Search Results

The device is a general-purpose ultrasound system. Specific clinical applications remain the same as previously cleared: Fetal/OB; Abdominal (including GYN, pelvic and infertility monitoring/follicle development); Pediatric; Small Organ (breast, testes, thyroid etc.); Neonatal and Adult Cephalic; Cardiac (adult and pediatric); Musculo-skeletal Conventional and Superficial; Peripheral Vascular; Transvaginal (including GYN); Transrectal.

The systems are full-featured Track 3 ultrasound systems, primarily for general radiology use and specialized for OB/GYN with particular features for real-time 3D/4D acquisition. They consist of a mobile console with keyboard control panel; color LCD/TFT touch panel, color video display and optional image storage and printing devices. including mechanical and electronic scanning transducers, which highly accurate real-time three-dimensional provide imaging supporting all standard acquisition modes. Voluson E10 is identical in hardware and software compared to the Voluson E8 and Voluson E6 with the exception of scan channels. Voluson E10 has more than Voluson E8 and E6. Voluson E10 also has additional hardware for the 4D electronic probes: eM6C and eM6C G2. The basic software is the same as the predicate and no additional software functions were added in this submission.

The provided document is a 510(k) Premarket Notification Submission for GE Healthcare's Voluson E Series ultrasound systems. It focuses on demonstrating substantial equivalence to a predicate device rather than presenting a study with specific acceptance criteria and detailed device performance metrics for a new clinical application.

Therefore, many of the requested details about acceptance criteria, device performance, sample sizes, expert ground truth, adjudication methods, MRMC studies, standalone performance, and training set information are not available in this document. This submission details an update to existing devices with improved hardware and minor software improvements, asserting that the intended use and performance remain substantially equivalent to the previously cleared predicate.

Here's what can be extracted and what is not available from the provided text:

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

• Acceptance Criteria: Not explicitly stated as pass/fail criteria for a new clinical performance study. The submission focuses on demonstrating substantial equivalence through a comparison of technological characteristics, safety standards, and intended use as described in the "Determination of Substantial Equivalence" section. Implicitly, the acceptance criteria are that the updated device must meet the same safety, effectiveness, and performance levels as its predicate, especially concerning acoustic output, electrical/thermal/mechanical safety, biocompatibility, and software functionality.
• Reported Device Performance: No specific numerical performance metrics (e.g., sensitivity, specificity, accuracy) are provided in this document as it's not a clinical performance study. The document states:
  • "The proposed Voluson E Series (Voluson E6 / Voluson E8 / Voluson E10) is substantially equivalent to the predicate devices with regards to intended use, imaging capabilities, technological characteristics and safety and effectiveness."
  • "The proposed Voluson E Series and predicate Voluson E Series systems have the same clinical intended use."
  • "The proposed Voluson E Series and predicate Voluson E Series systems have the same imaging modes."
  • "The proposed Voluson E Series and predicate Voluson E Series systems have similar capability in terms of performing measurements, capturing digital images, reviewing and reporting studies."
  • "The systems have acoustic power levels which are below the applicable FDA limits."

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/Not provided. This submission did not involve a clinical study with a test set of patient data to evaluate performance for a new clinical claim. It's a technical and regulatory review for substantial equivalence.

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/Not provided. No clinical ground truth was established as no clinical study was conducted for this submission.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

• Not applicable/Not provided. No clinical study was performed.

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

• No. This document explicitly states: "The subject of this premarket submission... did not require clinical studies to support substantial equivalence." Therefore, no MRMC study was conducted. Also, the device is a general-purpose ultrasound system with improved hardware and existing software features, not an AI-assisted diagnostic tool discussed in the context of improving human reader performance.

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

• No. This submission is for an ultrasound system, not a standalone algorithm.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

• Not applicable/Not provided. No new clinical ground truth was established for this submission. The "ground truth" for demonstrating substantial equivalence primarily relies on technical specifications, adherence to safety standards, and documented equivalence to a legally marketed predicate device's performance, which was presumably established in its original clearance.

8. The sample size for the training set

• Not applicable/Not provided. As no new clinical algorithm with a training set is discussed or developed in this submission, this information is not relevant. The software improvements mentioned are to existing features, implying an iterative development process rather than a new AI model requiring a separate training set.

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

• Not applicable/Not provided. No new training set or associated ground truth establishment is described in this document.

Ask a specific question about this device

The device is a general-purpose ultrasound system. Specific clinical applications remain the same as previously cleared: Fetal/OB; Abdominal (including GYN, pelvic and infertility monitoring/follicle development); Pediatric; Small Organ (breast, testes, thyroid etc.); Neonatal and Adult Cephalic; Cardiac (adult and pediatric); Musculo-skeletal Conventional and Superficial; Peripheral Vascular; Transvaginal (including GYN); Transrectal

The systems are full-featured Track 3 ultrasound systems, primarily for general radiology use and specialized for OB/GYN with particular features for real-time 3D/4D acquisition. They consist of a mobile console with keyboard control panel color LCD/TFT touch panel color video display and optional image storage and printing devices. They provide high performance ultrasound imaging and analysis and have comprehensive networking and DICOM capability. They utilize a variety of linear, curved linear, matrix phased array transducers including mechanical and electronic scanning transducers, which provide highly accurate real-time three-dimensional imaging supporting all standard acquisition modes.

The provided document is a 510(k) Premarket Notification Submission for the GE Healthcare Voluson E6, Voluson E8, and Voluson E10 ultrasound systems. It does not contain information about acceptance criteria or a study proving the device meets acceptance criteria for an AI/ML-driven medical device. Instead, it details the substantial equivalence of the new Voluson E Series models to previously cleared predicate devices, primarily focusing on modifications to the ultrasound system itself and new transducer capabilities.

Specifically, the document states:

• "Summary of Clinical Tests: The subject of this premarket submission, Voluson E Series (Voluson E6 / Voluson E8 / Voluson E10), did not require clinical studies to support substantial equivalence."

This indicates that clinical performance data for proving specific acceptance criteria related to AI/ML device performance (like accuracy, sensitivity, specificity, or human improvement with AI assistance) was not part of this particular submission for the overall ultrasound system.

The document mentions new software features like "IOTA Adnex Model" and "SonoCNS (Sono Central Nervous System)," but it does not specify performance metrics or studies conducted to establish their acceptance criteria or prove their performance. The "IOTA Adnex Model" is described as a tool to aid in the diagnosis of cancer by giving a probability of risk, explicitly stating "this software cannot be used to diagnose cancer." This suggests it is a non-diagnostic aid, which typically has different regulatory requirements compared to diagnostic AI/ML algorithms.

Therefore, based on the provided text, I cannot describe the acceptance criteria or a study proving the device meets those criteria for an AI/ML device as it's not present in this 510(k) summary. The submission focuses on hardware and existing technology equivalence.

Ask a specific question about this device

The device is a general-purpose ultrasound system. Specific clinical applications remain the same as previously cleared: Fetal/OB; Abdominal (including GYN, pelvic and infertility monitoring/follicle development); Pediatic; Small Organ (breast, testes, thyroid etc.); Neonatal and Adult Cephalic; Cardiac (adult and pediatric); Musculo-skeletal Conventional and Superficial; Peripheral Vascular; Transvaginal (including GYN); Transrectal

The systems are full-featured Track 3 ultrasound systems, primarily for general radiology use and specialized for OB/GYN with particular features for real-time 3D/4D acquisition. They consist of a mobile console with keyboard control panel; color LCD/TFT touch panel, color video display and optional image storage and printing devices. They provide high performance ultrasound imaging and analysis and have comprehensive networking and DICOM capability. They utilize a variety of linear, curved linear, matrix phased array transducers including mechanical and electronic scanning transducers. which provide highly accurate real-time three-dimensional imaging supporting all standard acquisition modes.

This is a 510(k) premarket notification for the GE Healthcare Voluson E6, Voluson E8, and Voluson E10 ultrasound systems. The document states that clinical studies were not required to support substantial equivalence. Therefore, there is no information about specific acceptance criteria related to a study proving device performance, sample sizes for test or training sets, data provenance, expert ground truth establishment, adjudication methods, or MRMC comparative effectiveness studies.

The document focuses on demonstrating substantial equivalence to predicate devices (K162269 Voluson E6_E8_E10 Diagnostic Ultrasound System and K150087 Vivid E80/E90/E95 Diagnostic Ultrasound System) through technological characteristics, intended use, imaging capabilities, safety, and compliance with recognized standards.

Table of Acceptance Criteria and Reported Device Performance:

Since no clinical studies were performed, there are no specific performance metrics reported for the device against acceptance criteria in the traditional sense of a clinical trial. The "acceptance criteria" here are implicitly met by demonstrating substantial equivalence to predicate devices and compliance with safety and performance standards.

Specific Information Regarding Studies:

1. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective):

   • No clinical test set was used, as clinical studies were not required for this 510(k) submission. Non-clinical tests were performed to ensure compliance with standards.

2. 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 test set requiring expert ground truth was utilized.

3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

   • Not applicable due to the absence of a clinical test set.

4. 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:

   • No MRMC comparative effectiveness study was conducted or reported. The submission focuses on substantial equivalence of the ultrasound system itself, not on specific AI assistance features that would require such a study for performance evaluation. While new software features like "IOTA Simple Rules," "Fetal Heart Analysis," and "SonoMetrium" are mentioned, their specific performance metrics requiring MRMC studies are not detailed or were not deemed necessary for this 510(k) due to claimed substantial equivalence.

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

   • Not applicable, as the device is a diagnostic ultrasound system, not a standalone algorithm. The mentioned software features are integrated into the system.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • Not applicable, as no clinical studies with ground truth were conducted. Compliance with safety and performance standards was demonstrated through non-clinical testing.

7. The sample size for the training set:

   • Not applicable, as no clinical studies were conducted, and therefore no training set was explicitly mentioned. The development of software features would involve internal datasets, but details are not provided in this regulatory document.

8. How the ground truth for the training set was established:

   • Not applicable, for the reasons stated above.

Ask a specific question about this device

The device is a general purpose ultrasound system. Specific clinical applications remain the same as previously cleared: Fetal/OB; Abdominal (including GYN, pelvic and infertility monitoring/follicle development); Pediatric; Small Organ (breast, testes, thyroid etc.); Neonatal and Adult Cephalic; Cardiac (adult and pediatric); Musculo-skeletal Conventional and Superficial; Peripheral Vascular; Transvaginal (including GYN); Transrectal

The systems are full-featured Track 3 ultrasound systems, primarily for general radiology use and specialized for OB/GYN with particular features for real-time 3D/4D acquisition. They consist of a mobile console with keyboard control panel; color LCD/TFT touch panel, color video display and optional image storage and printing devices. They provide high performance ultrasound imaging and analysis and have comprehensive networking and DICOM capability. They utilize a variety of linear, curved linear, matrix phased array transducers including mechanical and electronic scanning transducers, which highly accurate real-time three-dimensional provide imaging supporting all standard acquisition modes.

Based on the provided document, the device (GE Voluson E6, Voluson E8, Voluson E10 ultrasound systems) did not require clinical studies to support substantial equivalence. This means that the device meets acceptance criteria primarily through demonstrating substantial equivalence to predicate devices and adherence to non-clinical safety and performance standards, rather than through a study proving device performance against specific clinical acceptance criteria.

Therefore, many of the requested details about acceptance criteria and a study proving their fulfillment are not applicable or cannot be extracted from this document. The document primarily focuses on demonstrating that the new device shares the same intended use, technological characteristics, and safety and effectiveness as already cleared predicate devices.

Here's what can be inferred from the provided text:

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

Since no clinical study was conducted as part of this 510(k) submission to demonstrate specific performance metrics against clinical acceptance criteria, such a table cannot be created from the provided text. The "acceptance criteria" for this submission are primarily focused on equivalence to predicate devices and adherence to recognized standards.

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

• Not Applicable. No clinical test set data is described due to the nature of the 510(k) submission relying on substantial equivalence, not de novo clinical performance.

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

• Not Applicable. No ground truth for a test set is described.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

• Not Applicable. No adjudication method for a test set is described.

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. Such a study was not performed as per the statement: "The subject of this premarket submission... did not require clinical studies to support substantial equivalence." The document mentions "improved semi-automation to the existing software feature SonoVCAD Heart" and a "Fetal Cardio preset," which suggests some level of AI/automation, but no MRMC study or effectiveness data is provided.

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

• Not Applicable. No standalone algorithm performance study is described. The device is an ultrasound system with integrated features, not a standalone AI algorithm.

7. The type of ground truth used (expert concensus, pathology, outcomes data, etc):

• Not Applicable. No ground truth for specific clinical performance is described as clinical studies were not required. The "ground truth" for this submission revolves around documented adherence to engineering standards and comparison to predicate devices.

8. The sample size for the training set:

• Not Applicable. No training set for an AI/algorithm is described, as no clinical study or specific AI performance evaluation was submitted in this document. While the device does have "improved semi-automation" for SonoVCAD Heart, details about its development (including training sets) are not within this summary.

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

• Not Applicable. No training set or its associated ground truth establishment is described.

Ask a specific question about this device

The device is a general purpose ultrasound system. Specific clinical applications remain the same as previously cleared: Fetal/OB; Abdominal (including GYN, pelvic and infertility monitoring/follicle development); Pediatric; Small Organ (breast, testes, thyroid etc.); Neonatal and Adult Cephalic; Cardiac (adult and pediatric); Musculo-skeletal Conventional and Superficial; Peripheral Vascular; Transvaginal (including GYN); Transrectal

The systems are full-featured Track 3 ultrasound systems, primarily for general radiology use and specialized for OB/GYN with particular features for realtime 3D/4D acquisition. They consist of a mobile console with keyboard control panel; color LCD/TFT touch panel, color video display and optional image storage and printing devices. They provide high performance ultrasound imaging and analysis and have comprehensive networking and DICOM capability. They utilize a variety of linear, curved linear, matrix phased array transducers including mechanical and electronic scanning transducers, which provide highly accurate realtime three dimensional imaging supporting all standard acquisition modes.

The provided FDA 510(k) summary for the GE Healthcare Voluson E6, Voluson E8, and Voluson E10 Diagnostic Ultrasound Systems does not contain details about acceptance criteria or a specific study that proves the device meets acceptance criteria in the context of an AI/algorithm-driven device with performance metrics like sensitivity, specificity, etc.

This submission is for a general-purpose ultrasound system, and the "study" described is a non-clinical evaluation to ensure the device's safety and effectiveness compared to a predicate device. The information provided heavily emphasizes substantial equivalence to a previously cleared ultrasound system (K142472).

Therefore, I cannot extract information to fill in most of the requested fields related to acceptance criteria and device performance based on the input text. However, I can provide what is present, highlighting the absence of AI-specific performance criteria.

Here's an analysis based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

This document does not provide a table of performance acceptance criteria (e.g., sensitivity, specificity, accuracy) for an AI/algorithm feature, nor does it report such performance. The "acceptance criteria" here are framed around compliance with safety standards and equivalence to a predicate device.

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

Not applicable in the context of AI performance studies. The non-clinical tests would have involved various hardware and software validation tests, but not a "test set" of clinical cases for AI performance.

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

Not applicable for an AI performance study. Ground truth in this context would refer to engineering and safety standards compliance.

4. Adjudication Method for the Test Set

Not applicable for an AI performance study.

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

No. The document explicitly states: "The subject of this premarket submission, Voluson E Series (Voluson E6 / Voluson E8 / Voluson E10), did not require clinical studies to support substantial equivalence." This indicates no MRMC study or any clinical study was performed for this 510(k) submission.

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

Not applicable for a standalone AI performance. The document describes an "improved version of an existing software feature SonoAVC called SonoAVC Antral (Antral follicle count)" which "The algorithm has more sensitivity to detect antral (small) follicles." However, no standalone performance study results or acceptance criteria for this improved sensitivity are provided. The claim is made, but no supporting data in the form of a performance study is included in this summary.

7. The Type of Ground Truth Used

For the general ultrasound system and its components (including the SonoAVC Antral feature), the "ground truth" for demonstrating substantial equivalence primarily relies on:

• Engineering measurements and tests against established medical device safety standards (e.g., acoustic output, electrical safety).
• Comparison to the performance and specifications of the predicate device (K142472 Voluson E6_E8_E10 Diagnostic Ultrasound System).
• The improved SonoAVC Antral feature claims "more sensitivity to detect antral (small) follicles," implying that some form of internal validation was done against either expert assessment or another reliable method to establish "ground truth" for follicle detection. However, details of such validation are not provided in this summary.

8. The Sample Size for the Training Set

Not applicable. This document does not describe the development or training of an AI/ML model for which a training set size would be relevant. While the SonoAVC Antral is an algorithm, details on its development or training data are not present.

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

Not applicable. (See #8)

Summary of what is available from the document regarding "acceptance criteria" and "performance":

The acceptance criteria for this ultrasound system are based on demonstrating substantial equivalence to a predicate device (K142472 Voluson E6_E8_E10 Diagnostic Ultrasound System) regarding:

• Intended Use: The systems are for diagnostic ultrasound imaging and fluid flow analysis, with specific clinical applications (Fetal/OB, Abdominal, Pediatric, Small Organ, Neonatal/Adult Cephalic, Cardiac, Musculo-skeletal, Peripheral Vascular, Transvaginal, Transrectal) remaining the same as previously cleared.
• Technological Characteristics: Employing the same fundamental scientific technology and imaging modes as predicate devices.
• Safety and Effectiveness:
  • Manufactured with materials assessed as safe.
  • Acoustic power levels below FDA limits.
  • Compliance with various safety standards (AAMI/ANSI ES60601-1, IEC60601-1-2, IEC60601-2-37, NEMA UD 3, ISO10993-1, NEMA UD 2, ISO14971, NEMA DICOM).
  • Similar capability in measurements, digital image capture, reviewing, and reporting.
  • Designed in compliance with approved electrical and physical safety standards.
  • Transducers are equivalent to the predicate (with some removals and additions of new transducers (IC9-D and eM6C G2) whose applications are within the predicate's indications for use).
  • Addition of an improved SonoAVC Antral feature ("The algorithm has more sensitivity to detect antral (small) follicles"). No specific quantitative performance metric or acceptance criteria are given for this sensitivity improvement in this document.
  • Addition of a Fetal Cardio preset (already cleared in the predicate).
  • Addition of a card reader/bar code scanner.

Reported Device Performance:

The document primarily reports that the device conforms to applicable medical device safety standards and that its performance and features are substantially equivalent to the predicate device. The only specific performance claim related to an algorithm is that SonoAVC Antral has "more sensitivity to detect antral (small) follicles," but no quantifiable performance metrics, specific acceptance criteria, or a study detailing this improvement are provided in this summary. The non-clinical tests evaluated the device for safety (acoustic output, biocompatibility, cleaning/disinfection, thermal, electrical, electromagnetic, mechanical safety) and confirmed compliance with voluntary standards. No clinical studies were required or performed.

Ask a specific question about this device

The device is a general purpose ultrasound system. Specific clinical applications remain the same as previously cleared: Fetal/OB; Abdominal (including GYN, pelvic and infertility monitoring/follicle development); Pediatric; Small Organ (breast, testes, thyroid etc.); Neonatal and Adult Cephalic; Cardiac (adult and pediatric); Musculo-skeletal Conventional and Superficial; Peripheral Vascular; Transvaginal (including GYN); Transrectal

The systems are full-featured Track 3 ultrasound systems, primarily for general radiology use and specialized for OB/GYN with particular features for realtime 3D/4D acquisition. They consist of a mobile console with keyboard control panel; color LCD/TFT touch panel, color video display and optional image storage and printing devices. They provide high performance ultrasound imaging and analysis and have comprehensive networking and DICOM capability. They utilize a variety of linear, curved linear, matrix phased array transducers including mechanical and electronic scanning transducers, which provide highly accurate realtime three dimensional imaging supporting all standard acquisition modes.

This document describes the GE Voluson E6 / Voluson E8 / Voluson E10 Diagnostic Ultrasound Systems, which are general purpose ultrasound systems with specific applications primarily for OB/GYN. The submission is a 510(k) premarket notification, indicating that the device aims to demonstrate substantial equivalence to legally marketed predicate devices.

The information provided does not include details of specific clinical studies with acceptance criteria or performance metrics for new or altered indications. Instead, it focuses on demonstrating that the new Voluson E Series systems are substantially equivalent to their predicate devices based on technological characteristics, safety, and existing cleared indications for use.

Here's the breakdown of the information requested, based on the provided document:

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

The document does not provide a table of acceptance criteria or reported device performance in terms of clinical accuracy or diagnostic performance for the new system. The basis for clearance is "substantial equivalence" to predicate devices, meaning the device performs as intended and is as safe and effective as a legally marketed device. The performance is implied to be equivalent to the predicate devices. The document states:

• "The Voluson E Series (Voluson E6 / Voluson E8 / Voluson E10) is substantially equivalent to the predicate devices with regards to intended use, imaging capabilities, technological characteristics and safety and effectiveness."
• "The Voluson E Series and predicate Voluson E Series systems have the same clinical intended use."
• "The Voluson E Series and predicate Voluson E Series systems have the same imaging modes."
• "The Voluson E Series and predicate Voluson E Series systems transducers are identical except for the removal of three old transducers; no change to the indications for use."

2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)

This information is not provided in the document. The submission is for a general purpose diagnostic ultrasound system; specific clinical studies with defined test sets, sample sizes, or data provenance are typically not included in these types of 510(k) summary documents when demonstrating substantial equivalence for existing indications. The focus is on technical conformity and safety standards.

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)

This information is not provided. As no specific clinical performance study for a new indication is detailed, there's no mention of experts establishing ground truth for a test set.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set

This information is not provided.

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

A multi-reader multi-case (MRMC) comparative effectiveness study was not done and is not mentioned. The device is an ultrasound system and not explicitly described as having AI assistance in the provided summary. The submission focuses on the system's fundamental operational capabilities and safety, not on augmented diagnostic performance with AI.

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

A standalone algorithm performance study was not done and is not mentioned. The device is an ultrasound system.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

This information is not provided. No specific clinical performance evaluations requiring ground truth are detailed in the document.

8. The sample size for the training set

This information is not provided. The document describes an ultrasound system undergoing substantial equivalence review, not an AI/ML algorithm development process that typically involves training sets.

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

This information is not provided.

Ask a specific question about this device