Search Results
Found 258 results
510(k) Data Aggregation
(149 days)
Ask a specific question about this device
(47 days)
TruSPECT is intended for acceptance, transfer, display, storage, and processing of images for detection of radioisotope tracer uptakes in the patient's body. The device using various processing modes supported by the various clinical applications and various features designed to enhance image quality. The emission computerized tomography data can be coupled with registered and/or fused CT/MR scans and with physiological signals in order to depict, localize, and/or quantify the distribution of radionuclide tracers and anatomical structures in scanned body tissue for clinical diagnostic purposes. The acquired tomographic image may undergo emission-based attenuation correction.
Visualization tools include segmentation, colour coding, and polar maps. Analysis tools include Quantitative Perfusion SPECT (QPS), Quantitative Gated SPECT (QGS) and Quantitative Blood Pool Gated SPECT (QBS) measurements, Multi Gated Acquisition (MUGA) and Heart-to-Mediastinum activity ratio (H/M).
The system also includes reporting tools for formatting findings and user selected areas of interest. It is capable of processing and displaying the acquired information in traditional formats, as well as in three-dimensional renderings, and in various forms of animated sequences, showing kinetic attributes of the imaged organs.
TruSPECT is based on Windows operating system. Due to special customer requirements and the clinical focus the TruSPECT can be configured with different combinations of Windows OS based software options and clinical applications which are intended to assist the physician in diagnosis and/or treatment planning. This includes commercially available post-processing software packages.
TruSPECT is a processing workstation primarily intended for, but not limited to cardiac applications. The workstation can be integrated with the D-SPECT cardiac scanner system or used as a standalone post-processing station.
The TruSPECT Processing Station is a software-only medical device (SaMD) designed to operate on a dedicated, high-performance computer platform. It is distributed as pre-installed medical imaging software intended to support image visualization, quantitation, analysis, and comparison across multiple imaging modalities and acquisition time points. The software supports both functional imaging modalities, such as Single Photon Emission Computed Tomography (SPECT) and Nuclear Medicine (NM), as well as anatomical imaging modalities, such as Computed Tomography (CT).
The system enables integration, display, and analysis of multimodal image datasets to assist qualified healthcare professionals in image review and interpretation within the clinical workflow. The software is intended for use by trained medical professionals and assists in image assessment for various clinical applications, including but not limited to cardiology, electrophysiology, and organ function evaluation. The software does not perform automated diagnosis and does not replace the clinical judgment of the user.
The TruSPECT software operates on the Microsoft Windows® operating system and can be configured with various software modules and clinical applications according to user requirements and intended use. The configuration may include proprietary Spectrum Dynamics modules and commercially available third-party post-processing software packages operating within the TruSPECT framework.
The modified TruSPECT system integrates the TruClear AI application as part of its software suite. The TruClear AI module is a software-based image processing component designed to assist in the enhancement of SPECT image data acquired on the TruSPECT system. The module operates within the existing reconstruction and review workflow and does not alter the system's intended use, indications for use, or fundamental technology.
Verification and validation activities were performed to confirm that the addition of the TruClear AI module functions as intended and that overall system performance remains consistent with the previously cleared TruSPECT configuration. These activities included performance evaluations using simulated phantom datasets and representative clinical image data, conducted in accordance with FDA guidance. The results demonstrated that the modified TruSPECT system incorporating TruClear AI meets all predefined performance specifications and continues to operate within the parameters of its intended clinical use.
Here's a breakdown of the acceptance criteria and study details for the TruClear AI module of the TruSPECT Processing Station, based on the provided FDA 510(k) clearance letter:
Acceptance Criteria and Reported Device Performance
| Parameter | Acceptance Criteria | Reported Device Performance (Key Performance Results) |
|---|---|---|
| LVEF | Bland Altman Mean: ±3% | Strong correlation (r=0.94). Bland–Altman analyses showed mean differences within pre-specified acceptance criteria. |
| Bland Altman SD: ≤ 4% | (Implicitly met as mean differences were within criteria) | |
| Regression r (min): > 0.8 | r=0.94 | |
| Slope (range): 0.9 – 1.1 | (Implicitly met as mean differences were within criteria) | |
| Intercept (limit): ± 10% | (Implicitly met as mean differences were within criteria) | |
| EDV | Bland Altman Mean: ± 5 ml | Strong correlation (r=0.98). Bland–Altman analyses showed mean differences within pre-specified acceptance criteria. |
| Bland Altman SD: ≤ 8 ml | (Implicitly met as mean differences were within criteria) | |
| Regression r (min): > 0.8 | r=0.98 | |
| Slope (range): 0.9 – 1.1 | (Implicitly met as mean differences were within criteria) | |
| Intercept (limit): ± 10 ml | (Implicitly met as mean differences were within criteria) | |
| Perfusion Volume | Bland Altman Mean: ± 5 ml | Strong correlation. Bland–Altman analyses showed mean differences within pre-specified acceptance criteria. |
| Bland Altman SD: ≤ 8 ml | (Implicitly met as mean differences were within criteria) | |
| Regression r (min): > 0.8 | (Implicitly met as strong correlation noted) | |
| Slope (range): 0.9 – 1.1 | (Implicitly met as mean differences were within criteria) | |
| Intercept (limit): ± 10 ml | (Implicitly met as mean differences were within criteria) | |
| TPD | Bland Altman Mean: ± 3% | Strong correlation (r=0.98). Bland–Altman analyses showed mean differences within pre-specified acceptance criteria. |
| Bland Altman SD: ≤ 5% | (Implicitly met as mean differences were within criteria) | |
| Regression r (min): > 0.8 | r=0.98 | |
| Slope (range): 0.9 – 1.1 | (Implicitly met as mean differences were within criteria) | |
| Intercept (limit): ± 10% | (Implicitly met as mean differences were within criteria) | |
| Visual Similarity (Denoised vs. Reference) | (Not explicitly quantified as a numeric acceptance criterion range, but implied) | Denoised images were 'similar' to reference, consistent with high inter-reader agreement. Visual similarity ratings indicated denoised images were 'similar' to reference. |
| Inter-observer Agreement (Visual Comparison) | (Not explicitly quantified as an acceptance criterion) | 97–100% after dichotomization (scores ≥3 vs <3) across key metrics. |
Study Details
-
Sample size used for the test set and the data provenance:
- Test Set Sample Size: 24 patients (8 female, 16 male), which yielded 74 images.
- Data Provenance: Multi-center, retrospective dataset from three hospitals in the UK and Germany.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Two (2)
- Qualifications of Experts: Independent, board-certified nuclear medicine physicians.
-
Adjudication method for the test set:
- The document states "two independent, board-certified nuclear medicine physicians visually compared denoised low-count images to the high-count reference using a 5-point Likert scale; inter-observer percent agreement after dichotomization (scores ≥3 vs <3) was 97–100% across key metrics." This suggests a consensus-based approach for establishing some aspect of the ground truth, particularly for the visual similarity assessment, though not explicitly a formal 2+1 or 3+1 adjudication for defining disease status. The reference standard itself was the high-count image, and the experts were comparing the derived AI-processed images to this reference.
-
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:
- An MRMC comparative effectiveness study was not explicitly described in terms of human readers improving with AI vs. without AI assistance. The study focused on validating the AI algorithm's output against a reference standard (high-count image) using visual and quantitative assessment. The two nuclear medicine physicians visually compared the denoised images to the reference, not their own diagnostic performance with and without AI.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone performance assessment of the algorithm was conducted. The quantitative evaluation using the FDA-cleared Cedars-Sinai QPS/QGS to derive perfusion and functional parameters (TPD, volume, EDV, LVEF) directly compared the algorithm's output on low-count images (after denoising) to the high-count reference images. The Bland-Altman and correlation analyses are indicators of standalone performance.
-
The type of ground truth used:
- The primary reference standard (ground truth) for the study was the clinical routine high-count SPECT image (~1.0 MCounts) acquired under standard D-SPECT protocols.
- For quantitative parameters, FDA-cleared Cedars-Sinai QPS/QGS was used on the high-count reference images to derive the ground truth values for perfusion and functional parameters (TPD, volume, EDV, LVEF).
- For visual assessment, the "high-count reference" images served as the ground truth for comparison.
-
The sample size for the training set:
- The total dataset was 352 patients. The training/tuning set consisted of a portion of these patients; specifically, the "held-out test set" was 24 patients, meaning the remaining 328 patients (352 - 24) were used for training and tuning the algorithm.
-
How the ground truth for the training set was established:
- The document implies the same ground truth methodology was used for the training set as for the test set. The algorithm was trained to transform low-count images to effectively match the characteristics of the clinical routine high-count SPECT image as the "gold standard." The Cedars-Sinai QPS/QGS would also have been used on these high-count images to generate the quantitative targets for training, allowing the AI to learn to derive similar quantitative parameters from denoised low-count images.
Ask a specific question about this device
(104 days)
PeekMed web is a system designed to help healthcare professionals carry out pre-operative planning for several surgical procedures, based on their imported patients' imaging studies. Experience in usage and a clinical assessment are necessary for the proper use of the system in the revision and approval of the output of the planning. The multi-platform system works with a database of digital representations related to surgical materials supplied by their manufacturers.
This medical device consists of a decision support tool for qualified healthcare professionals to quickly and efficiently perform the pre-operative planning for several surgical procedures, using medical imaging with the additional capability of planning the 2D or 3D environment. The system is designed for the medical specialties within surgery, and no specific use environment is mandatory, whereas the typical use environment is a room with a computer. The patient target group is adult patients who have an injury or disability diagnosed previously. There are no other considerations for the intended patient population.
PeekMed web is a system designed to help healthcare professionals carry out pre-operative planning for several surgical procedures, based on their imported patients' imaging studies. Experience in usage and a clinical assessment are necessary for the proper use of the system in the revision and approval of the output of the planning.
The multi-platform system works with a database of digital representations related to surgical materials supplied by their manufacturers.
As the PeekMed web is capable of representing medical images in a 2D or 3D environment, performing relevant measurements on those images, and also capable of adding templates, it can then provide a total overview of the surgery. Being software, it does not interact with any part of the body of the user and/or patient.
The acceptance criteria and study proving device performance are described below, based on the provided FDA 510(k) clearance letter for PeekMed web (K252856).
1. Table of Acceptance Criteria and Reported Device Performance
The provided document lists the acceptance criteria but does not explicitly state the reported device performance for each metric from the validation studies. It only states that the efficacy results "met the acceptance criteria for ML model performance." Therefore, the "Reported Device Performance" column reflects this general statement.
| ML model | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| Segmentation | DICE is no less than 90%HD-95 is no more than 8STD DICE is between +/- 10%Precision is more than 85%Recall is more than 90% | Met the acceptance criteria for ML model performance |
| Landmarking | MRE is no more than 7mmSTD MRE is between +/- 5mm | Met the acceptance criteria for ML model performance |
| Classification | Accuracy is no less than 90%.Precision is no less than 85%Recall is no less than 90%F1 score is no less than 90% | Met the acceptance criteria for ML model performance |
| Detection | MAP is no less than 90%.Precision is no less than 85%Recall is no less than 90% | Met the acceptance criteria for ML model performance |
| Reconstruction | DICE is no less than 90%HD-95 is no more than 8STD DICE is between +/- 10%Precision is more than 85%Recall is more than 90% | Met the acceptance criteria for ML model performance |
2. Sample Size Used for the Test Set and Data Provenance
The document distinguishes between a "testing" dataset (used for internal evaluation during development) and an "external validation" dataset. The external validation dataset serves as the independent test set for assessing final model performance.
- Test Set (External Validation):
- Segmentation ML model: 672 unique datasets
- Landmarking ML model: 561 unique datasets
- Classification ML model: 367 unique datasets
- Detection ML model: 198 unique datasets
- Reconstruction ML model: 87 unique datasets
- Data Provenance: The document states that ML models were developed with datasets "from multiple sites." It does not specify the country of origin of the data nor explicitly state whether the data was retrospective or prospective, though "external validation datasets were collected independently of the development data" and "labeled by a separate team," suggesting a retrospective approach to data collection for the validation.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
The document mentions that the "External validation...was employed to provide an accurate assessment of the model's performance." and that the dataset was "labeled by a separate team". It does not specify the number of experts used or their specific qualifications (e.g., "radiologist with 10 years of experience").
4. Adjudication Method for the Test Set
The document states that the ground truth for the external validation dataset was "labeled by a separate team." It does not specify an adjudication method such as 2+1, 3+1, or if multiple experts were involved and how discrepancies were resolved.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
No, the document does not indicate that a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done to evaluate how much human readers improve with AI vs. without AI assistance. The testing focused on the standalone performance of the ML models against a predefined ground truth.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
Yes, a standalone performance evaluation (algorithm only without human-in-the-loop) was done. The performance data section describes the "efficacy results of the [specific] ML model using the testing and external validation datasets against the predefined ground truth," indicating an assessment of the algorithm's performance independent of human interaction during the measurement. The device is described as a "decision support tool" requiring "clinical assessment... for the proper use of the system in the revision and approval of the output," implying the algorithm provides output that a human reviews, but the performance testing described here is on the raw algorithm output.
7. The Type of Ground Truth Used
The ground truth used for both the training and test sets is referred to as "predefined ground truth" and established by "labeling" or a "separate team" for the external validation sets. This implies a human-generated expert consensus or annotation-based ground truth, although the specific expertise and method of consensus are not detailed. It is not explicitly stated as pathology or outcomes data.
8. The Sample Size for the Training Set
The ML models were trained with datasets from multiple sites totaling:
- 2852 X-ray datasets
- 2073 CT scans
- 209 MRIs
These total datasets were split as follows:
- Training Set: 80% of the total dataset for each modality.
- X-ray: 0.80 * 2852 = 2281.6 (approx. 2282)
- CT scans: 0.80 * 2073 = 1658.4 (approx. 1658)
- MRIs: 0.80 * 209 = 167.2 (approx. 167)
9. How the Ground Truth for the Training Set Was Established
The document states, "ML models were developed with datasets...We trained the ML models with 80% of the dataset..." and refers to "predefined ground truth." While it doesn't explicitly detail the process for training data, it is implied that the training data also had human-generated ground truth (annotations/labels), similar to the validation data, as ML models rely on labeled data for supervised learning. It mentions that "leakage between development and validation data sets did not occur," and the external validation set was "labeled by a separate team," suggesting the training data was also labeled by experts, possibly the "internal procedures" mentioned for ML model development.
Ask a specific question about this device
(116 days)
Alzevita is intended for use by neurologists and radiologists experienced in the interpretation and analysis of brain MRI scans. It enables automated labelling, visualization, and volumetric measurement of the hippocampus from high-resolution T1-weighted MRI images. The software facilitates comparison of hippocampal volume against a normative dataset derived from MRI scans of healthy control subjects aged 55 to 90 years, acquired using standardized imaging protocols on 1.5T/3T MRI scanners.
Alzevita is a cloud-based, AI-powered medical image processing software as a medical device intended to assist neurologists and radiologists with expertise in the analysis of 3D brain MRI scans. The software performs fully automated segmentation and volumetric quantification of the hippocampus, a brain structure involved in memory and commonly affected by neurodegenerative conditions.
Alzevita is designed to replace manual hippocampal segmentation workflows with a fast, reproducible, and standardized process. It provides quantitative measurements of hippocampal volume, enabling consistent outputs that can assist healthcare professionals in evaluating structural brain changes.
The software operates through a secure web interface and is compatible with commonly used operating systems and browsers. It accepts 3D MRI scans in DICOM or NIfTI format and displays the MRI image in the MRI viewer allowing trained healthcare professionals to view, zoom, and analyze the MRI scan alongside providing a visual and tabular volumetric analysis report.
The underlying algorithm used in Alzevita is locked, meaning it does not modify its behavior at runtime or adapt to new inputs. This ensures consistent performance and reproducibility of results across users and imaging conditions. Any future modifications to the algorithm including performance updates or model re-training will be submitted to the FDA for review and clearance prior to deployment, in compliance with FDA regulatory requirements and applicable guidance for AI/ML-based SaMD.
Here's a detailed description of the acceptance criteria and the study proving the Alzevita device meets those criteria, based on the provided FDA 510(k) clearance letter:
Acceptance Criteria and Device Performance
1. Table of Acceptance Criteria and Reported Device Performance
| Metric | Acceptance Criteria | Reported Device Performance (Alzevita 95% Confidence Intervals) | Criteria (Pass/Fail) |
|---|---|---|---|
| Overall Dice Score | ≥ 75% | (0.85, 0.86) | Pass |
| Overall Hausdorff Distance | ≤ 6.1 mm | (1.43, 1.59) | Pass |
| Overall Correlation Coefficient | ≥ 0.82 | Not explicitly given as CI, but stated as met | Pass |
| Overall Relative Volume Difference | ≤ 24.6% | Not explicitly given as CI, but stated as met | Pass |
| Overall Bland-Altman Mean Difference (Total Hippocampus Volume) | ≤ 1010 mm³ | Not explicitly given as CI, but stated as met | Pass |
| Subgroup Dice Score (Clinical Subgroups) | ≥ 83% (implied from results) | Control: (0.87, 0.88)MCI: (0.84, 0.85)AD: (0.82, 0.84) | Pass |
| Subgroup Hausdorff Distance (Clinical Subgroups) | ≤ 3 mm (implied from results) | Control: (1.32, 1.41)MCI: (1.44, 1.62)AD: (1.48, 2.10) | Pass |
| Subgroup Dice Score (Gender) | ≥ 83% (implied) | Female: (0.85, 0.87)Male: (0.84, 0.86) | Pass |
| Subgroup Hausdorff Distance (Gender) | ≤ 3 mm (implied) | Female: (1.40, 1.57)Male: (1.41, 1.66) | Pass |
| Subgroup Dice Score (Magnetic Field Strength) | ≥ 83% (implied) | 3T: (0.86, 0.87)1.5T: (0.83, 0.85) | Pass |
| Subgroup Hausdorff Distance (Magnetic Field Strength) | ≤ 3 mm (implied) | 3T: (1.38, 1.47)1.5T: (1.45, 1.79) | Pass |
| Subgroup Dice Score (Slice Thickness) | ≥ 83% (implied) | 1 mm: (0.87, 0.88)1.2 mm: (0.84, 0.85) | Pass |
| Subgroup Hausdorff Distance (Slice Thickness) | ≤ 3 mm (implied) | 1 mm: (1.35, 1.43)1.2 mm: (1.47, 1.72) | Pass |
| Subgroup Dice Score (US Geographical Region) | ≥ 83% (implied) | East US: (0.84, 0.86)West US: (0.85, 0.87)Central US: (0.85, 0.87)Canada: (0.82, 0.88) | Pass |
| Subgroup Hausdorff Distance (US Geographical Region) | ≤ 3 mm (implied) | East US: (1.44, 1.71)West US: (1.35, 1.55)Central US: (1.35, 1.47)Canada: (1.07, 2.34) | Pass |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: 298 subjects.
- Data Provenance: The test set data was collected from the publicly available ADNI (Alzheimer's Disease Neuroimaging Initiative) dataset. It is retrospective and sampled using stratified random sampling, with subjects recruited from ADNI 1 & ADNI 3 datasets.
- Geographical Distribution: Approximately equal geographical distribution within the USA (East coast, Central US regions, West coast) and Canada.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- Number of Experts: Three certified radiologists.
- Qualifications of Experts: They are described as "certified radiologists in India, adhering to widely recognized and standardized segmentation protocols." Specific experience level (e.g., years of experience) is not provided.
4. Adjudication Method for the Test Set
- Adjudication Method: A consensus ground truth was established by integrating individual delineations from the three certified radiologists into a single consensus mask for each case. This integration was performed using the STAPLE (Simultaneous Truth and Performance Level Estimation) algorithm.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- Was a MRMC study done? No, the document describes a standalone performance evaluation of the Alzevita algorithm against a consensus ground truth. There is no mention of a human-in-the-loop study comparing human readers with and without AI assistance.
- Effect size of human readers improvement: Not applicable, as no MRMC study was conducted.
6. Standalone Performance Study
- Was a standalone performance study done? Yes. The entire validation study described evaluates the Alzevita algorithm's performance in segmenting the hippocampus and calculating its volume against a ground truth, without human intervention in the segmentation process.
7. Type of Ground Truth Used
- Type of Ground Truth: Expert consensus. Specifically, it was established through manual segmentation by three certified radiologists, with their individual segmentations integrated via the STAPLE algorithm. This STAPLE-derived consensus mask served as the ground truth.
8. Sample Size for the Training Set
- Sample Size for Training Set: 200 cases.
9. How the Ground Truth for the Training Set Was Established
- Training Set Ground Truth Establishment: "Expert radiologists manually segmented the hippocampus to create the ground truth, which is then used as input for training the Alzevita segmentation model." The number and specific qualifications of the expert radiologists for the training set's ground truth are not detailed beyond "expert radiologists." There is no mention of an adjudication method like STAPLE for the training set ground truth, suggesting individual expert segmentation or an unspecified consensus process.
Ask a specific question about this device
(172 days)
AI-CVD® is an opportunistic AI-powered quantitative imaging tool that provides automated CT-derived anatomical and density-based measurements for clinician review. The device does not provide diagnostic interpretation or risk prediction. It is solely intended to aid physicians and other healthcare providers in determining whether additional diagnostic tests are appropriate for implementing preventive healthcare plans. AI-CVD® has a modular structure where each module is intended to report quantitative imaging measurements for each specific component of the CT scan. AI-CVD® quantitative imaging measurement modules include coronary artery calcium (CAC) score, aortic wall calcium score, aortic valve calcium score, mitral valve calcium score, cardiac chambers volumetry, epicardial fat volumetry, aorta and pulmonary artery sizing, lung density, liver density, bone mineral density, and muscle & fat composition.
Using AI-CVD® quantitative imaging measurements and their clinical evaluation, healthcare providers can investigate patients who are unaware of their risk of coronary heart disease, heart failure, atrial fibrillation, stroke, osteoporosis, liver steatosis, diabetes, and other adverse health conditions that may warrant additional risk assessment, monitoring or follow-up. AI-CVD® quantitative imaging measurements are to be reviewed by radiologists or other medical professionals and should only be used by healthcare providers in conjunction with clinical evaluation.
AI-CVD® is not intended to rule out the risk of cardiovascular diseases. AI-CVD® opportunistic screening software can be applied to non-contrast thoracic CT scans such as those obtained for CAC scans, lung cancer screening scans, and other chest diagnostic CT scans. Similarly, AI-CVD® opportunistic screening software can be applied to contrast-enhanced CT scans such as coronary CT angiography (CCTA) and CT pulmonary angiography (CTPA) scans. AI-CVD® opportunistic bone density module and liver density module can be applied to CT scans of the abdomen and pelvis. All volumetric quantitative imaging measurements from the AI-CVD® opportunistic screening software are adjusted by body surface area (BSA) and reported both in cubic centimeter volume (cc) and percentiles by gender reference data from people who participated in the Multi-Ethnic Study of Atherosclerosis (MESA) and Framingham Heart Study (FHS). Except for coronary artery calcium scoring, other AI-CVD® modules should not be ordered as a standalone CT scan but instead should be used as an opportunistic add-on to existing and new CT scans.
AI-CVD® is an opportunistic AI-powered modular tool that provides automated quantitative imaging reports on CT scans and outputs the following measurements:
- Coronary Artery Calcium Score
- Aortic Wall and Valves Calcium Scores
- Mitral Valve Calcium Score
- Cardiac Chambers Volume
- Epicardial Fat Volume
- Aorta and Main Pulmonary Artery Volume and Diameters
- Liver Attenuation Index
- Lung Attenuation Index
- Muscle and Visceral Fat
- Bone Mineral Density
The above quantitative imaging measurements enable care providers to take necessary actions to prevent adverse health outcomes.
AI-CVD® modules are installed by trained personnel only. AI-CVD® is executed via parent software which provides the necessary inputs and receives the outputs. The software itself does not offer user controls or access.
AI-CVD® reads a CT scan (in DICOM format) and extracts scan specific information like acquisition time, pixel size, scanner type, etc. AI-CVD® uses trained AI models that automatically segment and report quantitative imaging measurements specific to each AI-CVD® module. The output of each AI-CVD® module is inputted into the parent software which exports the results for review and confirmation by a human expert.
AI-CVD® is a post-processing tool that works on existing and new CT scans.
AI-CVD® passes if the human expert approves the segmentation highlighted by the AI-CVD® module is correctly placed on the target anatomical region. For example, Software passes if the human expert sees the AI-CVD® cardiac chamber volumetry module highlighted the heart anatomy.
AI-CVD® fails if the human expert sees the segmentation highlighted by the AI-CVD® module is not correctly placed on the target anatomical region. For example, Software fails if the human expert sees the AI-CVD® cardiac chamber volumetry module highlighted the lungs anatomy or a portion of the sternum or any adjacent organs. Furthermore, Software fails if the human expert sees that the quality of the CT scan is compromised by image artifacts, severe motion, or excessive noise.
The user cannot change or edit the segmentation or results of the device. The user must accept or reject the segmentation where the AI-CVD® quantitative imaging measurements are performed.
AI-CVD® is an AI-powered post-processing tool that works on non-contrast and contrast-enhanced CT scans of chest and abdomen.
AI-CVD® is a multi-module deep learning-based software platform developed to automatically segment and quantify a broad range of cardiovascular, pulmonary, musculoskeletal, and metabolic biomarkers from standard chest or whole-body CT scans. AI-CVD® system builds upon the open-source TotalSegmentator as its foundational segmentation framework, incorporating additional supervised learning and model training layers specific to each module's clinical task.
The provided FDA 510(k) Clearance Letter for AI-CVD® outlines several modules, each with its own evaluation. However, the document does not provide a single, comprehensive table of acceptance criteria with reported device performance for all modules. Instead, it describes clinical validation studies and agreement analyses, generally stating "acceptable bias and reproducibility" or "acceptable agreement and reproducibility" without specific numerical thresholds or metrics. Similarly, detailed information on sample sizes, ground truth establishment methods (beyond general "manual reference standards" or "human expert knowledge"), and expert qualifications is quite limited for most modules.
Here's an attempt to extract and synthesize the information based on the provided text, recognizing the gaps:
Acceptance Criteria and Study Details for AI-CVD®
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state numerical acceptance criteria for each module. Instead, it describes performance in terms of agreement with manual measurements or gold standard references, generally stating "acceptable bias and reproducibility" or "comparable performance." The table below summarizes what is reported.
| AI-CVD® Module | Acceptance Criteria (Implicit/General) | Reported Device Performance |
|---|---|---|
| Coronary Artery Calcium Score | Comparative safety and effectiveness with expert manual measurements. | Demonstrated comparative safety and effectiveness between expert manual measurements and both automated Agatston CAC scores and AI-derived relative density-based calcium scores. |
| Aortic Wall & Aortic Valve Calcium Scores | Acceptable bias and reproducibility compared to manual reference standards. | Bland-Altman agreement analyses demonstrated acceptable bias and reproducibility across imaging protocols. |
| Mitral Valve Calcium Score | Reproducible quantification compared to manual measurements. | Agreement analyses demonstrated reproducible mitral valve calcium quantification across imaging protocols. |
| Cardiac Chambers Volume | Based on previously FDA-cleared technology (AutoChamber™ K240786). | (No new performance data presented for this specific module as it leverages a cleared predicate). |
| Epicardial Fat Volume | Acceptable agreement and reproducibility with manual measurements. | Agreement studies comparing AI-derived epicardial fat volumes with manual measurements and across non-contrast and contrast-enhanced CT acquisitions demonstrated acceptable agreement and reproducibility. |
| Aorta & Main Pulmonary Artery Volume & Diameters | Low bias and comparable performance with manual reference measurements. | Agreement studies comparing AI-derived measurements with manual reference measurements demonstrated low bias and comparable performance across gated and non-gated CT acquisitions. Findings support reliability. |
| Liver Attenuation Index | Acceptable reproducibility across imaging protocols. | Agreement analysis comparing AI-derived liver attenuation measurements across imaging protocols demonstrated acceptable reproducibility. |
| Lung Attenuation Index | Reproducible measurements across CT acquisitions. | Agreement studies demonstrated reproducible lung density measurements across gated and non-gated CT acquisitions. |
| Muscle & Visceral Fat | Acceptable reproducibility across imaging protocols. | Agreement analyses between AI-derived fat and muscle measurements demonstrated acceptable reproducibility across imaging protocols. |
| Bone Mineral Density | Based on previously FDA-cleared technology (AutoBMD K213760). | (No new performance data presented for this specific module as it leverages a cleared predicate). |
2. Sample Size and Data Provenance for the Test Set
- Coronary Artery Calcium (CAC) Score:
- Sample Size: 913 consecutive coronary calcium screening CT scans.
- Data Provenance: "Real-world" data acquired across three community imaging centers. This suggests a retrospective collection from a U.S. or similar healthcare system, though the specific country of origin is not explicitly stated. The term "consecutive" implies that selection bias was minimized.
- Other Modules (Aortic Wall/Valve, Mitral Valve, Epicardial Fat, Aorta/Pulmonary Artery, Liver, Lung, Muscle/Visceral Fat):
- The document refers to "agreement analyses" and "agreement studies" but does not specify the sample size for the test sets used for these individual modules.
- Data Provenance: The document generally states that "clinical validation studies were performed based upon retrospective analyses of AI-CVD® measurements performed on large population cohorts such as the Multi-Ethnic Study of Atherosclerosis (MESA) and Framingham Heart Study (FHS)." It is unclear if these cohorts were solely used for retrospective analysis, or if the "real-world" data mentioned for CAC was also included for other modules. MESA and FHS are prospective, longitudinal studies conducted primarily in the U.S.
3. Number of Experts and Qualifications for Ground Truth
- Coronary Artery Calcium (CAC) Score:
- Number of Experts: Unspecified, referred to as "expert manual measurements."
- Qualifications: Unspecified, but implied to be human experts capable of performing manual Agatston scoring.
- Other Modules:
- Number of Experts: Unspecified, generally referred to as "manual reference standards" or "manual measurements."
- Qualifications: Unspecified.
4. Adjudication Method for the Test Set
The document does not describe a specific adjudication method (e.g., 2+1, 3+1) for establishing ground truth on the test set. It mentions "expert manual measurements" or "manual reference standards," suggesting that the ground truth was established by human experts, but the process of resolving discrepancies among multiple experts (if any were used) is not detailed.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
-
Was an MRMC study done? No, the document does not describe an MRMC comparative effectiveness study where human readers' performance with and without AI assistance was evaluated. The performance data presented focuses on the standalone AI performance compared to human expert measurements.
-
Effect Size of Human Reader Improvement: Not applicable, as an MRMC study was not described.
6. Standalone (Algorithm Only) Performance Study
- Was a standalone study done? Yes, the described performance evaluations for all modules (where new performance data was presented) are standalone performance studies. The studies compare the AI-CVD® algorithm's output directly against manual measurements or established reference standards.
7. Type of Ground Truth Used
- Coronary Artery Calcium Score: Expert manual measurements (Agatston scores).
- Aortic Wall and Aortic Valve Calcium Scores: Manual reference standards.
- Mitral Valve Calcium Score: Manual measurements.
- Epicardial Fat Volume: Manual measurements.
- Aorta and Main Pulmonary Artery Volume and Diameters: Manual reference measurements.
- Liver Attenuation Index: (Implicitly) Manual reference measurements or established methods for hepatic attenuation.
- Lung Attenuation Index: (Implicitly) Manual reference measurements or established methods for lung density.
- Muscle and Visceral Fat: (Implicitly) Manual reference measurements.
- Cardiac Chambers Volume & Bone Mineral Density: Leveraged previously cleared predicate devices, suggesting the ground truth for their original clearance would apply.
8. Sample Size for the Training Set
The document provides information on the foundational segmentation framework (TotalSegmentator) and hints at customization for AI-CVD® modules:
- TotalSegmentator (Foundational Framework):
- General anatomical segmentation: 1,139 total body CT cases.
- High-resolution cardiac structure segmentation: 447 coronary CT angiography (CCTA) scans.
- AI-CVD® Custom Datasets: The document states that "Custom datasets were constructed for coronary artery calcium scoring, aortic and valvular calcifications, cardiac chamber volumetry, epicardial and visceral fat quantification, bone mineral density assessment, liver fat estimation, muscle mass and quality, and lung attenuation analysis." However, it does not provide the specific sample sizes for these custom training datasets for each AI-CVD® module.
9. How Ground Truth for the Training Set Was Established
- TotalSegmentator (Foundational Framework): The architecture utilizes nnU-Net, which was trained on the described CT cases. Implicitly, these cases would have had expert-derived ground truth segmentations for training the neural network.
- AI-CVD® Custom Datasets: "For each module, iterative model enhancement was applied: human reviewers evaluated model-generated segmentations and corrected any inaccuracies, and these corrections were looped back into the training process to improve performance and generalizability." This indicates that human experts established and refined the ground truth by reviewing and correcting model-generated segmentations, which were then used for retraining. The qualifications of these "human reviewers" are not specified.
Ask a specific question about this device
(266 days)
The MediAI-BA is designed to view and quantify bone age from 2D Posterior Anterior (PA) view of left-hand radiographs using deep learning techniques to aid in the analysis of bone age assessment of patients between 2 to 18 years old for pediatric radiologists. The results should not be relied upon alone by pediatric radiologists to make diagnostic decisions. The images shall be with left hand and wrist fully visible within the field of view, and shall be without any major bone destruction, deformity, fracture, excessive motion, or other major artifacts.
Limitations:
- This software is not intended for use in patients with growth disorders caused by congenital anomalies (e.g., Down syndrome, Noonan syndrome, congenital adrenal hyperplasia, methylmalonic acidemia, skeletal dysplasia, chronic renal disease, or prior long-term steroid exposure), as these conditions may cause complex skeletal changes beyond bone maturation.
- Images showing anatomical variations or notable abnormalities (e.g., bone tumors, sequelae of fractures, or congenital deformities) in the region required for interpretation are excluded from the intended use.
This AI-based software utilizes an internal algorithm that integrates global skeletal maturity features extracted from the whole hand radiograph with local skeletal maturity features derived from key Regions of Interest (ROIs). By synthesizing these skeletal maturity features, the software determines the accurate final bone age.
MediAI-BA provides an optional heatmap visualization that highlights regions contributing to the AI model output. The heatmap is intended only as supplementary, qualitative information to illustrate internal AI operations and is not intended for clinical interpretation, growth plate localization, or independent bone age assessment.
The confidence score graph is an internal model visualization intended only to illustrate the relative sharpness of the model's output distribution. It is not calibrated to clinical likelihood, has not been clinically validated, and is not intended to support diagnostic decisions or selection of a specific bone age.
Here's a breakdown of the acceptance criteria and study details for the MediAI-BA device, based on the provided FDA 510(k) clearance letter:
MediAI-BA Acceptance Criteria and Device Performance
1. Table of Acceptance Criteria and Reported Device Performance:
| Acceptance Criteria (Performance Metric) | Target (Implicit from "no significant bias" and "high consistency") | Reported Device Performance and Confidence Intervals |
|---|---|---|
| Deming Regression - Slope | Close to 1 (indicating no proportional bias) | 1.000 (95% CI: 0.989–1.002) |
| Deming Regression - Intercept | Close to 0 (indicating no systematic bias) | 0.08 (95% CI: −0.004–0.158) |
| Bland-Altman Analysis - 95% Limits of Agreement | Narrow range (demonstrating high consistency and agreement) | −0.66 (−1.96 SD) to 0.71 (+1.96 SD) |
| Frequency Distribution of Differences - Mean | Close to 0 (indicating negligible average difference) | 0.026 years |
| Frequency Distribution of Differences - Standard Deviation | Low (indicating high precision) | 0.3505 years |
| Frequency Distribution of Differences - Cases within 0.5 years | High percentage (indicating strong agreement for a large majority of cases) | 89% of all cases |
| Heatmap Consistency (SSIM) | ≥ 0.85 (for most evaluation cases under normal conditions) | Most of 30 evaluation cases met criteria under brightness adjustment and Gaussian noise. All 5 cases met criteria under rotation. |
| Heatmap Accuracy | Bone age changes observed when highlighted region is masked (indicating region's contribution to output) | Bone age changes observed in 27 out of 30 cases when the highlighted region of the heatmap was masked. |
Study Details
2. Sample size used for the test set and the data provenance:
- Sample Size: 600 cases.
- Data Provenance:
- Country of Origin: United States.
- Collection Sites: Five sites across multiple states and multiple clinical organizations.
- Retrospective/Prospective: Not explicitly stated, but the description of "collected from five sites" suggests a retrospective collection of existing images for this study. The phrase "None of the cases used in this study were utilized for training or development of the MediAI-BA model" reinforces that these were untouched test cases.
- Demographics: 50.0% males and 50.0% females. Racial/ethnic composition included White, Hispanic, Black, Asian & Pacific Islander, among others.
- Image Sources: X-ray scanner manufacturers included Samsung Electronics, Carestream Health, Kodak, Siemens, and Konica Minolta.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Four evaluators.
- Qualifications of Experts: Not explicitly stated, but the context of "pediatric radiologists" in the Indications for Use and the assertion that the device "demonstrated performance comparable to bone age readings obtained by human evaluators using the GP atlas method" strongly imply that these evaluators were pediatric radiologists experienced in bone age assessment using the GP (Greulich and Pyle) atlas method.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- The document states that ground truth was "established by four evaluators." It does not specify the exact adjudication method (e.g., whether it was consensus, average, or majority rule among the four).
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, an MRMC comparative effectiveness study was not explicitly described. The study compared the device's standalone performance against the ground truth established by human evaluators. It did not evaluate how human readers' performance might improve when assisted by the AI.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done:
- Yes, a standalone performance study was done. The performance metrics (Deming regression, Bland-Altman, frequency distribution of differences) directly compare the "software's bone age analysis results" and "MediAI-BA outputs" against the "ground truth." This is a direct measurement of the algorithm's standalone performance.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):
- The ground truth was established by "four evaluators" using the "GP atlas method." This indicates expert consensus/interpretation using a recognized standard (GP atlas).
8. The sample size for the training set:
- Not specified in the provided text. The document explicitly states that "None of the cases used in this study were utilized for training or development of the MediAI-BA model," but does not give details about the training set itself.
9. How the ground truth for the training set was established:
- Not specified in the provided text.
Ask a specific question about this device
(154 days)
The PVAD IQ software is intended for non-invasive analysis of ultrasound images to detect and measure structures from cardiac ultrasound of patients 18 years old and above, with a Percutaneous Ventricular Assist Device (PVAD). Such use is typically utilized for clinical decision support by a qualified physician.
PVAD IQ is a Software as a Medical Device (SaMD) solution designed to support clinicians in the positioning of Percutaneous Ventricular Assist devices (PVADs) through ultrasound image-based assessment. Percutaneous Ventricular Assist device is a temporary device used to provide hemodynamic support for patients experiencing cardiogenic shock or undergoing high-risk percutaneous coronary interventions (PCI).
The PVAD IQ software is a machine learning model (MLM) based software, that operates on ultrasound clips (as the system input) and provides two outputs with regards to PVAD patients:
-
Landmark identification and measurement - provides the two landmarks position detection, and computation of the mean distance between the two landmarks- the aortic annulus and the PVAD inlet.
-
Acceptability classification, which is a binary classification of ultrasound clips that are "acceptable" or "non-acceptable", in terms of visibility of the two landmarks. A clip is defined as acceptable when both landmarks are simultaneously visible in a manner suitable for quantitative imaging.
The User Interface (UI) enables the user to review or hide the mean distance measurement, annotate desired images, and add manual measurement, while keeping the raw data for further review as needed.
The software output is shown on the screen either as the mean distance measurement, or as a notification related to non-acceptable clips.
The PVAD IQ Software, a machine learning model (MLM) based software, provides two primary outputs for patients with Percutaneous Ventricular Assist Devices (PVADs): landmark identification and measurement (specifically, the distance between the aortic annulus and the PVAD inlet) and acceptability classification of ultrasound clips.
1. Acceptance Criteria and Reported Device Performance
The study established pre-specified acceptance criteria for the PVAD IQ software's performance, which it met.
| Acceptance Criteria | Threshold | Reported Device Performance |
|---|---|---|
| Distance Measurement (MAE) | Below 0.5 cm | 0.42 cm (95% CI: 0.38–0.47 cm) |
| Acceptability Classification (Cohen's Kappa) | Above 0.6 | 0.71 (95% CI: 0.66–0.75) |
| Landmark Detection (AUC) - PVAD Inlet | Above 0.8 | 0.92 (0.9–0.94) |
| Landmark Detection (AUC) - Aortic Annulus | Above 0.8 | 0.98 (0.95, 1) |
| Landmark Position (MAE) - PVAD Inlet | Below 0.5 cm | 0.44 cm (0.41–0.48 cm) |
| Landmark Position (MAE) - Aortic Annulus | Below 0.5 cm | 0.31 cm (0.3–0.33 cm) |
2. Sample Size and Data Provenance for Test Set
- Sample Size: 963 clips
- Number of Patients: 186 patients
- Data Provenance: Geographically distinct test datasets. While specific countries are not mentioned, the ground truth annotations were provided by US (United States) board certified cardiac sonographers. The timing (retrospective or prospective) is not specified, but the data was used for evaluating a previously trained model, which often implies a retrospective application to a held-out test set.
3. Number and Qualifications of Experts for Ground Truth (Test Set)
- Number of Experts: Not explicitly stated as a specific number of individual experts. The document refers to "US (United States) board certified cardiac sonographers."
- Qualifications of Experts: "US (United States) board certified cardiac sonographers experienced in PVAD/Impella® echocardiographic imaging."
4. Adjudication Method for Test Set
The adjudication method is not explicitly stated in the provided document. It only mentions that ground truth annotations were "provided by US (United States) board certified cardiac sonographers." It does not specify if multiple sonographers reviewed each case, how disagreements were resolved, or if a consensus mechanism (like 2+1 or 3+1) was used.
5. MRMC Comparative Effectiveness Study
An MRMC (Multi-Reader Multi-Case) comparative effectiveness study comparing AI assistance with unassisted human readers was not mentioned in the provided document. The study focused on the standalone performance of the PVAD IQ software.
6. Standalone Performance Study
Yes, a standalone (algorithm only without human-in-the-loop performance) study was conducted. The reported performance metrics (MAE, Cohen's Kappa, AUC) directly assess the algorithm's performance against the established ground truth.
7. Type of Ground Truth Used
The ground truth used was expert consensus/annotations. Specifically, "Ground truth annotations for the distance between the aortic annulus and the PVAD inlet were provided by US (United States) board certified cardiac sonographers experienced in PVAD/Impella® echocardiographic imaging." This implies human experts manually defining the "correct" measurements and classifications.
8. Sample Size for the Training Set
The sample size for the training set is not provided in this document. The document states that the PVAD IQ software is "trained with clinical data" but does not specify the volume or characteristics of this training data.
9. How Ground Truth for Training Set Was Established
The method for establishing ground truth for the training set is not explicitly detailed in this document. It broadly states that the software uses "non-adaptive machine learning algorithms trained with clinical data" and "refining annotations" is part of model retraining (under PCCP). While it can be inferred that ground truth for training data would also involve expert annotations, similar to the test set, the specific process, number of experts, or their qualifications for the training data are not provided.
Ask a specific question about this device
(93 days)
The Neosoma software uses an artificial intelligence algorithm (i.e., deep learning neural networks) to contour (segment) known or previously diagnosed brain tumors on MRI images for qualified and trained medical professionals.
The technology is meant for informational purposes only and not intended to replace the clinician's current standard practice of manual contouring. The software does not alter the original MRI image, nor is it intended to be used to detect tumors for diagnosis. The software is intended to be used on adult patients only.
When using the Neosoma software in a radiation oncology planning workflow, or other clinical workflows, it is intended for generating Gross Tumor Volume (GTV) contours. For all clinical workflows, medical professionals must finalize (confirm or modify) the contours generated by the Neosoma software, as necessary, using an external platform available at the facility that supports DICOM viewing/editing functions, such as image visualization software and treatment planning system.
Neosoma Brain Mets is a Software as a Medical Device (SaMD) that is designed specifically for the semi-automatic segmentation of previously diagnosed brain metastases. This functionality is applicable to the T1 post-contrast sequence, which is routinely obtained in clinical practice through brain Magnetic Resonance Imaging (MRI).
It is important to note that the standard criterion for diagnosing brain metastasis includes the presence of a known primary cancer that has been identified as having metastasized to the brain. Accordingly, Neosoma Brain Mets is not intended for use with images representing other types of brain lesions.
Furthermore, Neosoma Brain Mets is specifically designed for use in adult patient populations (age 22 and older). As such, its usage should be confined to this demographic to ensure compliance with its intended use parameters and to maximize the accuracy and relevance of its results.
The analysis performed by the AI includes semi-automatic segmentation of the metastasis based on pixel signal intensity. The volumes are calculated using non-machine-learning post-processing from the AI segmentation output. For this segmentation, the software requires one MRI sequence (T1 post-contrast) as input, and it outputs post-processed images that contain color-coded segmentations, as well as volumetric measurements.
Here's an analysis of the acceptance criteria and study details for the Neosoma Brain Mets device, based on the provided FDA 510(k) clearance letter:
Neosoma Brain Mets - Acceptance Criteria and Study Details
1. Acceptance Criteria and Reported Device Performance
| Metric | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| Sensitivity | ≥ 0.85 | 0.90 (95% CI: 0.87 - 0.94) |
| False Positive Rate | ≤ 5 false positive lesions per MRI | 0.57 lesions per MRI (95% CI: 0.35 - 0.80) |
| DSC (Dice Similarity Coefficient) | ≥ 0.70 | 0.86 (95% CI: 0.83 - 0.89) |
| HD95 (95th percentile Hausdorff Distance) | ≤ 2.94 mm | 1.78 mm (95% CI: 1.02 - 2.54) |
| MSD (Mean Surface Distance) | ≤ 0.66 mm | 0.36 mm (95% CI: 0.16 - 0.56) |
2. Test Set Sample Size and Data Provenance
- Sample Size for Test Set: 70 subjects, each with one MRI (total of 70 MRIs).
- Data Provenance: Retrospective, multicenter study. Acquired from medical sites inside and outside of the US that were not included in the training dataset to ensure device generalizability. The data involved standard-of-care MRI protocols on Canon, GE, Siemens, and Toshiba scanners at both 1.5T and 3.0T.
- Patient Demographics in Test Set: Age range of 28 to 84, covering a diverse group of ethnic backgrounds. The distribution of primary cancers was consistent with the known epidemiology of brain metastases. A subgroup analysis demonstrated consistent device performance across various factors including site, imaging manufacturer, field strength, patient race and ethnicity, age, gender, primary cancer, and site geography.
3. Number of Experts and Qualifications for Ground Truth
- Number of Experts: Three.
- Qualifications of Experts: US board-certified neuroradiologists with expertise in measuring brain metastases.
4. Adjudication Method for the Test Set
The document explicitly states that the reference standard (ground truth) was established using three US board-certified neuroradiologists. However, it does not specify the adjudication method used (e.g., 2+1, 3+1, majority vote, or consensus). It simply states that the "reference standard (ground truth) was established using" these three experts.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No MRMC comparative effectiveness study involving human readers with and without AI assistance is described in the provided text. The study focuses on the standalone performance of the AI algorithm compared to an expert-established ground truth.
6. Standalone Performance (Algorithm Only)
Yes, a standalone (algorithm only, without human-in-the-loop performance) study was done. The report describes the clinical performance of the "Neosoma Brain Mets" device (the AI algorithm) against a reference standard established by experts. The performance metrics (Sensitivity, False Positive Rate, DSC, HD95, MSD) are all measures of the algorithm's direct output compared to the ground truth.
7. Type of Ground Truth Used
The ground truth used was expert consensus (or interpretation by multiple experts). It was established by three US board-certified neuroradiologists.
8. Sample Size for the Training Set
The document states that the test dataset was acquired from medical sites that were not included in the training dataset. However, it does not specify the sample size for the training set.
9. How the Ground Truth for the Training Set Was Established
The document does not provide information on how the ground truth for the training set was established. It only describes the establishment of the ground truth for the test set.
Ask a specific question about this device
(203 days)
Overjet CBCT Assist is a software for the analysis of dental and craniomaxillofacial Cone Beam Computed Tomography (CBCT) images. The software utilizes artificial intelligence/machine learning algorithms to provide automated segmentations, user-delineated or automated measurements, and 2D/3D visualizations. These tools are intended to assist dental professionals in their review and interpretation of CBCT images by facilitating anatomical assessment and supporting their diagnostic and treatment planning process. The device is not intended as a replacement for a complete clinician's review or their clinical judgement.
Overjet CBCT Assist (OCBCTA) is a cloud-based software designed to assist dental professionals in the visualization and assessment of Cone Beam Computed Tomography (CBCT) images. The software enables interactive review of 3D CBCT data through volume rendering and multi-planar reconstruction (MPR) views and provides manual and automated tools to support diagnostic interpretation and treatment planning.
Overjet CBCT Assist uses machine learning-based segmentation algorithms to automatically identify and label anatomical and restorative structures, including permanent teeth, maxillofacial anatomy, and prior dental treatments such as implants, root canal therapy, crowns, and fillings. These outputs support clinical workflows by enhancing visualization and enabling measurement of relevant features.
Here's a breakdown of the acceptance criteria and the study proving the device meets those criteria, based on the provided FDA 510(k) Clearance Letter for Overjet CBCT Assist:
Acceptance Criteria and Reported Device Performance
| Acceptance Criteria Category | Specific Metric | Predetermined Threshold (Implicit) | Reported Device Performance |
|---|---|---|---|
| Segmentation Accuracy | Instance-level sensitivity for restorative structures | Pass/Exceed threshold | 87.0% with 95% CI (82.3%, 91.2%) - Surpassed required threshold |
| Instance-level sensitivity for dental anatomy | Pass/Exceed threshold | 93.9% with 95% CI (91.7%, 95.9%) - Surpassed required threshold | |
| Dice similarity coefficient for all segmented structures | Individually associated thresholds | Passed individually associated thresholds across all evaluated classes | |
| Measurement Accuracy | Mean Absolute Error (MAE) for automated linear measurements | Target threshold | Met target thresholds for MAE |
| Root Mean Square Error (RMSE) for automated linear measurements | Target threshold | Met target thresholds for RMSE | |
| Tooth Numbering Accuracy | Tooth-level sensitivity for tooth numbering | Implicit target | Met target thresholds |
| Tooth-level accuracy for tooth numbering | Implicit target | Met target thresholds |
Note on "Implicit Thresholds": The document states that the results "met or exceeded all pre-specified performance goals" and "surpassing the required threshold" or "passed their individually associated thresholds." While the exact numerical thresholds are not explicitly provided in this section, the text clearly indicates that such targets were defined and successfully achieved.
Study Details
1. Sample Size and Data Provenance
- Test Set Sample Size: 100 CBCT scans
- Data Provenance: Retrospective. The scans were obtained from a demographically and anatomically diverse patient population in the U.S. (indicated by the use of U.S.-licensed radiologists).
2. Number and Qualifications of Experts for Ground Truth
- Number of Experts: Three (3)
- Qualifications of Experts: U.S.-licensed oral and maxillofacial radiologists and dentists.
3. Adjudication Method for the Test Set
The document states, "Images were independently reviewed and annotated by three U.S.-licensed oral and maxillofacial radiologists and dentists. The resulting segmentations served as the reference standard against which the device's outputs were compared." This implies a consensus-based approach where the collective annotations of the three experts formed the ground truth. The specific adjudication method (e.g., 2+1, 3+1) is not explicitly stated. However, "independently reviewed and annotated" suggests individual contributions were then likely combined to form a final consensus ground truth.
4. MRMC Comparative Effectiveness Study
- Was an MRMC study done? No, based on the provided text. The study evaluated the standalone clinical performance of the device against expert-derived ground truth. There is no mention of human readers evaluating cases with and without AI assistance to measure improvement.
5. Standalone Performance Study
- Was a standalone study done? Yes, explicitly stated: "Additionally, Overjet performed a standalone clinical performance study using retrospective CBCT data to evaluate the accuracy of automated segmentations and measurements."
6. Type of Ground Truth Used
- Type of Ground Truth: Expert consensus (annotations generated by licensed oral and maxillofacial radiologists and dentists).
7. Sample Size for the Training Set
- Training Set Sample Size: Not specified in the provided text. The document only details the test set for the performance study.
8. How Ground Truth for the Training Set was Established
- Establishment of Training Set Ground Truth: Not specified in the provided text. While it's implied that AI models require ground truth for training, the methodology for establishing this ground truth is not detailed in this section of the 510(k) summary.
Ask a specific question about this device
(220 days)
AutoDensity is a post-processing software intended to estimate spine Bone Mineral Density (BMD) from EOSedge dual energy images for orthopedic pre-surgical assessment applications. It is an opportunistic tool that enables immediate assessment of bone density from EOSedge images acquired for other purposes.
AutoDensity is not intended to replace DXA screening. Suspected low BMD should be confirmed by a DXA exam.
Clinical judgment and experience are required to properly use the software.
Based on EOSedge™ system's images acquired with the dual energy protocols cleared in K233920, AutoDensity software provides an estimate of the Bone Mineral Density (BMD) for L1-L4 in EOSedge AP radiographs of the spine. These values are used to aid in BMD estimation in orthopedic surgical planning workflows to help inform patient assessment and surgical decisions. AutoDensity is opportunistic in nature and provides BMD information with equivalent radiation dose compared to the EOSedge images concurrently acquired and used for general radiographic exams. AutoDensity is not intended to replace DXA screening.
Here's a breakdown of the acceptance criteria and the study details for the AutoDensity device, based on the provided FDA 510(k) clearance letter:
1. Acceptance Criteria and Reported Device Performance
Device Name: AutoDensity
Intended Use: Post-processing software to estimate spine Bone Mineral Density (BMD) from EOSedge dual energy images for orthopedic pre-surgical assessment applications.
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Vertebral Level Identification Accuracy | |
| Percent of levels correctly identified ≥ 90% | Testing confirms that the AutoDensity ROI detection algorithm meets performance thresholds. (Specific percentage not provided, but stated to meet criterion). |
| Spine ROI Accuracy (Dice Coefficient) | |
| Lower boundary of 95% CI of mean Dice Coefficient ≥ 0.80 | Testing confirms that the AutoDensity ROI detection algorithm meets performance thresholds. (Specific value not provided, but stated to meet criterion). |
| BMD Precision (Phantom - CV%) | |
| CV% < 1.5% (compared to reference device) | Results met the acceptance criterion (CV% < 1.5%). |
| BMD Agreement (Phantom - max difference) | |
| (Specific numeric criterion not explicitly stated, but implies clinical equivalence to reference device) | Maximum BMD difference of 0.057 g/cm² for the high BMD phantom vertebra, and a difference of < 0.018 g/cm² for clinically relevant BMD range. |
| BMD Precision (Clinical - CV%) | |
| (Specific numeric criterion not explicitly stated, but implies acceptable clinical limits) | AutoDensity precision CV% was 2.23% [95% CI: 1.78%, 2.98%], which is within the range of acceptable clinical limits for the specified pre-surgical orthopedic patient assessment. |
| BMD Agreement (Clinical - Bland-Altman) | |
| (Specific numeric criterion not explicitly stated, but implies equivalence to other commercial bone densitometers) | Bland-Altman bias was 0.045 g/cm², and limits of agreement (LoA) were [-0.088 g/cm², 0.178 g/cm²]. Stated as equivalent to published agreement between other commercial bone densitometers. |
2. Sample Sizes and Data Provenance
Test Set (for ROI Performance Evaluation):
- Sample Size: 129 patients.
- Data Provenance: All cases obtained from EOSedge systems (K233920). The document does not specify the country of origin but mentions a clinical study with 65% US subjects and 35% French subjects for clinical performance testing, which might suggest a similar distribution for the test set, though it's not explicitly stated for the ROI test set. The data was retrospective as it was "obtained from EOSedge systems."
3. Number of Experts and Qualifications for Ground Truth
For ROI Performance Evaluation Test Set:
- Number of Experts: At least 3 (implied by "3 truther majority voting principle") plus one senior US board certified expert radiologist who acted as the gold standard adjudicator.
- Qualifications:
- Two trained technologists (for initial ROI and level identification).
- One senior US board-certified expert radiologist (for supervision, review, selection of most accurate set, and final adjustments).
4. Adjudication Method for the Test Set
For ROI Performance Evaluation Test Set:
- Adjudication Method: A "3 truther majority voting principle" was used, with input from a senior US board-certified expert radiologist (acting as the "gold standard"). The radiologist reviewed results, selected the more accurate set, and made necessary adjustments. This combines elements of majority voting with expert adjudication.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- Was an MRMC study done? No, the provided document does not mention an MRMC comparative effectiveness study where human readers' performance with and without AI assistance was evaluated. The performance data presented focuses on the standalone performance of the AI algorithm and its agreement/precision with a reference device or clinical measurements.
6. Standalone Performance Study (Algorithm Only)
- Was a standalone study done? Yes. The "Region of Interest (ROI) Performance Evaluation" section explicitly states: "To assess the standalone performance of the AI algorithm of AutoDensity, the test was performed with..." This section details the evaluation of the algorithm's predictions against ground truth for vertebral level identification and spine ROI accuracy.
7. Type of Ground Truth Used
For ROI Performance Evaluation Test Set:
- Type of Ground Truth: Expert consensus with adjudication. Ground truths for ROIs and level identification were established by two trained technologists under the supervision of a senior US board-certified radiologist. The radiologist made the final informed decision, often described as a "gold standard."
8. Sample Size for the Training Set
- Training Set Sample Size: The AI algorithm was trained using 4,679 3D reconstructions and 9,358 corresponding EOS (K152788) or EOSedge (K233920) biplanar 2D X-ray images.
9. How Ground Truth for the Training Set was Established
- The document implies that the training data was "selected to only keep relevant images with the fields of view of interest." However, it does not explicitly detail how the ground truth for the training set was established (e.g., whether it used expert annotations, a similar adjudication process, or other methods). It primarily focuses on the test set ground truth establishment.
Ask a specific question about this device
Page 1 of 26