서울의대 / 장범섭, 전승혁, 김인아*
- 딥러닝 기계학습 모델의 모식도: Image 학습능력에 뛰어난 Convolutional Neural Network과 sequence 학습능력에 뛰어난 Long-Short Term Memory 구조를 동시에 사용하고 임상정보는 neural network로 연결하여 brain MR 이미지 상 나타나는 의심병변이 pseudoprogression인지 progression 인지 예측하게 한다.
- 환자의 임상정보와 이미지정보를 같이 학습한 기계학습 모델이 둘 중 한가지만 학습한 경우보다 테스트셋에서 뛰어난 예측력을 보였다.
Abstract
We aimed to investigate the feasibility of machine learning (ML) algorithm to distinguish pseudoprogression (PsPD) from progression (PD) in patients with glioblastoma (GBM). We recruited the patients diagnosed as primary GBM who received gross total resection (GTR) and concurrent chemoradiotherapy in two institutions from April 2010 to April 2017 and presented suspicious contrast-enhanced lesion on brain magnetic resonance imaging (MRI) during follow-up. Patients from two institutions were allocated to training (N = 59) and testing (N = 19) datasets, respectively. We developed a convolutional neural network combined with a long short-term memory ML structure. MRI data, which was 9 axial post-contrast T1-weighted images in our study, and clinical features were incorporated (Model 1). In the testing set, the trained Model 1 resulted in AUC of 0.83, AUPRC of 0.87, and F1-score of 0.74 using optimal threshold. The performance was superior to that of Model 2 (CNN-LSTM model with MRI data alone) and Model 3 (random forest model with clinical feature alone). The developed algorithm involving MRI data and clinical features could help making decision during follow-up of patients with GBM treated with GTR and concurrent CCRT.
Author information
Jang BS1, Jeon SH1, Kim IH1,2, Kim IA3,4.
1
Department of Radiation Oncology, Seoul National University Hospital, Seoul, Korea.
2
Institute of Radiation Medicine, Cancer Research Institute, Seoul National University College of Medicine, Seoul, Korea.
3
Department of Radiation Oncology, Seoul National University Bundang Hospital, Seongnamsi, Korea. inah228@snu.ac.kr.
4
Institute of Radiation Medicine, Cancer Research Institute, Seoul National University College of Medicine, Seoul, Korea. inah228@snu.ac.kr.
이달의 연구자 바로가기
http://www.rmwebzine.re.kr/newshome/mtnmain.php?mtnkey=articleview&mkey=scatelist&mkey2=76&aid=2826