The Avenda Health AI Prostate Cancer Planning Software is an artificial intelligence (AI)-based decision support software, indicated as an adjunct to the review of magnetic resonance (MR) prostate images and biopsy findings in the prostate oncological workflow. The Avenda Health AI Prostate Cancer Planning Software is designed to support the prostate oncological workflow by helping the user with the segmentation of MR image features, including the prostate; in the evaluation, quantification, and documentation of lesions; and in pre-planning for diagnostic and interventional procedures such as biopsy and/or soft tissue ablation. The device is intended to be used by physicians trained in the oncological workflow in a clinical setting for planning and guidance for clinical, interventional, diagnostic, and/or treatment procedures of the prostate.

The Avenda Health Al Prostate Cancer Planning Software's lesion characterization functions are intended for use on patients with a pathology-confirmed Gleason Grade Group (GGG) ≥ 2 lesion and for whom corresponding biopsy coordinate information have been uploaded. These functions are indicated for the extent of known disease. Extent of known disease refers to the boundary of a pathology confirmed lesion of GGG ≥ 2 for a particular patient. Specifically, using prostate MR images, biopsy, pathology, and clinical data, the device creates and displays a cancer map that assigns a probability to each voxel within the prostate, indicating its probability for containing clinically significant prostate cancer (csPCa, defined as GGG ≥ 2 ). A user selects a threshold for the cancer map to create a boundary of the lesion. The lesion boundary is assigned an Encapsulation Confidence Score indicating the confidence that all csPCa is encapsulated within the boundary. The Encapsulation Confidence Score is from a lookup table generated by a database of cases with known ground-truth. When interpreted by a trained physician, this information may be useful in supporting lesion characterization and subsequent patient management.

The Avenda Health Al Prostate Planning Software may also be used as a medical image application, for the viewing. manipulation, 3D-visualization, and comparison of MR prostate images can be viewed in a number of output formats including volume rendering. It enables visualization of information that would otherwise have to be visually compared disjointedly.

Device Description

The Avenda Health AI Prostate Cancer Planning Software ("AI Prostate Cancer Planning Software" or "Software") is an artificial intelligence (AI)-based decision support software, indicated as an adjunct to the review of magnetic resonance (MR) prostate images and biopsy findings in the prostate oncological workflow. The Avenda Health AI Prostate Cancer Planning Software is designed to support the prostate oncological workflow by helping the user with the segmentation of MR image features, including the prostate; in the evaluation, quantification, and documentation of lesions; and in pre-planning for diagnostic and interventional procedures such as biopsy and/or soft tissue ablation. The device is intended to be used by physicians trained in the oncological workflow in a clinical setting for planning and guidance for clinical, interventional, diagnostic, and/or treatment procedures of the prostate. The software has three main features:

1. Artificial Intelligence (AI) Powered Prostate MRI Segmentation Tool,
1. AI Powered Lesion Contour Tool, and
1. Simulated Interventional Tool Placement.

The user can choose which subset of features of the Software to employ based on the specific oncological workflow. Not all features are required to be used for every workflow. Once the user has completed planning and has reviewed and verified the information, it can be exported into a supported file format such that it can be imported into a compatible interventional system or biopsy system.

AI/ML Overview

The provided text is a 510(k) summary for the Avenda Health AI Prostate Cancer Planning Software. While it describes the device, its intended use, and generally states that performance testing was conducted, it does not provide a detailed table of acceptance criteria and reported device performance metrics with specific values beyond high-level summaries of reader study results. Similarly, it does not explicitly detail the sample size for the training set or the exact method used to establish ground truth for the training set.

However, based on the provided text, I can extract and infer some information to answer your questions as best as possible.

Acceptance Criteria and Study to Prove Device Meets Criteria

The document states that the device was deemed "substantially equivalent" to a predicate device (Quantitative Insights, Inc. QuantX) based on "performance bench, usability, and reader performance testing." While specific numerical acceptance criteria for each test are not explicitly detailed in a table, the effectiveness of the device is primarily demonstrated through the Multi-Reader, Multi-Case (MRMC) study for human reader performance and standalone performance testing for the prostate segmentation and lesion contouring algorithms.

1. Table of Acceptance Criteria and Reported Device Performance

As a detailed table of specific acceptance criteria values is not present, I will construct a table based on the stated performance outcomes for the key functionalities assessed. The document describes the "superiority" of the device-assisted contours over standard of care, implying these performance improvements were the implicit "acceptance criteria" for demonstrating effectiveness.

Feature Assessed	Acceptance Criteria (Implicitly Met)	Reported Device Performance (Mean)
Lesion Contouring (Reader Study - AI Assisted vs. SOC)	Improved sensitivity in encapsulating csPCa compared to SOC.	97.4% (AI-assisted) vs. 38.2% (SOC)
	Improved specificity compared to hemi-gland contours.	72.1% (AI-assisted)
	Improved balanced accuracy compared to SOC and hemi-gland contours.	84.7% (AI-assisted) vs. 67.2% (SOC) & 75.9% (hemi-gland)
	Improved "clinical quality" of contours.	99% (AI-assisted) vs. 60% (hemi-gland) of cases
	Improved complete csPCa encapsulation rate.	72.8% (AI-assisted) vs. 1.6% (SOC)
Prostate Segmentation (Standalone)	Accurately segment the prostate organ in T2-weighted MRI.	Achieved in a standalone test set of 137 patients. (Specific metric e.g., Dice Score not provided)
Lesion Contouring (Standalone)	Accuracy in contouring GGG >2 lesions.	Validated in an independent whole mount pathology dataset of N=50 patients. (Specific metric e.g., Dice Score not provided)

Note: The document presents the results as demonstrations of improvement and validation rather than explicitly defined "acceptance criteria" with thresholds that were individually met. The P-values (< 0.0001) indicate statistical significance for the observed improvements.

2. Sample Sizes Used for the Test Set and Data Provenance

Human Reader Study Test Set:
- Cases: Composed of cases within a prostate whole mount pathology database derived from GGG 2-3 patients. The exact number of cases is not explicitly stated beyond "Overall, the study dataset consisted of cases..."
- Data Provenance: Implied to be from a general "prostate whole mount pathology database." The country of origin is not specified.
- Retrospective/Prospective: The use of an existing "pathology database" implies the data was retrospective.
Standalone Performance Testing Test Sets:
- Prostate Segmentation Test Set: 137 patients.
- Lesion Contouring Test Set: N=50 patients (independent whole mount pathology dataset).
- Data Provenance: Not specified for either dataset.
- Retrospective/Prospective: The use of existing "standalone test datasets" and "whole mount pathology dataset" implies the data was retrospective.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications

Human Reader Study Ground Truth:
- Number of Experts: Not explicitly stated as directly establishing ground truth for the test set. Instead, the ground truth was "whole mount pathology data."
- Qualifications: Not applicable as ground truth was pathology.
Standalone Performance Testing Ground Truth:
- Prostate Segmentation & Lesion Contouring: Ground truths were "clinically valid ground truths" and "whole mount pathology data." The number and qualifications of experts involved in creating or confirming these ground truths are not specified in the provided text.

4. Adjudication Method for the Test Set

Human Reader Study: The ground truth was "whole mount pathology data." This is a definitive ground truth and typically does not require adjudication in the same way as expert consensus based on image review. The readers in the MRMC study provided their contours, which were then compared against this pathology ground truth.
Standalone Performance Testing: Ground truth established against "clinically valid ground truths" and "whole mount pathology data." Adjudication methods for establishing these ground truths are not specified.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and the Effect Size of how human readers improve with AI vs without AI assistance

Yes, an MRMC study was done.
Effect Size / Improvement:
- Sensitivity (csPCa encapsulation): Mean 97.4% (with AI) vs 38.2% (SOC) – an improvement of 59.2 percentage points.
- Specificity (compared to hemi-gland contours): Mean 72.1% (with AI). (SOC specificity not given in direct comparison, but "superior specificity" is stated).
- Balanced Accuracy: Mean 84.7% (with AI) vs 67.2% (SOC) – an improvement of 17.5 percentage points. Also 84.7% (with AI) vs 75.9% (hemi-gland) – an improvement of 8.8 percentage points.
- Complete csPCa Encapsulation Rate: 72.8% (with AI) vs 1.6% (SOC) – an improvement of 71.2 percentage points.
- "Clinical Quality": Improved in 99% of cases with AI vs 60% with hemi-gland contours – an improvement of 39 percentage points.

The document consistently states p-values of < 0.0001, indicating a highly statistically significant improvement for all measured metrics when readers used the AI-assisted tool compared to SOC methods.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done

Yes, standalone performance testing was done for:
- Prostate Segmentation Algorithm: "accurately segment the prostate organ in T2-weighted MRI in a standalone test set of 137 patients."
- Lesion Contouring Algorithm: "validated for accuracy in contouring GGG >2 lesions in the intended use population within a representative, independent whole mount pathology dataset of N=50 patients."

7. The Type of Ground Truth Used

Human Reader Study: "Whole mount pathology data" registered to pre-operative T2-weighted MRI. This is a definitive, pathology-based ground truth.
Standalone Performance Testing:
- Prostate Segmentation: "Clinically valid ground truths." (Specifics not provided)
- Lesion Contouring: "Whole mount pathology data."

8. The Sample Size for the Training Set

The sample size for the training set used to develop the AI algorithms is not explicitly stated in the provided 510(k) summary.

9. How the Ground Truth for the Training Set Was Established

The method for establishing ground truth for the training set is not explicitly stated. The document mentions that the lesion characterization functions' "Encapsulation Confidence Score is from a lookup table generated by a database of cases with known ground-truth." This implies the training data for the lesion characterization component also relied on "known ground-truth," likely pathology, but the process of its establishment is not detailed for the training set itself.

Summary

{0}------------------------------------------------

Image /page/0/Picture/0 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo in blue, with the words "U.S. FOOD & DRUG" stacked on top of the word "ADMINISTRATION".

November 22, 2022

Avenda Health, Inc. % Brittany Berry-Pusey, Ph.D. Co-Founder and COO 4130 Overland Avenue CULVER CITY CA 90230

Re: K221624

Trade/Device Name: Avenda Health AI Prostate Cancer Planning Software Regulation Number: 21 CFR 892.2060 Regulation Name: Radiological computer-assisted diagnostic software for lesions suspicious of cancer Regulatory Class: Class II Product Code: POK Dated: October 23, 2022 Received: October 24, 2022

Dear Brittany Berry-Pusey:

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 (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 located 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.

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

{1}------------------------------------------------

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 803) for devices or postmarketing safety reporting (21 CFR 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 (OS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 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,

FDA

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

{2}------------------------------------------------

Indications for Use

510(k) Number (if known) K221624

Device Name

Avenda Health AI Prostate Cancer Planning Software

Indications for Use (Describe)

X 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) Notification K221624

GENERAL INFORMATION [807.92(a)(1)]

Applicant:

Avenda Health, Inc. 4130 Overland Avenue Culver City, CA 90230 USA

Contact Person:

Brittany Berry-Pusey, Ph.D. Co-Founder and COO, Avenda Health, Inc. Phone: 310-957-5202 Email: brit@avendahealth.com

Prepared By:

Veranex, Inc. Regulatory, Clinical, and Quality Services 224 Airport Parkway, Suite 250 San Jose, CA 95110 USA

Date Prepared: November 18, 2022

DEVICE INFORMATION [807.92(a)(2)]

Trade Name:

Avenda Health AI Prostate Cancer Planning Software

Generic/Common Name:

Medical Image Software Application and Decision Support Software

Classification:

21 CFR$892.2060, Radiological computer-assisted diagnostic software for lesions suspicious of cancer

Product Code:

POK, Computer-Assisted Diagnostic Software For Lesions Suspicious For Cancer

{4}------------------------------------------------

PREDICATE DEVICE [807.92(a)(3)]

Quantitative Insights, Inc. QuantX (DEN170022)

DEVICE DESCRIPTION [807.92(a)(4)]

1. Artificial Intelligence (AI) Powered Prostate MRI Segmentation Tool,
1. AI Powered Lesion Contour Tool, and
1. Simulated Interventional Tool Placement.

INDICATIONS FOR USE [807.92(a)(5)]

The Avenda Health AI Prostate Cancer Planning Software's lesion characterization functions are intended for use on patients with a pathology-confirmed Gleason Grade Group (GGG)> 2 lesion and for whom corresponding biopsy coordinate information have been uploaded. These functions are indicated for the evaluation of the extent of known disease. Extent of known disease refers to the boundary of a pathology confirmed lesion of GGG≥ 2 for a particular patient. Specifically, using prostate MR images, biopsy, pathology, and clinical data, the device creates and displays a cancer map that assigns a probability to each voxel within the prostate, indicating its probability for containing clinically significant prostate cancer (csPCa, defined as GGG≥ 2). A user selects a threshold for the cancer map to create a boundary of the lesion. The

{5}------------------------------------------------

5.0 510(k) SUMMARY

lesion boundary is assigned an Encapsulation Confidence Score indicating the confidence that all csPCa is encapsulated within the boundary. The Encapsulation Confidence Score is from a lookup table generated by a database of cases with known ground-truth. When interpreted by a trained physician, this information may be useful in supporting lesion characterization and subsequent patient management.

The Avenda Health AI Prostate Planning Software may also be used as a medical image application, for the viewing, manipulation, 3D-visualization, and comparison of MR prostate images. The images can be viewed in a number of output formats including volume rendering. It enables visualization of information that would otherwise have to be visually compared disjointedly.

COMPARISON OF TECHNOLOGICAL CHARACTERISTICS WITH THE PREDICATE DEVICES [807.92(a)(6)]

Avenda Health, Inc. believes that the Avenda Health AI Prostate Cancer Planning Software (the "Proposed Device") is substantially equivalent to the predicate device, Quantitative Insights, Inc. QuantX (DEN170022, "QuantX"). Like QuantX, the Proposed Device is used by physicians to support tasks within the oncological workflow. The range of functionalities supported by the Proposed Device, which include segmentation, lesion characterization, and image overlays (i.e., simulated tool placement to support subsequent treatment planning), in addition to basic magnetic resonance image (MRI) and medical information review functionalities, is similar to those available in the identified predicate device. QuantX is selected as the predicate device because, like the Proposed Device, its primary imaging functionality is to characterize lesions suspicious for cancer through an artificial intelligence-powered algorithm and provide information to support the physician user's interpretation of the patient's medical and imaging information. DynaCAD is selected as a reference device to support the performance testing methodology for the prostate segmentation function. The Proposed Device is substantially equivalent to the identified predicate device.

SUBSTANTIAL EQUIVALENCE

The Proposed Device and the predicate device have the same intended use and similar Indications for Use. Both devices also have similar technological characteristics, and any differences in technological characteristics do not raise different questions of safety and effectiveness. The results of performance bench, usability, and reader performance testing demonstrated that the Proposed Device meets the established specifications necessary for consistent performance to achieve its intended use as safely and as effectively as the predicate device. Further, the results of the performance bench, usability, and reader performance testing confirmed that the technological differences do not raise different questions of safety and effectiveness. As such, the Avenda Health AI Prostate Cancer Planning Software is substantially equivalent to the predicate device, QuantX (DEN170022).

PERFORMANCE DATA [807.92(b)]

All necessary testing was conducted on the Avenda Health AI Prostate Cancer Planning Software to support a determination of substantial equivalence to the predicate devices.

Non-clinical Testing Summary:

{6}------------------------------------------------

Avenda has performed software verification, validation, and usability testing to demonstrate that: 1) the device performs to its intended use in accordance with design specifications, and 2) the technological differences presented in the Proposed Device do not raise different questions of safety and effectiveness. These tests include:

Software verification and validation demonstrated that the Proposed Device performs in ● accordance with its specification for every requirement and functionality.
Standalone performance testing for the prostate segmentation and lesion contouring algorithms within standalone test datasets, established against clinically valid ground truths. Specifically, the prostate segmentation algorithm has been determined to accurately segment the prostate organ in T2-weighted MRI in a standalone test set of 137 patients. Furthermore, the lesion contouring algorithm has been validated for accuracy in contouring GGG >2 lesions in the intended use population within a representative, independent whole mount pathology dataset of N=50 patients.
Human factors usability testing for the Proposed Device has demonstrated that . representative intended users can use the device safely and effectively, without significant use-related risks.

Reader Study Summary:

A multi-reader, multi-case (MRMC) study was conducted for the Avenda Health AI Prostate Cancer Planning Software ("Proposed Device") to demonstrate that the device improves reader performance for prostate cancer lesion contouring in the intended use population.

Overall, the study dataset consisted of cases within a prostate whole mount pathology database derived from GGG 2-3 patients, which is representative of the device patient population. Each whole mount sample included 3D surfaces and pathology labels representing tumors as annotated on the whole mount prostatectomy slides, which are registered to preoperative T2-weighted MRI. Ten practicing urologists or radiologists from different institutions with a range of experience levels (2 to 23 years of clinical practice experience) participated in this reader study. Each reader reviewed each case. For each case, the reader created a prostate cancer lesion contour based both on standard of care (SOC) practices and with the assistance of the Proposed Device. The lesion contours created with each method were evaluated against whole mount pathology data as ground truth and subsequently compared to one another as well as hemi-gland contours, in order to assess the ability of the Proposed Device to improve reader ability in lesion contouring.

The study results demonstrated that lesion contours produced using the Proposed Device had superior sensitivity (mean 97.4% vs 38.2%, p < 0.0001) compared to SOC contours and superior specificity compared to hemi-gland contours (mean 72.1%, p < 0.0001). Furthermore, lesion contours produced using the Proposed Device were superior to both SOC and hemi-gland contours using measures of balanced accuracy (mean 84.7% vs 67.2% & 75.9% respectively, p < 0.0001) and "clinical quality" (in 99% and 60% of cases respectively, p < 0.0001). On average, the readers achieved a complete csPCa encapsulation rate of 72.8% with the Proposed Device, and only 1.6% with SOC methods (p < 0.0001).

The outcomes of this study demonstrated improved reader performance, and showed that readers, when using the Proposed Device, can create lesion contours that better fully encapsulate csPCa

{7}------------------------------------------------

5.0 510(k) SUMMARY

while excluding as much non-csPCa tissue as possible. The proposed device helps resolve the systematic underestimation of csPCa present with SOC manual contouring methods, while simultaneously sparing much of the benign tissue unnecessarily encapsulated with hemi-gland contours. These findings demonstrate that the Proposed Device improves reader performance as intended in the intended user population when used in accordance with the instructions for use.

CONCLUSIONS

The Avenda Health AI Prostate Cancer Planning Software (Proposed Device) and the predicate device QuantX (DEN170022) are both intended as a medical image software application for MRI which can be used to support the clinical workflow of oncological diagnostic and interventional procedures. The devices have the same intended use and similar Indications for Use. Both devices also have similar technological characteristics, and any differences in technological characteristics do not raise different questions of safety and effectiveness. The collective performance bench, usability, and reader performance testing results demonstrated that the Proposed Device performed to its intended use in accordance with its specifications, and confirmed the technological differences presented in the Proposed Device do not raise different questions of safety and effectiveness.

SUMMARY

The Avenda Health AI Prostate Cancer Planning Software is substantially equivalent to the identified predicate device.

{8}------------------------------------------------

	Avenda Health AI Prostate CancerPlanning Software(Proposed Device)	Predicate Device:Quantitative Insights, Inc. QuantX(DEN170022)	Rationale for SubstantialEquivalence
Indications for Use	The Avenda Health AI Prostate CancerPlanning Software is an artificialintelligence (AI)-based decision supportsoftware, indicated as an adjunct to thereview of magnetic resonance (MR)prostate images and biopsy findings in theprostate oncological workflow. TheAvenda Health AI Prostate CancerPlanning Software is designed to supportthe prostate oncological workflow byhelping the user with the segmentation ofMR image features, including the prostate;in the evaluation, quantification, anddocumentation of lesions; and in pre-planning for diagnostic and interventionalprocedures such as biopsy and/or softtissue ablation. The device is intended tobe used by physicians trained in theoncological workflow in a clinical settingfor planning and guidance for clinical,interventional, diagnostic, and/or treatmentprocedures of the prostate.	QuantX is a computer-aided diagnosis(CADx) software device used to assistradiologists in the assessment andcharacterization of breast abnormalitiesusing MR image data. The softwareautomatically registers images, andsegments and analyzes user-selectedregions of interest (ROI). QuantX extractsimage data from the ROI to providevolumetric analysis and computeranalytics based on morphological andenhancement characteristics. Theseimaging (or radiomic) features are thensynthesized by an artificial intelligencealgorithm into a single value, the QI score,which is analyzed relative to a database ofreference abnormalities with knownground truth.	Similar to the predicate device.
	The Avenda Health AI Prostate CancerPlanning Software's lesioncharacterization functions are intended foruse on patients with a pathology-confirmedGleason Grade Group (GGG) $\geq$ 2 lesionand for whom corresponding biopsycoordinate information have beenuploaded. These functions are indicatedfor the evaluation of the extent of knowndisease. Extent of known disease refers tothe boundary of a pathology confirmedlesion of GGG $\geq$ 2 for a particular patient.Specifically, using prostate MR images,	QuantX is indicated for evaluation ofpatients presenting for high-risk screening,diagnostic imaging workup, or evaluationof extent of known disease. Extent ofknown disease refers to both theassessment of the boundary of a particularabnormality as well as the assessment ofthe total disease burden in a particularpatient. In cases where multipleabnormalities are present, QuantX can beused to assess each abnormalityindependently.
		This device provides information that maybe useful in the characterization of breastabnormalities during image interpretation.For the QI score and component radiomicfeatures, the QuantX device provides
	Avenda Health AI Prostate CancerPlanning Software(Proposed Device)	Predicate Device:Quantitative Insights, Inc. QuantX(DEN170022)	Rationale for SubstantialEquivalence
	biopsy, pathology, and clinical data, thedevice creates and displays a cancer mapthat assigns a probability to each voxelwithin the prostate, indicating itsprobability for containing clinicallysignificant prostate cancer (csPCa, definedas GGG $≥2$ ). A user selects a threshold forthe cancer map to create a boundary of thelesion. The lesion boundary is assigned anEncapsulation Confidence Score indicatingthe confidence that all csPCa isencapsulated within the boundary. TheEncapsulation Confidence Score is from alookup table generated by a database ofcases with known ground-truth. Wheninterpreted by a trained physician, thisinformation may be useful in supportinglesion characterization and subsequentpatient management.The Avenda Health AI Prostate PlanningSoftware may also be used as a medicalimage application, for the viewing,manipulation, 3D-visualization, andcomparison of MR prostate images. Theimages can be viewed in a number ofoutput formats including volumerendering. It enables visualization ofinformation that would otherwise have tobe visually compared disjointedly.	comparative analysis to lesions withknown outcomes using an image atlas andhistogram display format.QuantX may also be used as an imageviewer of multi-modality digital images,including ultrasound and mammography.The software also includes tools that allowusers to measure and document images,and output in a structured report.Limitations: QuantX is not intended forprimary interpretation of digitalmammography images.
Regulation Number	§892.2060, Radiological computer-assisteddiagnostic software for lesions suspiciousof cancer.	§892.2060, Radiological computer-assisted diagnostic software for lesionssuspicious of cancer.	Same as the predicate device.
	Avenda Health AI Prostate CancerPlanning Software(Proposed Device)	Predicate Device:Quantitative Insights, Inc. QuantX(DEN170022)	Rationale for SubstantialEquivalence
Product Codes:	POK, Computer-Assisted DiagnosticSoftware For Lesions Suspicious ForCancer	POK, Computer-Assisted DiagnosticSoftware For Lesions Suspicious ForCancer	Same as the predicate device.
Primary Intended User	Trained physicians in the intendedworkflow (Radiologist/Urologist)	Trained physicians in the intendedworkflow (Radiologist)	Same as the predicate device –intended for use by theappropriate trained physicians.
Anatomical Site:	Prostate only	Breast only	Different, but same intendeduse and the differences do notraise different questions ofsafety or effectiveness.
Oncological Workflow ofInterest	Prostate Cancer	Breast Cancer	Different, but same intendeduse within the workflow andthe differences do not raisedifferent questions of safety oreffectiveness.
Clinical Workflow StepsWhere Used:	Image Review and Workflow SupportInterventional/Treatment Planning andGuidance for Diagnostic and InterventionalProcedures	Image Review and Workflow Support	Similar to the predicate device.
Platform/Architecture	Cloud-only solution	Software-only platform	Similar – both devices areWeb-based software devices.
DICOM Compatible	Yes	Yes	Same as the predicate device.
Type of Scans	MR, DICOM-compatible	MR, DICOM-compatible	Same as the predicate device.
Image Navigation Tools	● Pan, zoom, rotate, slice scroll (viewmultiple slices)	● Pan, zoom, rotate, change in contrast,slice scroll (view multiple slices)	Same as the predicate device.
	Avenda Health AI Prostate CancerPlanning Software(Proposed Device)	Predicate Device:Quantitative Insights, Inc. QuantX(DEN170022)	Rationale for SubstantialEquivalence
	• Adjust window level,minimize/maximize
Image Review tools:	• 2D	• 2D	Similar to the predicate device.
	• 3D	• 3D
	• MPR	• MIPS
Image Manipulation andAnalysis	Interventional tool, trajectory, and damagevolume overlay (overlay profilescustomizable by the user)	Measure and document images	Different, but same intendeduse and the differences do notraise different questions ofsafety or effectiveness.
Image Segmentation:	Algorithm-driven segmentation of theprostate gland with the possibility ofmanual adjustment	Automated segmentation of the ROI	Similar to the predicate device.
Measurement Functionalities	Prostate gland:• Volume• ROIs within the prostateFor each Lesion:• Location• Volume	For each lesion:• Volume• Surface Area	Similar to the predicate device.
CADx Task	Assessment and characterization ofprostate lesions/abnormalities confirmed tocontain csPCA through biopsy and MRimage data.	Assessment and characterization of breastabnormalities using MR image data.	Similar to the predicate devicewith respect to analysis ofimage-based information forassessment of lesions.
Lesion Analysis Supported	Extent of Disease (boundary and totalburden)	Risk Stratification, Classification, Extentof Disease (boundary and total burden)	Subset of the functionalities ofthe predicate device.
	Avenda Health AI Prostate CancerPlanning Software(Proposed Device)	Predicate Device:Quantitative Insights, Inc. QuantX(DEN170022)	Rationale for SubstantialEquivalence
CADx Algorithm	Machine learning-based algorithm basedon patient information and imagemorphological, intensity, and geometriccharacteristics.	Machine learning-based algorithm basedon image morphological and enhancementcharacteristics.	Similar to the predicate device.
CADx Outputs	Cancer Estimation MapDefault Lesion ContourEncapsulation Confidence Score	QI ScoreSimilar Cases Database (via Image Atlasand Histogram Display)	The Proposed Device utilizesdifferent outputs from thepredicate device. As theseoutputs do not impact theintended use and are similarlysupplementary to informationreviewed by the physician as apart of standard of care, theydo not raise different questionsof safety or effectiveness.
User Must Approve/ RejectResults:	Yes	Yes	Same as the predicate device.
Export Formats:	DICOM Planning assets Intervention plan for supported systems	DICOM	Similar – both devices allowexport of findings for use infuture oncological steps.

Table 1: Substantial Equivalence Table

{9}------------------------------------------------

{10}------------------------------------------------

{11}------------------------------------------------

5.0 510(k) SUMMARY

{12}------------------------------------------------

Regulation Number and Section

§ 892.2060 Radiological computer-assisted diagnostic software for lesions suspicious of cancer.

(a)
Identification. A radiological computer-assisted diagnostic software for lesions suspicious of cancer is an image processing prescription device intended to aid in the characterization of lesions as suspicious for cancer identified on acquired medical images such as magnetic resonance, mammography, radiography, or computed tomography. The device characterizes lesions based on features or information extracted from the images and provides information about the lesion(s) to the user. Diagnostic and patient management decisions are made by the clinical user.(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 algorithms including, but not limited to, a detailed description of the algorithm inputs and outputs, each major component or block, and algorithm limitations.
(ii) A detailed description of pre-specified performance testing protocols and dataset(s) used to assess whether the device will improve reader performance as intended.
(iii) Results from performance testing protocols that demonstrate that the device improves reader performance in the intended use population when used in accordance with the instructions for use. The performance assessment must be based on appropriate diagnostic accuracy measures (
e.g., receiver operator characteristic plot, sensitivity, specificity, predictive value, and diagnostic likelihood ratio). The test dataset must contain sufficient numbers of cases from important cohorts (e.g., subsets defined by clinically relevant confounders, effect modifiers, concomitant diseases, 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) Standalone performance testing protocols and results of the device.
(v) Appropriate software documentation (
e.g., device hazard analysis; software requirements specification document; software design specification document; traceability analysis; and description of verification and validation activities including system level test protocol, pass/fail criteria, results, and cybersecurity).(2) Labeling must include:
(i) A detailed description of the patient population for which the device is indicated for use.
(ii) A detailed description of the intended reading protocol.
(iii) A detailed description of the intended user and recommended user training.
(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, including 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) Detailed instructions for use.
(viii) 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 (
e.g., lesion and organ characteristics, disease stages, and imaging equipment).