Published on in Vol 14 (2026)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/86155, first published .
Enhanced Magnetic Resonance Imaging–Based Knee Cartilage Segmentation Using a Swin-UNet Conditional Generative Adversarial Network: Development and Validation Study

Enhanced Magnetic Resonance Imaging–Based Knee Cartilage Segmentation Using a Swin-UNet Conditional Generative Adversarial Network: Development and Validation Study

Enhanced Magnetic Resonance Imaging–Based Knee Cartilage Segmentation Using a Swin-UNet Conditional Generative Adversarial Network: Development and Validation Study

Jun Young Park   1 * , MD, PhD ;   Ji-Hoon Nam   2, 3, 4 * , MSc ;   Shakhboz Abdigapporov   3 , MSc ;   Jong-Keun Kim   5 , MD, PhD ;   Yong-Gon Koh   6 , MD ;   Byung Woo Cho   7 , MD, PhD ;   Hyuck Min Kwon   8 , MD, PhD ;   Kwan Kyu Park   8 , MD, PhD ;   Kyoung-Tak Kang   2, 3, 4 , PhD

1 Department of Orthopaedic Surgery, Yonsei University College of Medicine, Yongin Severance Hospital, Yongin-si, Gyeonggi-do, Republic of Korea

2 Department of Mechanical Engineering, Yonsei University, Seoul, Seoul, Republic of Korea

3 Clevion Co., Ltd., Seoul, Republic of Korea

4 Skyve R&D LAB, Skyve Co., Ltd., Seoul, Republic of Korea

5 Department of Orthopaedic Surgery, HeungK Hospital, Seoul, Republic of Korea

6 Department of Orthopaedic Surgery, Joint Reconstruction Center, Yonsei Sarang Hospital, Seoul, Republic of Korea

7 Department of Orthopaedic Surgery, Yonsei University College of Medicine, Gangnam Severance Hospital, Seoul, Republic of Korea

8 Department of Orthopaedic Surgery, Yonsei University College of Medicine, Severance Hospital, Seoul, Republic of Korea

*these authors contributed equally

Corresponding Author:

  • Kyoung-Tak Kang, PhD
  • Department of Mechanical Engineering
  • Yonsei University
  • 50 Yonsei-ro
  • Seodaemun-gu
  • Seoul, Seoul 03722
  • Republic of Korea
  • Phone: 82 2-2123-4827
  • Fax: 1 2-362-2736
  • Email: tagi1024@gmail.com