TY  - JOUR
AU  - Yu, Kun-Hsing
AU  - Lee, Tsung-Lu Michael
AU  - Yen, Ming-Hsuan
AU  - Kou, S C
AU  - Rosen, Bruce
AU  - Chiang, Jung-Hsien
AU  - Kohane, Isaac S
PY  - 2020
DA  - 2020/8/5
TI  - Reproducible Machine Learning Methods for Lung Cancer Detection Using Computed Tomography Images: Algorithm Development and Validation
JO  - J Med Internet Res
SP  - e16709
VL  - 22
IS  - 8
KW  - computed tomography, spiral
KW  - lung cancer
KW  - machine learning
KW  - early detection of cancer
KW  - reproducibility of results
AB  - Background: Chest computed tomography (CT) is crucial for the detection of lung cancer, and many automated CT evaluation methods have been proposed. Due to the divergent software dependencies of the reported approaches, the developed methods are rarely compared or reproduced. Objective: The goal of the research was to generate reproducible machine learning modules for lung cancer detection and compare the approaches and performances of the award-winning algorithms developed in the Kaggle Data Science Bowl. Methods: We obtained the source codes of all award-winning solutions of the Kaggle Data Science Bowl Challenge, where participants developed automated CT evaluation methods to detect lung cancer (training set n=1397, public test set n=198, final test set n=506). The performance of the algorithms was evaluated by the log-loss function, and the Spearman correlation coefficient of the performance in the public and final test sets was computed. Results: Most solutions implemented distinct image preprocessing, segmentation, and classification modules. Variants of U-Net, VGGNet, and residual net were commonly used in nodule segmentation, and transfer learning was used in most of the classification algorithms. Substantial performance variations in the public and final test sets were observed (Spearman correlation coefficient = .39 among the top 10 teams). To ensure the reproducibility of results, we generated a Docker container for each of the top solutions. Conclusions: We compared the award-winning algorithms for lung cancer detection and generated reproducible Docker images for the top solutions. Although convolutional neural networks achieved decent accuracy, there is plenty of room for improvement regarding model generalizability. 
SN  - 1438-8871
UR  - https://www.jmir.org/2020/8/e16709
UR  - https://doi.org/10.2196/16709
UR  - http://www.ncbi.nlm.nih.gov/pubmed/32755895
DO  - 10.2196/16709
ID  - info:doi/10.2196/16709
ER  -