation between UFF values and MRI-PDFF (e.g., correlation coefficient $\ge 0.8$) | Original study: Correlation coefficient = 0.87Confirmatory study (US/EU): Correlation coefficient = 0.90(Confirmatory study (UGFF vs UDFF): Correlation coefficient = 0.88) | Yes |
| Acceptable Limits of Agreement with MRI-PDFF (e.g., small offset and LOA with high percentage of patients within LOA) | Original study: Offset = -0.32%, LOA = -6.0% to 5.4%, 91.6% patients within LOAConfirmatory study (US/EU): Offset = -0.1%, LOA = -3.6% to 3.4%, 95.0% patients within LOA | Yes |
| No statistically significant effect of BMI, SCD, and other demographic confounders on AC, BSC, and SNR measurements (Implied) | The results of the clinical study indicate that BMI, SCD, and other demographic confounders do not have a statistically significant effect on measurements of the AC, BSC, and SNR. | Yes |
2. Sample size used for the test set and the data provenance
Auto Abdominal Color Assistant 2.0:
- Sample Size: 49 individual subjects (1186 annotation images)
- Data Provenance: Retrospective, from the USA (100%).
Auto Aorta Measure Assistant:
- Sample Size:
- Long View Aorta: 36 subjects
- Short View Aorta: 35 subjects
- Data Provenance: Retrospective, from Japan and USA.
Auto Common Bile Duct (CBD) Measure Assistant:
- Sample Size: 25 subjects
- Data Provenance: Retrospective, from USA (40%) and Japan (60%).
UGFF Clinical Study:
- Sample Size:
- Original study: 582 participants
- Confirmatory study (US/EU): 15 US patients and 5 EU patients (total 20)
- Confirmatory study (UGFF vs UDFF): 24 EU patients
- Data Provenance: Retrospective and Prospective implicitly (clinical study implies data collection).
- Original Study: Japan (Asian population)
- Confirmatory Study (US/EU): US and EU (demographic info unavailable for EU patients, US patients: BMI 21.0-37.5, SCD 13.9-26.9)
- Confirmatory Study (UGFF vs UDFF): EU
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Auto Abdominal Color Assistant 2.0:
- Number of Experts: Not specified. The text mentions "Readers to ground truth the 'anatomy'".
- Qualifications of Experts: Not specified.
Auto Aorta Measure Assistant:
- Number of Experts: Not specified. The text mentions "Readers to ground truth the AP measurement..." and an "Arbitrator to select most accurate measurement among all readers." This implies multiple readers and a single arbitrator.
- Qualifications of Experts: Not specified.
Auto Common Bile Duct (CBD) Measure Assistant:
- Number of Experts: Not specified. The text mentions "Readers to ground truth the diameter..." and an "Arbitrator to select most accurate measurement among all readers." This implies multiple readers and a single arbitrator.
- Qualifications of Experts: Not specified.
UGFF Clinical Study:
- Number of Experts: Not applicable, as ground truth was established by MRI-PDFF measurements, not expert consensus on images.
4. Adjudication method for the test set
Auto Abdominal Color Assistant 2.0:
- Adjudication Method: Not explicitly described as a specific method (e.g., 2+1). The process mentions "Readers to ground truth" and then comparison to AI predictions, but no specific adjudication among multiple readers' initial ground truths.
Auto Aorta Measure Assistant:
- Adjudication Method: Implies an arbitrator-based method. "Arbitrator to select most accurate measurement among all readers." This suggests multiple readers provide measurements, and a single arbitrator makes the final ground truth selection.
Auto Common Bile Duct (CBD) Measure Assistant:
- Adjudication Method: Implies an arbitrator-based method. "Arbitrator to select most accurate measurement among all readers." Similar to the Aorta assistant.
UGFF Clinical Study:
- Adjudication Method: Not applicable. Ground truth was established by MRI-PDFF measurements.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
Auto Abdominal Color Assistant 2.0:
- MRMC Study: Not explicitly stated as a comparative effectiveness study showing human improvement. The study focuses on the algorithm's performance against ground truth.
- Effect Size (Human Improvement with AI): Not reported.
Auto Aorta Measure Assistant:
- MRMC Study: Yes, an implicit MRMC study comparing human performance with and without AI. Readers performed measurements with and without AI assistance.
- Effect Size (Human Improvement with AI):
- Long View Aorta (Keystrokes): Average keystrokes reduced from 4.132 (without AI) to 1.236 (with AI).
- Short View Aorta (Keystrokes): Average keystrokes reduced from 7.05 (without AI) to 2.307 (with AI).
- (No specific improvement in diagnostic accuracy for human readers with AI is stated, primarily focuses on efficiency via keystrokes).
Auto Common Bile Duct (CBD) Measure Assistant:
- MRMC Study: Yes, an implicit MRMC study comparing human performance with and without AI. Readers performed measurements with and without AI assistance.
- Effect Size (Human Improvement with AI):
- Porta Hepatis CBD (Keystrokes): Average reduction in keystrokes for measurements with AI vs. manually is 1.62 +/- 0.375.
- (No specific improvement in diagnostic accuracy for human readers with AI is stated, primarily focuses on efficiency via keystrokes).
UGFF Clinical Study:
- MRMC Study: No, this was a standalone algorithm performance study compared to a reference standard (MRI-PDFF) and a predicate device (UDFF). It did not involve human readers using the AI tool.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Auto Abdominal Color Assistant 2.0:
- Standalone Performance: Yes. The reported accuracy, sensitivity, specificity, and DICE score are for the algorithm's performance.
Auto Aorta Measure Assistant:
- Standalone Performance: Yes, implicitly. The "AI baseline measurement" was compared for accuracy against the arbitrator-selected ground truth. While keystrokes involved human interaction to use the AI, the measurement accuracy is an algorithm output.
Auto Common Bile Duct (CBD) Measure Assistant:
- Standalone Performance: Yes, implicitly. The "AI baseline measurement" was compared for accuracy against the arbitrator-selected ground truth.
UGFF Clinical Study:
- Standalone Performance: Yes. The study directly assesses the correlation and agreement of the UGFF algorithm's output with MRI-PDFF and another ultrasound-derived fat fraction algorithm.
7. The type of ground truth used
Auto Abdominal Color Assistant 2.0:
- Ground Truth Type: Expert consensus for anatomical visibility ("Readers to ground truth the 'anatomy' visible in static B-Mode image.")
Auto Aorta Measure Assistant:
- Ground Truth Type: Expert consensus from multiple readers, adjudicated by an arbitrator, for specific measurements ("Arbitrator to select most accurate measurement among all readers.")
Auto Common Bile Duct (CBD) Measure Assistant:
- Ground Truth Type: Expert consensus from multiple readers, adjudicated by an arbitrator, for specific measurements ("Arbitrator to select most accurate measurement among all readers.")
UGFF Clinical Study:
- Ground Truth Type: Outcomes data / Quantitative Reference Standard: MRI Proton Density Fat Fraction (MRI-PDFF %).
8. The sample size for the training set
Auto Abdominal Color Assistant 2.0:
- Training Set Sample Size: Not specified beyond "The exams used for test/training validation purpose are separated from the ones used during training process".
Auto Aorta Measure Assistant:
- Training Set Sample Size: Not specified beyond "The exams used for regulatory validation purpose are separated from the ones used during model development process".
Auto Common Bile Duct (CBD) Measure Assistant:
- Training Set Sample Size: Not specified beyond "The exams used for regulatory validation purpose are separated from the ones used during model development process".
UGFF Clinical Study:
- Training Set Sample Size: Not specified. The study describes validation but not the training phase.
9. How the ground truth for the training set was established
Auto Abdominal Color Assistant 2.0:
- Training Set Ground Truth: Not explicitly detailed, but implied to be similar to the test set ground truthing process: "Information extracted purely from Ultrasound B-mode images" and "Readers to ground truth the 'anatomy'".
Auto Aorta Measure Assistant:
- Training Set Ground Truth: Not explicitly detailed, but implied to be similar to the test set ground truthing process: "Information extracted purely from Ultrasound B-mode images" and "Readers to ground truth the AP measurement...".
Auto Common Bile Duct (CBD) Measure Assistant:
- Training Set Ground Truth: Not explicitly detailed, but implied to be similar to the test set ground truthing process: "Information extracted purely from Ultrasound B-mode images" and "Readers to ground truth the diameter...".
UGFF Clinical Study:
- Training Set Ground Truth: Not specified for the training set, but for the validation set, the ground truth was MRI-PDFF measurements.
Ask a specific question about this device
(261 days)
Velacur is intended to provide estimates of tissue stiffness generated from shear wave speed measurements (40-70 Hz), ultrasound attenuation and Velacur Determined Fat Fraction (VDFF). The Velacur Determined Fat Fraction combines ultrasound attenuation and backscatter coefficient measurements. The device is indicated to non-invasively determine liver tissue stiffness, attenuation, and Velacur Determined Fat Fraction. VDFF is not intended to be used in pediatric patients. These are meant to be used in conjunction with other clinical indicators in order to aid in clinical management of patients with liver diseases, including hepatic steatosis.
The device is intended to be used in a clinical setting and by trained medical professionals.
Velacur is a portable device intended to non-invasively measure the stiffness and attenuation of the liver via measurement of liver tissue shear modulus and ultrasound attenuation. This is done by measuring the wavelength or wave speed of mechanically created shear waves within the orqan of the patient. Attenuation is measured directly via the loss in power of the ultrasound beam.
The device is designed to be used at the point of care, in clinics and hospitals. The device is used by a medical profession, an employee of the clinic/hospital. The activation unit is placed under the patient, while lying supine on an exam bed. The activation unit vibrates at frequencies 40, 50, and 60 Hz causing shear waves within the liver of the patient. The ultrasound transducer is placed on the patient's skin, over the intercostal space, and is used to take volumetric scans of the liver while shear waves are occurring. The device includes two algorithms designed to help users detect good quality shear waves and identify liver tissue. From the scan data, the device calculates tissue stiffness and attenuation.
Minor hardware and software changes were made to the organ guide (cleared in K223287) was also extended to add more optional overlays on top of the liver overlay to help with optimizing the scan and training users to obtain adequate images. The significant change is the addition of a new output measure for Velacur, an ultrasound derived fat fraction (VDFF).
Here's a breakdown of the acceptance criteria and study details for the Velacur device, as described in the provided FDA 510(k) summary:
1. Table of Acceptance Criteria and Reported Device Performance
The document describes two separate machine learning algorithms: the Velacur Determined Fat Fraction (VDFF) algorithm, the Organ Guide Extension, and the Wave Quality Guide. Each has its own acceptance criteria and performance metrics.
| Feature/Algorithm | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| Velacur Determined Fat Fraction (VDFF) | ||
| Correlation (VDFF vs. MRI-PDFF) | Not explicitly stated an "acceptance criterion" value, but implied to be strong based on predicate device testing. | 0.85 [0.77-0.91] (correlation coefficient [95% CI] in validation cohort) |
| AUC for 5% Steatosis Detection | Not explicitly stated an "acceptance criterion" value. | 0.97 [0.89-0.99] (AUC [95% CI] for detection of 5% steatosis) |
| Organ Guide Extension | ||
| Dice Coefficient | > 0.7 | Not explicitly stated the exact achieved value, but implies met acceptance criteria. |
| Pixel Accuracy | > 80% | Not explicitly stated the exact achieved value, but implies met acceptance criteria. |
| Wave Quality Guide | ||
| Dice Coefficient | > 0.7 | Not explicitly stated the exact achieved value, but implies met acceptance criteria. |
| Sensitivity | > 80% | Not explicitly stated the exact achieved value, but implies met acceptance criteria. |
| Specificity | > 80% | Not explicitly stated the exact achieved value, but implies met acceptance criteria. |
2. Sample Size Used for the Test Set and Data Provenance
-
Velacur Determined Fat Fraction (VDFF):
- Test Set Sample Size: 70 new patients
- Data Provenance: From 3 separate sites (with different Velacur operators). Implied to be prospective, as it's separate from the training data. The document states "Data was collected from sites across the US and Canada" for training, and "Evaluation data was collected... from separate patients, sites and collected by different users than the data used for training in order to ensure data independence," suggesting a similar geographical distribution for the test set. Retrospective/prospective not explicitly stated for this particular validation cohort, but the nature of MRI scans for ground truth implies it would be collected alongside the Velacur scans.
-
Organ Guide Extension:
- Test Set Sample Size: More than 800 images from 21 patients.
- Data Provenance: "Evaluation data was collected from volunteers and patients with non-alcoholic fatty liver disease and non-alcoholic steatohepatitis. All patients were recruited from hepatology clinics." Data was collected from sites across the US and Canada (implied to be similar for evaluation as for training). Data for evaluation was explicitly stated to be from "separate patients, sites and collected by different users than the data used for training," indicating an independent, possibly prospective collection for evaluation.
-
Wave Quality Guide:
- Test Set Sample Size: More than 4,000 images from 36 patients.
- Data Provenance: "Evaluation data was collected from volunteers and patients with non-alcoholic fatty liver disease and non-alcoholic steatohepatitis. All patients were recruited from hepatology clinics." Data was collected from sites across the US and Canada (implied to be similar for evaluation as for training). Data for evaluation was explicitly stated to be from "separate patients, sites and collected by different users than the data used for training," indicating an independent, possibly prospective collection for evaluation.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
-
Velacur Determined Fat Fraction (VDFF):
- Number of Experts: Not specified.
- Qualifications of Experts: Not specified. The MRI scans were "assessed to create the final measurement," implying expert interpretation without explicitly stating the number or qualifications.
-
Organ Guide Extension:
- Number of Experts: Not specified.
- Qualifications of Experts: "experts in the field of sonography and/or ultrasound elastography." No specific experience level (e.g., years) is provided.
-
Wave Quality Guide:
- Number of Experts: Not specified.
- Qualifications of Experts: "experts in the field of ultrasound elastography." No specific experience level (e.g., years) is provided.
4. Adjudication Method for the Test Set
The document does not explicitly describe an adjudication method (such as 2+1 or 3+1) for establishing ground truth for any of the algorithms. It generally states that ground truth was established by experts or through MRI-PDFF assessment, implying a single assessment per case or a consensus without detailing the process.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance was not reported in this document. The studies focus on the standalone performance of the AI algorithms.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done
Yes, standalone performance studies were done for all three components:
- Velacur Determined Fat Fraction (VDFF): The reported correlation coefficient and AUC are measures of the algorithm's direct performance against a ground truth (MRI-PDFF).
- Organ Guide Extension: The Dice Coefficient and pixel accuracy measure the algorithm's ability to segment organs directly.
- Wave Quality Guide: The Dice Coefficient, sensitivity, and specificity measure the algorithm's direct ability to identify good quality waves.
7. The Type of Ground Truth Used
- Velacur Determined Fat Fraction (VDFF): MRI Proton Density Fat Fraction (MRI-PDFF). This is considered a highly accurate quantitative measure for liver fat.
- Organ Guide Extension: Manual image segmentation by experts.
- Wave Quality Guide: Manual image segmentation by experts.
8. The Sample Size for the Training Set
- Velacur Determined Fat Fraction (VDFF): 112 patients from 4 sites (used for parameter fitting/training).
- Organ Guide Extension: More than 5,000 patient images.
- Wave Quality Guide: More than 15,000 patient images from 100+ patients.
9. How the Ground Truth for the Training Set Was Established
- Velacur Determined Fat Fraction (VDFF): MRI-PDFF scans were assessed to create the final measurement.
- Organ Guide Extension: Manual image segmentation by experts in the field of sonography and/or ultrasound elastography.
- Wave Quality Guide: Manual image segmentation by experts in the field of ultrasound elastography.
Ask a specific question about this device
(19 days)
For ACUSON Juniper
The ACUSON Juniper ultrasound imaging system is intended to provide images of, or signals from, inside the body by an appropriately trained healthcare professional in a clinical setting for the following applications: Abdominal, Obstetrics, Gynecology, Small Parts, Pediatric, Neonatal, Vascular, Urology, Echocardiography, Musculoskeletal, and Intraoperative applications using different ultrasound transducers for different applications.
The system also provides the ability to measure anatomical structures and provides analysis packages that provide information used by a physician for clinical diagnostic purposes.
The Arterial Health Package (AHP) software provides the physician with the capability to measure Intima Media Thickness and the option to reference normative tables that have been validated in peer-reviewed studies. The information is intended to provide the physician with an easily understood tool for communicating with patients regarding state of their cardiovascular system.
For ACUSON Juniper Select
The ACUSON Juniper Select ultrasound imaging system is intended to provide images of, or signals from, inside the body by an appropriately trained healthcare professional in a clinical setting for the following applications: Abdominal, Obstetrics, Gynecology, Small Parts, Pediatric, Vascular, Urology, Echocardiography and Musculoskeletal applications using different ultrasound transducers for different applications.
The system also provides the ability to measure anatomical structures and provides analysis packages that provide information used by a physician for clinical diagnostic purposes.
The Arterial Health Package (AHP) software provides the physician with the capability to measure Intima Media Thickness and the option to reference normative tables that have been validated in peer-reviewed studies. The information is intended to provide the physician with an easily understood tool for communicating with patients regarding state of their cardiovascular system.
The ACUSON Juniper Diagnostic Ultrasound System and ACUSON Juniper Select Diagnostic Ultrasound System are the multi-purpose mobile, software controlled, diagnostic ultrasound systems with an on-screen display for thermal and mechanical indices related to potential bio-effect mechanisms. Their function is to acquire harmonic ultrasound echo data and display it in B-Mode, M-Mode, Pulsed (PW) Doppler Mode, Continuous (CW) Doppler Mode, Color Doppler Mode, Color M mode, Doppler Tissue Image, Amplitude Doppler Mode, a combination of modes, or Harmonic Imaging and 3D Imaging, or Harmonic Imaging and 4D imaging on a Flat Panel Display.
This is a 510(k) premarket notification for an ultrasound system, which primarily focuses on demonstrating substantial equivalence to a predicate device rather than presenting novel clinical performance data that would typically require specific acceptance criteria and a detailed study report.
Therefore, the requested information regarding acceptance criteria and the study that proves the device meets the acceptance criteria in the context of device performance, human reader improvement, and ground truth establishment is not available in the provided text.
The document states: "The subject of this premarket submission, ACUSON Juniper and ACUSON Juniper Select, did not require clinical studies to support substantial equivalence." This means that no specific clinical performance study was conducted to establish new performance metrics against predefined acceptance criteria for clinical diagnostic accuracy or effectiveness.
Instead, the submission focuses on demonstrating substantial equivalence through:
- Comparison of Indications for Use and Technological Characteristics: The document includes tables comparing the new device's indications for use and features with those of the predicate device (K221190) and reference devices (K183575, K213487). The primary claim is that the new device is "substantially equivalent ... with regards to intended use, indications for use, technological characteristics (Transducers, accessories and software features) and safety and effectiveness."
- Nonclinical Tests: These tests focus on safety aspects like acoustic output, biocompatibility, cleaning/disinfection, thermal safety, electromagnetic compatibility, and mechanical safety, conforming to applicable medical device safety standards (e.g., IEC 62359, AAMI ES60601-1, IEC 60601-1-2, IEC 60601-2-18, IEC 60601-2-37, ISO 10993-1).
In summary, there were no specific acceptance criteria for diagnostic performance established in this submission, nor was there a clinical study designed to demonstrate performance against such criteria. The "proof" of meeting acceptance criteria is the demonstration of substantial equivalence to already cleared devices based on technological similarity and nonclinical safety testing.
Ask a specific question about this device
(34 days)
The ACUSON Sequoia ultrasound imaging system is intended to provide images of, or signals from, inside the body by an appropriately trained healthcare professional in a clinical setting for the following applications: Fetal. Abdominal. Pediatric, Neonatal Cephalic, Small Parts, OB/GYN (useful for visualization of the ovaries, follicles, uterus and other pelvic structures), Cardiac, Pelvic, Vascular, Adult Cephalic, Musculoskeletal and Peripheral Vascular applications.
The system supports the Ultrasonically-Derived Fat Fraction (UDFF) measurement tool to report an index that can be useful as an aid to a physician managing adult patients with hepatic steatosis.
The system also provides the ability to measure anatomical structures for fetal, abdominal, pediatric, small organ, cardiac, transrectal, transvaginal, peripheral vessel, musculoskeletal and calculation packages that provide information to the clinician that may be used adjunctively with other medical data obtained by a physician for clinical diagnosis purposes.
The ACUSON Sequoia Diagnostic Ultrasound System is a multi-purpose mobile, software controlled, diagnostic ultrasound system with an on-screen display of thermal and mechanical indices related to potential bio-effect mechanisms. Its function is to transmit and receive ultrasound echo data and display it in B-Mode, M-Mode, Pulsed (PW) Doppler Mode, Continuous (CW) Doppler Mode. Color Doppler Mode. Color M Mode. Doppler Tissue Mode. Amplitude Doppler Mode, a combination of modes, Panoramic Imaging, Contrast agent Imaging, Virtual Touch Strain Imaging, Virtual Touch - pSWE Imaging, Virtual Touch - SWE Imaging, syngo Velocity Vector Imaging, Custom Tissue Imaging, 3D/4D Volume Imaging and Harmonic Imaging on a Display.
Theprovided text primarily focuses on the FDA's substantial equivalence determination for the ACUSON Sequoia Diagnostic Ultrasound System, explaining that clinical studies were not required as the device uses the same technology and principles as existing devices. Therefore, the document does not contain the information requested regarding acceptance criteria and a study proving the device meets them, in the typical sense of a clinical performance study.
However, I can extract the information provided about the device's characteristics and the non-clinical tests relied upon for substantial equivalence.
Here's a breakdown of the available information in relation to your request, highlighting what is not present:
1. A table of acceptance criteria and the reported device performance:
This information is not provided in a clinical performance context. The document states that clinical studies were not required for substantial equivalence. The "acceptance criteria" here relate to compliance with regulatory standards and equivalency to predicate devices.
| Acceptance Criteria (Implied for Substantial Equivalence and Safety) | Reported Device Performance (as stated in the document) |
|---|---|
| Conformance to applicable medical device safety standards | Device has been evaluated for acoustic output, biocompatibility, cleaning and disinfection effectiveness, thermal, electromagnetic, and mechanical safety, and conforms to applicable medical device safety standards. |
| Compliance with specific voluntary standards | Complies with: - IEC 62359: Edition 2.1 2017-09 - AAMI ES60601-1:2005/(R)2012 and A1:2012, C1:2009/(R)2012 and A2:2010/(R)2012 - IEC 60601-1:2005 - IEC 60601-1-2 Edition 4.0 2014-02 - IEC 60601-2-18: Edition 3.0 2009-08 - IEC 60601-2-37 Edition 2.1 2015 - ISO 10993-1 Edition 2.1 2017-09 |
| Substantial Equivalence to predicate devices in intended use and technological characteristics | The ACUSON Sequoia Diagnostic Ultrasound System is substantially equivalent to ACUSON Sequoia (K201462) and ACUSON S family (K183575) regarding intended use and technological characteristics. |
| Inclusion of new or improved features | Updated indications for use to add UDFF (Ultrasonically-Derived Fat Fraction), Auto pSWE, Auto IMT, eSieDoppler, Virtual Workstation, and Image Rotate (features previously cleared on predicate/reference devices). |
| Design and development process conforms to quality system regulations | Conforms to 21 CFR 820 Quality System Regulation and ISO 13485:2016 quality system standards. |
Regarding a clinical study proving device meets acceptance criteria:
The document explicitly states: "Since the ACUSON Sequoia Diagnostic Ultrasound System uses the same technology and principles as existing devices, clinical studies were not required to support substantial equivalence." (Page 9)
Therefore, the following information points are not applicable or not available from the provided text for a clinical performance study:
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):
Not applicable, as no clinical performance study was conducted.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience):
Not applicable, as no clinical performance study was conducted.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
Not applicable, as no clinical performance study was conducted.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:
Not applicable, as no clinical performance study was conducted. The document doesn't mention AI assistance in this context, only new features.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
Not applicable, as no clinical performance study was conducted.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):
Not applicable, as no clinical performance study was conducted.
8. The sample size for the training set:
Not applicable, as no clinical performance study was conducted using a training set in the context of a new algorithm requiring performance evaluation.
9. How the ground truth for the training set was established:
Not applicable, as no clinical performance study was conducted using a training set.
Ask a specific question about this device
Page 1 of 1