의학물리학

  • [PLoS One.] Evaluation of Computer-Aided Nodule Assessment and Risk Yield (CANARY) in Korean patients for prediction of invasiveness of ground-glass opacity nodule

    연세대 / 이주영, 김진성*

  • 출처
    PLoS One.
  • 등재일
    2021 Jun 14
  • 저널이슈번호
    16(6):e0253204. doi: 10.1371/journal.pone.0253204. eCollection 2021.
  • 내용

    바로가기  >

    Abstract
    Differentiating the invasiveness of ground-glass nodules (GGN) is clinically important, and several institutions have attempted to develop their own solutions by using computed tomography images. The purpose of this study is to evaluate Computer-Aided Analysis of Risk Yield (CANARY), a validated virtual biopsy and risk-stratification machine-learning tool for lung adenocarcinomas, in a Korean patient population. To this end, a total of 380 GGNs from 360 patients who underwent pulmonary resection in a single institution were reviewed. Based on the Score Indicative of Lung Cancer Aggression (SILA), a quantitative indicator of CANARY analysis results, all of the GGNs were classified as "indolent" (atypical adenomatous hyperplasia, adenocarcinomas in situ, or minimally invasive adenocarcinoma) or "invasive" (invasive adenocarcinoma) and compared with the pathology reports. By considering the possibility of uneven class distribution, statistical analysis was performed on the 1) entire cohort and 2) randomly extracted six sets of class-balanced samples. For each trial, the optimal cutoff SILA was obtained from the receiver operating characteristic curve. The classification results were evaluated using several binary classification metrics. Of a total of 380 GGNs, the mean SILA for 65 (17.1%) indolent and 315 (82.9%) invasive lesions were 0.195±0.124 and 0.391±0.208 (p < 0.0001). The area under the curve (AUC) of each trial was 0.814 and 0.809, with an optimal threshold SILA of 0.229 for both. The macro F1-score and geometric mean were found to be 0.675 and 0.745 for the entire cohort, while both scored 0.741 in the class-equalized dataset. From these results, CANARY could be confirmed acceptable in classifying GGN for Korean patients after the cutoff SILA was calibrated. We found that adjusting the cutoff SILA is needed to use CANARY in other countries or races, and geometric mean could be more objective than F1-score or AUC in the binary classification of imbalanced data.

     

     

     

     

    Affiliations

    Juyoung Lee  1   2 , Brian Bartholmai  3 , Tobias Peikert  4 , Jaehee Chun  1 , Hojin Kim  1 , Jin Sung Kim  1 , Seong Yong Park  5
    1 Department of Radiation Oncology, Yonsei Cancer Center, Yonsei University College of Medicine, Seoul, Korea.
    2 Department of Integrative Medicine, Major in Digital Healthcare, Yonsei University College of Medicine, Seoul, Korea.
    3 Department of Radiology, Mayo Clinic, Rochester, Minnesota, United States of America.
    4 Division of Pulmonary and Critical Care Medicine, Department of Medicine, Mayo Clinic, Rochester, Minnesota, United States of America.
    5 Department of Thoracic and Cardiovascular Surgery, Yonsei University College of Medicine, Seoul, Korea.

  • 편집위원

    최근들어 폐암의 하위 분류 중 가장 빈번하게 발견되는 폐선암은, 병리검사로부터 알 수 있는 침습도에 따라 PFS(progress-free survival, 무진행생존)가 달라지고 이에 따른 대응 전략 및 폐 절제술의 수행 범위가 달라지는 등의 이유로 인해 정확히 구분하는 것이 중요합니다. 이를 위해 미국의 Mayo Clinic에서 머신러닝 알고리즘에 기반해 CT 영상을 이용해 폐선암의 침습도를 예측하는 소프트웨어인 CANARY(Computer-aided Nodule Assessment and Risk Yield)를 개발해 미국 내 몇몇 기관과 다수의 환자에 대해 검증해왔고, 이번 연구에서는 세브란스병원의 폐선암 환자들의 수술 전 CT 데이터를 이용, CANARY가 한국의 환자들에 잘 적용되는지 검증해 보았습니다.
    이번 연구를 통해 비침습적으로 수술 전에 폐선암을 분류할 수 있는 1) CANARY의 성능을 검증하고, 2) CANARY를 다른 기관에서 사용하기 위해서는 기준이 되는 지표를 기관에 맞게 조정하는 과정이 필요함을 발견하였고, 3) 이진 분류 모델의 성능 평가 과정에서 클래스가 균일하지 않은 경우, 흔히 쓰이는 F1-score, ROAUC보다 geometric mean, bookmaker informedness 등의 지표가 객관적일 수 있음을 확인할 수 있었습니다.

    2021-06-30 16:39:13

  • 덧글달기
    덧글달기
       IP : 35.173.35.159

    등록