Search Results

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:

• 1. 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.
• 2. 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.
• 5. A CAD created 3D rendition of the suspect cancerous tissue within the transparent 3D prostate gland.
• 6. 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.

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.

Ask a specific question about this device