(120 days)
Saige-Dx analyzes digital breast tomosynthesis (DBT) mammograms to identify the presence of soft tissue lesions and calcifications that may be indicative of cancer. For a given DBT mammogram, Saige-Dx analyzes the DBT image stacks and the accompanying 2D images, including full field digital mammography and/or synthetic images. The system assigns a Suspicion Level, indicating the strength of suspicion that cancer may be present, for each detected finding and for the entire case. The outputs of Saige-Dx are intended to be used as a concurrent reading aid for interpreting physicians on screening mammograms with compatible DBT hardware.
Saige-Dx is a software device that processes screening mammograms using artificial intelligence to aid interpreting radiologists. By automatically detecting the presence or absence of soft tissue lesions and calcifications in mammography images, Saige-Dx can help improve reader performance, while also reducing time. The software takes as input a set of x-ray mammogram DICOM files from a single digital breast tomosynthesis (DBT) study and generates finding-level outputs for each image analyzed, as well as an aggregate case-level assessment. Saige-Dx processes both the DBT image stacks and the associated 2D images (full-field digital mammography (FFDM) and/or synthetic 2D images) in a DBT study. For each image, Saige-Dx outputs bounding boxes circumscribing any detected findings and assigns a Finding Suspicion Level to each finding, indicating the degree of suspicion that the finding is malignant. Saige-Dx uses the results of the finding-level analysis to generate a Case Suspicion Level, indicating the degree of suspicion for malignancy across the case. Saige-Dx encapsulates the finding and caselevel results into a DICOM Structured Report (SR) object containing markings that can be overlaid on the original mammogram images using a viewing workstation and a DICOM Secondary Capture (SC) object containing a summary report of the Saige-Dx results.
Here's a breakdown of the acceptance criteria and the study proving the device meets those criteria, based on the provided text:
Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Implicit) | Reported Device Performance |
|---|---|
| Reader Performance Improvement (MRMC Study) | |
| - Increase in Radiologist AUC when aided by Saige-Dx. | The average AUC of radiologists increased from 0.865 (unaided) to 0.925 (aided), a difference of 0.06 (95% CI: 0.041, 0.079, p 10 years in practice) breast imaging specialists, plus a third as an adjudicator. |
- Qualifications of Experts for Ground Truth: MQSA qualified, highly experienced (>10 years in practice) breast imaging specialists.
- Adjudication Method: For exams with discrepancies between the two truthers' assessment of density, lesion type, and/or lesion location, a third truther served as the adjudicator.
- MRMC Comparative Effectiveness Study: Yes.
- Effect Size (Human Reader Improvement with AI vs. without AI):
- Average AUC increased by 0.06 (from 0.865 unaided to 0.925 aided).
- Average reader sensitivity increased by 8.8%.
- Average reader specificity increased by 0.9%.
- Effect Size (Human Reader Improvement with AI vs. without AI):
- Standalone Performance: No, this specific study was for human reader performance with and without AI.
- Type of Ground Truth: Expert consensus with pathology confirmation for cancer cases. Each mammogram had a ground truth status of "cancer" or "non-cancer." For cancer exams, malignant lesions were annotated based on the biopsied location that led to malignant pathology.
- Sample Size for Training Set: Not explicitly stated, but the text mentions "six datasets across various geographic locations in the US and the UK," indicating a large, diverse dataset.
- How Ground Truth for Training Set was Established: Not explicitly detailed for the training set, but it is stated that "DeepHealth ensured that there was no overlap between the data used to train and test the Saige-Dx Al algorithm." It can be inferred that similar robust methods (likely expert review and pathology confirmation) were used, given the thoroughness described for the test set.
2. Standalone Study (Performance Testing: Standalone Study)
- Sample Size for Test Set: 1304 cases (136 cancer, 1168 non-cancer).
- Data Provenance: Retrospective, blinded, multi-center study. Collected from 9 clinical sites in the United States. All data came from clinical sites that had never been used previously for training or testing of the Saige-Dx AI algorithm.
- Number of Experts for Ground Truth: "Truthed using similar procedures to those used for the reader study," which implies two highly experienced breast imaging specialists and a third adjudicator.
- Qualifications of Experts for Ground Truth: Implied to be MQSA qualified, highly experienced (>10 years in practice) breast imaging specialists, consistent with the reader study.
- Adjudication Method: Implied to be consistent with the reader study (third truther for discrepancies).
- MRMC Comparative Effectiveness Study: No, this was a standalone performance study of the algorithm only.
- Standalone Performance: Yes. Saige-Dx exhibited an AUC of 0.930 (95% CI: 0.902, 0.958).
- Type of Ground Truth: Implied to be expert consensus with pathology confirmation, consistent with the reader study, as data was "collected and truthed using similar procedures."
- Sample Size for Training Set: Not explicitly stated, but the data used was specifically excluded from the test set for this study, confirming separation.
- How Ground Truth for Training Set was Established: Implied to be through expert review and pathology confirmation, given the "similar procedures" used for test set truthing and the isolation of training data.
§ 892.2090 Radiological computer-assisted detection and diagnosis software.
(a)
Identification. A radiological computer-assisted detection and diagnostic software is an image processing device intended to aid in the detection, localization, and characterization of fracture, lesions, or other disease-specific findings on acquired medical images (e.g., radiography, magnetic resonance, computed tomography). The device detects, identifies, and characterizes findings based on features or information extracted from images, and provides information about the presence, location, and characteristics of the findings to the user. The analysis is intended to inform the primary diagnostic and patient management decisions that are made by the clinical user. The device is not intended as a replacement for a complete clinician's review or their clinical judgment that takes into account other relevant information from the image or patient history.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Design verification and validation must include:
(i) A detailed description of the image analysis algorithm, including a description of the algorithm inputs and outputs, each major component or block, how the algorithm and output affects or relates to clinical practice or patient care, and any algorithm limitations.
(ii) A detailed description of pre-specified performance testing protocols and dataset(s) used to assess whether the device will provide improved assisted-read detection and diagnostic performance as intended in the indicated user population(s), and to characterize the standalone device performance for labeling. Performance testing includes standalone test(s), side-by-side comparison(s), and/or a reader study, as applicable.
(iii) Results from standalone performance testing used to characterize the independent performance of the device separate from aided user performance. The performance assessment must be based on appropriate diagnostic accuracy measures (
e.g., receiver operator characteristic plot, sensitivity, specificity, positive and negative predictive values, and diagnostic likelihood ratio). Devices with localization output must include localization accuracy testing as a component of standalone testing. The test dataset must be representative of the typical patient population with enrichment made only to ensure that the test dataset contains a sufficient number of cases from important cohorts (e.g., subsets defined by clinically relevant confounders, effect modifiers, concomitant disease, and subsets defined by image acquisition characteristics) such that the performance estimates and confidence intervals of the device for these individual subsets can be characterized for the intended use population and imaging equipment.(iv) Results from performance testing that demonstrate that the device provides improved assisted-read detection and/or diagnostic performance as intended in the indicated user population(s) when used in accordance with the instructions for use. The reader population must be comprised of the intended user population in terms of clinical training, certification, and years of experience. The performance assessment must be based on appropriate diagnostic accuracy measures (
e.g., receiver operator characteristic plot, sensitivity, specificity, positive and negative predictive values, and diagnostic likelihood ratio). Test datasets must meet the requirements described in paragraph (b)(1)(iii) of this section.(v) Appropriate software documentation, including device hazard analysis, software requirements specification document, software design specification document, traceability analysis, system level test protocol, pass/fail criteria, testing results, and cybersecurity measures.
(2) Labeling must include the following:
(i) A detailed description of the patient population for which the device is indicated for use.
(ii) A detailed description of the device instructions for use, including the intended reading protocol and how the user should interpret the device output.
(iii) A detailed description of the intended user, and any user training materials or programs that address appropriate reading protocols for the device, to ensure that the end user is fully aware of how to interpret and apply the device output.
(iv) A detailed description of the device inputs and outputs.
(v) A detailed description of compatible imaging hardware and imaging protocols.
(vi) Warnings, precautions, and limitations must include situations in which the device may fail or may not operate at its expected performance level (
e.g., poor image quality or for certain subpopulations), as applicable.(vii) A detailed summary of the performance testing, including test methods, dataset characteristics, results, and a summary of sub-analyses on case distributions stratified by relevant confounders, such as anatomical characteristics, patient demographics and medical history, user experience, and imaging equipment.