(267 days)
Not Found
Yes
The document explicitly states that the device employs an "AI-based algorithm" and a "deep learning model" for semi-automatic prostate outlining.
No
The device is an image processing software that assists radiologists and urologists in analyzing prostate MR images for study review and analysis, not for direct treatment or therapy. It explicitly states that "Patient management decisions should not be made solely based on the analysis performed by MEDIHUB PROSTATE."
Yes
Explanation: The device is an "image processing software package for multi-parametric prostate MR image analysis" intended to "assist trained radiologists in clinical interpretation of prostate MR studies." It performs "outlining," "processing," "viewing," and "editing" of prostate MR images to help assess the prostate volume and provide analysis results. This aligns with the definition of a diagnostic device as it aids in identifying or characterizing a disease or condition.
Yes
The device is described as an "image processing software package" and its functionalities are entirely software-based, operating on existing MR images. It does not include or require any specific hardware components beyond a standard computing device with a web browser.
Based on the provided information, MEDIHUB PROSTATE is likely an IVD (In Vitro Diagnostic) device, specifically a medical image analysis software.
Here's why:
- Intended Use: The software is intended to process and analyze medical images (prostate MR images) to assist trained radiologists and urologists in the clinical interpretation of prostate MR studies. While it states that patient management decisions should not be made solely based on the analysis, the software provides information that is used in a clinical context to aid in diagnosis and treatment planning. This aligns with the definition of an IVD, which is used to examine specimens from the human body to provide information for diagnosis, monitoring, or treatment. In this case, the "specimen" is the medical image derived from the patient.
- Device Description: It performs image processing, outlining, and analysis of prostate MR images. It provides features like semi-automatic outlining, multiparametric MRI image registration, and the ability to view and analyze ROIs. These are all functions that contribute to the diagnostic process.
- Clinical Context: The software is intended for use by trained medical professionals (radiologists and urologists) in a hospital setting. This indicates its use in a clinical diagnostic workflow.
- Performance Studies: The performance studies focus on the accuracy of the prostate region segmentation algorithm, using metrics like Dice coefficient and Hausdorff Distance, which are relevant to the accuracy of image analysis for diagnostic purposes.
- Predicate Device: The mention of a predicate device (K202501; Quantib Prostate) is a strong indicator that this device is being compared to other legally marketed IVD devices for similar purposes.
While the software doesn't directly analyze a biological sample like blood or urine, the analysis of medical images derived from a patient's body falls under the broader scope of IVD devices, particularly in the context of providing information for diagnosis.
The fact that it uses AI/deep learning for semi-automatic outlining further reinforces its role as a sophisticated tool intended to assist in the diagnostic process.
Therefore, based on the intended use, device description, clinical context, and comparison to a predicate IVD device, MEDIHUB PROSTATE is highly likely to be classified as an IVD device.
No
The letter does not state that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device; PCCP is only mentioned as "Not Found" in the provided text.
Intended Use / Indications for Use
MEDIHUB PROSTATE is an image processing software package that performs outlining, processing, viewing, and editing of prostate MR images. The software can support study review and analysis of prostate MR data with computed modules. The analysis result can be presented in various formats, including images overlaid onto source MR images and a structured report.
MEDIHUB PROSTATE semi-automatically outlines the prostate based on MR images by contour, and it requires the user to edit with image manipulating tools and confirm the final result. The package provides additional functionalities including registered multiparametric-MRI viewing and combining MR sequences into a single image to support visualization. Edited PI-RADS report and semi annotated prostate region can be viewed in each single image in the final report.
MEDIHUB PROSTATE is intended to be used by trained radiologists and urologists. Patient management decisions should not be made solely based on the analysis performed by MEDIHUB PROSTATE.
Limitations:
-
MEDIHUB PROSTATE has been validated for use with Siemens 3T Vida and Skyra MRI machines.
-
MEDIHUB PROSTATE is also designed for use with the Siemens 3T T2 MRI series, supporting slice thicknesses ranging from 3.5 mm to 5 mm.
-
MEDIHUB PROSTATE has been tested on patients aged 55 years and above.
Product codes
QIH
Device Description
MEDIHUB PROSTATE is an image processing software package for multi-parametric prostate MR image analysis. The analysis may assist trained radiologists in clinical interpretation of prostate MR studies. It can be accessed through a web browser, and provides the following main features:
- A semi-automatic processing module that outlines the prostate region and performs multiparametric MRI image registration.
- A user-interaction module in which the user can edit and approve the computed prostate outline and determine PSA density using serum PSA level.
- A user-interaction module in which the user can view multi-parametric MRI images, and outline and analyze ROIs. This extension will also apply a mathematical operation on the input images to combine information from another MRI sequences into a single combination image.
- A semi-automatic processing module that collects all results for exporting and transferring back to the user.
All measurements are manual except for the prostate volume, which is semi-automatic and requires user review. The method for measuring prostate volume is straightforward and unaffected by patient demographics. Users have the option to outline the prostate either completely manually or with semi-automatic assistance. This device is not intended to be used for fully automatic prostate delineation. It does not involve any segmentation functions by itself. The AI functionality is limited to assessing the total prostate volume, without segmenting lesions.
In semi-automatic mode, our device employs an AI-based algorithm to initially outline the prostate volume, and then it requires the user to edit, review and approve. Additionally, the device calculates the total prostate volume. However, users are responsible for performing all other image annotations and measurements manually. This implies that the final decision should be confirmed by the user, and the user should not rely solely on the device's analysis.
Additional annotations and measurements: all calculated manually
- PI-RADS
- Location of seminal vesicles
- Prostate zones
- DWI and DCE graphs
Mentions image processing
Yes
Mentions AI, DNN, or ML
Yes
Input Imaging Modality
MR images (T2-weighted, DWI, ADC, DCE)
Anatomical Site
Prostate
Indicated Patient Age Range
55 years and above
Intended User / Care Setting
Trained radiologists and urologists / Hospital
Description of the training set, sample size, data source, and annotation protocol
The Study Population Dataset (which is the same as the algorithm development dataset) consists of three sets: Korea, US (University of Missouri Health Care), and ProstateX (open dataset). The dataset was split into Training/Validation/Testing. Data from Korea (n=828) and US (n=845) were used for training and validation. The Training dataset and the Validation dataset were stratified at a ratio of 9:1. The ground truthing was conducted by expert-level radiologists. They independently annotated the prostate images, and these annotations were then consolidated into a definitive ground truth through a majority rule approach.
Description of the test set, sample size, data source, and annotation protocol
The Clinical Test Dataset includes stand-alone performance US (n=114) and reader performance US (n=73 from stand-alone performance). In the Study Population Dataset, the Training/Validation datasets and the Testing dataset were stratified at a ratio of 9:1. The data used to demonstrate performance of the device included Siemens 3T Vida and Skyra systems with slice thickness ranging from 3.5 to 5 mm. For Stand-alone Performance, 114 T2 MR images (University of Missouri Hospital) were used. The prostate region segmentation ground truth was produced by three expert radiologists. For Algorithm Performance Testing, test datasets of Korea patients and ProstateX (open dataset) were utilized. The ground truth was produced by three expert radiologists and consolidated into a definitive ground truth through a majority rule approach with discussion and mutual agreement.
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
Algorithm Performance Testing:
- Study Type: Performance check test on prostate region segmentation algorithm.
- Sample Size: Not explicitly stated, but utilized test datasets of Korea patients and ProstateX (open dataset).
- Standalone Performance: Performance was measured by the mean value of Dice coefficient and Hausdorff Distance of the test group.
- Key Results: The pass/fail criterion for each dataset was a mean Dice coefficient exceeding 0.894. All three test datasets met this criterion, demonstrating that Dice coefficients surpassed 0.866 in every case.
Clinical Testing (Stand-alone Performance):
- Study Type: Verification of stand-alone performance of the prostate region segmentation algorithm.
- Sample Size: 114 T2 MR images.
- Standalone Performance: Mean Dice coefficient and Hausdorff distance were measured by comparing the algorithm's output to ground truth produced by three expert radiologists.
- Key Results: The mean Dice coefficient was higher than the predefined primary efficacy evaluation criterion (0.894). The overall Dice coefficient was 0.928 (95% CI: [0.925, 0.931]), and the Hausdorff distance was 2.171 (95% CI: [1.097, 3.245]).
Clinical Testing (Reader Performance):
- Study Type: Comparison of reader performance with and without the prostate region segmentation algorithm.
- Sample Size: 73 cases from the stand-alone performance dataset.
- Key Results: Dice coefficients of the investigators' performances were calculated by comparing the ground truth of the prostate region segmentation with each investigator's segmentation results. The results were better when all three expert radiologists used the prostate region segmentation algorithm of MEDIHUB PROSTATE, regardless of race and age. The improvements in the Dice coefficient for prostate outlining performance for the three radiologists when using the algorithm were 0.156, 0.011, and 0.008, respectively.
Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)
- Dice Coefficient (mean, 95% CI)
- Hausdorff Distance (mean, 95% CI)
Predicate Device(s):
Reference Device(s):
Not Found
Predetermined Change Control Plan (PCCP) - All Relevant Information
Not Found
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).
0
Image /page/0/Picture/0 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: on the left, there is a symbol representing the Department of Health & Human Services-USA, and on the right, there is the text "FDA U.S. FOOD & DRUG ADMINISTRATION" in blue. The text is arranged in three lines, with "FDA" on the first line, "U.S. FOOD & DRUG" on the second line, and "ADMINISTRATION" on the third line.
June 21, 2024
JLK Inc. % John Smith Partner Hogan Lovells US LLP 555 13th Street, NW Washington, District of Columbia 20004
Re: K233196
Trade/Device Name: Medihub Prostate Regulation Number: 21 CFR 892.2050 Regulation Name: Medical Image Management And Processing System Regulatory Class: Class II Product Code: QIH Dated: May 10, 2024 Received: May 10, 2024
Dear John Smith:
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.
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).
1
Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30, Design controls; 21 CFR 820.90, Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review. the OS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 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 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-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (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.
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-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/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-device-advice-comprehensive-regulatoryassistance/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,
Daniel M. Krainak, PhD Assistant Director 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
2
Indications for Use
510(k) Number (if known) K233196
Device Name MEDIHUB PROSTATE
Indications for Use (Describe)
MEDIHUB PROSTATE is an image processing software package that performs outlining, processing, viewing, and editing of prostate MR images. The software can support study review and analysis of prostate MR data with computed modules. The analysis result can be presented in various formats, including images overlaid onto source MR images and a structured report.
MEDIHUB PROSTATE semi-automatically outlines the prostate based on MR images by contour, and it requires the user to edit with image manipulating tools and confirm the final result. The package provides additional ties including registered multiparametric-MRI viewing and combining MR sequences into a single image to support visualization. Edited PI-RADS report and semi annotated prostate region can be viewed in each single image in the final report.
MEDIHUB PROSTATE is intended to be used by trained radiologists. Patient management decisions should not be made solely based on the analysis performed by MEDIHUB PROSTATE.
Limitations:
-
MEDIHUB PROSTATE has been validated for use with Siemens 3T Vida and Skyra MRI machines.
-
MEDIHUB PROSTATE is also designed for use with the Siemens 3T T2 MRI series, supporting slice thicknesses ranging from 3.5 mm to 5 mm.
-
MEDIHUB PROSTATE has been tested on patients aged 55 years and above.
| 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."
3
510(k) SUMMARY JLK's MEDIHUB PROSTATE K233196
SUBMITTER -
JLK Inc. 5, Teheran-ro 33-gil, Gangnam-gu, Seoul, Republic of Korea Phone: (+82) 02 6925 6189 FAX: (+82) 0505 300 4051 Contact person / E-mail: Dongmin Kim / dmkim@jlkgroup.com Date Prepared: June 14, 2024
II. DEVICE
Name of Device: MEDIHUB PROSTATE Common or Usual Name: MEDIHUB PROSTATE Classification Name: Medical imaqe management and processing system Regulatory Class: II Product Code: QIH Classification regulation: 21 CFR 892.2050
III. PREDICATE DEVICE
Device: Quantib Prostate Manufacturer: Quantib B.V. 510(k) No: K202501 Product Code: LLZ Regulatory Class: II
IV. DEVICE DESCRIPTION
MEDIHUB PROSTATE is an image processing software package for multi-parametric prostate MR image analysis. The analysis may assist trained radiologists in clinical interpretation of prostate MR studies. It can be accessed through a web browser, and provides the following main features:
- . A semi-automatic processing module that outlines the prostate region and performs multiparametric MRI image registration.
- . A user-interaction module in which the user can edit and approve the computed prostate outline and determine PSA density using serum PSA level.
- . A user-interaction module in which the user can view multi-parametric MRI images, and outline and analyze ROIs. This extension will also apply a mathematical operation on the input images to combine information from another MRI sequences into a single combination image.
4
- A semi-automatic processing module that collects all results for exporting and transferring back to the user.
All measurements are manual except for the prostate volume, which is semi-automatic and requires user review. The method for measuring prostate volume is straightforward and unaffected by patient demographics. Users have the option to outline the prostate either completely manually or with semi-automatic assistance. This device is not intended to be used for fully automatic prostate delineation. It does not involve any segmentation functions by itself. The Al functionality is limited to assessing the total prostate volume, without segmenting lesions.
In semi-automatic mode, our device employs an Al-based algorithm to initially outline the prostate volume, and then it requires the user to edit, review and approve. Additionally, the device calculates the total prostate volume. However, users are responsible for performing all other image annotations and measurements manually. This implies that the final decision should be confirmed by the user, and the user should not rely solely on the device's analysis.
Additional annotations and measurements: all calculated manually
- PI-RADS
- Location of seminal vesicles
- . Prostate zones
- . DWI and DCE graphs
V. INDICATIONS FOR USE
MEDIHUB PROSTATE is an image processing software package that performs outlining, processing, viewing, and editing of prostate MR images. The software can support study review and analysis of prostate MR data with computed modules. The analysis result can be presented in various formats, including images overlaid onto source MR images and a structured report.
MEDIHUB PROSTATE semi-automatically outlines the prostate based on MR images by contour, and it requires the user to edit with image manipulating tools and confirm the final result. The package provides additional functionalities including registered multiparametric-MRI viewing and combining MR sequences into a single image to support visualization. Edited PI-RADS report and semi annotated prostate region can be viewed in each single image in the final report.
MEDIHUB PROSTATE is intended to be used by trained radiologists and urologists. Patient management decisions should not be made solely based on the analysis performed by MEDIHUB PROSTATE.
Limitations:
- . MEDIHUB PROSTATE has been validated for use with Siemens 3T Vida and Skyra MRI machines.
- . MEDIHUB PROSTATE is also designed for use with the Siemens 3T T2 MRI series, supporting slice thicknesses ranging from 3.5 mm to 5 mm.
- . MEDIHUB PROSTATE has been tested on patients aged 55 years and above.
5
VI. COMPARISON OF TECHNOLOGICAL CHARACTERISTICS WITH THE PREDICATE DEVICE
MEDIHUB PROSTATE shares similar indications for use, technological characteristics, and principles of operation with its predicate device. At a high level, both the subject device and predicate device are based on the same technological elements as follows:
| Item | MEDIHUB PROSTATE | Quantib Prostate
(K202501) | Substantial
Equivalence |
|------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------|
| Regulatory Data | | | |
| Regulatory
Class | Class II | Class II | Equivalent |
| Classification
Name | Medical image management
and processing system | Picture archiving and
communications system | Equivalent1 |
| Regulation
Number | 21 CFR 892.2050 | 21 CFR 892.2050 | Equivalent |
| Product Code | QIH | LLZ | Equivalent |
| Use | | | |
| Target users | Trained medical professionals | Trained medical professionals | Equivalent |
| Anatomical site | Prostate | Prostate | Equivalent |
| Where used | Hospital | Hospital | Equivalent |
| Workflow
Considerations | User can approve or reject results User can inspect and edit prostate segmentation User can enter PSA value and compute PSA density User can create and update regions of interest (ROIs) User can add and update annotations (text) to analysis User can manually set a PI-RADS score using a PI-RADS interactive worksheet | User can approve or reject results User can inspect and edit prostate segmentation User can enter PSA value and compute PSA density User can create and update regions of interest (ROIs) User can add and update annotations (text) to analysis User can manually set a PI-RADS score using a PI-RADS interactive worksheet | Equivalent |
| Item | MEDIHUB PROSTATE | Quantib Prostate
(K202501) | Substantial
Equivalence |
| Design | • Semi-automatic prostate
segmentation
• Multi parametric image
review
• Biparametric combination
image viewer
• Basic image manipulation
tools, Thresholding tool
• User interface to
create/update user generated
ROIs | • Semi-automatic prostate
segmentation
• Multi parametric image
review
• Biparametric combination
image viewer
• Basic image manipulation
tools, Thresholding tool
• User interface to
create/update user generated
ROIs | Equivalent |
| Non-clinical
performance | • Bench testing performed to
test the functionality of the
system
• This included
characterization of the
standalone performance of
the prostate segmentation
algorithm. | • Bench testing performed to
test the functionality of the
system
• This included
characterization of the
standalone performance of
the prostate segmentation
algorithm. | Equivalent |
| Clinical
performance | • Prostate segmentation
algorithm was tested in a
clinical use context
• i.e. as a semiautomatic
algorithm after correction by
trained clinicians. | • Prostate segmentation
algorithm was tested in a
clinical use context
• i.e. as a semiautomatic
algorithm after correction by
trained clinicians. | Equivalent |
| Standards met | • ISO 14971 – Medical devices
-Application of risk
management to medical
devices
• IEC 62304 – Medical device
software - Software life cycle
processes
• IEC 62366 – Medical
devices - Application of
usability engineering to
medical devices | • ISO 14971 – Medical devices
-Application of risk
management to medical
devices
• IEC 62304 – Medical device
software - Software life cycle
processes
• IEC 62366 – Medical
devices - Application of
usability engineering to
medical devices | Equivalent |
| SW verification
and validation | • Tested in accordance with
verification and validation
processes and planning
• The testing results support
that all the system
requirements have met their
acceptance criteria and are
adequate for its intended use | • Tested in accordance with
verification and validation
processes and planning
• The testing results support
that all the system
requirements have met their
acceptance criteria and are
adequate for its intended use | Equivalent |
| Item | MEDIHUB PROSTATE | Quantib Prostate
(K202501) | Substantial
Equivalence |
| Compatibility
with the
environment
and other
devices | DICOM compatible | DICOM compatible | Equivalent |
| Reported
measures | Prostate gland Volume, PSA
density, ROIs within the
prostate, with for each ROI:
• Volume
• Average ADC value
• PI-RADS score
• Location | Prostate gland volume, PSA
density, ROIs within the
prostate, with for each ROI:
• Volume
• Average ADC value
• PI-RADS score
• Location | Equivalent |
| Required input | DICOM compatible data, type
of MRI scans: T2-weighted,
DWI, ADC, DCE | DICOM compatible data, type
of MRI scans: T2-weighted,
DWI, ADC, DCE | Equivalent |
Substantial Equivalence Chart
1 The name of the generic devices regulated under 21 C.F.R. 892.2050 has been changed from Picture archiving and communications system to Medical image management and processing system as part of FDA's implementation of the 21st Century Cures Act.
6
7
VII. PERFORMANCE DATA
Data Description
Image /page/7/Figure/3 description: The image shows a flow chart of the study population dataset and the clinical test dataset. The study population dataset includes data from Korea (n=908), US (n=981), and ProstateX (n=19). The training dataset includes data from Korea (n=828) and US (n=845), which is further divided into training dataset Korea (n=748) and US (n=709) and validation dataset Korea (n=80) and US (n=136). The clinical test dataset includes stand-alone performance US (n=114) and reader performance US (n=73 from stand-alone performance).
Study Population Dataset: The Study Population Dataset is the same as algorithm development dataset. The dataset consists of three sets, Korea, US (the University of Missouri Health Care), and ProstateX (open dataset is split into Training/Validation/Testing dataset. In Phase I, a Stand-alone Performance test was conducted, and in Phase II, a Reader Performance test was conducted. In the Study Population Dataset, the Training/Validation datasets and the Testing dataset were stratified at a ratio of 9:1. Additionally, within the Training/Validation split, the Training dataset and the Validation dataset were further stratified at a ratio of 9:1. The data used
8
to demonstrate performance of the device included Siemens 3T Vida and Skyra systems with slice thickness ranging from 3.5 to 5 mm.
Algorithm Performance Testing
A performance check test was conducted on the prostate region segmentation algorithm of MEDIHUB PROSTATE. The performance was obtained by comparing the ground truth produced by three expert radiologists and the results of the prostate region segmentation algorithm. The performance was measured by the mean value of Dice coefficient and Hausdorff Distance of the test group. The results were obtained and calculated by computer coding, and the score for each case was recorded. Utilizing the test datasets of Korea patients, and ProstateX (open dataset), the performance of the prostate region segmentation function was evaluated. Calculating the Dice coefficient between ground-truth and algorithm prediction vields the performance. The passffail criterion for each dataset is whether the mean Dice coefficient exceeds 0.894, which is determined by analyzing the results of the most recent state-of-the-art prostate region segmentation algorithm published in the past 5 years; this value is the average of performance in articles whose performance is greater than the average of the entire references. The value is calculated as the lower limit of 99%, confidence interval based on the performances of whole reference. As a consequence, the criteria were met by all three test datasets.
Clinical Testing (Stand-alone Performance)
The purpose of this study is to verify the stand-alone performance of the prostate region segmentation algorithm. MEDIHUB PROSTATE was developed by applying a deep learning technique on T2 prostate MRI. The clinical test investigator collected data that met the inclusion criteria and no subjects met the exclusion criteria. Based on a total of 114 T2 MR images (University of Missouri Hospital) the final validity evaluation was performed on prostate region seqmentation ground truth produced by three expert radiologists. In this clinical test, it was confirmed that mean Dice coefficient was higher than the predefined primary efficacy evaluation criterion. The clinical testing results demonstrated that the overall Dice coefficient and Hausdoff distance were 0.928 and 2.171, respectively, with the 95% confidence intervals for these measurements being [0.925, 0.931] for the Dice coefficient and [1.097, 3.245] for the Hausdoff distance.
Ground Truthing Process
The ground truthing was conducted by expert-level radiologists. They independently annotated the prostate images, and these annotations were then consolidated into a definitive ground truth through a majority rule approach. The rationale for employing consensus among three radiologists, resolved through discussion and mutual agreement in cases of ties, ensures a reliable and unbiased representation of the prostate, crucial for the accurate clinical performance evaluation of our device.
| Gender, n(%) | Male, 114 (100%) |
|---|---|
| Age | Mean ± SD |
| 66.38 ± 5.33 | |
| Age | Median (Min, Max) |
| 66 (57, 78) |
Clinical Testing Dataset Distribution
Demographic information on subjects (N=114)
9
| Age group, n (%) | ട് -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | 14 (12.3%) |
|---|---|---|
| 60~69 | 63 (55.3%) | |
| 70~79 | 37 (32.5%) | |
| White | 106 (92.9%) | |
| Races | African American | 7 (6.1%) |
| Asian | 1 (0.9%) |
- As indicated in a paper by Mavropoulos (2007)², there is no significant association between race and prostate size. Given that race or ethnicity does not impact measuring prostate area or volume.
95% confidence interval of the dice coefficient and Hausdorff distance calculated by comparing ground truth and the result of algorithms by race
| Race | Dice Coefficient | Hausdorff Distance |
|---|---|---|
| White | 0.929 | |
| *[0.925, 0.933] | 2.173 | |
| *[2.066, 2.280] | ||
| African | ||
| American | 0.925 | |
| *[0.902, 0.949] | 2.085 | |
| *[1.711, 2.459] | ||
| Asian | 0.917 | |
| *[nan, nan] | 2.929 | |
| *[nan, nan] |
- 95% Confidence Interval
95% confidence interval of the dice coefficient and Hausdorff distance calculated by comparing ground truth and the result of algorithms by age
| Age | Dice Coefficient | Hausdorff Distance |
|---|---|---|
| 6 Mavropoulos, J. C., Partin, A. W., Amling, C. L., Terris, M. K., Kane, C. J., Aronson, W. J., .. & Freedland, S. J. (2007). Do racial differences in prostate size explain higher serum prostate-specific antigen concentrations among black men'?. Urology, 69(0), 1138-1142. |
10
for prostate outlining performance for the three radiologists when using the prostate region segmentation algorithm of MEDIHUB-PROSTATE were 0.156, 0.011, and 0.008, respectively.
| Properties | Value |
|---|---|
| Sites | University of Missouri Health Care |
| Field Strengths | 3T |
| MR Scanner Manufacturer | SIEMENS, Siemens HealthCare GmbH |
| Thickness | 3.5mm, 5mm |
| Purpose of Al | Prostate region semi auto-segmentation |
Properties of Performance Testing Cases
Safety Implications
MEDIHUB PROSTATE is intended to support trained radiologists. The software does not make diagnoses; it provides quantification results that must be interpreted by a trained radiologists and urologists before using the device. MEDIHUB PROSTATE is both software applications running on off-the-shelve hardware. In conclusion, MEDIHUB PROSTATE does not introduce any new safety issues compared to the predicate device Quantib Prostate.
VIII. DISCUSSION & CONCLUSIONS
Discussion
MEDIHUB PROSTATE employs a deep learning model to semi-automatically outline the prostate region. Its performance is evaluated using the Dice coefficient against ground-truth data from Korea patients, US patients, and an open dataset (ProstateX). The pass/fail criterion, set at a mean Dice coefficient of 0.894, is determined by recent state-of-the-art algorithms. Results show that all three test datasets meet this criterion, with Dice coefficients surpassing 0.866 in every case, demonstrating substantial equivalence.
Conclusions
MEDIHUB PROSTATE is semi-automatic image processing software. Clinical test results indicate its safety as it does not affect patients according to the software's results. By utilizing the semiautomatic drawing function of the software, it demonstrates efficiency in improving the accuracy of user's prostate region segmentation, making it as safe and effective as the Quantib Prostate. MEDIHUB PROSTATE has the same intended uses and similar indications, technological characteristics, and principles of operation as its predicate device. In addition, the minor technological differences between the MEDIHUB PROSTATE and its predicate devices raise no new issues of safety or effectiveness. Performance data demonstrate that the MEDIHUB PROSTATE is as safe and effective as the Quantib Prostate. Thus, the MEDIHUB PROSTATE is substantially equivalent.