← Product Code [QIH](/productcode/QIH) · K252332

# Folliscan (K252332)

_Mim Fertility · QIH · Apr 20, 2026 · Radiology · SESE_

**Canonical URL:** https://fda.innolitics.com/device/K252332

## Device Facts

- **Applicant:** Mim Fertility
- **Product Code:** [QIH](/productcode/QIH.md)
- **Decision Date:** Apr 20, 2026
- **Decision:** SESE
- **Submission Type:** Traditional
- **Regulation:** 21 CFR 892.2050
- **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 |
| --- | --- | --- | --- | --- | --- |
| K252332 · Apr 20, 2026 | Folliscan | Mim Fertility | Retrospective clinical transvaginal ultrasound cine-loop and 3D scan datasets; Multi-center clinical registry/database (2,132 patients) | The device performance was evaluated using a large, multi-site, multi-scanner retrospective dataset of clinical ultrasound images to demonstrate substantial equivalence in follicle detection and measurement accuracy. | Retrospective clinical data; Multi-center study; Ultrasound imaging; AI/ML performance validation |

### Clinical Evidence

| Study Design | Population | Comparator | Key Endpoints |
| --- | --- | --- | --- |
| Folliscan Multi-Center Performance Evaluation; Retrospective multi-center cohort study; Follow-up/Duration: Data collected between June 2019 and September 2025; Study Period: 2019-2025 | Patients undergoing transvaginal ultrasound examinations for fertility monitoring; Sample Size: 2,132 patients (6,404 DICOM files); Number of Sites: 7 fertility centers (Poland, Australia, Argentina, Chile, Turkey, and the United States) | Not applicable for this study | Ovary count agreement, measurement accuracy (RMSE and bias for d1, d2, and volume), precision, recall, and F1 score |

## Indications for Use

FOLLISCAN is a software application package. It is designed to quantify image data acquired on compatible ultrasound systems. FOLLISCAN is used as an aid to clinicians to interpret images by calculating the number and size of ovarian follicles in a transvaginal ultrasound volume sweep of the ovaries.

## Device Story

Folliscan is an AI-based software application for automated follicle monitoring; inputs are DICOM-formatted transvaginal ultrasound cine-loop videos (2D and 3D); software performs semi-automatic measurement and tracking of follicle size and count; accessed via web browser or API; results require manual verification by clinician using DICOM viewer; aids clinical decision-making during ovulation monitoring; benefits include standardized, efficient follicle quantification; operates as a retrospective analysis tool without patient contact or energy application.

## Clinical Evidence

Performance evaluated on a multi-site, multi-scanner dataset (6,404 DICOM files from 2,132 patients). Held-out test set included 138 scans from 64 patients. Primary endpoints (ovary count agreement and measurement accuracy) met acceptance criteria; global count agreement Wilson test lower bounds ≥0.70; RMSE for diameter d1 ≤ 1.2 mm (95% CI). Secondary metrics included precision (90.2% global), recall (77.6% global), and F1 score (83.4% global). Ground truth established via multi-stage manual annotation and expert validation.

## Technological Characteristics

Software-based medical device; utilizes AI/ML-based automatic segmentation algorithms; processes DICOM-formatted transvaginal ultrasound cine-loop (2D+t) and 3D datasets; non-adaptive (locked) algorithm; web-based or API deployment; compatible with various ultrasound systems (e.g., Siemens, Samsung, GE, BK Medical) via DICOM standard connectivity.

## Regulatory 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.

## Special Controls

*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).

## Predicate Devices

- Follicle Clarity ([K212012](/device/K212012.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 & DRUG ADMINISTRATION

MIM Fertility
% Mariel Chavez
Regulatory Specialist
Prime Path Medtech
1321 Upland Dr.
Suite 6792
Houston, Texas 77043

April 20, 2026

Re: K252332
Trade/Device Name: Folliscan
Regulation Number: 21 CFR 892.2050
Regulation Name: Medical Image Management And Processing System
Regulatory Class: Class II
Product Code: QIH
Dated: March 6, 2026
Received: March 6, 2026

Dear Mariel Chavez:

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 & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov

{1}

K252332 - Mariel Chavez
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 13485 clause 8.3 (Nonconforming product), ISO 13485 clause 8.5.2 (Corrective action), and ISO 13485 clause 8.5.3 (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 ISO 13485 clause 7.5) and document changes and approvals in the Medical Device File (ISO 13485 clause 4.2.3).

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

{2}

K252332 - Mariel Chavez
Page 3

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-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)

Jessica Lamb, Ph.D
Assistant Director
DHT8B: Division of Radiological Imaging
Devices and Electronic Products
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.

Submission Number (if known)

K252332

Device Name

Folliscan

Indications for Use (Describe)

FOLLISCAN is a software application package. It is designed to quantify image data acquired on compatible ultrasound systems. FOLLISCAN is used as an aid to clinicians to interpret images by calculating the number and size of ovarian follicles in a transvaginal ultrasound volume sweep of the ovaries.

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."

{4}

K252332

# 510(k) Summary

# 510(k) SUMMARY

A 510(k) summary for this traditional 510(k) in accordance with the requirements of 21 CFR 807.92.

Submitter: MIM Fertility
Swieradowska 47, 02-662,
Warszawa Poland

Company Contact Person: Urszula Sankowska
Phone: +48 606 366 958
Email: Ula@mimfertility.ai

Submission Correspondent: Mariel Chavez, Regulatory Affairs Consultant
Address: 1321 Upland Dr. Suite 6792 Houston, TX 77043
Phone: +1 954-260-0026
Email: mchavez@primepathmedtech.com

Date Prepared: 10 April 2026

Proprietary Name: Folliscan

Common Name: Automated Radiological Image Processing Software

Product Code: QIH

Device Classification: Class II, 21 CFR 892.2050

Primary Predicate Device: Follicle Clarity (K212012)

# Device Description:

The FOLLISCAN application is a medical software product based on artificial intelligence algorithms that provides information on the number and size of ovarian follicles based on cine loop videos (both 2D and 3D) from transvaginal ultrasound examinations used in the process of monitoring ovulation during ovarian ultrasound examination.

The primary functions of FOLLISCAN is the semi-automatic measurement and tracking of follicle size and count.

FOLLISCAN medical device can be used through a web browser or through a programmatic API using a validated connector.

The obtained results should be verified manually using DICOM viewer before clinical usage

{5}

# Indications for Use:

FOLLISCAN is a software application package. It is designed to quantify image data acquired on compatible ultrasound systems. FOLLISCAN is used as an aid to clinicians to interpret images by calculating the number and size of ovarian follicles in a transvaginal ultrasound volume sweep of the ovaries.

# Comparison to Predicate Devices:

The Subject Device is functionally equivalent to the predicate device. The following table demonstrates the functional specifications of the Subject Device are substantially equivalent to the Predicate Device and raise no new questions regarding safety and effectiveness of the device.

Device Comparison Table

|  Specification | Subject Device: FOLLISCAN | Predicate Device: Follicle Clarity | Comparison Result  |
| --- | --- | --- | --- |
|  Administrative Information  |   |   |   |
|  Product Name | FOLLISCAN Software | Follicle Clarity Software | N/A  |
|  510(k) Holder | MIM Fertility | Cycle Clarity LLC | N/A  |
|  510(k) Number | K252332 | K212012 | N/A  |
|  Common Name | Picture Archiving and Communication System | Picture Archiving and Communication System | Identical to predicate  |
|  Regulation Number | 21 CFR 892.2050 | 21 CFR 892.2050 | Identical to predicate  |
|  Classification Name | System, Image Processing, Radiological | System, Image Processing, Radiological | Identical to predicate  |
|  Product Code | QIH | QIH | Identical to predicate  |
|  Regulatory Classification | Class II | Class II | Identical to predicate  |
|  Intended Use  |   |   |   |
|  Intended Use | FOLLISCAN is a software application package designed to view and quantify image data acquired on compatible ultrasound systems. | Follicle Clarity Software is a software application package. It is designed to view and quantify image data acquired on compatible ultrasound systems. | Identical to predicate. Predicate and subject devices are both software medical devices intended to quantify image data on compatible ultrasound systems.  |
|  Prescription Only? | Yes | Yes | Identical to predicate  |
|  Technological Characteristics  |   |   |   |

{6}

|  Application Description | The FOLLISCAN application is a medical software product based on artificial intelligence | Follicle Clarity software detects hypoechoic structures (i.e., follicles) in transvaginal | Equivalent. Both software systems utilize  |
| --- | --- | --- | --- |
|  Specification | Subject Device: FOLLISCAN | Predicate Device: Follicle Clarity | Comparison Result  |
| --- | --- | --- | --- |
|   | algorithms that provide information on the number and size of ovarian follicles based on cine loop videos (both 2D and 3D) from transvaginal ultrasound examinations used in the process of monitoring ovulation during ovarian ultrasound examinations. | ultrasound images and measures their size. The application measures structures within the ultrasound images using automatic segmentation technology. The software utilizes “locked” (non-adaptive) machine learning algorithms to identify the contours of the targeted structure within the ultrasound image. A report of measurement data is displayed. | proprietary algorithms to detect and quantify structures within ultrasound images. Subject and predicate devices utilize machine learning/AI algorithms to identify specific contours of the anatomy using automatic segmentation technology and quantify structures based on this analysis. Both devices specifically detect and analyze follicle number and size.  |
|  Target User Population | Interpreting clinicians | Interpreting clinicians | Identical to predicate  |
|  How Supplied? | Software application | Software application | Identical to predicate  |
|  Use of machine learning algorithm? | Yes | Yes | Identical to predicate  |
|  Required Patient Clinical Data (Imaging) Format | DICOM | DICOM | Identical to predicate  |

{7}

|  Ultrasound Compatibility | - Siemens ACUSON NX3 | - Voluson, E6, E8, E10 | Equivalent.  |
| --- | --- | --- | --- |
|   |  - Samsung HERA W9 | - Philips  |   |
|   |  - GE Voluson GE Voluson P8 | - Siemens Acuson Version | The subject device has been proven to be compatible and able to process any ultrasound that has a DICOM standard connectivity enabled.  |
|   |  - GE Voluson E8  |   |   |
|   |  - BK Medical Sonix  |   |   |
|   |  - S10  |   |   |
|   |  |   |   |
|   |  |   |   |
|   |  |   |   |

# Comparison of Indications for Use to the Predicate Device:

FOLLISCAN is a software application package designed to view and quantify image data acquired on compatible ultrasound systems.

The predicate device, Follicle Clarity Software, is a software application package designed to view and quantify image data acquired on compatible ultrasound systems.

The indications for use of FOLLISCAN are identical to those of the predicate device. Both devices are intended to view and quantify image data obtained from compatible ultrasound systems for clinical use.

# Comparison of Technological Characteristics to Predicate Device:

FOLLISCAN is a software-based medical device that utilizes artificial intelligence (AI)-based algorithms to analyze transvaginal ultrasound cine-loop data (2D and 3D). The software identifies and quantifies ovarian follicles by providing measurements of follicle number and size.

The predicate device, Follicle Clarity Software, is a software application that detects hypoechoic structures (i.e., ovarian follicles) in transvaginal ultrasound images and measures their size using automatic segmentation technology. The software employs "locked" (non-adaptive) machine learning algorithms to identify the contours of the targeted structures and generates a report of measurement data.

Both FOLLISCAN and Follicle Clarity are software-based devices that analyze transvaginal ultrasound data to detect and measure ovarian follicles. Both devices utilize algorithm-based image processing techniques, including machine learning-based segmentation, to identify follicular structures and provide quantitative measurement outputs for clinical use.

Differences between the devices include the type of input data and implementation of algorithms. FOLLISCAN is designed to process cine-loop ultrasound data (2D+t) and 3D datasets, whereas Follicle Clarity is designed to analyze ultrasound images. Additionally, while both devices utilize machine learning-based approaches for structure identification, Follicle Clarity explicitly employs "locked" (non-adaptive) algorithms, and FOLLISCAN similarly utilizes fixed algorithms that do not adapt or change during clinical use.

These differences in technological characteristics do not alter the fundamental principles of operation, as both devices rely on established image analysis and segmentation techniques to identify and measure

{8}

ovarian follicles from ultrasound data. The similarities in intended functionality and underlying technology support that these differences do not raise new questions of safety and effectiveness.

## Summary of Performance Data

Nonclinical testing was conducted to include: software verification & validation, risk management assessments, requirements review and traceability, and design review. The nonclinical and clinical testing conducted on the Folliscan device demonstrates that it is as safe, as effective, and performs as well as or better than the legally marketed predicate device. Because the Folliscan is a software-only device that retrospectively analyzes existing transvaginal ultrasound cine-loops and 3D scans without patient contact, energy application, or alteration to clinical management, it presents no additional safety risks, and no device-related adverse events or complications were observed or expected during testing.

|  Primary Endpoint | Acceptance Criteria | Values (95% CI)  |
| --- | --- | --- |
|  Ovary Count Agreement (global) | <10 mm: |Δcount| ≤ ±5 follicles per ovary
- Wilson test 95% Lower bound≥0,70 | <10 mm: 0.920 (0.863, 0.955)  |
|   |  ≥10 and <17 mm: |Δcount| ≤ ±2 follicles per ovary
- Wilson test Lower bound≥0,70 | ≥10 and <17 mm: 0.957 (0.908,0.980)  |
|   |  ≥17 mm: |Δcount| ≤ ±1 follicle per ovary
- Wilson test Lower bound≥0,70 | ≥17 mm: 0.957 (0.908, 0.980)  |
|  Ovary Count Agreement (US) | <10 mm: |Δcount| ≤ ±5 follicles per ovary
- Wilson test 95% Lower bound≥0,70 | <10 mm: 0.978 (0.884, 0.996)  |
|   |  ≥10 and <17 mm: |Δcount| ≤ ±2 follicles per ovary
- Wilson test Lower bound≥0,70 | ≥10 and <17 mm: 0.911 (0.793,0.965)  |
|   |  ≥17 mm: |Δcount| ≤ ±1 follicle per ovary
- Wilson test Lower bound≥0,70 | ≥17 mm: 0.911 (0.793, 0.965)  |

{9}

|  Ovary Count Agreement (OUS) | <10 mm: |Δcount| ≤ ±5 follicles per ovary
- Wilson test 95% Lower bound≥0,70 | <10 mm: 0.892 (0.813, 0.941)  |
| --- | --- | --- | --- | --- |
|   |  ≥10 and <17 mm: |Δcount| ≤ ±2 follicles per ovary
- Wilson test Lower bound≥0,70 | ≥10 and <17 mm: 0.978 (0.925,0.994)  |
|   |  ≥17 mm: |Δcount| ≤ ±1 follicle per ovary
- Wilson test Lower bound≥0,70 | ≥17 mm: 0.978 (0.925, 0.994)  |
|  Measurement Accuracy RMSE d1 (global) | Upper 95% CI bound for RMSE d1 ≤ 2.0 mm | 1.021 (0.934, 1.109)  |
|  Measurement Accuracy RMSE d1 (US) | Upper 95% CI bound for RMSE d1 ≤ 2.0 mm | 1.195 (1.038, 1.365)  |
|  Measurement Accuracy RMSE d1 (OUS) | Upper 95% CI bound for RMSE d1 ≤ 2.0 mm | 0.940 (0.838, 1.047)  |
|  Measurement Accuracy Bias d1 (global) | Upper 95% CI bound for |bias d1| ≤ 1.0 mm | -0.532 (-0.581, -0.485)  |
|  Measurement Accuracy Bias d1 (US) | Upper 95% CI bound for |bias d1| ≤ 1.0 mm | -0.612 (-0.725, -0.509)  |
|  Measurement Accuracy Bias d1 (OUS) | Upper 95% CI bound for |bias d1| ≤ 1.0 mm | -0.499 (-0.553, -0.448)  |
|  Measurement Accuracy RMSE d2 (global) | Upper 95% CI bound for RMSE d2 ≤ 2.0 mm | 0.779 (0.715, 0.846)  |
|  Measurement Accuracy RMSE d2 (US) | Upper 95% CI bound for RMSE d2 ≤ 2.0 mm | 0.927 (0.806, 1.059)  |
|  Measurement Accuracy RMSE d2 (OUS) | Upper 95% CI bound for RMSE d2 ≤ 2.0 mm | 0.710 (0.634, 0.786)  |
|  Measurement Accuracy Bias d2 (global) | Upper 95% CI bound for |bias d2| ≤ 1.0 mm | -0.330 (-0.368, -0.290)  |
|  Measurement Accuracy Bias d2 (US) | Upper 95% CI bound for |bias d2| ≤ 1.0 mm | -0.419 (-0.507, -0.336)  |
|  Measurement Accuracy Bias d2 (OUS) | Upper 95% CI bound for |bias d2| ≤ 1.0 mm | -0.293 (-0.337, -0.250)  |
|  Measurement Accuracy RMSE volume (global) | Upper 95% CI bound for RMSE volume ≤ 1.0 mL (1000 mm³) | 13.923 (11.742, 16.094)  |

{10}

Table 1. Summarizing the performance data - primary endpoints

|  Secondary Endpoint | Value  |
| --- | --- |
|  MAE Δcount (global) | 2.101 (1.761-2.471)  |
|  MAE Δcount (US) | 1.400 (0.956-1.911)  |
|  MAE Δcount (OUS) | 2.441 (1.989-2.925)  |
|  Precision (global) | 90.2 (88.3-92.0)  |
|  Precision (US) | 89.2 (85.7-92.3)  |
|  Precision (OUS) | 90.6 (88.2-92.9)  |
|  Recall (global) | 77.6 (74.9-80.1)  |
|  Recall (US) | 80.0 (76.1-83.7)  |
|  Recall (OUS) | 76.7 (73.3-80.0)  |
|  F1 Score (global) | 83.4 (81.5-85.2)  |
|  F1 Score (US) | 84.4 (81.3-87.0)  |
|  F1 Score (OUS) | 83.1 (80.6-85.4)  |

Table 2. Summarizing the performance data - secondary endpoints

Taken together, these results demonstrate that the Follican device provides clinically accurate and reliable automated follicle detection, counting, and measurement across a diverse, multi-site, multi-scanner dataset, and that it is substantially equivalent to the identified predicate device.

# AI Ground Truth and Data Independence:

Ground truth for the held-out test set was established using a multi-stage, fully manual annotation and expert-validation workflow. All scans were first annotated with tracked follicle boxes, and pixel-level instance masks were then created and refined with access to the full temporal context of each recording. Gynecology experts, blinded to device outputs and clinical outcomes, reviewed the annotations, identified missing follicles, corrected inaccurate masks, removed non-follicular structures, and only expert-approved annotations were retained in the final reference dataset. The resulting reference standard comprised per-ovary follicle counts in clinical size bins and manual follicle measurements derived from the final contour annotations. No synthetic or automatically generated annotations were used in training, validation, or testing.

{11}

The development dataset was collected from 2,132 patients between June 2019 and September 2025 across seven fertility centers in Poland, Australia, Argentina, Chile, Turkey, and the United States, totaling 6,404 DICOM files. These data were split into 5,972 training scans and 294 validation scans, while the held-out test set comprised 138 scans from 64 patients obtained from five clinics, including 45 scans from Advanced Fertility Center of Texas (United States). Dataset independence was verified by maintaining distinct training, validation, and test cohorts for model fitting, hyperparameter selection, and final performance evaluation, respectively. In addition, AFC Texas was reserved entirely for the held-out test set and was not used during training or validation; scans acquired on BK Medical Sonix and GE Voluson P8 systems originated exclusively from this held-out U.S. site, providing an additional site-and scanner-level check of independence. Even where some clinics contributed data to both development and test splits, the recordings used for testing were different from those used for training or validation. Moreover, no images of the same patient are shared between training, validation and test datasets.

## Conclusion:

Based on the comparisons described above, the subject device, FOLLISCAN, has the same intended use as the predicate device, Follicle Clarity (K212012), and similar technological characteristics. Any differences in technological characteristics, including the type of input data and algorithm implementation, do not raise new questions of safety and effectiveness.

Therefore, FOLLISCAN is substantially equivalent to the legally marketed predicate device, Follicle Clarity (K212012).

---

**Source:** [https://fda.innolitics.com/device/K252332](https://fda.innolitics.com/device/K252332)

**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