A deep learning-based precision volume calculation approach for kidney and tumor segmentation on computed tomography images. (June 2022)

• Record Type: Journal Article
• Authors: Hsiao, Chiu-Han; Sun, Tzu-Lung; Lin, Ping-Cherng; Peng, Tsung-Yu; Chen, Yu-Hsin; Cheng, Chieh-Yun; Yang, Feng-Jung; Yang, Shao-Yu; Wu, Chih-Horng; Lin, Frank Yeong-Sung; Huang, Yennun
• Is Part Of: Computer methods and programs in biomedicine. Volume 221(2022)
• Publication Date: 2022-06
• Subjects: Deep learning -- Kidney volume -- Preprocessing -- Semantic segmentation; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.106861
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: An lightweight ResNet-41 model is proposed for kidney segmentation in abdomen CT images. An optimized kidney volume calculation system is proposed to determine the kidney volume precisely. ResNet-41 and EfficientNet deep learning models are evaluated on the KiTS19 database and achieved a Dice score of 0.9648 for kidney segmentation and 0.7294 for all types of tumor detections, respectively. Abstract: Previously, doctors interpreted computed tomography (CT) images based on their experience in diagnosing kidney diseases. However, with the rapid increase in CT images, such interpretations were required considerable time and effort, producing inconsistent results. Several novel neural network models were proposed to automatically identify kidney or tumor areas in CT images for solving this problem. In most of these models, only the neural network structure was modified to improve accuracy. However, data pre-processing was also a crucial step in improving the results. This study systematically discussed the necessary pre-processing methods before processing medical images in a neural network model. The experimental results were shown that the proposed pre-processing methods or models significantly improve the accuracy rate compared with the case without data pre-processing. Specifically, the dice score was improved from 0.9436 to 0.9648 for kidney segmentation and 0.7294 for all types of tumor detections. The performance was suitable for clinical applications with lower computational resources based on the proposed medical image processing methods and deep learning models. The cost efficiency and effectiveness were also achieved for automatic kidney volume calculation and tumor detection accurately.