Search Results

Heuron ICH is radiological computer-aided triage and notification software designed for the analysis of non-contrast head CT images in adults or transitional adolescents aged 18 and older. This device is intended to aid appropriately trained medical specialists and hospital networks in streamlining workflow by identifying and communicating suspected positive findings of Intracranial hemorrhage (ICH).

Heuron ICH employs an artificial intelligence algorithm to analyze non-contrast CT images, flagging cases with identified findings through a dedicated application that operates in parallel with the standard of care image interpretation process. Users receive notifications for cases with suspected findings, which include compressed preview images provided for informational purposes only and are not intended for diagnostic use beyond notification. Importantly, Heuron ICH does not modify the original medical images and is not intended to serve as a diagnostic device.

The results generated by Heuron ICH are intended to complement other patient information and assist medical specialists in prioritizing and triaging medical images. Notified medical specialists are responsible for viewing the full non-contrast CT images in accordance with established standard of care practices.

Heuron ICH registers with the hospital's Picture Archiving and Communication System (PACS) using IP, Port, AE title, and TLS authentication details. It automatically receives Non-Contrast Computed Tomography (NCCT) images in DICOM format from PACS. Upon connection request from PACS to Heuron ICH, the system verifies the IP, Port, AE title, and TLS authentication information before accepting the image transmission. The product does not query PACS to retrieve images. Instead, it receives images automatically from PACS systems that are allowed access by registering a list (white list) of PACS systems capable of uploading images to the product.

The Heuron ICH is an artificial intelligence-based solution that analyzes non-contrast CT images and provides a notification of suspected positive cases of intracranial hemorrhage (ICH) for prioritization of review. Heuron ICH uses deep learning (DL) technique of a convolutional neural network (CNN). Dataset obtained from the RSNA (Radiological Society of North America) Brain CT Hemorrhage Challenge 2019 was used for training and development of the model. Once the DICOM images transmitted from PACS are uploaded to the Heuron ICH server, the images become accessible through the worklist. The worklist displays patient identification information (Patient ID, name, age, etc.) and analysis status for convenient reference. Images received by Heuron ICH server are analyzed in the order of reception.

During the analysis, if ICH is suspected, the server provides users with a notification. The notifications include compressed preview images, which are not to be used for diagnostic use, but only for informational purposes. It is important to note that the software does not provide segmentation, analysis, or intermediate outputs to users. These notifications can be sent to registered email addresses, mobile SMS, and through the mobile app push notification feature.

Here's a breakdown of the acceptance criteria and the study proving the Heuron ICH device meets these criteria, based on the provided FDA 510(k) Clearance Letter.

Acceptance Criteria and Device Performance

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document specifies the acceptance criteria as the lower bound of the 95% Confidence Interval for both sensitivity and specificity.

Study Details

2. Sample Size and Data Provenance

• Test Set Sample Size: 600 NCCT images
• Data Provenance:
  • Country of Origin: United States (obtained from three different hospitals located in the US)
  • Retrospective or Prospective: Retrospective

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: 3
• Qualifications of Experts: US board-certified neuroradiologists

4. Adjudication Method for the Test Set

• Adjudication Method: 2+1. Two US board-certified neuroradiologists (truthers) independently interpreted each NCCT image. In case of disagreement between these two, a third truther reviewed the case to establish the final ground truth.

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

• Was an MRMC study done? No. The document describes a "standalone performance study." While it mentions "time-to-notification" comparison to standard of care, it doesn't detail a comparative effectiveness study involving human readers with and without AI assistance for diagnostic accuracy improvements.

6. Standalone Performance Study

• Was a standalone (algorithm only) performance study done? Yes. The document explicitly states, "The standalone performance study results exceeded the acceptance criteria..."

7. Type of Ground Truth Used

• Type of Ground Truth: Expert Consensus. The ground truth was determined by the interpretion of NCCT images by two US board-certified neuroradiologists, with a third neuroradiologist resolving disagreements.

8. Sample Size for the Training Set

• Training Set Sample Size: Not explicitly stated in the provided text. The document mentions, "Dataset obtained from the RSNA (Radiological Society of North America) Brain CT Hemorrhage Challenge 2019 was used for training and development of the model," but does not specify the exact number of images from this dataset used for training.

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

• Ground Truth Establishment for Training Set: The document states that the "Dataset obtained from the RSNA (Radiological Society of North America) Brain CT Hemorrhage Challenge 2019 was used for training and development of the model." While the specific method of ground truth establishment for that particular dataset isn't detailed here, it implies relying on the ground truth provided with the RSNA challenge dataset, which typically involves expert human annotation.

Ask a specific question about this device

Veuron-Brain-pAb3 is software for the registration, fusion, display, and analysis of medical images from multiple modalities including MRI and PET. The software aids clinicians in the assessment and quantification of pathologies from PET Amyloid scans of the human brain. It enables anatomic analysis and visualization of amyloid protein concentration through the calculation of standard uptake volume ratio (SUVR) within target reqions of interest and comparison to those within the reference regions. The software is deployed via medical imaging workplaces and is organized as a series of workflows which are specific to use with radio-tracer and disease combinations.

The Veuron-Brain-pAb3 is a standalone software for quantitative analysis of the PET amyloid by automatically calculating the "Standardized Uptake Value Ratio (SUVR)". The calculated result is only used as a reference to support the accuracy of the medical professional's diagnosis of dementia in patients. It also helps with accurate visual interpretation through visualization functions. Various PET amyloid images can be processed by using diverse options provided for users to choose in the image process.

The provided text describes the acceptance criteria and the study that proves the device meets those criteria for the Veuron-Brain-pAb3, a medical imaging software.

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

The document doesn't provide explicit acceptance criteria in a quantitative format (e.g., minimum accuracy percentages, SUVR ranges) for the Veuron-Brain-pAb3. Instead, it states that "Software verification and validation was performed to demonstrate the new functions perform as intended." and "The testing results support that all the system requirements have met their acceptance criteria and are adequate for its intended use."

However, the key functions that define the device's performance, as outlined in the "Summary of Technological Characteristics" and "Device Description," are:

• Automatic calculation of Standardized Uptake Value Ratio (SUVR) within target regions of interest and comparison to reference regions.
• Anatomic analysis and visualization of amyloid protein concentration.
• Registration, fusion, and display of medical images (MRI and PET).
• Accurate visual interpretation through visualization functions.

The document implicitly states that these functions perform as intended, which serves as the "reported device performance" meeting the unspecified acceptance criteria.

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

The document does not explicitly state the sample size used for the test set. However, it mentions under 'Segmentation Algorithm' that the CNN model was "trained [on] 3D brain MR images were collected from one domestic institution." This suggests the data used for testing (and training) was from a single domestic institution. It doesn't specify if the data was retrospective or prospective, but given it's part of a model training and validation process, it's highly likely to be retrospective.

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

The document does not specify the number or qualifications of experts used to establish the ground truth for the test set. The ground truth for the segmentation algorithm appears to be implicitly derived from the "3D brain MR images collected from one domestic institution" used for training the CNN model, meaning the "truths" would be the labeled segmentations used to train the model. Given the device's function is quantitative analysis (SUVR calculation), the ground truth for the SUVR calculation itself would be based on the established methodology of SUVR calculation rather than expert annotation for each case.

4. Adjudication method for the test set:

The document does not describe any adjudication method for the test set.

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. The document explicitly states: "No clinical testing was conducted." Therefore, an MRMC comparative effectiveness study was not performed.

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

Yes, implicitly. The device is described as "standalone software for quantitative analysis of the PET amyloid by automatically calculating the 'Standardized Uptake Value Ratio (SUVR)'." The "Non-Clinical Performance Testing" section mentions "Software verification and validation was performed to demonstrate the new functions perform as intended," which would involve evaluating the algorithm's performance in isolation. While the results are not quantitatively detailed, the device's core function is an automated calculation, suggesting standalone performance was assessed.

7. The type of ground truth used:

The type of ground truth for the core SUVR calculation is methodology-based (the calculation itself is a defined process). For the segmentation algorithm, the ground truth would be expert-annotated segmentations of brain MR images, used for training the CNN model.

8. The sample size for the training set:

The document does not specify the exact sample size for the training set, only stating that the CNN model for segmentation was "trained [on] 3D brain MR images were collected from one domestic institution."

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

The ground truth for the CNN model used for segmentation was established through the collection of "3D brain MR images were collected from one domestic institution" that were used to train the model. This implies that these images likely came with pre-existing or expert-derived segmentations necessary for supervised learning. For the SUVR calculation itself, the ground truth is inherently defined by the mathematical formula and anatomical regions used in its computation.

Ask a specific question about this device

Veuron-Brain-mN1 is intended for use in the post-acquisition image enhancement of 3T MR images of the brain acquired through a 3D gradient-echo sequence. When used in combination with other clinical information, the Veuron-Brain-mN1 application may aid the qualified radiologist with diagnosis by providing enhanced visualization of tissue structures with magnetic susceptibility contrasts in brain 3T MR images.

Veuron-Brain mN1 is a post-processing software intended to provide visualization, manipulation and reconstruction capabilities, including susceptibility map-weighted images, of 3D gradient multi echo brain 3T MR images. The Veuron-Brain-mN1 aids in the clinical analysis of brain structures from MR images.

Here's an analysis of the provided text regarding the acceptance criteria and study for the Veuron-Brain-mN1 device:

Based on the provided text, there is no specific clinical study described that proves the device meets detailed acceptance criteria for diagnostic performance outcomes (e.g., sensitivity, specificity, accuracy). The document focuses on non-clinical performance and technological equivalence to a predicate device.

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

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state specific quantifiable acceptance criteria for diagnostic performance, nor does it provide a table of performance metrics (like sensitivity, specificity, or accuracy) derived from a clinical study.

The text mentions:

• "unit tests and integration tests were performed, and all results met the acceptance criteria."
• "The predefined acceptance criteria were met to demonstrate substantial equivalence to the predicate."

However, these "acceptance criteria" are related to system functionality, software verification and validation, and basic performance metrics like Contrast-to-Noise Ratio (CNR) and Signal-to-Noise Ratio (SNR) in phantom and clinical images, rather than clinical diagnostic accuracy.

General Device Performance (from text):

• Functionality: Unit and integration tests met acceptance criteria.
• Safety: Demonstrated through meeting software verification and validation standards (ISO 14971, ISO 62304, IEC 62366).
• Effectiveness (Non-clinical):
  • Evaluated using phantom testing representing the range of susceptibility values in brain tissue.
  • Evaluated on clinical images using CNR/SNR metrics.
  • Scanner models: Siemens Healthcare's and Philips's, 3T field strength.
  • Results supported that "all the system requirements have met their acceptance criteria and are adequate for its intended use."

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

The document does not specify a sample size for a "test set" in the context of a clinical performance study.

• For the non-clinical performance evaluation mentioned: "The device performance was also evaluated on clinical images using CNR/SNR metrics."
  • Sample Size: Not specified.
  • Data Provenance: Not specified (e.g., country of origin, retrospective or prospective). It only mentions "clinical images."

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

The document does not mention the use of experts to establish ground truth for a clinical test set. The performance evaluation described is non-clinical (phantom, CNR/SNR on clinical images), not based on expert-derived ground truth for diagnostic accuracy.

4. Adjudication Method for the Test Set

Since no clinical test set with expert-established ground truth is described, there is no adjudication method mentioned.

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

The document does not describe an MRMC comparative effectiveness study. It does not mention human readers improving with or without AI assistance.

6. Standalone (Algorithm Only) Performance Study

The description of the non-clinical performance ("The device performance was evaluated using phantom testing... Additionally, the device performance was also evaluated on clinical images using CNR/SNR metrics.") describes the standalone performance of the algorithm. However, this is primarily focused on image quality metrics (CNR/SNR) and system functionality, not diagnostic accuracy in a clinical context.

7. Type of Ground Truth Used for Performance Evaluation

For the non-clinical performance evaluation:

• Phantom Testing: Ground truth is inherent in the known susceptibility values of the phantom (engineered truth).
• Clinical Images with CNR/SNR: The "ground truth" here relates to objective image quality metrics (CNR, SNR), not a clinical diagnosis or pathology.

8. Sample Size for the Training Set

The document explicitly states, "The software algorithms are not based on machine learning." Therefore, there is no training set in the deep learning/machine learning sense.

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

As the algorithms are not based on machine learning, there is no training set and thus no ground truth established for a training set.

Ask a specific question about this device

The Veuron-Brain-pAb2 is a software for the registration, fusion, display and analysis of medical images from multiple modalities including MRI and PET. The software aids clinician in the assessment and quantification of pathologies from PET Amyloid scans of the human brain. It enables automatic analysis and visualization of amyloid protein concentration through the calculation of standard uptake volume ratios (SUVR) within target regions of interest and comparison to those within the reference regions. The software is deployed via medical imaging workplaces and is organized as a series of workflows which are specific to use with radiotracer and disease combinations.

The Veuron-Brain-pAb2 is stand-alone software to automatically calculate the "Standardized Uptake Value Ratio (SUVR)" for quantitative analysis of amyloid PET. The calculated result is just used as a reference supporting the accuracy of the diagnosis of patients' dementia for the medical professional. It also helps with accurate visual interpretation through visualization functions. Various amyloid PET images can be processed by providing a variety of options for users to choose in the image process.

The provided text describes the Veuron-Brain-pAb2 device, a software for the registration, fusion, display, and analysis of medical images (MRI and PET) to aid clinicians in assessing and quantifying pathologies from PET Amyloid scans of the human brain. It enables automatic analysis and visualization of amyloid protein concentration through the calculation of standard uptake volume ratios (SUVR).

However, the document is a 510(k) summary and primarily focuses on demonstrating substantial equivalence to a predicate device (Veuron-Brain-pAb). While it mentions "bench testing" and that the "measurement tool performance meets its pre-defined requirements," it does not provide explicit details about specific acceptance criteria, reported device performance metrics against those criteria, or the study design (including sample size, ground truth establishment, expert qualifications, or adjudication methods) that would typically prove such acceptance.

Therefore, many of your requested details cannot be extracted from this document.

Here's a breakdown of what can and cannot be answered from the provided text:

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

• Cannot be fully provided. The document states, "Bench testing is done to show that the system is suitable for its intended use and that the measurement tool performance meets its pre-defined requirements. This did not reveal any issues with the system, demonstrating that the performance of Veuron-Brain-pAb2 is as safe and effective as its predicate device."
  • This implies that there were pre-defined requirements (acceptance criteria) and that the device met them. However, the document does not list these specific acceptance criteria (e.g., accuracy thresholds for SUVR calculation, registration precision limits) or the quantitative results of the device's performance against them.

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

• Cannot be provided. The document mentions "bench testing" but does not describe the test set size, its provenance, or whether it was retrospective or prospective.

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)

• Cannot be provided. The document does not describe the method for establishing ground truth for any test set or the involvement or qualifications of experts in such a process.

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

• Cannot be provided. No adjudication method 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

• Cannot be provided. The document does not mention an MRMC study or any assessment of human reader improvement with AI assistance. The device is described as aiding clinicians and providing automatic analysis but not specifically as an AI assistance tool in an MRMC context within this summary.

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

• Partially addressed, but not with specific performance metrics. The device is described as "stand-alone software to automatically calculate the 'Standardized Uptake Value Ratio (SUVR)' for quantitative analysis of amyloid PET." This indicates that the core SUVR calculation is standalone. However, the document does not present specific standalone performance metrics (e.g., sensitivity, specificity, accuracy) for this calculation. It merely states that its performance "is as safe and effective as its predicate device."

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

• Cannot be provided. The document does not specify the type of ground truth used for performance evaluation.

8. The sample size for the training set

• Cannot be provided. The document does not mention a training set or its size.

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

• Cannot be provided. No information about a training set or its ground truth establishment is present.

Ask a specific question about this device

The Veuron-Brain-pAb is a software for the registration, fusion, display and analysis of medical images from multiple modalities including MRI and PET. The software aids clinician in the assessment and quantification of pathologies from PET Amyloid scans of the human brain. It enables automatic analysis and visualization of amyloid protein concentration through the calculation of standard uptake volume ratios (SUVR) within target regions of interest and comparison to those within the reference regions. The software is deployed via medical imaging workplaces and is organized as a series of workflows which are specific to use with radio-tracer and disease combinations.

The Veuron-Brain-pAb is stand-alone software to automatically calculate the "Standardized Uptake Value Ratio (SUVR)" for quantitative analysis of amyloid PET. The calculated result supports the accuracy of the diagnosis of patients' dementia for the medical professional. It also helps with accurate visual interpretation through visualization functions. Various amyloid PET images can be processed by providing a variety of options for users to choose in the image process.

The provided Presubmission document does not contain the detailed acceptance criteria and study results for the Veuron-Brain-pAb device's performance in the quantitative analysis of amyloid PET scans. The document primarily focuses on demonstrating substantial equivalence to predicate devices based on intended use, design features, and general technological characteristics.

However, based on the information provided, here's what can be extracted and what is missing:

1. Table of Acceptance Criteria and Reported Device Performance

This information is not provided in the document. The document states "Bench testing is done to show that the system is suitable for its intended use and that the measurement tool performance meets its pre-defined requirements," and that "This did not reveal any issues with the system, demonstrating that the performance of Veuron-Brain-pAb is as safe and effective as its predicate devices." However, specific quantitative acceptance criteria (e.g., accuracy, precision, correlation with ground truth for SUVR values) and the actual numerical performance results against these criteria are not reported.

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

This information is not provided in the document. The document mentions "non-clinical study performance" and "bench testing" but does not specify the sample size of the test set used or the provenance (country of origin, retrospective/prospective) of the data.

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

This information is not provided in the document. The document does not describe how ground truth was established for any performance testing.

4. Adjudication Method (e.g., 2+1, 3+1, none) for the Test Set

This information is not provided in the document. There is no mention of expert adjudication for ground truth.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size

This information is not provided in the document. The document focuses on standalone device performance and substantial equivalence to predicate devices, not on comparative effectiveness with human readers.

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

Yes, the document implies that standalone performance testing was conducted. It states, "The Veuron-Brain-pAb is stand-alone software to automatically calculate the 'Standardized Uptake Value Ratio (SUVR)' for quantitative analysis of amyloid PET." The "non-clinical study performance" and "bench testing" described would likely refer to the evaluation of this standalone performance. However, specific results beyond the general statement of "no issues" are not presented.

7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.)

This information is not provided in the document. Given the device calculates SUVR for amyloid PET, the ground truth would typically involve either:

• Standardized quantitative methods using a reference region for SUVR calculation (which the device aims to automate).
• Correlation with definitive histopathological findings (e.g., brain biopsy/autopsy) or clinical outcomes for amyloid burden.
• Concordance with expert readings or a consensus panel on amyloid positivity/negativity.
  The document does not specify which, if any, of these were used as ground truth for testing.

8. The Sample Size for the Training Set

This information is not provided in the document. The document does not discuss the development or training of the algorithm.

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

This information is not provided in the document, as the training set and its ground truth establishment are not discussed.

Ask a specific question about this device