(310 days)
ProstatID™ is a radiological computer assisted detection (CADe) and diagnostic (CADx) software device for use in a healthcare facility or hospital to assist trained radiologists in the detection, assessment and characterization of prostate abnormalities, including cancer lesions using MR image data with the following indications for use.
ProstatID analyzes T2W, DWI and ADC MRI data. ProstatID does not include DCE images in its analysis.
ProstatID software is intended for use as a concurrent reading aid for physicians interpreting prostate MRI exams of patients presented for high-risk screening or diagnostic imaging, from compatible MRI systems, to identify regions suspicious for prostate cancer and assess their likelihood of malignancy.
Outputs of the device include the volume of the prostate and locations, as well as the extent of suspect lesions, with index scores indicating the likelihood that cancer is present, as well as an exam score by way of PI-RADS interpretation suggestion. "Extent of suspect lesions" refers to both the assessment of the boundary of a particular abnormality, as well as identification of multiple abnormalities. In cases where multiple are present, ProstatID can be used to assess each abnormality independently.
Outputs of this device should be interpreted with all available MR data consistent with ACR clinical recommendations (e.g., dynamic contract enhanced if available) in context of PI-RADs v2, and in conjunction with bi-parametric MRI acquired with either surface or endorectal MRI accessory coils from compatible MRI systems. Analysis by ProstatID is not intended as a replacement for interpreting prostate abnormalities using MR image data consistent with clinical recommendations (including DCE); nor should patient management decisions be made solely on the basis of ProstatlD.
ProstatID™ is a radiological computer assisted detection (CADe) and diagnostic (CADx) softwareonly device for use in a healthcare facility or hospital to assist trained radiologists in the detection, assessment, and characterization of lesions suspicious for cancer using MR image data. ProstatID is intended for use as a concurrent reading aid for physicians interpreting prostate MRI exams of patients presented for high-risk screening or diagnostic imaging, from compatible MRI systems. Deep learning and Random Forest algorithms are applied to the DICOM image set of MRI Axial Images (T2W, DWI, and ADC) of the prostate for recognition of the prostate gland, its central gland, and recognition and classifying the likelihood of malignancy of any suspicious lesions. Algorithms are trained with a large database of biopsy-proven examples of normal, benign, and cancerous tissues.
The software is not installed on the user's MRI system, workstation, or any device other than the cloud-based servers configured as a Software as a Service (SaaS) model.
ProstatID offers the following functions which may be used during the concurrent interpretation:
-
- Computer aided detection (CAD) presented as a colorized translucent overlay of the 2D axial T2 images to highlight locations where the device detected suspicious soft tissue lesions.
-
- An appended post-processed T2W image set that can be viewed concurrently and linked three dimensionally via standard DICOM viewing with the original image set.
- Decision Support is provided by the regional overlay scores on a continuous scale 3. ranging from 0-1 with the higher scores indicating a higher level of suspicion (LOS).
- A suggested LOS or overall PI-RADS exam score. 4.
-
- A CAD created 3D rendition of the suspect cancerous tissue within the transparent 3D prostate gland.
-
- A .PDF report summarizing the software results with 2D and 3D images indicating suspect cancerous regions if detected.
Results of ProstatID are computed in a processing server which accepts prostate MRI exams in DICOM format as input, identifies the required axial image sets and processes them, deletes all others, and sends the output to append to the unique patient study destination using the DICOM protocol and format for post-processed images and reports. Use of the device is supported for images from the following MRI systems: Philips 1.5T, GE 3.0T, Philips 3.0T and Siemens 3.0T. Common destinations are medical workstations, PACS and RIS that utilize DICOM image transfer. ProstatID is offered as a virtual or SaaS application and runs on dedicated servers. Implementation requires secure VPN connection between client and SaaS server.
Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:
Acceptance Criteria and Reported Device Performance
The acceptance criteria are implied by the primary and secondary endpoints of the clinical performance assessment, which focused on improving diagnostic accuracy (AUC) and detection accuracy (wAFROC) for radiologists when using ProstatID.
| Acceptance Criteria (Endpoint) | Target/Goal (Implied) | Reported Device Performance |
|---|---|---|
| Primary Endpoint: Diagnostic Accuracy (AUC) | Statistically significant improvement in AUC for readers with ProstatID vs. without ProstatID. | Improvement in AUC: +0.042 (from 0.629 without CAD to 0.671 with CAD) |
| Statistical Significance: p=0.0291 (statistically significant at α=0.05) | ||
| Secondary Endpoint: Detection Accuracy (FROC) | Statistically significant improvement in wAFROC for readers with ProstatID vs. without ProstatID. | Improvement in wAFROC (θ): +0.043 (from 0.387 without CAD to 0.430 with CAD) |
| Statistical Significance: p=0.034 (statistically significant at α=0.05) |
Study Details
-
1. Sample sizes used for the test set and the data provenance:
-
Test Set (Clinical Performance Assessment): 150 patient cases.
- 130 cases had complete follow-up.
- 20 cases were MRI-negative without complete follow-up.
-
Data Provenance: Retrospective study design. The text does not explicitly state the country of origin, but given the FDA submission, it's likely primarily US-based or from regions with compatible MRI standards and clinical practices.
-
-
2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- The document implies that the ground truth for the test set (130 cases with complete follow-up) was based on biopsy results, which are definitive for cancer presence.
- For the 20 MRI-negative cases without complete follow-up, a "consensus opinion of a panel of experts" was used to estimate potential false negatives. The number of experts in this panel is not specified.
- The qualifications of these experts are not explicitly stated, but they would be expected to be radiologists or uropathologists given the context of prostate cancer diagnosis.
-
3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- For the 130 cases with complete follow-up, the ground truth was based on biopsy results, which typically don't require further adjudication.
- For the 20 MRI-negative cases without complete follow-up, a "consensus opinion" of a panel of experts was used. The specific adjudication method (e.g., how consensus was reached, if there was a tie-breaker) is not detailed.
-
4. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:
- Yes, an MRMC study was done.
- Effect Size (Improvement with AI vs. without AI assistance):
- Diagnostic Accuracy (AUC): The average AUC for readers improved by +0.042 (from 0.629 without CAD to 0.671 with CAD).
- Detection Accuracy (wAFROC): The average wAFROC (θ) for readers improved by +0.043 (from 0.387 without CAD to 0.430 with CAD).
-
5. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone performance assessment was conducted.
- Results:
- Diagnostic Accuracy (Lesion-level ROC Analysis): AUC of 0.710.
- Standalone Detection Performance (FROC Analysis): Sensitivity of 80% at 1 false positive per patient, and 98% at 3 false positives per patient.
- Detection Performance (AFROC): CAD vs. Readers: ProstatID performed better than readers' unassisted read (Δθ = +0.169), which was statistically significant (p=0.029).
-
6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- The primary ground truth used for the majority of the test set (130 cases in the clinical study and the 150 cases for standalone assessment) was biopsy-proven examples (pathology results).
- For a subset of 20 MRI-negative cases without complete follow-up, a "consensus opinion of a panel of experts" was used, complemented by simulation and bootstrapping to account for potential false negatives.
-
7. The sample size for the training set:
- The document states that the algorithms were "trained with a large database of biopsy-proven examples of normal, benign, and cancerous tissues." However, the specific sample size of the training set is not provided.
-
8. How the ground truth for the training set was established:
- The ground truth for the training set was established using "biopsy-proven examples of normal, benign, and cancerous tissues." This indicates that pathology/biopsy results were used to define the ground truth for 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.