← Product Code [QDQ](/submissions/RA/subpart-b%E2%80%94diagnostic-devices/QDQ) · K253682

# DeepHealth ProstateAI (K253682)

_Quantib B.V. · QDQ · Apr 29, 2026 · Radiology · SESE_

**Canonical URL:** https://fda.innolitics.com/submissions/RA/subpart-b%E2%80%94diagnostic-devices/QDQ/K253682

## Device Facts

- **Applicant:** Quantib B.V.
- **Product Code:** [QDQ](/submissions/RA/subpart-b%E2%80%94diagnostic-devices/QDQ.md)
- **Decision Date:** Apr 29, 2026
- **Decision:** SESE
- **Submission Type:** Traditional
- **Regulation:** 21 CFR 892.2090
- **Device Class:** Class 2
- **Review Panel:** Radiology
- **Attributes:** AI/ML, Software as a Medical Device, Real-World Evidence

## Real-World Evidence

| Submission | Device | Sponsor | RWD Sources | RWE Use Summary | Key Tags |
| --- | --- | --- | --- | --- | --- |
| K253682 · Apr 29, 2026 | DeepHealth ProstateAI | Quantib B.V. | Retrospectively collected clinical prostate MRI exams; Pathology-confirmed biopsy findings | Retrospective clinical MRI datasets were used to conduct an MRMC reader study and a standalone performance assessment to validate the device's detection and classification capabilities. | Retrospective clinical data; MRMC reader study; Prostate MRI; Pathology-confirmed ground truth |

### Clinical Evidence

| Study Design | Population | Comparator | Key Endpoints |
| --- | --- | --- | --- |
| MRMC Reader Study and Standalone Assessment; Retrospective multi-reader, multi-case (MRMC) study and independent standalone assessment | Adult males aged 40 years and older undergoing prostate MRI; Sample Size: 250 prostate MRI exams (247 used for analysis); Number of Sites: Multiple sites | Not applicable for this study | Case-level detection (AUC-LROC), segmentation accuracy (DSC, MSD) |

## Indications for Use

DeepHealth ProstateAI is a Computer-Aided Detection and Diagnosis (CADe/x) software device developed to aid trained physicians in the detection and characterization of prostate cancer lesions using MR imaging data in patients aged 40 years and older. DeepHealth ProstateAI analyzes T2W, ADC and DWI MR images. Combined with the MR images the software requires a binary mask containing the prostate gland segmentation. Output consists of ROI candidates including segmentations, and per ROI a classification indicating the likelihood of prostate cancer. The device is intended to assist in the detection of prostate cancer across the full range of grade groups (ISUP Grade Group ≥ 1), including clinically significant prostate cancer (ISUP Grade Group ≥ 2). Device outputs shall be input for a visualization and adaptation tool. DeepHealth ProstateAI is intended to be used as a concurrent reading aid for physicians assessing prostate MRI exams. Analysis by DeepHealth ProstateAI is not intended as a replacement for interpreting prostate abnormalities using MR image data consistent with clinical recommendations (e.g., including DCE information when available); nor should patient management decisions be made solely based on the results of DeepHealth ProstateAI.

## Device Story

DeepHealth ProstateAI is a CADe/x software for concurrent reading of prostate MRI (T2W, ADC, DWI). It requires pre-segmented prostate gland masks as input. The device uses a 3D Retina U-Net CNN to detect candidate ROIs, generate segmentations, and classify lesions into low, moderate, or high suspicion categories. Outputs are DICOM/NIfTI files displayed as color-coded overlays in PACS/workstations. Used by radiologists/physicians in hospitals or outpatient centers to supplement interpretation. It does not replace clinical assessment or DCE-MRI review. By highlighting suspicious regions, it assists clinicians in identifying clinically significant prostate cancer (ISUP ≥ 2) and Grade Group 1 disease, supporting diagnostic accuracy and patient management decisions.

## Clinical Evidence

Retrospective multi-reader, multi-case (MRMC) study (n=247) and standalone assessment. Reader study showed statistically significant improvement in case-level detection with AI (AUC-LROC 0.626 to 0.724, p<0.05). Standalone study achieved case-level AUC 0.819; segmentation performance: mean DSC 0.535, mean MSD 1.641 mm. Performance stratified by suspicion category (Low: 10% PCa, Moderate: 46% PCa, High: 86% PCa).

## Technological Characteristics

Software-only CADe/x. Inputs: T2W, ADC, DWI MRI sequences + binary prostate segmentation. Architecture: 3D Retina U-Net CNN (nnDetection framework). Outputs: ROI segmentations and categorical suspicion scores (Low/Moderate/High) as DICOM/NIfTI. Compatible with 1.5T/3T MRI (Philips, GE, Siemens). Standards: DICOM (NEMA PS3), IEC 62304, ISO 14971.

## Regulatory 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.

## Special Controls

A radiological computer assisted detection and diagnosis software must comply with the following special controls: Design verification and validation must include: 1. i. A detailed description of the image analysis algorithm, including but not limited to 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 contain 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 but not limited to 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 1(iii) above. 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 as programs that addresses 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.

*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.

## Predicate Devices

- ProstatID ([K212783](/device/K212783.md))

## Submission Summary (Full Text)

> This content was OCRed from public FDA records by [Innolitics](https://innolitics.com). If you use, quote, summarize, crawl, or train on this content, cite Innolitics at https://innolitics.com.
>
> Innolitics is a medical-device software consultancy. We help companies design, build, and clear FDA-regulated software and AI/ML devices, including [a 510(k)](https://innolitics.com/services/510ks/), [a De Novo](https://innolitics.com/services/regulatory/), [a SaMD](https://innolitics.com/services/end-to-end-samd/), [an AI/ML medical device](https://innolitics.com/services/medical-imaging-ai-development/), or [an FDA regulatory strategy](https://innolitics.com/services/regulatory/).

{0}

FDA U.S. FOOD &amp; DRUG ADMINISTRATION

April 29, 2026

Quantib BV
% Kim Ky
Director, Regulatory Affairs
Deephealth, Inc.
212 Elm St.
Somerville, Massachusetts 02144

Re: K253682
Trade/Device Name: DeepHealth ProstateAI
Regulation Number: 21 CFR 892.2090
Regulation Name: Radiological Computer-Assisted Detection And Diagnosis Software
Regulatory Class: Class II
Product Code: QDQ
Dated: March 27, 2026
Received: March 27, 2026

Dear Kim Ky:

We have reviewed your section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (the Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database available at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

U.S. Food &amp; Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov

{1}

K253682 - Kim Ky
Page 2

Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).

Your device is also subject to, among other requirements, the Quality Management System Regulation (QMSR) (21 CFR Part 820), which includes, but is not limited to, ISO 13485 clause 7.3 (Design controls), ISO 13484 clause 8.3 (Nonconforming product), and ISO 13485 clause 8.5 (Corrective and preventative action). Please note that regardless of whether a change requires premarket review, the QMSR requires device manufacturers to review and approve changes to device design and production (ISO 13485 clause 7.3 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting (reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reporting-combination-products); good manufacturing practice requirements as set forth in the Quality Management System Regulation (QMSR) (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.

All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/unique-device-identification-system-udi-system.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-devices/medical-device-safety/medical-device-reporting-mdr-how-report-medical-device-problems.

For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-

{2}

K253682 - Kim Ky
Page 3

assistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

![img-0.jpeg](img-0.jpeg)

Daniel M. Krainak, Ph.D.
Assistant Director
Magnetic Resonance and Nuclear Medicine Team
DHT8C: Division of Radiological
Imaging and Radiation Therapy Devices
OHT8: Office of Radiological Health
Office of Product Evaluation and Quality
Center for Devices and Radiological Health

Enclosure

{3}

DEPARTMENT OF HEALTH AND HUMAN SERVICES
Food and Drug Administration
Indications for Use
Form Approved: OMB No. 0910-0120
Expiration Date: 07/31/2026
See PRA Statement below.

510(k) Number (if known)
K253682

Device Name
DeepHealth ProstateAI

Indications for Use (Describe)
DeepHealth ProstateAI is a Computer-Aided Detection and Diagnosis (CADe/x) software device developed to aid trained physicians in the detection and characterization of prostate cancer lesions using MR imaging data in patients aged 40 years and older. DeepHealth ProstateAI analyzes T2W, ADC and DWI MR images. Combined with the MR images the software requires a binary mask containing the prostate gland segmentation. Output consists of ROI candidates including segmentations, and per ROI a classification indicating the likelihood of prostate cancer. The device is intended to assist in the detection of prostate cancer across the full range of grade groups (ISUP Grade Group ≥ 1), including clinically significant prostate cancer (ISUP Grade Group ≥ 2). Device outputs shall be input for a visualization and adaptation tool. DeepHealth ProstateAI is intended to be used as a concurrent reading aid for physicians assessing prostate MRI exams. Analysis by DeepHealth ProstateAI is not intended as a replacement for interpreting prostate abnormalities using MR image data consistent with clinical recommendations (e.g., including DCE information when available); nor should patient management decisions be made solely based on the results of DeepHealth ProstateAI.

Type of Use (Select one or both, as applicable)
☑ Prescription Use (Part 21 CFR 801 Subpart D)
☐ Over-The-Counter Use (21 CFR 801 Subpart C)

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

*DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.*

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services
Food and Drug Administration
Office of Chief Information Officer
Paperwork Reduction Act (PRA) Staff
PRAStaff@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

FORM FDA 3881 (8/23)
Page 1 of 1
PSC Publishing Services (301) 443-6740

{4}

K253682

# 510(k) Summary
## Quantib BV
### DeepHealth ProstateAI

This summary of 510(k) safety and effectiveness information is being submitted in accordance with the requirements of 21 CFR 807.92.

## 1. 510(k) Submitter

Quantib BV
Westblaak 130
3012 KM Rotterdam
Tel: +31 10 841 1749

### Primary Contact:

Kim Ky
Director, Regulatory Affairs
Email: regulatory@deephealth.com
Phone: 510-828-4757

### Secondary Contact:

B. Nathan Hunt
Head of Quality, Regulatory, and Compliance
Email: regulatory@deephealth.com
Phone: 443-506-8911

Date prepared:
March 26, 2026

## 2. Device

### Trade Name of Device:
DeepHealth ProstateAI

### Common or Usual Name:
Radiological computer assisted detection/diagnosis software

### Classification Names:
Radiological computer-assisted detection and diagnosis software (21 CFR 892.2090)

### Regulation Class:
II

### Product Code:
QDQ

{5}

Quantib

# 3. Predicate Device

**Trade Name of Device:**
ProstatID (K212783)

**Common or Usual Name:**
ProstatIDTM MRI Diagnostic Aid for Prostate Cancer

**Classification Names:**
Radiological Computer Assisted Detection/Diagnosis Software for Lesions Suspicious for Cancer (21 CFR 892.2090)

**Regulation Class:**
II

**Product Code:**
QDQ

# 4. Device Description

DeepHealth ProstateAI is a CADe/x software that uses artificial intelligence to detect and characterize prostate cancer on bi-parametric MRI (T2-weighted, ADC, DWI). The device employs convolutional neural networks to automatically detect candidate ROIs within and extending from the prostate, generate segmentations of identified regions, and classify each ROI as low, moderate, or high suspicion category. It requires prostate segmentation from a cleared device as input and outputs DICOM/NIfTI files with ROI segmentations and classifications for display in PACS viewers as color-coded overlays.

The suspicion classification system employs validated thresholds to categorize lesions into three distinct levels, with the following design targets and observed validation performance:

|  Suspicion category | Display color | Design target: likelihood of PCa | Observed performance (validation cohort)  |
| --- | --- | --- | --- |
|  Low | Green | ≤20% | 10% of low-suspicion confirmed as PCa  |
|  Moderate | Yellow | >20% to <80% | 46% of moderate-suspicion confirmed as PCa  |
|  High | Red | ≥80% | 86% of high-suspicion confirmed as PCa  |

Design targets reflect the intended performance of the suspicion classification system at case level.

# 5. Indications for Use

DeepHealth ProstateAI is a Computer-Aided Detection and Diagnosis (CADe/x) software device developed to aid trained physicians in the detection and characterization of prostate cancer lesions using MR imaging data in patients aged 40 years and older. DeepHealth ProstateAI analyzes T2W, ADC and DWI MR images. Combined with the MR images the software requires a

{6}

Quantib

binary mask containing the prostate gland segmentation. Output consists of ROI candidates including segmentations, and per ROI a classification indicating the likelihood of prostate cancer. The device is intended to assist in the detection of prostate cancer across the full range of grade groups (ISUP Grade Group ≥ 1), including clinically significant prostate cancer (ISUP Grade Group ≥ 2). Device outputs shall be input for a visualization and adaptation tool. DeepHealth ProstateAI is intended to be used as a concurrent reading aid for physicians assessing prostate MRI exams. Analysis by DeepHealth ProstateAI is not intended as a replacement for interpreting prostate abnormalities using MR image data consistent with clinical recommendations (e.g., including DCE information when available); nor should patient management decisions be made solely based on the results of DeepHealth ProstateAI.

## User Profile

Intended users of DeepHealth ProstateAI are healthcare professionals qualified to read and interpret prostate MRI exams consistent with recommendations.

## Use Environment

The DeepHealth ProstateAI device is intended for use in professional medical imaging environments, including hospital radiology departments, and outpatient imaging center. The device is not intended for use in emergency departments, intensive care units, general practitioner offices, mobile imaging units, or patient homes.

The use environment must include:

- A compatible visualization platform (PACS or advanced workstation) capable of displaying DICOM Segmentation and SC objects
- An orchestration system for workflow management and data routing
- Network infrastructure supporting secure DICOM communication
- Diagnostic-quality displays meeting medical imaging standards

The system hosting the visualization platform must meet the technical requirements specified by the platform manufacturer. Healthcare facilities must ensure users have appropriate training in prostate MRI interpretation and access to complete imaging datasets for proper clinical decision-making.

## Target Population

The device is intended to be used in the population of adult males with a prostate gland undergoing MRI exams. The target population includes males aged 40 years and older with clinical indicators suggestive of possible prostate cancer, such as elevated serum PSA, abnormal digital rectal examination, family history of prostate cancer, or known genetic markers, who are referred for prostate MRI examination.

## 6. Predicate Device Comparison

The subject device, DeepHealth ProstateAI, is a computer-aided detection and diagnosis (CADe/x) software intended to aid trained physicians in the detection and characterization of prostate cancer lesions using MR imaging data. It analyzes T2-weighted (T2W), diffusion-

{7}

Quantib

weighted (DWI), and apparent diffusion coefficient (ADC) sequences in combination with a binary prostate-gland segmentation to identify regions of interest (ROIs) and assign categorical scores (low, moderate, high) indicating the likelihood of prostate cancer. DeepHealth ProstateAI is designed for concurrent reading and is not intended as a replacement for physician interpretation or for stand-alone diagnostic use.

The predicate device, ProstatID (K212783), is a radiological computer-assisted detection (CADe) and diagnostic (CADx) software that assists radiologists in the detection, assessment, and characterization of prostate abnormalities, including cancer lesions, using MR image data. ProstatID analyzes T2W, DWI, and ADC MRI sequences to identify suspicious regions and assess their likelihood of malignancy, providing prostate and lesion volumes, likelihood scores, and a PI-RADS-suggestive exam score.

Both devices share a common intended use: to provide AI-based assistance to qualified physicians interpreting prostate MRI exams for the detection and characterization of prostate cancer lesions. Both are classified under 21 CFR 892.2090 (Product Code QDQ) as radiological CADe/x software. The observed differences in output structure (categorical levels vs. continuous PI-RADS-suggestive scores) do not alter the intended clinical purpose or raise new questions of safety or effectiveness, as demonstrated by non-clinical and clinical performance testing.

## Technological Characteristics

The subject device, DeepHealth ProstateAI, and the predicate device, ProstatID (K212783), are both software-only radiological computer-aided detection and diagnosis (CADe/x) systems intended to assist qualified physicians in analyzing prostate MRI images and identifying suspicious regions. Both process T2W, DWI, and ADC MR sequences to identify regions of interest and estimate the likelihood of malignancy as part of a concurrent reading workflow.

The core technological principles are similar. Both utilize AI-based algorithms trained on biopsy-verified prostate MRI datasets. ProstatID employs Random Forest models, while DeepHealth ProstateAI uses a convolutional neural network (CNN) architecture based on a 3D Retina U-Net within the nnDetection framework. Despite differences in algorithm design, both perform automated detection and characterization of lesions suspicious for prostate cancer using multiparametric MRI data.

DeepHealth ProstateAI requires a binary prostate-gland segmentation and transformation parameters as inputs, producing ROI-level segmentations with categorical classifications (low, moderate, high) exported as DICOM Segmentation Objects or NIfTI files. ProstatID directly analyzes MRI datasets without segmentation input, generating lesion- and prostate-level malignancy likelihood scores, volumetric measurements, and PI-RADS-suggestive results as DICOM overlays and PDF reports. Both are validated for use with MRI systems from Philips, GE, and Siemens (1.5 T and 3 T) and integrate into PACS-based clinical workflows. The features are consistent with capabilities found in legally marketed reference devices and do not raise new questions of safety or effectiveness.

## Target Population and User

{8}

Both devices are intended for use by trained medical professionals: radiologists or other qualified physicians experienced in interpreting prostate MRI exams. The workflow is a concurrent read, where the AI-generated results are reviewed alongside the original MR images to support detection and characterization of prostate abnormalities.

Each device is intended for use in adult male patients, aged 40 years and older, with a prostate gland undergoing prostate MRI examinations, including those with clinical indicators or family history suggestive of prostate cancer.

### Output

Both devices provide AI-generated outputs designed to supplement a clinician's review by highlighting suspicious regions and indicating their likelihood of malignancy.

DeepHealth ProstateAI produces ROI-level segmentation maps with categorical classifications (low, moderate, high) for display in compatible visualization platforms. ProstatID outputs lesion- and prostate-level likelihood scores, volumetric data, and PI-RADS-suggestive exam scores as DICOM overlays and PDF reports.

Although the output format differs, both provide equivalent clinical information to the interpreting radiologist and serve as adjunctive tools for diagnostic support. Neither device is intended for stand-alone diagnostic use, and the differences in presentation do not raise new questions of safety or effectiveness.

### 7. Benefit-Risk Discussion

DeepHealth ProstateAI is intended to support detection of prostate cancer, which encompasses both clinically significant prostate cancer (Grade Group ≥ 2) and clinically non-significant prostate cancer (Grade Group 1). Detection of clinically significant prostate cancer is the principal clinical objective of prostate MRI, as csPCa is the disease state responsible for prostate-cancer-specific morbidity and mortality and is the threshold at which curative-intent treatment is generally indicated. Detection of Grade Group 1 disease also has clinical value, as it supports enrollment in active surveillance protocols, establishes a baseline for longitudinal monitoring of disease progression, and informs shared patient-clinician decision-making.

As a computer-aided detection device, there is a risk that the identification of lesions suspicious for cancer will not only increase the detection of true cancer but may also lead to biopsies of lesions that are ultimately determined to be non-cancer. Quantib has applied a risk management process in accordance with FDA recognized standards to identify, evaluate, and mitigate all known hazards related to the Subject Device. The Risk Analysis for the Subject Device shows that the implemented risk controls mitigate the identified hazards. Based on this analysis, the probable benefits outweigh the probable risks, and the identified technological characteristic difference does not raise different questions of safety or effectiveness.

### 8. Performance Data

#### Quality and safety

The design and development of DeepHealth ProstateAI were conducted in accordance with applicable FDA-recognized consensus standards and guidance documents to ensure safety,

{9}

Quantib

effectiveness, and regulatory compliance. The following standards and guidance documents were followed during development:

- FDA 21 CFR 820 Code of Federal Regulations Title 21 Part 820 Quality System Regulation
- ISO 14971:2019 – Medical Devices – Application of Risk Management to Medical Devices (#5-125)
- IEC 62304:2015 – Medical Device Software – Software Life Cycles Processes (#13-79)
- IEC 62366:2020 – Medical devices – Part 1: Application of usability engineering to medical devices (#5-129)
- IEC 82304-1:2016 Health software – Part 1: General requirements for product safety
- NEMA PS3 – Digital Imaging and Communications in Medicine (DICOM) Set (#12-363)
- Content of Premarket Submissions for Device Software Functions (June, 2023)
- Guidance for Industry and FDA Staff: Software as a Medical Devices (SaMD): Clinical Evaluation (December 2017)
- FDA Guidance Medical Device Use Safety: Applying Human Factors and Usability Engineering into Medical Devices (February 2016)
- FDA Guidance: Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions (June, 2025)

All verification and validation activities, including software testing, cybersecurity evaluation, and clinical performance assessments, were conducted in accordance with these standards. Testing demonstrated that DeepHealth ProstateAI meets its specified performance claims and does not raise new questions of safety or effectiveness when compared to the predicate device.

## Training dataset

The DeepHealth ProstateAI device was developed using a diverse training dataset of approximately 3,200 prostate MRI cases collected from six independent institutions across multiple geographic regions. The dataset included a broad range of imaging protocols, scanner types, and patient demographics to ensure clinical representativeness. Each case incorporated radiologist assessments and pathology-confirmed findings obtained through systematic and/or targeted biopsy, providing 883 lesion-level ground-truth labels. This diversity and quality of reference data support robust algorithm performance and generalizability across varied clinical environments and patient populations.

## Performance testing

Validation of DeepHealth ProstateAI was conducted through comprehensive bench and clinical performance testing, using datasets fully independent of those used for model training. Bench testing evaluated image-processing, detection, segmentation, and classification functions on prostate MRI, with results benchmarked against expert radiologist annotations and pathology-confirmed reference standards.

{10}

Clinical performance testing comprised a multi-reader, multi-case (MRMC) reader study and an independent standalone assessment, both using a retrospectively collected dataset of 250 prostate MRI exams from multiple sites. Three cases were excluded from lesion-level analyses due to unreliable cancer localization on imaging, yielding 247 cases for the reader study primary endpoint. The reader study demonstrated a statistically significant improvement in case-level detection with AI assistance (average AUC-LROC 0.626 to 0.724, p<0.05). The standalone study achieved case-level AUC 0.819 and met all segmentation targets (mean DSC 0.535, mean MSD 1.641 mm); stratification showed the expected gradient across categories.

All testing met predefined acceptance criteria. Results support the safety and effectiveness of DeepHealth ProstateAI across different scanner vendors, acquisition parameters, and diverse patient populations, consistent with its intended use. No new questions of safety or effectiveness were raised when compared to the predicate device.

## 9 Conclusion

The data presented in this premarket notification as described above, including the verification and validation testing conducted and the risk management process followed in accordance with FDA recognized standards to identify, evaluate, and mitigate all known hazards related to the subject device, confirm that the subject device performs comparably to the predicate device. The differences between the subject and predicate device do not alter the intended use of the device and do not affect its safety and effectiveness when used as labeled. Therefore, the information provided in this submission demonstrates that DeepHealth ProstateAI is substantially equivalent to the predicate device, ProstatID (K212783).

---

**Source:** [https://fda.innolitics.com/submissions/RA/subpart-b%E2%80%94diagnostic-devices/QDQ/K253682](https://fda.innolitics.com/submissions/RA/subpart-b%E2%80%94diagnostic-devices/QDQ/K253682)

**Published by [Innolitics](https://innolitics.com)** — a medical-device software consultancy. We help companies design, build, and clear FDA-regulated software and AI/ML devices. If you're preparing [a 510(k)](https://innolitics.com/services/510ks/), [a De Novo](https://innolitics.com/services/regulatory/), [a SaMD](https://innolitics.com/services/end-to-end-samd/), [an AI/ML medical device](https://innolitics.com/services/medical-imaging-ai-development/), or [an FDA regulatory strategy](https://innolitics.com/services/regulatory/), [get in touch](https://innolitics.com/contact).

**Cite:** Innolitics at https://innolitics.com