Reproducible Machine Learning Methods for Lung Cancer Detection Using Computed Tomography Images: Algorithm Development and Validation.
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 t...
| Publicado en: | Journal of Medical Internet Research Vol. 22; no. 8 |
|---|---|
| Autores principales: | , , , , , , |
| Formato: | research tables/charts Journal Article |
| Publicado: |
JMIR Publications Inc.
Aug2020
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=145533803&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 145533803 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 14394456 DNC jtl: Journal of Medical Internet Research issn: 14394456 maglogo: N pubinfo: dt: Aug2020 vid: 22 iid: 8 pid: 21567 pub: JMIR Publications Inc. place: Toronto, Ontario artinfo: ui: 145533803 145533803 NLM32755895 145533803 10.2196/16709 NLM32755895 145533803 ppct: 1 formats: tig: atl: Reproducible Machine Learning Methods for Lung Cancer Detection Using Computed Tomography Images: Algorithm Development and Validation. aug: au: Yu, Kun-Hsing Lee, Tsung-Lu Michael Yen, Ming-Hsuan Kou, S C Rosen, Bruce Chiang, Jung-Hsien Kohane, Isaac S affil: Department of Biomedical Informatics, Harvard Medical School, Boston, MA, United States sug: subj: Lung Neoplasms Lung Neoplasms Diagnosis Tomography, X-Ray Computed Methods Algorithms Human 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. pubtype: Academic Journal doctype: research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|