Predicate Devices

Reference Devices

AI/ML (Artificial Intelligence / Machine Learning)

Yes
The summary explicitly states that the contours are generated by "deep-learning algorithms" and that the device should be installed on a server supporting "deep learning processing." Deep learning is a subset of machine learning.

Therapeutic

No.
The device is a software tool used in radiation therapy treatment planning to assist professionals by providing initial contours of organs at risk; it is not directly involved in delivering therapy or treating conditions.

Diagnostic

No

The device description explicitly states, "EFAI HCAPSeg is not intended to be used for decision making or to detect lesions." It is presented as an "adjunct tool" to assist in radiation therapy treatment planning by providing initial contours, not for diagnostic purposes.

SaMD (Software as a Medical Device)

Yes

The device is explicitly described as "standalone software" and its function is to process existing CT images to generate contours. While it requires a server for processing and a treatment planning system for use, these are external components and the device itself is the software.

IVD (In Vitro Diagnostic)

Based on the provided information, this device is not an IVD (In Vitro Diagnostic).

Here's why:

IVD Definition: In Vitro Diagnostics are medical devices used to perform tests on samples taken from the human body (like blood, urine, tissue) to provide information about a person's health. This information is used for diagnosis, monitoring, or screening.
EFAI HCAPSeg's Function: EFAI HCAPSeg is a software device that processes medical images (CT scans) to automatically delineate anatomical structures (organs at risk) for use in radiation therapy planning. It does not analyze biological samples from the patient.
Intended Use: The intended use clearly states it's for assisting radiation oncology professionals during radiation therapy treatment planning by providing initial contours on non-contrast CT images. This is a workflow tool for image processing, not a diagnostic test performed on a biological sample.
Device Description: The device description reinforces that it takes DICOM CT images as input and outputs RTSTRUCT files (contour data). There is no mention of handling biological samples or performing laboratory-style tests.

In summary, EFAI HCAPSeg operates on medical images, not biological samples, and its purpose is to facilitate radiation therapy planning, not to diagnose or monitor a patient's health through analysis of bodily fluids or tissues. Therefore, it does not fit the definition of an In Vitro Diagnostic device.

PCCP (Predetermined Change Control Plan) Authorized

No
The letter does not explicitly state that the FDA has reviewed and approved or cleared a PCCP for this specific device.

Overview

Intended Use / Indications for Use

EFAI HCAPSeg is a software device intended to assist trained radiation oncology professionals, including, but not limited to, radiation oncologists, medical physicists, and dosimetrists, during their clinical workflows of radiation therapy treatment planning by providing initial contours of organs at risk on non-contrast CT images. EFAI HCAPSeg is intended to be used on adult patients only.

The contours are generated by deep-learning algorithms and then transferred to radiation therapy treatment planning systems. EFAI HCAPSeg must be used in conjunction with a DICOM-compliant treatment planning system to review and edit results generated. EFAI HCAPSeg is not intended to be used for decision making or to detect lesions.

EFAI HCAPSeg is an adjunct tool and is not intended to replace a clinician's judgment and manual contouring of the normal organs on CT. Clinicians must not use the software generated output alone without review as the primary interpretation.

Product codes

QKB

Device Description

EFAI RTSuite CT HCAP-Segmentation System, herein referred to as EFAI HCAPSeg, is a standalone software that is designed to be used by trained radiation oncology professionals to automatically delineate organs-at-risk (OARs) on CT images. This auto-contouring of OARs is intended to facilitate radiation therapy workflows.

The device receives CT images in DICOM format as input and automatically generates the contours of OARs, which are stored in DICOM format and in RTSTRUCT modality. The device does not offer a user interface and must be used in conjunction with a DICOM-compliant treatment planning system to review and edit results. Once data is routed to EFAI HCAPSeg, the data will be processed and no user interaction is required, nor provided.

The deployment environment is recommended to be in a local network with an existing hospital-grade IT system in place. EFAI HCAPSeg should be installed on a specialized server supporting deep learning processing. The configurations are only being operated by the manufacturer:

Local network setting of input and output destinations;
Presentation of labels and their color; ●
Processed image management and output (RTSTRUCT) file management. ●

Mentions image processing

Yes

Mentions AI, DNN, or ML

The contours are generated by deep-learning algorithms and then transferred to radiation therapy treatment planning systems.

Input Imaging Modality

Non-contrast CT images

Anatomical Site

Head & Neck, Chest, Abdomen & Pelvis

Indicated Patient Age Range

Adult patients only.

Intended User / Care Setting

Trained radiation oncology professionals, including, but not limited to, radiation oncologists, medical physicists, and dosimetrists. The deployment environment is recommended to be in a local network with an existing hospital-grade IT system in place.

Description of the training set, sample size, data source, and annotation protocol

During the process of model development, a total of 1,846 adult cases were collected between 2008 and 2018 from the radiation oncology department in Taiwan. These cases were subsequently divided into training and testing datasets, consisting of 1,410 and 436 cases, respectively. These cases covered a range of body parts, including the Head & Neck, Chest, and/or Abdomen & Pelvis.

The demographic information for both the training and test datasets. including age, gender, and CT manufacturer are presented in Table B. The data population included a balanced distribution between females and males. The acquired data encompasses CT manufacturers such as Siemens, GE Medical Systems, Philips, Toshiba.

Table C displays the number of images/cases per OAR for both the training and test datasets. (Table provided lists OAR, Number of Cases, and Number of Images for Training Dataset).

Description of the test set, sample size, data source, and annotation protocol

During the process of model development, a total of 1,846 adult cases were collected between 2008 and 2018 from the radiation oncology department in Taiwan. These cases were subsequently divided into training and testing datasets, consisting of 1,410 and 436 cases, respectively. These cases covered a range of body parts, including the Head & Neck, Chest, and/or Abdomen & Pelvis.

The company used the testing dataset to conduct an internal validation to assess the performance of the EFAI HCAPSeg. The process of ground-truthing, involving the manual contouring of each OAR, was undertaken by three board-certified radiation oncologists. The data collection and ground truth protocol was done following the identical procedures as those of the predicate device. Table C displays the number of images/cases per OAR for both the training and test datasets. (Table provided lists OAR, Number of Cases, and Number of Images for Testing Dataset).

A standalone performance test was also performed. The test was conducted to compare the OAR contouring capabilities of EFAI HCAPSeg against the comparison device. The dataset used in this study comprised 157 non-contrast CT cases consecutively collected from the United States (U.S.), all meeting the established inclusion criteria. All data used during the standalone performance evaluation was acquired independently from product development training and internal testing.

The study population contained 30.57% females, 57.96% males, and 11.46% gender not reported. The mean age was 61.69 years old with standard deviation (SD) of 11.90 years old. The acquired data encompasses CT manufacturers such as GE (43.31%), Philips (36.30%), Siemens (9.55%), Toshiba (2.55%), PNS (0.64%), and not reported (7.64%). Location, Race and Ethnic distribution within the study data patient population was unavailable. The cancer types included head-and-neck cancer, pancreas cancer, colorectal cancer, breast cancer, bladder cancer, prostate cancer, stomach cancer, gynecologic cancer, sarcoma, and metastatic tumors from multiple origins.

Each of the OAR contouring was generated by three board-certified radiation oncologists as the ground truth (GT).

Summary of Performance Studies

Nonclinical Tests:

Study Type: Internal validation during model development.
Sample Size: 436 cases (Testing Dataset).
Key Results: Overall, the mean Dice coefficient (DSC) was 0.85 for OAR contouring compared to the ground truth (GT). This result, surpassing the pre-specified performance objectives, confirms the validation of the EFAI HCAPSeg algorithm's performance.

Clinical Tests (Standalone Performance Test):

Study Type: Standalone performance test comparing EFAI HCAPSeg against a comparison device.
Sample Size: 157 non-contrast CT cases consecutively collected from the United States (U.S.).
Acceptance Criteria:
- For OARs present in both EFAI HCAPSeg and the comparison device, the mean Dice coefficient (DSC) of OARs for each body part (Head & Neck, Chest, and Abdomen & Pelvis) should be non-inferior to that of the comparison device, with a pre-specified margin.
- For OARs unique to the EFAI HCAPSeg, the mean DSC of unique OARs should be superior to a pre-specified value.
Overall Performance: Mean DSC of 0.83.
MRMC: Not applicable / Not Found.
Standalone Performance:
- Mean DSC for OARs present in both devices:
  - Head & Neck: EFAI HCAPSeg = 0.80, Comparison Device = 0.75
  - Chest: EFAI HCAPSeg = 0.90, Comparison Device = 0.84
  - Abdomen & Pelvis: EFAI HCAPSeg = 0.90, Comparison Device = 0.82
- Mean DSC for OARs unique to EFAI HCAPSeg: 0.82
- Median 95% Hausdorff Distance (HD) overall: 2.23 mm
- Median 95% HD for OARs present in both devices:
  - Head & Neck: EFAI HCAPSeg = 2.17 mm, Comparison Device = 3.09 mm
  - Chest: EFAI HCAPSeg = 2.23 mm, Comparison Device = 3.87 mm
  - Abdomen & Pelvis: EFAI HCAPSeg = 2.28 mm, Comparison Device = 3.90 mm
- Median 95% HD for OARs unique to EFAI HCAPSeg: 2.24 mm
Key Results: The non-inferiority tests indicated that EFAI HCAPSeg successfully met the primary endpoint across all body parts. The overall data showed a median 95% HD of 2.23 mm. Subgroup analyses by gender, age group, CT manufacturer, and CT slice thickness demonstrated consistent and reliable performance.

Key Metrics

Dice coefficient (DSC), 95% Hausdorff Distance (HD).

Predicate Device(s)

K220264

Reference Device(s)

K191928, K220598

Predetermined Change Control Plan (PCCP) - All Relevant Information

Not Found

Regulation Number and Section

§ 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).

Summary

0

September 25, 2023

Image /page/0/Picture/1 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, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.

Ever Fortune.AI Co., Ltd. % Ti-Hao Wang Chief Technology Officer 8 F., No. 573, Sec. 2, Taiwan Blvd., West Dist. Taichung City, 403020 TAIWAN

Re: K231928

Trade/Device Name: EFAI RTSUITE CT HCAP-Segmentation System Regulation Number: 21 CFR 892.2050 Regulation Name: Medical image management and processing system Regulatory Class: Class II Product Code: QKB Dated: August 31, 2023 Received: September 1, 2023

Dear Ti-Hao Wang:

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 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

1

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 (QS) 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 medical devices and radiation-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.

Locon Weidner

Lora D. Weidner, Ph.D. Assistant Director Radiation Therapy 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) K231928

Device Name EFAI RTSuite CT HCAP-Segmentation System

Indications for Use (Describe)

EFAI HCAPSeg is a software device intended to assist trained radiation oncology professionals, including, but not limited to, radiation oncologists, medical physicists, and dosimetrists, during their clinical workflows of radiation therapy treatment planning by providing initial contours of organs at risk on non-contrast CT images. EFAI HCAPSeg is intended to be used on adult patients only.

The contours are generated by deep-learning algorithms and then transferred to radiation therapy treatment planning systems. EFAI HCAPSeg must be used in conjunction with a DICOM-compliant treatment planning system to review and edit results generated. EFAI HCAPSeg is not intended to be used for decision making or to detect lesions.

EFAI HCAPSeg is an adjunct tool and is not intended to replace a clinician's judgment and manual contouring of the normal organs on CT. Clinicians must not use the software generated output alone without review as the primary interpretation.

Type of Use (Select one or both, as applicable)

Prescription Use (Part 21 CFR 801 Subpart D)	X
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

Image /page/3/Picture/0 description: The image shows the logo for Ever Fortune AI. The logo consists of a stylized human figure in teal with a green circle containing a network of lines and dots for the head. To the right of the figure is the text "EVER" stacked on top of "FORTUNE.AI" in teal. The "O" in fortune is replaced with a green circle containing a network of lines and dots.

510(k) Summary

K231928

1. General Information

510(k) Sponsor	Ever Fortune.AI Co., Ltd.
Address	Rm. D, 8F. No. 573, Sec. 2 Taiwan Blvd.
West Dist.
Taichung City 403020
TAIWAN
Applicant	Joseph Chang
Contact Information	886-04-23213838 #216
joseph.chang@everfortune.ai
Correspondence Person	Ti-Hao Wang, CTO
Contact Information	886-04-23213838 #168
tihao.wang@everfortune.ai
Date Prepared	June 28, 2023

2. Proposed Device

Proprietary Name	EFAI RTSuite CT HCAP-Segmentation System
Common Name	EFAI HCAPSeg
Classification Name	Radiological Image Processing Software For Radiation Therapy
Regulation Number	21 CFR 892.2050
Regulation Name	Medical Image Management and Processing System
Product Code	QKB
Regulatory Class	II

3. Predicate Device

Proprietary Name	EFAI RTSuite CT HN-Segmentation System
Premarket Notification	K220264
Classification Name	Radiological Image Processing Software For Radiation Therapy
Regulation Number	21 CFR 892.2050
Regulation Name	Medical Image Management and Processing System
Product Code	QKB
Regulatory Class	II

4

Image /page/4/Picture/0 description: The image shows the logo for EVER FORTUNE.AI. The logo features a stylized figure of a person in teal, with a green network-like design for the head. The text "EVER FORTUNE.AI" is displayed to the right of the figure, also in teal. The word "FORTUNE" has a similar network-like design in place of the letter "O".

4. Device Description

EFAI RTSuite CT HCAP-Segmentation System, herein referred to as EFAI HCAPSeg, is a standalone software that is designed to be used by trained radiation oncology professionals to automatically delineate organs-at-risk (OARs) on CT images. This auto-contouring of OARs is intended to facilitate radiation therapy workflows.

The device receives CT images in DICOM format as input and automatically generates the contours of OARs, which are stored in DICOM format and in RTSTRUCT modality. The device does not offer a user interface and must be used in conjunction with a DICOM-compliant treatment planning system to review and edit results. Once data is routed to EFAI HCAPSeg, the data will be processed and no user interaction is required, nor provided.

The deployment environment is recommended to be in a local network with an existing hospital-grade IT system in place. EFAI HCAPSeg should be installed on a specialized server supporting deep learning processing. The configurations are only being operated by the manufacturer:

Local network setting of input and output destinations;
Presentation of labels and their color; ●
Processed image management and output (RTSTRUCT) file management. ●

5. Intended Use

EFAI HCAPSeg is a software device intended to assist trained radiation oncology professionals, including, but not limited to, radiation oncologists, medical physicists, and dosimetrists, during their clinical workflows of radiation therapy treatment planning by providing initial contours of organs at risk on non-contrast CT images. EFAI HCAPSeg is intended to be used on adult patients only.

The contours are generated by deep-learning algorithms and then transferred to radiation therapy treatment planning systems. EFAI HCAPSeg must be used in conjunction with a DICOM-compliant treatment planning system to review and edit results generated. EFAI HCAPSeg is not intended to be used for decision making or to detect lesions.

EFAI HCAPSeg is an adjunct tool and is not intended to replace a clinician's judgment and manual contouring of the normal organs on CT. Clinicians must not use the software generated output alone without review as the primary interpretation.

5

Image /page/5/Picture/0 description: The image contains a logo for Ever Fortune AI. The logo consists of a teal icon on the left, resembling a person with a head made of interconnected dots. To the right of the icon, the words "EVER" and "FORTUNE.AI" are written in teal, with the "FORTUNE.AI" text positioned below "EVER" and featuring a similar interconnected dot design in place of the letter "O".

6. Comparison of Technological Characteristics with Predicate Device

Table A below provides a comparison of the intended use and key technological features of EFAI HCAPSeg with that of the Predicate, EFAI HNSeg (K220264), as well as the reference devices.

Characteristic	Proposed Device	Predicate Device	Reference Device- 1	Reference Device- 2
Company	Ever Fortune.AI Co., Ltd.
(EFAI)	Ever Fortune.AI Co., Ltd.
(EFAI)	Xiamen Manteia Technology
LTD.	Radformation, Inc.
Device Name	EFAI HCAPSeg	EFAI HNSeg	AccuContour™	AutoContour RADAC V2
510k Number	K231928	K220264	K191928	K220598
Regulation No.	21CFR 892.2050	21CFR 892.2050	21CFR 892.2050	21CFR 892.2050
Classification	II	II	II	II
Product Code	QKB	QKB	QKB	QKB
Intended
Use/Indication
for Use	EFAI HCAPSeg is a software
device intended to assist trained
radiation
oncology
professionals, including, but not
limited to, radiation oncologists,
physicists,
medical
and
dosimetrists,
their
during
clinical workflows of radiation
therapy treatment planning by
providing initial contours of
organs at risk on non-contrast
CT images. EFAI HCAPSeg is
intended to be used on adult
patients only.	EFAI HNSeg is a software
device intended to assist trained
radiation
oncology
professionals, including, but not
limited to, radiation oncologists,
medical
physicists,
and
dosimetrists,
during
their
clinical workflows of radiation
therapy treatment planning by
providing initial contours of
organs at risk in the head and
neck region on non-contrast CT
images.
EFAI
HNSeg
is
intended to be used on adult
patients only.	It is used by radiation oncology
department
register
to
multimodality
images
and
CT
segment
(non-contrast)
generate needed
to
images,
information
treatment
for
planning, treatment evaluation
and treatment adaptation.	is
AutoContour
intended
to
assist
radiation
treatment
in contouring and
planners
reviewing
structures within
medical images in preparation
for radiation therapy treatment
planning.

Table A. Comparison with the Predicate and Reference Devices
--------------------------------------------------------------	--

6

Image /page/6/Picture/0 description: The image contains a logo for a company called EVER FORTUNE.AI. The logo consists of a stylized human figure with a circular head made of interconnected nodes, suggesting a network or AI connection. The text "EVER FORTUNE.AI" is written in a sans-serif font, with the word "FORTUNE" having a similar node-based design element within it.

| | The contours are generated by
deep-learning algorithms and
then transferred to radiation
therapy treatment planning
systems. EFAI HCAPSeg must
be used in conjunction with a
DICOM-compliant treatment
planning system to review and
edit results generated. EFAI
HCAPSeg is not intended to be
used for decision making or to
detect lesions.

EFAI HCAPSeg is an adjunct
tool and is not intended to
replace a clinician's judgment
and manual contouring of the
normal organs on CT. Clinicians
must not use the software
generated output alone without
review as the primary
interpretation. | The contours are generated by
deep-learning algorithms and
then transferred to radiation
therapy treatment planning
systems. EFAI HNSeg must be
used in conjunction with a
DICOM-compliant treatment
planning system to review and
edit results generated. EFAI
HNSeg is not intended to be
used for decision making or to
detect lesions.

EFAI HNSeg is an adjunct tool
and is not intended to replace a
clinician's judgment and manual
contouring of the normal organs
on CT. Clinicians must not use
the software generated output
alone without review as the
primary interpretation. | | | | | | | application compatible with
Linux.

Windows python-based
automatic contouring
application supporting
Microsoft Windows 10 (64-bit)
and Microsoft Windows Server
2016. |
|-------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------|------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Segmentation
(Contouring)
Technology | Deep learning | Deep learning | Deep learning | Deep learning | User Population | Trained medical professionals
including, but not limited to,
radiation oncologists, medical
physicists, and dosimetrists. | Trained medical professionals
including, but not limited to,
radiation oncologists, medical
physicists, and dosimetrists. | It is used by radiation oncology
department. | Radiation treatment planners |
| Operating
System | Linux Ubuntu 20.04 | Linux Ubuntu 20.04 | Microsoft Windows | Windows based .NET front-end
application that also serves as
agent Uploader supporting
Microsoft Windows 10 (64-bit)
and Microsoft Windows Server
2016.

Cloud-based Server based
automatic contouring | Supported
Modalities | Non-contrast CT | Non-contrast CT | Segmentation Features:
Non-Contrast CT
Registration Features: CT, MRI,
PET | CT or MR input for contouring
or registration/fusion.
PET/CT input for
registration/fusion only.
DICOM RTSTRUCT for output |
| Localization
and Definition
of Objects
(ROI) | Organ-at risk of head and neck,
chest, abdomen, and pelvis | Organ-at risk of head and neck
region | Organ-at-risk, including head
and neck, thorax, abdomen and
pelvis (for both male and
female) | AutoContour is intended to
assist radiation treatment
planners in contouring and
reviewing structures within
medical images in preparation
for radiation therapy treatment
planning.
CT or MR input for contouring
of anatomical regions: Head and
Neck, Thorax, Abdomen and
Pelvis | | | | | |
| Organ-at risk
(OAR) | A_Aorta,
A_Carotid_L,
A_Carotid_R,
Bladder,
Bone_Mandible,
BrachialPlex_L,
BrachialPlex_R,
Brain, | Brain, BrainStem, Esophagus,
Eye_L, Eye_R, Lens_L,
Lens_R, Mandible,
OpticChiasm, OpticNerve_L,
OpticNerve_R, OralCavity, | A_Aorta,
Bladder,
Bone_Mandible,
BrachialPlex_L,
BrachialPlex_R,
Brain,
Brainstem, Breast_L, Breast_R, | CT Models:
A_Aorta, A_Aorta_Asc,
A_Aorta_Dsc, A_LAD,
Bladder, Bone_Ilium_L,
Bone_Ilium_R, | | | | | |

7

Image /page/7/Picture/0 description: The image contains a logo for a company called EVER FORTUNE.AI. The logo consists of a stylized human figure in teal, with a green globe-like shape with interconnected nodes as its head. To the right of the figure, the company name "EVER" is written in teal, with "FORTUNE.AI" below it, also in teal. The dot in "FORTUNE.AI" is replaced with a smaller version of the globe-like shape.

8

Image /page/8/Picture/0 description: The image shows the logo for Ever Fortune AI. The logo consists of a stylized figure with a green circle containing a network of white dots as its head. To the right of the figure, the text "EVER" is displayed in a larger font, with "FORTUNE.AI" below it in a smaller font. The colors used in the logo are shades of teal and green.

| Brainstem, Breast L, Breast R,
Bronchus_Prox, Cavity_Oral,
Cochlea_L,
Cochlea_R,
Duodenum,
Ear Internal L,
Ear_Internal_R, Ear Middle L,
Ear_Middle_R, Esophagus,
Eye_L,
Eye_R,
FemurHeadNeck L,
FemurHeadNeck R,
Gallbladder, Glnd Submand L,
Glnd Submand R,
Glnd_Thyroid,
Heart,
Hippocampus_L,
Hippocampus_R,
IAC_L,
IAC_R,
Joint TM_L,
Joint TM_R,
Kidney_L,
Kidney_R, Larynx, Lens_L,
Lens_R, Liver, LN_Neck_IA,
LN_Neck_IB_L,
LN_Neck_IB_R,
LN_Neck_II_L,
LN_Neck_II_R,
LN_Neck_III_L,
LN_Neck_III_R,
LN_Neck_IV_L,
LN_Neck_IV_R,
LN_Neck_V_L,
LN_Neck_V_R, LN Pelvics,
Lobe_Temporal_L,
Lobe_Temporal_R, Lung_L,
Lung_R, OpticChiasm,
OpticNrv_L, OpticNrv_R,
Pancreas, Parotid L, Parotid R,
PenileBulb, Pituitary, Prostate,
Rectum, Seminal Ves,
Spc_Bowel, SpinalCanal,
SpinalCord, Spleen, Stomach,
Testis, Trachea, Uterus, | arotid L,
SpinalCord, Thyroid, Trachea | Parotid_R,
Cavity_Oral,
Cochlea_L,
Cochlea_R,
Duodenum,
Ear Internal L, Ear Internal R,
Ear Middle L, Ear Middle R,
Esophagus, Eye_L,
Eye_R,
FemurHeadNeck_L,
FemurHeadNeck R,
Glnd_Submand_L,
Glnd_Submand_R,
Glnd_Thyroid,
Heart,
Hippocampus_L,
Hippocampus_R,
IAC_L,
IAC_R,
Joint TM_L,
Joint TM_R,
Kidney_L,
Kidney_R, Larynx, Lens_L,
Lens_R, Liver,
Lobe_Temporal_L,
Lobe_Temporal_R, Lung_L,
Lung_R, OpticChiasm,
OpticNrv_L, OpticNrv_R,
Pancreas, Parotid_L, Parotid_R,
Pituitary, Prostate, Rectum,
SeminalVes, Spc_Bowel,
SpinalCanal, SpinalCord,
Spleen, Stomach, Testis,
Trachea, Vestibule_R | Bone_Mandible, Bowel_Bag,
BrachialPlex_L,
BrachialPlex_R, Brain,
Brainstem, Breast L, Breast R,
Bronchus, Carina,
CaudaEquina, Cavity_Oral,
Cochlea_L, Cochlea_R,
Ear Internal L, Ear Internal R,
Esophagus, External, Eye_L,
Eye_R, Femur_L, Femur_R,
Femur_RTOG_L,
Femur_RTOG_R,
Glnd_Lacrimal_L,
Glnd_Lacrimal_R,
Glnd_Submand_L,
Glnd_Submand_R,
Glnd_Thyroid, HDR_Cylinder,
Heart, Humerus_L, Humerus_R,
Kidney_L, Kidney_R,
Kidney_Outer_L,
Kidney_Outer_R, Larynx,
Lens_L, Lens_R, Lips,
LN_Ax_L, LN_Ax_R,
LN_IMN_L, LN_IMN_R,
LN_Neck_IA,
LN_Neck_IB-V_L,
LN_Neck_IB-V_R,
LN_Neck_II_L,
LN_Neck_II_R,
LN_Neck_II-IV_L,
LN_Neck_II-IV_R,
LN_Neck_III_L,
LN_Neck_III_R,
LN_Neck_IV_L,
LN_Neck_IV_R,
LN_Neck_VIA,
LN_Neck_VIIA_L,
LN_Neck_VIIA_R, | | V_Venacava_I,
Vestibule_L,
Vestibule_R | | | LN_Neck_VIIB_L,
LN_Neck_VIIB_R,
LN_Pelvics, LN_Sclav_L,
LN_Sclav_R, Liver, Lung_L,
Lung_R, Marrow_Ilium_L,
Marrow_Ilium_R,
Musc_Constrict, OpticChiasm,
OpticNrv_L, OpticNrv_R,
Parotid_L, Parotid_R,
PenileBulb, Pituitary, Prostate,
Rectum, Rib, SeminalVes,
SpinalCanal, SpinalCord,
Stomach, Trachea,
V_Venacava_S
MR Models:
OpticChiasm, OpticNrv_L,
OpticNrv_R, Brainstem,
Hippocampus_L,
Hippocampus_R |
|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------|----------------------------------------------|--|--|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Compatible
Treatment
Planning
System | No Limitation on TPS model,
DICOM 3.0 compliance
required. | No Limitation on TPS model,
DICOM 3.0 compliance
required. | No Limitation on TPS model,
DICOM 3.0 compliance
required | No Limitation | | | | |
| Automated
Workflow | EFAI HCAPSeg automatically
processes input image data and
sends the results as DICOM-RT
Structure Sets to a
user-configurable target node. | EFAI HNSeg automatically
processes input image data and
sends the results as DICOM-RT
Structure Sets to a
user-configurable target node. | AccuContour automatically
processes input image data | Automatically contour, allow
the user to review and modify,
generate DICOM-compliant
structure set data. | | | | |
| User Interface | No | No | Yes | Yes | | | | |

9

Image /page/9/Picture/0 description: The image contains a logo for a company called "EVER FORTUNE.AI". The logo consists of two parts: a stylized human figure with a network-like head and the company name. The human figure is teal and has a rounded shape. The company name is written in a sans-serif font, with "EVER" in a larger size and "FORTUNE.AI" in a smaller size below it. The color of the text matches the color of the human figure.

10

Image /page/10/Picture/0 description: The image contains a logo for a company called "EVER FORTUNE.AI". The logo consists of a stylized figure with a circular head and a plus-shaped body, colored in a gradient of teal. The head of the figure is a green sphere with white dots and lines, resembling a network or a globe. To the right of the figure, the company name "EVER" is written in large, teal letters, and below it, "FORTUNE.AI" is written in smaller letters, also in teal.

7. Performance Data

Performance of the EFAI HCAPSeg has been evaluated and verified in accordance with software specifications and applicable performance standards through software verification and validation testing. Additionally, the software validation activities were performed in accordance with IEC 62304:2006/A1:2016 - Medical device software - Software life cvcle processes, in addition to the FDA Guidance documents, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices"(2005) and the recently published "Content of Premarket submissions for Devices Software Functions (11-04-2021), and "Content of Premarket Submission for Management of Cybersecurity in Medical Devices."

To establish the performance of the EFAI HCAPSeg, the performance was validated by clinical and nonclinical tests.

Nonclinical Tests

During the process of model development, a total of 1,846 adult cases were collected between 2008 and 2018 from the radiation oncology department in Taiwan. These cases were subsequently divided into training and testing datasets, consisting of 1,410 and 436 cases, respectively. These cases covered a range of body parts, including the Head & Neck, Chest, and/or Abdomen & Pelvis.

The demographic information for both the training and test datasets. including age, gender, and CT manufacturer are presented in Table B. The data population included a balanced distribution between females and males. The acquired data encompasses CT manufacturers such as Siemens, GE Medical Systems, Philips, Toshiba.

| | Training Dataset
(n=1,410) | Testing Dataset
(n=436) |
|--------------------|-------------------------------|----------------------------|
| Age | | |
| 18 - 49 years old | 95 | 16 |
| 50 - 69 years old | 772 | 219 |
| Above 70 years old | 235 | 64 |
| N/A | 308 | 137 |
| Gender | | |
| Female | 563 | 110 |
| Male | 581 | 154 |
| N/A | 266 | 172 |
| CT Manufacturer | | |
| Siemens | 914 | 289 |

Table B. Demographic Information for Training and Test Data Sets

11

Image /page/11/Picture/0 description: The image shows the logo for EVER FORTUNE.AI. The logo features a stylized human figure in teal, with a green globe-like head made of interconnected dots. To the right of the figure, the word "EVER" is written in a teal sans-serif font, with "FORTUNE.AI" below it in a smaller font, also in teal. The logo has a clean and modern design.

GE Medical Systems	436	109
Philips	56	35
Toshiba	1	2
N/A	3	1

The company used the testing dataset to conduct an internal validation to assess the performance of the EFAI HCAPSeg. The process of ground-truthing, involving the manual contouring of each OAR, was undertaken by three board-certified radiation oncologists. The data collection and ground truth protocol was done following the identical procedures as those of the predicate device. Table C displays the number of images/cases per OAR for both the training and test datasets.

Table C. Number of Images/Cases per OAR for Training and Testing Datasets

	Training Dataset		Testing Dataset
OAR	Number of Cases	Number of Images	Number of Cases	Number of Images
A_Aorta	1,091	77,731	119	7,030
A_Carotid_L	350	15,124	114	4,883
A_Carotid_R	347	11,883	114	4,118
Bladder	458	7,366	61	988
Bone_Mandible	667	17,013	66	1,457
BrachialPlex_L	474	17,909	113	3,903
BrachialPlex_R	473	16,978	113	3,643
Brain	484	22,154	66	2,894
Brainstem	484	11,126	66	1,403
Breast_L	350	14,049	76	2,832
Breast_R	347	14,495	75	2,727
Bronchus_Prox	353	7,523	113	2,315
Cavity_Oral	613	12,899	66	1,320
Cochlea_L	471	926	66	126
Cochlea_R	475	1,077	66	125
Duodenum	686	19,167	77	2,063
Ear_Internal_L	484	2,945	66	375
Ear_Internal_R	484	2,428	66	308
Ear_Middle_L	484	2,162	66	277
Ear_Middle_R	484	2,128	66	258
Esophagus	1,126	61,405	114	4,844
Eye_L	482	6,150	66	721
Eye_R	484	6,182	66	727
FemurHeadNeck_L	462	13,358	61	1,819
FemurHeadNeck_R	457	13,136	61	1,802
Gallbladder	309	3,095	168	1,609
Glnd_Submand_L	604	7,233	66	808
Glnd_Submand_R	592	7,343	66	788
Glnd_Thyroid	838	14,605	114	1,956
Heart	716	22,271	119	3,012
Hippocampus_L	478	4,653	66	534
Hippocampus_R	475	4,432	66	463
IAC_L	117	326	105	176
IAC_R	121	333	100	148
Joint_TM_L	481	2,339		229
Joint_TM_R	484	2,231		233
Kidney_L	762	22,347	119	3,310
Kidney_R	720	20,989	119	3,407
Larynx	723	13,548	114	2,134
Lens_L	475	1,716		214
Lens_R	476	1,628	66	203
Liver	853	37,523	119	5,061
LN_Neck_IA	98	484	73	297
LN_Neck_IB_L	98	1,385	73	905
LN_Neck_IB_R	98	1,376	73	960
LN_Neck_II_L	98	1,936	73	1,201
LN_Neck_II_R	98	1,937	73	1,201
LN_Neck_III_L	98	1,083	73	817
LN_Neck_III_R	98	1,082	73	817
LN_Neck_IV_L	98	1,220	73	1,003
LN_Neck_IV_R	98	1,219	73	1,003
LN_Neck_V_L	98	2,773	73	2,227
LN_Neck_V_R	98	2,768	73	2,227
LN_Pelvics	220	9,486	177	7,872
Lobe_Temporal_L	481	10,045	66	1,175
Lobe_Temporal_R	483	10,141	66	1,185
Lung_L	896	50,332	119	4,261
Lung_R	878	49,483	119	4,263
OpticChiasm	479	1,793	66	279
OpticNrv_L	479	1,832	66	255
OpticNrv_R	479	2,089	66	276
Pancreas	757	16,684	77	1,707
Parotid_L	515	12,722	66	1,513
Parotid_R	514	12,408	66	1,501
PenileBulb	91	430	73	333
Pituitary	475	1,419	66	197
Prostate	205	2,887	75	1,091
Rectum	456	12,836	61	1,779
SeminalVes	206	1,534	75	613
Spc_Bowel	737	51,228	77	6,304
SpinalCanal	1,269	119,225	157	12,760
SpinalCord	1,407	139,337	157	13,881
Spleen	793	21,027	119	3,051
Stomach	808	25,949	119	3,758
Testis	128	1,301	67	801
Trachea	876	31,998	76	2,543
Uterus	163	4,087	78	1,522
V_Venacava_I	510	24,117	119	3,201
Vestibule_L	470	1,035	66	133
Vestibule_R	480	1,002	66	113

12

Image /page/12/Picture/0 description: The image shows the logo for Ever Fortune AI. The logo consists of a stylized human figure in teal with a green globe above its head. To the right of the figure, the word "EVER" is written in teal, with "FORTUNE.AI" written below it in a smaller font, also in teal. The logo appears to be for a company that specializes in artificial intelligence.

13

Image /page/13/Picture/0 description: The image shows the logo for Ever Fortune AI. The logo consists of a stylized figure of a person with a green globe on top of their head. The text "EVER" is to the right of the figure, and below that is "FORTUNE.AI". The text and figure are all in a light blue color.

14

Image /page/14/Picture/0 description: The image contains a logo for a company called "EVER FORTUNE.AI". The logo consists of a stylized human figure with a circular head made of interconnected dots, suggesting a network or AI connection. The text "EVER" is placed above "FORTUNE.AI" in a sans-serif font, with the "O" in "FORTUNE" replaced by a similar circular network design.

Overall, the mean Dice coefficient (DSC) was 0.85 for OAR contouring compared to the ground truth (GT). This result, surpassing the pre-specified performance objectives, confirms the validation of the EFAI HCAPSeg algorithm's performance.

Clinical Tests

A standalone performance test was also performed. The test was conducted to compare the OAR contouring capabilities of EFAI HCAPSeg against the comparison device. The dataset used in this study comprised 157 non-contrast CT cases consecutively collected from the United States (U.S.), all meeting the established inclusion criteria. All data used during the standalone performance evaluation was acquired independently from product development training and internal testing.

The study population contained 30.57% females, 57.96% males, and 11.46% gender not reported. The mean age was 61.69 years old with standard deviation (SD) of 11.90 years old. The acquired data encompasses CT manufacturers such as GE (43.31%), Philips (36.30%), Siemens (9.55%), Toshiba (2.55%), PNS (0.64%), and not reported (7.64%). Location, Race and Ethnic distribution within the study data patient population was unavailable. The cancer types included head-and-neck cancer, pancreas cancer, colorectal cancer, breast cancer, bladder cancer, prostate cancer, stomach cancer, gynecologic cancer, sarcoma, and metastatic tumors from multiple origins.

Each of the OAR contouring was generated by three board-certified radiation oncologists as the ground truth (GT). The acceptance criteria were defined as the following:

· For OARs present in both EFAI HCAPSeg and the comparison device, the mean Dice coefficient (DSC) of OARs for each body part (Head & Neck, Chest, and Abdomen & Pelvis) should be non-inferior to that of the comparison device, with a pre-specified margin.
For OARs unique to the EFAI HCAPSeg, the mean DSC of unique OARs should be ● superior to a pre-specified value.

The overall performance showed a mean DSC of 0.83 and the non-inferiority tests indicated that EFAI HCAPSeg successfully met the primary endpoint across all body parts. Specifically, EFAI HCAPSeg achieved mean DSC values of 0.80, 0.90, and 0.90 in Head & Neck, Chest, and Abdomen & Pelvis, respectively, while the comparison device vielded slightly lower values of 0.75, 0.84, and 0.82 for the same body parts. Furthermore, when considering OARs unique to EFAI HCAPSeg. the mean DSC value reached 0.82. As shown in Table D, these results strongly indicate the successful attainment of the acceptance criteria for the primary endpoint was met.

15

Image /page/15/Picture/0 description: The image shows the logo for Ever Fortune AI. The logo consists of a teal-colored figure with a green circle on top, representing a person with a connected network on their head. To the right of the figure, the words "EVER FORTUNE.AI" are written in teal, with the "O" in "FORTUNE" replaced by a similar connected network symbol. The logo appears to be for a company specializing in artificial intelligence.

		EFAI HCAPSeg		Comparison Device		Statistical Result +
		Mean DSC	SD	Mean DSC	SD	p-value
OARs Present in Both
EFAI HCAPSeg and the
Comparison Device	Head & Neck	0.80	0.21	0.75	0.25