Predicate Devices

Reference Devices

AI/ML (Artificial Intelligence / Machine Learning)

Yes
The device description explicitly states "deep-learning-based automatic contouring" and the "Mentions AI, DNN, or ML" field is marked as "Yes".

Therapeutic

No
The device aids in treatment planning by contouring organs but does not directly deliver therapy or treat a disease.

Diagnostic

No

Explanation: The device's intended use is for "initial contouring" to assist clinicians in "treatment planning or other professions where a segmented mask of organs is needed." It does not provide a diagnosis or aid in diagnosing a disease by detecting, monitoring, or predicting the existence of a condition. Its function is to process images for a specific medical procedure, not for diagnostic purposes.

SaMD (Software as a Medical Device)

Yes

The device is explicitly described as "standalone software" and its functions are entirely software-based (image processing, contouring, data management). There is no mention of accompanying hardware components required for its operation beyond a standard computing platform.

IVD (In Vitro Diagnostic)

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

Here's why:

IVDs analyze biological samples: In Vitro Diagnostics are devices used to examine specimens derived from the human body (like blood, urine, tissue) to provide information about a person's health.
This device analyzes medical images: OncoStudio processes CT images, which are medical images of the body, not biological samples.
The intended use is image processing for treatment planning: The primary function is to automatically contour organs on CT scans for use in radiation therapy treatment planning. This is an image analysis and processing task, not a diagnostic test performed on a biological sample.

The device falls under the category of medical image processing software, specifically for radiation oncology applications. The information provided clearly describes its function in analyzing and segmenting anatomical structures from medical images.

PCCP (Predetermined Change Control Plan) Authorized

No
The provided text does not contain any explicit statement that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device.

Overview

Intended Use / Indications for Use

OncoStudio provides deep-learning-based automatic contouring to organs at risk in DICOM-RT format from CT images. This software could be used as an initial contouring for the clinicians to be confirmed by the radiation oncology department for treatment planning or other professions where a segmented mask of organs is needed.

Deep learning contouring from Head & Neck, Thorax, Abdomen, and Pelvis
Generates DICOM-RT structure of contoured objects
Manual Contouring
Receive, transmit, store, retrieve, display, and process medical images and DICOM objects

Product codes

QKB

Device Description

OncoStudio is a standalone software that provides deep-learning-based automatic contouring to organs at risk in DICOM-RT format from CT images. This software could be used as an initial contouring for the clinicians to be confirmed by the radiation oncology department for treatment planning or other professions where a segmented mask of organs is needed.

Deep learning contouring from Head & Neck, Thorax, Abdomen, and Pelvis
Generates DICOM-RT structure of contoured objects
Manual Contouring
Receive, transmit, store, retrieve, display, and process medical images and DICOM objects

It also has the following general functions:

Patient management;
Review of processed images;
Open and Save of files.

Mentions image processing

Yes

Mentions AI, DNN, or ML

Yes

Input Imaging Modality

CT Images. DICOM RTSTRUCT for output

Anatomical Site

Head & Neck, Thorax, Abdomen, Pelvis

Indicated Patient Age Range

Adult only

Intended User / Care Setting

Used as an initial contouring for the clinicians to be confirmed by the radiation oncology department for treatment planning or other professions where a segmented mask of organs is needed.

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

We collected training data from mainly three datasets of source : OneMedNet, Yonsei Severance Hospital, and University Hospital Basel, Switzerland. OneMedNet is a purchased set of CT data, mainly comprised of U.S.A. population. Yonsei Severance Hospital is located in South Korea, and we collected mainly Eastern population data from this source. The Basel data is known as TotalSegmentator dataset, which is open for public at this moment.
The collected data comprises a total of 2,438 dataset, consisting of 315 datasets from the US, 871 from Korea, and 1,252 from Europe.
The data was constructed with various ethnics (White, Black, Asian, Hispanic, Latino, African, American, etc.), and the training model can be obtained by performing generalization without differences according to ethnicity.
We allocated 310 data as training dataset, which is more than one-tenth of the total 2,438 dataset, and used the remaining data(2128) for training.
Ground truth segmentations were established by three radiation oncologists following international clinical quidelines.
The ground truth annotations for the dataset of Yonsei Severance Hospital(Korea) and OneMedNet(U.S) were established by three different radiation oncologists with 3-20 years of clinical practice following RTOG and clinical quidelines using manual annotation. The radiation oncologists included associate professor, assistant professor, and radiation oncologist resident from two institutions (Yonsei Cancer Center, Samsung Seoul Hospital)
Ground Truthing process:

First, the 1 radiation oncologist manually delineated the organs
Second, segmentation results generated by 1 radiation oncologist are sequentially edited and confirmed by 2 radiation oncologists. In this editing process, the first radiation oncologist makes corrections, and the corrected results are received and finalized by another radiation oncologist.
In case of University Hospital Basel (Europe) dataset is public data comprising 104 anatomical structures. A total of 1,368 CT images were randomly sampled from the years 2012, 2016, and 2020 from the University Hospital Basel through picture archiving and communication system (PACS). The Nora Imaging Platform was used for manual segmentation and further refinement of generated segmentations for ground truth. Segmentation was supervised by two physicians with 3 (M.S.) and 6 years (H.B.) of experience in body imaging, respectively.
Out of a total of 2,438 images, 2,128 were allocated as training data. The allocated training data consists of 731 images from Yonsei Severance Hospital(Republic of Korea), 194 images from OneMedNet(U.S.A), and 1203 images from University Hospital Basel(Switzerland).
The training datasets consist of 62% of Contrast CT and 38% of Non-Contrast CT. The study population comprises 62% males and 38% females, with 22% under 49 years old, 47% aged 50-70 years, and 31% over 70 years old.
The data was constructed with various ethnics (White, Black, Asian, Hispanic, Latino, African, American, etc.), and the result can be obtained by performing generalization without performance differences according to ethnicity.
The acquired data encompasses CT manufacturers such as GE (2%), Siemens (72%), Philips (9%), Toshiba (11%), and unknown manufacturer(6%)

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

For evaluation, we created a test dataset that was not involved in any kind of training process. The splitting was performed at the patient level to ensure that images from the same patient were not present in more than one dataset. A comprehensive audit was conducted to confirm the integrity of the data-splitting process and ensure that no patient overlap occurred between datasets.
Ground truth segmentations were established by three radiation oncologists following international clinical guidelines.
The dataset used in this test comprises a total of 310 CT images, with 140, 121, and 49 images collected from Yonsei Severance Hospital (Republic of Korea), OneMedNet (U.S.A.), and University Hospital Basel (Switzerland), respectively, each meeting the established inclusion criteria. All data used during the standalone performance evaluation was composed independently of product development training.
The images consist of 54% of Contrast CT and 46% of Non-Contrast CT. The study population comprises 58% males and 42% females, with 13% under 49 years old, 54% aged 50-70 years, and 28% over 70 years old.
The data was constructed with various ethnics (White, Black, Asian, Hispanic, Latino, African, American, etc.), and the result can be obtained by performing generalization without performance differences according to ethnicity.
The acquired data encompasses CT manufacturers such as GE (2%), Siemens (56%), Philips (14%), Toshiba (22%), and unknown manufacturer(6%)
Ground truth segmentations were established by three radiation oncologists following international clinical guidelines.

Summary of Performance Studies

Standalone performance test. For the structures being compared, the mean Dice coefficient (DSC) of structures for each anatomical region (Head & Neck, Thorax, Abdomen, and Pelvis) should meet the established criteria.

Key Metrics

Mean Dice coefficient (DSC)

Predicate Device(s)

K230685

Reference Device(s)

K232899

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

Image /page/0/Picture/0 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services logo on the left and the FDA acronym along with the full name of the agency on the right. The Department of Health & Human Services logo is a stylized depiction of a human figure. The FDA acronym is in a blue square, and the words "U.S. FOOD & DRUG ADMINISTRATION" are in blue text to the right of the square.

February 24, 2025

OncoSoft. Co., Ltd. Boram Kim RA/QA Manager 37, Myeongmul-gil, Seodaemun-gu SEOUL, 03776 KOREA, SOUTH

Re: K242994

Trade/Device Name: OncoStudio (OS-01) Regulation Number: 21 CFR 892.2050 Regulation Name: Medical image management and processing system Regulatory Class: Class II Product Code: QKB Dated: January 23, 2025 Received: January 23, 2025

Dear Boram Kim:

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

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

Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device"

1

(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 System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30, Design controls; 21 CFR 820.90, Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).

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

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-device-advicecomprehensive-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-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-regulatory

2

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,

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

3

Indications for Use

Form Approved: OMB No. 0910-0120 Expiration Date: 07/31/2026 See PRA Statement below.

Submission Number (if known)

K242994

Device Name

OncoStudio (OS-01)

Indications for Use (Describe)

OncoStudio provides deep-learning-based automatic contouring to organs at risk in DICOM-RT format from CT images. This software could be used as an initial contouring for the clinicians to be confirmed by the radiation oncology department for treatment planning or other professions where a segmented mask of organs is needed.

· Deep learning contouring from Head & Neck, Thorax, Abdomen, and Pelvis
· Generates DICOM-RT structure of contoured objects
· Manual Contouring
· Receive, transmit, store, retrieve, display, and process medical images and DICOM objects

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

510(k) Summary

[As Required by 21 CFR 807.92]

1. Date Prepared [21 CFR 807.92(a)(a)]

January 23, 2025

2. Submitter's Information [21 CFR 807.92(a)(1)]

Name of Manufacturer: OncoSoft Co., Ltd. 37, Myeongmul-gil, Seodaemun-gu, Seoul, Republic of Korea ● Address: (03776) ● Contact Name: Boram Kim ● Telephone No.: +82-10-6305-7428 ● Email Address: kbrstar@oncosoft.io
1. Trade Name, Common Name, Classification [21 CFR 807.92(a)(2)]

510(k) Number	K242994
Trade/Device/Model Name	OncoStudio / OS-01
Device Classification Name	Medical Image Management and Processing System
Regulation Number	21 CFR 892.2050
Classification Product Code	QKB
Device Class	Class II
510(k) Review Panel	Radiology

5

4. Identification of Predicate Device(s) [21 CFR 807.92(a)(3)]

The identified predicate device within this submission is shown as follow;

Predicate Device

510(k) Number	K230685
Trade/Device/Model Name	AutoContour Model RADAC V3
Device Classification Name	Medical Image Management And Processing System
Regulation Number	21 CFR 892.2050
Classification Product Code	OKB
Device Class	Class II
510(k) Review Panel	Radiology

Reference Device

510(k) Number	K232899
Trade/Device/Model Name	AI-Rad Companion Organs RT
Device Classification Name	Medical Image Management And Processing System
Regulation Number	21 CFR 892.2050
Classification Product Code	OKB
Device Class	Class II
510(k) Review Panel	Radiology

These predicate devices have not been subject to a design-related recall

6

5. Description of the Device [21 CFR 807.92(a)(4)]

OncoStudio is a standalone software that provides deep-learning-based automatic contouring to organs at risk in DICOM-RT format from CT images. This software could be used as an initial contouring for the clinicians to be confirmed by the radiation oncology department for treatment planning or other professions where a segmented mask of organs is needed.

Deep learning contouring from Head & Neck, Thorax, Abdomen, and Pelvis
· Generates DICOM-RT structure of contoured objects
Manual Contouring
· Receive, transmit, store, retrieve, display, and process medical images and DICOM objects

It also has the following general functions:

Patient management;
· Review of processed images;
Open and Save of files.

6. Indications for use [21 CFR 807.92(a)(5)]

OncoStudio provides deep-learning-based automatic contouring to organs at risk in DICOM-RT format from CT images. This software could be used as an initial contouring for the clinicians to be confirmed by the radiation oncology department for treatment planning or other professions where a segmented mask of organs is needed.

Deep learning contouring from Head & Neck, Thorax, Abdomen, and Pelvis
· Generates DICOM-RT structure of contoured objects
Manual Contouring
· Receive, transmit, store, retrieve, display, and process medical images and DICOM objects

7

7. Technological Characteristics (Equivalence to Predicate Device) [21 CFR 807.92(a)(6)]

There are no significant differences in the technological characteristics of these devices compared to the predicate devices which adversely affect safety or effectiveness. Provided below is a table summarizing and comparing the technological characteristics of the OncoStudio and the predicate devices:

[Table 1. Comparison of Proposed Device to Predicate Device and Reference Device]

	Subject Device	Predicate Device	Reference Device1
Item	OncoStudio	AutoContour Model RADAC
V3	AI-Rad Companion
Organs RT	SE
Note
Regulation
Name	Medical Image Management
And Processing System	Medical Image
Management And
Processing System	Medical Image
Management And
Processing System	-
Regulation
Number	21 CFR 892.2050	21 CFR 892.2050	21 CFR 892.2050	-
Product
Code	QKB	QKB	QKB	-
Class	II	II	II	-
510k
Number	K242994	K230685	K232899	-
Indication
for Use	OncoStudio provides deep-
learning-based automatic
contouring to organs at risk
in DICOM-RT format from CT
images. This software could
be used as an initial
contouring for the clinicians
to be confirmed by the
radiation oncology
department for treatment
planning or other professions
where a segmented mask of
organs is needed.
• Deep learning
contouring from Head &
Neck, Thorax, Abdomen,
and Pelvis
• Generates DICOM-RT
structure of contoured
objects
• Manual Contouring
• Receive, transmit, store	AutoContour is intended to
assist radiation treatment
planners in contouring and
reviewing structures within
medical images in
preparation for radiation
therapy treatment
planning	AI-Rad Companion
Organs RT is a post-
processing software
intended to
automatically
contour DICOM CT
and MR predefined
structures using
deep-learning-based
algorithms. Contours
that are generated
by AI-Rad
Companion Organs
RT may be used as
input for clinical
workflows including
external beam
radiation therapy
treatment planning.
AI-Rad Companion
Organs RT must be
used in conjunction
with appropriate	Same

8

K242994

| | retrieve, medical images and DICOM
objects | | | Treatment Planning
Systems and
Interactive
Contouring
applications, to
review, edit, and
accept contours
generated by AI-Rad
Companion Organs
RT. The output of AI-
Rad Companion
Organs RT are
intended to be used
by trained medical
professionals. The
software is not
intended to
automatically detect
or contour lesions. | |
|----------------------------------|-------------- | | • A_Aorta | | • A_Carotid_L | | • A_Carotid_R | | • A_Coronary_R | | • A_Iliac_L | | • A_Iliac_R | | • A_LAD | | • A_Subclavian_L | | • A_Subclavian_R | | • Anus | | • Atrium_L | Regions of
Interest(R
OIs) | • Atrium_R | | • Autochthon_L | | • Autochthon_R | | • Bag_Bowel | | • Bladder | | • Bone_Mandible | | • Bowel_Large | | • Bowel_Small | | • BrachialPlex_L | | • BrachialPlex_R | | • Brachiocephalic_Trunk | | • Brain | | • Brainstem | | • Breast_L | | • Breast_R display, and process
| software such as
---------------------------------------------------------|--------------------|------------------|-------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------|
| • LN_Sclav_L_RTOG | • A_Aorta | • LN_Ax_L | (166 OARs) | |
| • LN_Sclav_R_ESTRO | • A_Aorta_Asc | • LN_Ax_L1_L | Full list of OAR is not provided | |
| • LN_Sclav_R_RTOG | • A_Aorta_Dsc | • LN_Ax_L1_R | | |
| • Larynx | • A_LAD | • LN_Ax_L2_L | | |
| • Lens_L | • A_Pulmonary | • LN_Ax_L2_L3_L | | |
| • Lens_R | • Bladder | • LN_Ax_L2_L3_R | | |
| • Liver | • Bladder_F | • LN_Ax_L2_R | | |
| • Lobe_Temporal_L | • Bone_Ilium_L | • LN_Ax_L3_L | | |
| • Lobe_Temporal_R | • Bone_Ilium_R | • LN_Ax_L3_R | | |
| • Lung_L | • Bone_Mandible | • LN_Ax_R | | |
| • Lung_LLL | • Bone_Pelvic | • LN_IMN_L | | |
| • Lung_LUL | • Bone_Skull | • LN_IMN_R | | |
| • Lung_R | • Bone_Sternum | • LN_IMN_RC_L | | Differ |
| • Lung_RLL | • Bowel | • LN_IMN_RC_R | | ent |
| • Lung_RML | • Bowel_Bag | • LN_Inguinofem_L | | |
| • Lung_RUL | • Bowel_Large | • LN_Inguinofem_R | | |
| • OpticChiasm | • Bowel_Small | • LN_Neck_IA | | |
| • OpticNrv_L | • BrachialPlex_L | • LN_Neck_IB-V_L | | |
| • OpticNrv_R | • BrachialPlex_R | • LN_Neck_IB-V_R | | |
| • Pancreas | • Brain | • LN_Neck_II_L | | |
| • Parotid_L | • Brainstem | • LN_Neck_II_R | | |
| • Parotid_R | • Breast_L | • LN_Neck_II-IV_L | | |
| • Pharynx | • Breast_R | • LN_Neck_II-IV_R | | |
| • Pituitary | • Bronchus | • LN_Neck_II-V_L | | |
| • Prostate | • BuccalMucosa | • LN_Neck_II-V_R | | |
| • Rectum | • Carina | • LN_Neck_III_L | | |

9

K242994

• Bronchus_L	• Rib01_L	• CaudaEquina	• LN_Neck_III_R
• Bronchus_R	• Rib01_R	• Cavity_Oral	• LN_Neck_IV_L
• CaudaEquina	• Rib02_L	• Cavity_Oral_Ext	• LN_Neck_IV_R
• Cavity_Oral	• Rib02_R	• Chestwall_L	• LN_Neck_V_L
• Clavicle_L	• Rib03_L	• Chestwall_OAR	• LN_Neck_V_R
• Clavicle_R	• Rib03_R	• Chestwall_R	• LN_Neck_VIA
• Cochlea_L	• Rib04_L	• Chestwall_RC_L	• LN_Neck_VIIA_L
• Cochlea_R	• Rib04_R	• Chestwall_RC_R	• LN_Neck_VIIA_R
• Colon	• Rib05_L	• Cochlea_L	• LN_Neck_VIIB_L
• Kidney_Cortex_L	• Rib05_R	• Cochlea_R	• LN_Neck_VIIB_R
• Kidney_Cortex_R	• Rib06_L	• Colon_Sigmoid	• LN_Paraaortic
• Costal_Cartilages	• Rib06_R	• Cornea_L	• LN_Pelvics
• Duodenum	• Rib07_L	• Cornea_R	• LN_Pelvic_NRG
• Esophagus	• Rib07_R	• Duodenum	• LN_Sclav_L
• Eye_L	• Rib08_L	• Ear_Internal_L	• LN_Sclav_R
• Eye_R	• Rib08_R	• Ear_Internal_R	• LN_Sclav_RADCOMP_L
• Femur_Head_L	• Rib09_L	• Esophagus	• LN_Sclav_RADCOMP_R
• Femur_Head_R	• Rib09_R	• External	• Lobe_Temporal_L
• Femur_L	• Rib10_L	• Eye_L	• Lobe_Temporal_R
• Femur_R	• Rib10_R	• Eye_R	• Lung_L
• Gallbladder	• Rib11_L	• Femur_Head_L	• Lung_R
• Glnd_Adrenal_L	• Rib11_R	• Femur_Head_R	• Macula_L
• Glnd_Adrenal_R	• Rib12_L	• Femur_L	• Macula_R
• Glnd_Submand_L	• Rib12_R	• Femur_R	• Marrow_Ilium_L
• Glnd_Submand_R	• Sacrum	• Femur_RTOG_L	• Marrow_Ilium_R
• Glnd_Thyroid	• Scapula_L	• Femur_RTOG_R	• Musc_Constrict
• Gluteus_Maximus_L	• Scapula_R	• GallBladder	• Nipple_L
• Gluteus_Maximus_R	• Colon_Sigmoid	• Genitals_F	• Nipple_R
• Gluteus_Medius_L	• Skull	• Genitals_M	• OpticChiasm
• Gluteus_Medius_R	• SpinalCord	• Glnd_Lacrimal_L	• OpticNrv_L
• Gluteus_Minimus_L	• Spleen	• Glnd_Lacrimal_R	• OpticNrv_R
• Gluteus_Minimus_R	• Sternum	• Glnd_Submand_L	• Pancreas
• Heart	• Stomach	• Glnd_Submand_R	• Parotid_L
• Hip_L	• Trachea	• Glnd_Thyroid	• Parotid_R
• Hip_R	• VB_C1	• HDR_Cylinder	• PenileBulb
• Hippocampus_L	• VB_C2	• Heart	• Pericardium
• Hippocampus_R	• VB_C3	• Hippocampus_L	• Pituitary
• Humerus_L	• VB_C4	• Hippocampus_R	• Prostate
• Humerus_R	• VB_C5	• Humerus_L	• Rectum
• Iliopsoas_L	• VB_C6	• Humerus_R	• Rectum_F
• Iliopsoas_R	• VB_C7	• Kidney_L	• Retina_L
• Joint_TM_L	• VB_L1	• Kidney_R	• Retina_R
• Joint_TM_R	• VB_L2	• Kidney_Outer_L	• Rib
• Kidney_L	• VB_L3		• Rib_L

10

K242994

	• Kidney_R	• VB_L4	• Kidney_Outer_R	• Rib_R
	• LN_Ax_L1_L	• VB_L5	• Larynx	• SeminalVes
	• LN_Ax_L1_R	• VB_S1	• Larynx_Glottic	• SpinalCanal
	• LN_Ax_L2_L	• VB_T01	• Larynx_NRG	• SpinalCord
	• LN_Ax_L2_R	• VB_T02	• Larynx_SG	• Spleen
	• LN_Ax_L3_L	• VB_T03	• Lens_L	• Stomach
	• LN_Ax_L3_R	• VB_T04	• Lens_R	• Trachea
	• LN_IMN_L	• VB_T05	• Lips	• UteroCervix
	• LN_IMN_R	• VB_T06	• Liver	• V_Venacava_I
	• LN_Neck_IA	• VB_T07		• V_Venacava_S
	• LN_Neck_IB_L	• VB_T08		• VB
	• LN_Neck_IB_R	• VB_T09		• VB_C1
	• LN_Neck_III_L	• VB_T10		• VB_C2
	• LN_Neck_III_R	• VB_T11		• VB_C3
	• LN_Neck_II_L	• VB_T12		• VB_C4
	• LN_Neck_II_R	• V_Brachioceph_L		• VB_C5
	• LN_Neck_IVA_L	• V_Brachioceph_R		• VB_C6
	• LN_Neck_IVA_R	• V_Iliac_L		• VB_C7
	• LN_Neck_IVB_L	• V_Iliac_R		• VB_L1
	• LN_Neck_IVB_R	• V_Portal_And_Splenic		• VB_L2
	• LN_Neck_VA_L	• V_Pulmonary		• VB_L3
	• LN_Neck_VA_R	• V_Venacava_I		• VB_L4
	• LN_Neck_VBC_L	• V_Venacava_S		• VB_L5
	• LN_Neck_VBC_R	• Ventricle_L		• VB_T01
	• LN_Sclav_L_ESTRO	• Ventricle_R		• VB_T02
				• VB_T03
				• VB_T04
				• VB_T05
				• VB_T06
				• VB_T07
				• VB_T08
				• VB_T09
				• VB_T10
				• VB_T11
				• VB_T12
				Windows based .NET
front-end application that
Operating
System	Local deployment on
Windows			also serves as agent
Uploader supporting
Microsoft Windows 10 (64-
bit) and Microsoft
Windows Server 2016.	Edge & Cloud
Deployment	Differ
ent
				Cloud-based Server based
automatic contouring
application compatible

C

11

| | | with Linux. Windows
python-based automatic
contouring application
supporting Microsoft
Windows 10 (64-bit) and
Microsoft Windows Server
2016. | | |
|---------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------|
| Image
Format | DICOM | DICOM | DICOM | Same |
| General
Functions | 1) Deep learning contouring
from Head & Neck, Thorax,
Abdomen, and Pelvis
2) Generates DICOM-RT
structure of contoured
objects
3) Manual Contouring
4) Receive, transmit, store,
retrieve, display, and process
medical images and DICOM
objects | 1) Automatically contour
various structures of
interest for radiation
therapy treatment
planning
2) Allow the user to review
and modify the resulting
contours
3) Generate DICOM-
compliant structure set
data the can be imported
into a radiation therapy
treatment planning system | CT or MR series of
images serve as
input for AI-Rad
Companion Organs
RT and are acquired
as part of a typical
scanner acquisition.
Once processed by
the AI algorithms,
generated contours
in DICOM-RTSTRUCT
format are reviewed
in a confirmation
window, allowing
clinical user to
confirm or reject the
contours before
sending to the target
system. Optionally,
the user may select
to directly transfer
the contours to a
configurable DICOM
node | Same |
| Algorithm | Deep Learning | Deep Learning | Deep Learning | Same |
| Compatibl
e Modality | CT Images. DICOM
RTSTRUCT for output | CT or MR input for
contouring or
registration/fusion. PET/CT
input for
registration/fusion only.
DICOM RTSTRUCT for
output | CT & MR Images | Equiv
alent |
| Segmentat
ion of
Organ | Head & Neck, Thorax,
Abdomen, Pelvis | Head and Neck, Thorax,
Abdomen, Pelvis | Head & Neck,
Thorax, Abdomen &
Pelvis Head & Neck
lymph nodes | Same |
| Workflow | Automatically processes input
image data contour organs | Automatically contour
various structures of | AI-Rad Companion
Organs RT | Same |
| | and DICOM sends generated
RT Structure set | interest for radiation
therapy treatment
planning using machine
learning based contouring | automatically
processes input
image data and
sends the results as
DICOM-RT Structure
Sets to a user-
configurable target
node | |
| Compatibl
e Scanner
Models | No Limitation on scanner
model, DICOM 3.0
compliance required. | No Limitation on scanner
model, DICOM 3.0
compliance required. | No Limitation on
scanner model,
DICOM 3.0
compliance required. | Same |
| Compatibl
e
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. | Same |
| Patient
Population | Adult only | Adult only | Adult only | Same |

12

The intended use of the predicate device and the subject device are equivalent. Both devices are intended to aid users to contour the body structure using artificial intelligence algorithm that can be used as an initial contouring for the clinicians to be confirmed by the radiation oncology department for treatment planning or other professions where a segmented mask of organs is needed.

A detailed comparison shows the subject device is substantially equivalent in indications for use, image format, general functions, algorithm, segmentation of organs, workflow, compatible scanner models, compatible treatment planning system and patient population to the predicate device. The differences between the subject and the predicate devices do not raise any new questions regarding safety and effectiveness.

8. Non-Clinical Test summary

The following data were provided in support of the substantial equivalence determination:

1. Software Validation
  The OncoStudio contains basic document level of concern software was designed and developed according to a software development process and was verified and validated. Software information is provided in accordance with FDA guidance:
"Content of Premarket Submissions for Device Software Functions," dated June 14, 2023. .
1. Performance characteristics

13

We collected training data from mainly three datasets of source : OneMedNet, Yonsei Severance Hospital, and University Hospital Basel, Switzerland. OneMedNet is a purchased set of CT data, mainly comprised of U.S.A. population. Yonsei Severance Hospital is located in South Korea, and we collected mainly Eastern population data from this source. The Basel data is known as TotalSegmentator dataset, which is open for public at this moment.

The collected data comprises a total of 2,438 dataset, consisting of 315 datasets from the US, 871 from Korea, and 1,252 from Europe.

The data was constructed with various ethnics (White, Black, Asian, Hispanic, Latino, African, American, etc.), and the training model can be obtained by performing generalization without differences according to ethnicity.

We allocated 310 data as training dataset, which is more than one-tenth of the total 2,438 dataset, and used the remaining data(2128) for training.

For evaluation, we created a test dataset that was not involved in any kind of training process. The splitting was performed at the patient level to ensure that images from the same patient were not present in more than one dataset. A comprehensive audit was conducted to confirm the integrity of the data-splitting process and ensure that no patient overlap occurred between datasets.

Ground truth seqmentations were established by three radiation oncologists following international clinical quidelines.

a) Ground Truthing

The ground truth annotations for the dataset of Yonsei Severance Hospital(Korea) and OneMedNet(U.S) were established by three different radiation oncologists with 3-20 years of clinical practice following RTOG and clinical quidelines using manual annotation. The radiation oncologists included associate professor, assistant professor, and radiation oncologist resident from two institutions (Yonsei Cancer Center, Samsung Seoul Hospital)

. Ground Truthing process
- First, the 1 radiation oncologist manually delineated the organs
- Second, seqmentation results generated by 1 radiation oncologist are sequentially edited and confirmed by 2 radiation oncologists. In this editing process, the first radiation oncologist makes corrections, and the corrected results are received and finalized by another radiation oncologist.

14

In case of University Hospital Basel (Europe) dataset is public data comprising 104 anatomical structures. A total of 1,368 CT images were randomly sampled from the years 2012, 2016, and 2020 from the University Hospital Basel through picture archiving and communication system (PACS). The Nora Imaging Platform was used for manual segmentation and further refinement of generated segmentations for ground truth. Segmentation was supervised by two physicians with 3 (M.S.) and 6 years (H.B.) of experience in body imaging, respectively.

b) Training

Out of a total of 2,438 images, 2,128 were allocated as training data. The allocated training data consists of 731 images from Yonsei Severance Hospital(Republic of Korea), 194 images from OneMedNet(U.S.A), and 1203 images from University Hospital Basel(Switzerland).

The training datasets consist of 62% of Contrast CT and 38% of Non-Contrast CT. The study population comprises 62% males and 38% females, with 22% under 49 years old, 47% aged 50-70 years, and 31% over 70 years old.

The data was constructed with various ethnics (White, Black, Asian, Hispanic, Latino, African, American, etc.), and the result can be obtained by performing generalization without performance differences according to ethnicity.

The acquired data encompasses CT manufacturers such as GE (2%), Siemens (72%), Philips (9%), Toshiba (11%), and unknown manufacturer(6%)

c) Segmentation Performance Test

A standalone performance test was conducted to compare the contouring capabilities of OncoStudio.

The dataset used in this test comprises a total of 310 CT images, with 140, 121, and 49 images collected from Yonsei Severance Hospital (Republic of Korea), OneMedNet (U.S.A.), and University Hospital Basel (Switzerland), respectively, each meeting the established inclusion criteria. All data used during the standalone performance evaluation was composed independently of product development training.

The images consist of 54% of Contrast CT and 46% of Non-Contrast CT. The study population comprises 58% males and 42% females, with 13% under 49 years old, 54% aged 50-70 years, and 28% over 70 years old.

The data was constructed with various ethnics (White, Black, Asian, Hispanic, Latino, African, American, etc.), and the result can be obtained by performing generalization without performance differences according to ethnicity.

15

The acquired data encompasses CT manufacturers such as GE (2%), Siemens (56%), Philips (14%), Toshiba (22%), and unknown manufacturer(6%)

Ground truth segmentations were established by three radiation oncologists following international clinical guidelines.

For the structures being compared, the mean Dice coefficient (DSC) of structures for each anatomical region (Head & Neck, Thorax, Abdomen, and Pelvis) should meet the established criteria.

Cybersecurity

· "Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions", on September 27, 2023

9. Substantial Equivalence [21 CFR 807.92(b)(1) and 807.92]

There are no significant differences between the subject, predicate and reference devices, K230685 and K232899 that would adversely affect the use of the product. It is substantially equivalent to the predicate device in indications for use and technology characteristics.

10. Conclusion [21 CFR 807.92(b)(3)]

In according with the Federal Food & Drug and cosmetic Act, 21 CFR Part 807, and based on the information provided in this premarket notification, concludes that the OncoStudio is substantially equivalent in safety and effectiveness to the predicate device as described herein.