K-numberK242994
Device nameOncoStudio (OS-01)
ApplicantOncosoft. Co., Ltd.
Product codeQKB
Device classClass II
Decision dateFeb 24, 2025
DecisionSubstantially Equivalent
Regulation892.2050
AI Summary extracted from FDA summary PDF · never regenerated
Intended use

OncoStudio (OS-01) is a standalone software that provides deep-learning-based automatic contouring of organs at risk from CT images in DICOM-RT format. It is intended to assist radiation oncology clinicians by generating initial contours of anatomical structures (Head & Neck, Thorax, Abdomen, Pelvis) that can be reviewed, edited, and confirmed by trained professionals for radiation therapy treatment planning or other clinical workflows requiring organ segmentation.

Technological characteristics

OncoStudio uses deep learning algorithms to automatically contour organs from CT images and generate DICOM-RT structure sets. It operates on local Windows deployment, processes DICOM 3.0 compliant images, supports manual contouring capabilities, and includes patient management and image review functions. The device supports contouring of up to 166 organs of interest across four anatomical regions and is compatible with any DICOM 3.0 compliant scanner and treatment planning system.

Test standards cited

Not stated in this summary.

Substantial equivalence argument

OncoStudio is substantially equivalent to the predicate device (AutoContour Model RADAC V3, K230685) because both are deep-learning-based automatic contouring systems classified as Medical Image Management and Processing Systems (21 CFR 892.2050, Class II). Both devices have identical indications for use, employ the same deep learning algorithm approach, process DICOM images with DICOM-RT output, target the same adult patient population, and are compatible with any DICOM 3.0 compliant scanner and treatment planning system. The differences in specific organs of interest, deployment architecture, and operating system do not raise new safety or effectiveness concerns, as both devices require clinician review and confirmation before use in treatment planning.

Extracted by AI from the official FDA summary PDF →
Source

View the full FDA submission: accessdata.fda.gov

Researching this as a predicate?
Want a transparent AI-ranking score, AI-discovered related predicates, ongoing safety and warning-letter monitoring, full predicate chain lineage, and a drafted SE rationale — all saved to your own project? That's what an account adds.
Start free trial →

Everything you need for a 510(k) submission. Nothing you don't.

14-day free trial. No setup. Cancel anytime.

Start free trial →
Building an AI or ML-enabled device? Predicate search, PCCP tracking, and AI-specific FDA intelligence — built exclusively for AI/ML devices. Try AIFDA Intel →