A deep learning based CT image analytics protocol to identify lung adenocarcinoma category and high-risk tumor area

• Published in: STAR protocols 2022-09, Vol.3 (3), p.101485-101485, Article 101485
• Main Authors: Chen, Liuyin, Qi, Haoyang, Lu, Di, Zhai, Jianxue, Cai, Kaican, Wang, Long, Liang, Guoyuan, Zhang, Zijun
• Format: Article
• Language: English
• Subjects: Bioinformatics; Biotechnology and bioengineering; Cancer; Computer sciences; Health Sciences; Protocol; Systems biology
• ISSN: 2666-1667; 2666-1667
• DOI: 10.1016/j.xpro.2022.101485

We present a protocol which implements deep learning-based identification of the lung adenocarcinoma category with high accuracy and generalizability, and labeling of the high-risk area on Computed Tomography (CT) images. The protocol details the execution of the python project based on the dataset used in the original publication or a custom dataset. Detailed steps include data standardization, data preprocessing, model implementation, results display through heatmaps, and statistical analysis process with Origin software or python codes. For complete details on the use and execution of this protocol, please refer to Chen et al. (2022). [Display omitted] •A deep learning protocol to identify the lung adenocarcinoma category•Identification of high-risk tumor areas•Code environment setup and code implementation•Code provided for data processing, deep model development, and results analyses Publisher’s note: Undertaking any experimental protocol requires adherence to local institutional guidelines for laboratory safety and ethics. We present a protocol which implements deep learning-based identification of the lung adenocarcinoma category with high accuracy and generalizability, and labeling of the high-risk area on Computed Tomography (CT) images. The protocol details the execution of the python project based on the dataset used in the original publication or a custom dataset. Detailed steps include data standardization, data preprocessing, model implementation, results display through heatmaps, and statistical analysis process with Origin software or python codes.