김경모 (서울대학교) | 한빛사논문 > 한빛사

한빛사논문

조회725

김경모Kyungmo Kim

서울대학교

Med. Image Anal. , 2023 Jul 8;89:102886 | https://doi.org/10.1016/j.media.2023.102886 PAIP 2020: Microsatellite instability prediction in colorectal cancer

Kyungmo Kim ^a,1, Kyoungbun Lee ^b,1, Sungduk Cho^c,1, Dong Un Kang ^d,1, Seongkeun Park ^e, Yunsook Kang ^e, Hyunjeong Kim ^e, Gheeyoung Choe ^f,g, Kyung Chul Moon ^g, Kyu Sang Lee ^f,g, Jeong Hwan Park ^h, Choyeon Hong ^b, Ramin Nateghi ⁱ, Fattaneh Pourakpour ^j, Xiyue Wang^k, Sen Yang ^l,m, Seyed Alireza Fatemi Jahromi ⁿ, Aliasghar Khani ⁿ, Hwa-Rang Kim ^o, Doo-Hyun Choi ^o, Chang Hee Han ^p, Jin Tae Kwak ^q, Fan Zhang ^r, Bing Han ^r, David Joon Ho ^s, Gyeong Hoon Kang ^f,t, Se Young Chun ^u, Won-Ki Jeong ^c, Peom Park ^v, Jinwook Choi ^w

^aInterdisciplinary program in Bioengineering, Seoul National University, Seoul 110-799, Republic of Korea
^bDepartment of Pathology, Seoul National University Hospital, Seoul, Republic of Korea
^cKorea University, College of Informatics, Department of Computer Science and Engineering, Seoul, Republic of Korea
^dDepartment of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea
^eDepartment of Biomedical Engineering, Seoul National University Hospital, Seoul, Republic of Korea
^fDepartment of Pathology, Seoul National University Bundang Hospital, Seongnam, Republic of Korea
^gDepartment of Pathology, Seoul National University College of Medicine, Seoul, Republic of Korea
^hDepartment of Pathology, Seoul National University College of Medicine, SMG-SNU Boramae Medical Center, Seoul, Republic of Korea
ⁱElectrical and Electronics Engineering Department, Shiraz University of Technology, Shiraz, Iran
^jIranian Brain Mapping Biobank, National Brain Mapping Laboratory, Tehran, Iran
^kCollege of Computer Science, Sichuan University, China
^lCollege of Biomedical Engineering, Sichuan University, China
^mTencent AI Lab, Shenzhen, China
ⁿDepartment of Computer Engineering, Sharif University of Technology, Tehran, Iran
^oGraduate School of Electronic and Electrical Engineering, Kyungpook National University, Republic of Korea
^pDepartment of Computer Science and Engineering, Sejong University, Seoul, Republic of Korea
^qSchool of Electrical Engineering, Korea University, Seoul, Republic of Korea
^rResearch and Development Center, Canon Medical Systems (China) Co., Ltd, Beijing, China
^sDepartment of Pathology, Memorial Sloan Kettering Cancer Center, New York, NY, USA
^tLaboratory of Epigenetics, Cancer Research Institute, Seoul National University College of Medicine, Republic of Korea
^uDepartment of Electrical and Computer Engineering, INMC, Seoul National University, Seoul, Republic of Korea
^vHuminTec, Suwon, Republic of Korea
^wDepartment of Biomedical Engineering, Seoul National University College of Medicine, Seoul, Republic of Korea

¹Equal contribution.
Corresponding authors: Gyeong Hoon Kang, Se Young Chun, Won-Ki Jeong, Peom Park, Jinwook Choi

Abstract

Microsatellite instability (MSI) refers to alterations in the length of simple repetitive genomic sequences. MSI status serves as a prognostic and predictive factor in colorectal cancer. The MSI-high status is a good prognostic factor in stage II/III cancer, and predicts a lack of benefit to adjuvant fluorouracil chemotherapy in stage II cancer but a good response to immunotherapy in stage IV cancer. Therefore, determining MSI status in patients with colorectal cancer is important for identifying the appropriate treatment protocol. In the Pathology Artificial Intelligence Platform (PAIP) 2020 challenge, artificial intelligence researchers were invited to predict MSI status based on colorectal cancer slide images. Participants were required to perform two tasks. The primary task was to classify a given slide image as belonging to either the MSI-high or the microsatellite-stable group. The second task was tumor area segmentation to avoid ties with the main task. A total of 210 of the 495 participants enrolled in the challenge downloaded the images, and 23 teams submitted their final results. Seven teams from the top 10 participants agreed to disclose their algorithms, most of which were convolutional neural network-based deep learning models, such as EfficientNet and UNet. The top-ranked system achieved the highest F1 score (0.9231). This paper summarizes the various methods used in the PAIP 2020 challenge. This paper supports the effectiveness of digital pathology for identifying the relationship between colorectal cancer and the MSI characteristics.

논문정보

형식Research article
게재일2023년 07월 (BRIC 등록일 2023-08-08)
연구진국내(교신)+국외 연구진
분야 의약학 > 종양의학

댓글 작성 로그인

CV 열람하기

연락처 보기