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

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.

AI/ML Overview

Based on the provided text, here's a description of the acceptance criteria and the study that proves the device meets those criteria for OncoStudio (OS-01):

The submission details a standalone performance test conducted to demonstrate the contouring capabilities of OncoStudio, an AI-powered software for automatic organ at risk contouring from CT images. The primary evaluation metric for acceptance was the Dice coefficient (DSC).

1. Acceptance Criteria and Reported Device Performance

The text explicitly states: "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." However, the specific numerical established criteria for the mean Dice coefficient for each anatomical region (Head & Neck, Thorax, Abdomen, and Pelvis) are not reported in the provided document. Similarly, the actual reported device performance (the mean DSC achieved for each region) is not explicitly stated in the visible sections.

To fully answer this, a table would look like this, but with missing data based on the provided text:

Anatomical Region	Acceptance Criteria (Mean Dice Coefficient)	Reported Device Performance (Mean Dice Coefficient)
Head & Neck	Not specified in text	Not reported in text
Thorax	Not specified in text	Not reported in text
Abdomen	Not specified in text	Not reported in text
Pelvis	Not specified in text	Not reported in text

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

Test Set Sample Size: 310 CT images.
- 140 images from Yonsei Severance Hospital (Republic of Korea)
- 121 images from OneMedNet (U.S.A.)
- 49 images from University Hospital Basel (Switzerland)
Data Provenance: The data is from South Korea, U.S.A., and Switzerland. The text specifies it was "collected from Yonsei Severance Hospital (Republic of Korea), OneMedNet (U.S.A.), and University Hospital Basel (Switzerland)". The data from OneMedNet is a "purchased set of CT data, mainly comprised of U.S.A. population." Yonsei Severance Hospital is in South Korea, and the Basel data is known as the TotalSegmentator dataset.
Retrospective or Prospective: Not explicitly stated, but the description of data collection "from the years 2012, 2016, and 2020 from the University Hospital Basel through picture archiving and communication system (PACS)" implies a retrospective collection for at least part of the dataset.

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

Number of Experts: Three radiation oncologists established the ground truth segmentations for the test set.
Qualifications of Experts (for Yonsei Severance Hospital and OneMedNet data): The radiation oncologists had "3-20 years of clinical practice," and included "associate professor, assistant professor, and radiation oncologist resident from two institutions (Yonsei Cancer Center, Samsung Seoul Hospital)."
Qualifications of Experts (for University Hospital Basel data): The ground truth segmentation was "supervised by two physicians with 3 (M.S.) and 6 years (H.B.) of experience in body imaging, respectively." (Note: this refers to the public dataset from Basel, which was used for training, but the text states for the test set that "Ground truth segmentations were established by three radiation oncologists following international clinical guidelines" without distinguishing the origin for the test set ground truth specifically in terms of expert type, likely implying the former expert group applied to the test set as well for consistency).

4. Adjudication Method for the Test Set

The ground truthing process for the Yonsei Severance Hospital and OneMedNet data (which largely comprises the test set) was:

"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."

This indicates a sequential review and confirmation process rather than a strict 2+1 or 3+1 consensus, with an initial delineator and then two subsequent reviewers/editors, likely leading to a consensus by the end of the process.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study comparing human readers with AI assistance vs. without AI assistance was not mentioned in the provided text. The study described is a standalone performance test of the algorithm.

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

Yes, a standalone performance test was done. The text explicitly states: "A standalone performance test was conducted to compare the contouring capabilities of OncoStudio."

7. The Type of Ground Truth Used

The ground truth used was expert consensus/manual annotation by radiation oncologists/physicians following international clinical guidelines (RTOG and clinical guidelines).

8. The Sample Size for the Training Set

Total Training Data: 2,128 images.
- 731 images from Yonsei Severance Hospital (Republic of Korea)
- 194 images from OneMedNet (U.S.A)
- 1203 images from University Hospital Basel (Switzerland)

The total collected data was 2,438 datasets (315 US, 871 Korea, 1252 Europe). From this, 310 data were allocated for the test dataset, and the remaining 2,128 were used for training.

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

The ground truth for the training set was established similarly to the test set:

For Yonsei Severance Hospital (Korea) and OneMedNet (U.S.) data: Established by three radiation oncologists with 3-20 years of clinical practice following RTOG and clinical guidelines using manual annotation. The process involved initial manual delineation by one radiation oncologist, followed by sequential editing and confirmation by two other radiation oncologists.
For University Hospital Basel (Europe) data (TotalSegmentator dataset): This is public data where ground truth was established by manual segmentation and refinement supervised by two physicians with 3 and 6 years of experience in body imaging.

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)

· 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)]

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)]

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 RADACV3	AI-Rad CompanionOrgans RT	SENote
RegulationName	Medical Image ManagementAnd Processing System	Medical ImageManagement AndProcessing System	Medical ImageManagement AndProcessing System	-
RegulationNumber	21 CFR 892.2050	21 CFR 892.2050	21 CFR 892.2050	-
ProductCode	QKB	QKB	QKB	-
Class	II	II	II	-
510kNumber	K242994	K230685	K232899	-
Indicationfor Use	OncoStudio provides deep-learning-based automaticcontouring to organs at riskin DICOM-RT format from CTimages. This software couldbe used as an initialcontouring for the cliniciansto be confirmed by theradiation oncologydepartment for treatmentplanning or other professionswhere a segmented mask oforgans is needed.• Deep learningcontouring from Head &Neck, Thorax, Abdomen,and Pelvis• Generates DICOM-RTstructure of contouredobjects• Manual Contouring• Receive, transmit, store	AutoContour is intended toassist radiation treatmentplanners in contouring andreviewing structures withinmedical images inpreparation for radiationtherapy treatmentplanning	AI-Rad CompanionOrgans RT is a post-processing softwareintended toautomaticallycontour DICOM CTand MR predefinedstructures usingdeep-learning-basedalgorithms. Contoursthat are generatedby AI-RadCompanion OrgansRT may be used asinput for clinicalworkflows includingexternal beamradiation therapytreatment planning.AI-Rad CompanionOrgans RT must beused in conjunctionwith appropriate	Same

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

K242994

	retrieve, display, and processmedical images and DICOMobjects				software such asTreatment PlanningSystems andInteractiveContouringapplications, toreview, edit, andaccept contoursgenerated by AI-RadCompanion OrgansRT. The output of AI-Rad CompanionOrgans RT areintended to be usedby trained medicalprofessionals. Thesoftware is notintended toautomatically detector contour lesions.
	• A_Aorta	• LN_Sclav_L_RTOG	• A_Aorta	• LN_Ax_L	(166 OARs)
	• A_Carotid_L	• LN_Sclav_R_ESTRO	• A_Aorta_Asc	• LN_Ax_L1_L	Full list of OAR is not provided
	• A_Carotid_R	• LN_Sclav_R_RTOG	• A_Aorta_Dsc	• LN_Ax_L1_R
	• A_Coronary_R	• Larynx	• A_LAD	• LN_Ax_L2_L
	• A_Iliac_L	• Lens_L	• A_Pulmonary	• LN_Ax_L2_L3_L
	• A_Iliac_R	• Lens_R	• Bladder	• LN_Ax_L2_L3_R
	• A_LAD	• Liver	• Bladder_F	• LN_Ax_L2_R
	• A_Subclavian_L	• Lobe_Temporal_L	• Bone_Ilium_L	• LN_Ax_L3_L
	• A_Subclavian_R	• Lobe_Temporal_R	• Bone_Ilium_R	• LN_Ax_L3_R
	• Anus	• Lung_L	• Bone_Mandible	• LN_Ax_R
	• Atrium_L	• Lung_LLL	• Bone_Pelvic	• LN_IMN_L
Regions ofInterest(ROIs)	• Atrium_R	• Lung_LUL	• Bone_Skull	• LN_IMN_R
	• Autochthon_L	• Lung_R	• Bone_Sternum	• LN_IMN_RC_L		Differ
	• Autochthon_R	• Lung_RLL	• Bowel	• LN_IMN_RC_R		ent
	• Bag_Bowel	• Lung_RML	• Bowel_Bag	• LN_Inguinofem_L
	• Bladder	• Lung_RUL	• Bowel_Large	• LN_Inguinofem_R
	• Bone_Mandible	• OpticChiasm	• Bowel_Small	• LN_Neck_IA
	• Bowel_Large	• OpticNrv_L	• BrachialPlex_L	• LN_Neck_IB-V_L
	• Bowel_Small	• OpticNrv_R	• BrachialPlex_R	• LN_Neck_IB-V_R
	• BrachialPlex_L	• Pancreas	• Brain	• LN_Neck_II_L
	• BrachialPlex_R	• Parotid_L	• Brainstem	• LN_Neck_II_R
	• Brachiocephalic_Trunk	• Parotid_R	• Breast_L	• LN_Neck_II-IV_L
	• Brain	• Pharynx	• Breast_R	• LN_Neck_II-IV_R
	• Brainstem	• Pituitary	• Bronchus	• LN_Neck_II-V_L
	• Breast_L	• Prostate	• BuccalMucosa	• LN_Neck_II-V_R
	• Breast_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 .NETfront-end application that
OperatingSystem	Local deployment onWindows			also serves as agentUploader supportingMicrosoft Windows 10 (64-bit) and MicrosoftWindows Server 2016.	Edge & CloudDeployment	Different
				Cloud-based Server basedautomatic contouringapplication compatible

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

		with Linux. Windowspython-based automaticcontouring applicationsupporting MicrosoftWindows 10 (64-bit) andMicrosoft Windows Server2016.
ImageFormat	DICOM	DICOM	DICOM	Same
GeneralFunctions	1) Deep learning contouringfrom Head & Neck, Thorax,Abdomen, and Pelvis2) Generates DICOM-RTstructure of contouredobjects3) Manual Contouring4) Receive, transmit, store,retrieve, display, and processmedical images and DICOMobjects	1) Automatically contourvarious structures ofinterest for radiationtherapy treatmentplanning2) Allow the user to reviewand modify the resultingcontours3) Generate DICOM-compliant structure setdata the can be importedinto a radiation therapytreatment planning system	CT or MR series ofimages serve asinput for AI-RadCompanion OrgansRT and are acquiredas part of a typicalscanner acquisition.Once processed bythe AI algorithms,generated contoursin DICOM-RTSTRUCTformat are reviewedin a confirmationwindow, allowingclinical user toconfirm or reject thecontours beforesending to the targetsystem. Optionally,the user may selectto directly transferthe contours to aconfigurable DICOMnode	Same
Algorithm	Deep Learning	Deep Learning	Deep Learning	Same
Compatible Modality	CT Images. DICOMRTSTRUCT for output	CT or MR input forcontouring orregistration/fusion. PET/CTinput forregistration/fusion only.DICOM RTSTRUCT foroutput	CT & MR Images	Equivalent
Segmentation ofOrgan	Head & Neck, Thorax,Abdomen, Pelvis	Head and Neck, Thorax,Abdomen, Pelvis	Head & Neck,Thorax, Abdomen &Pelvis Head & Necklymph nodes	Same
Workflow	Automatically processes inputimage data contour organs	Automatically contourvarious structures of	AI-Rad CompanionOrgans RT	Same
	and DICOM sends generatedRT Structure set	interest for radiationtherapy treatmentplanning using machinelearning based contouring	automaticallyprocesses inputimage data andsends the results asDICOM-RT StructureSets to a user-configurable targetnode
Compatible ScannerModels	No Limitation on scannermodel, DICOM 3.0compliance required.	No Limitation on scannermodel, DICOM 3.0compliance required.	No Limitation onscanner model,DICOM 3.0compliance required.	Same
CompatibleTreatmentPlanningSystem	No Limitation on TPS model,DICOM 3.0 compliancerequired.	No Limitation on TPSmodel, DICOM 3.0compliance required.	No Limitation on TPSmodel, DICOM 3.0compliance required.	Same
PatientPopulation	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.

{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.

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).