Segmentation of liver tumors with abdominal computed tomography using fully convolutional networks

Article type: Research Article

Authors: Chen, Chih-I^{a; b; c; d; e} | Lu, Nan-Han^{f; g; h} | Huang, Yung-Hui^h | Liu, Kuo-Ying^g | Hsu, Shih-Yen^d | Matsushima, Akariⁱ | Wang, Yi-Ming^{d; j; *} | Chen, Tai-Been^{h; k; *}

Affiliations: [a] Division of Colon and Rectal Surgery, Department of Surgery, E-DA Hospital, Kaohsiung City, Taiwan | [b] Division of General Medicine Surgery, Department of Surgery, E-DA Hospital, Kaohsiung City, Taiwan | [c] School of Medicine, College of Medicine, I-Shou University, Kaohsiung City, Taiwan | [d] Department of Information Engineering, I-Shou University, Kaohsiung City, Taiwan | [e] The School of Chinese Medicine for Post Baccalaureate, I-Shou University, Kaohsiung City, Taiwan | [f] Department of Pharmacy, Tajen University, Pingtung City, Taiwan | [g] Department of Radiology, E-DA Hospital, I-Shou University, Kaohsiung City, Taiwan | [h] Department of Medical Imaging and Radiological Science, I-Shou University, Kaohsiung City, Taiwan | [i] Department of Radiological Technology Faculty of Medical Technology, Teikyo University, Tokyo, Japan | [j] Department of Critical Care Medicine, E-DA hospital, I-Shou University, Kaohsiung City, Taiwan | [k] Institute of Statistics, National Yang Ming Chiao Tung University, Hsinchu, Taiwan

Correspondence: [*] Corresponding authors. Tai-Been Chen, Department of Medical Imaging and Radiological Science, I-Shou University, 8 Yida Road, Jiao-Su Village, Yan-Chao District, Kaohsiung City 82445, Taiwan. E-mail: ctb@isu.edu.tw.; Yi-Ming Wang, Department of Information Engineering, I-Shou University, 8 Yida Road, Jiao-Su Village, Yan-Chao District, Kaohsiung City 82445, Taiwan. E-mail: ed101632@edah.org.tw.

Abstract: BACKGROUND:Dividing liver organs or lesions depicting on computed tomography (CT) images could be applied to help tumor staging and treatment. However, most existing image segmentation technologies use manual or semi-automatic analysis, making the analysis process costly and time-consuming. OBJECTIVE:This research aims to develop and apply a deep learning network architecture to segment liver tumors automatically after fine tuning parameters. METHODS AND MATERIALS:The medical imaging is obtained from the International Symposium on Biomedical Imaging (ISBI), which includes 3D abdominal CT scans of 131 patients diagnosed with liver tumors. From these CT scans, there are 7,190 2D CT images along with the labeled binary images. The labeled binary images are regarded as gold standard for evaluation of the segmented results by FCN (Fully Convolutional Network). The backbones of FCN are extracted from Xception, InceptionresNetv2, MobileNetv2, ResNet18, ResNet50 in this study. Meanwhile, the parameters including optimizers (SGDM and ADAM), size of epoch, and size of batch are investigated. CT images are randomly divided into training and testing sets using a ratio of 9:1. Several evaluation indices including Global Accuracy, Mean Accuracy, Mean IoU (Intersection over Union), Weighted IoU and Mean BF Score are applied to evaluate tumor segmentation results in the testing images. RESULTS: The Global Accuracy, Mean Accuracy, Mean IoU, Weighted IoU, and Mean BF Scores are 0.999, 0.969, 0.954, 0.998, 0.962 using ResNet50 in FCN with optimizer SGDM, batch size 12, and epoch 9. It is important to fine tuning the parameters in FCN model. Top 20 FNC models enable to achieve higher tumor segmentation accuracy with Mean IoU over 0.900. The occurred frequency of InceptionresNetv2, MobileNetv2, ResNet18, ResNet50, and Xception are 9, 6, 3, 5, and 2 times. Therefore, the InceptionresNetv2 has higher performance than others. CONCLUSIONS:This study develop and test an automated liver tumor segmentation model based on FCN. Study results demonstrate that many deep learning models including InceptionresNetv2, MobileNetv2, ResNet18, ResNet50, and Xception have high potential to segment liver tumors from CT images with accuracy exceeding 90%. However, it is still difficult to accurately segment tiny and small size tumors by FCN models.

Keywords: Abdominal computerized tomography (CT), fully convolutional network, liver tumor segmentation

DOI: 10.3233/XST-221194

Journal: Journal of X-Ray Science and Technology, vol. 30, no. 5, pp. 953-966, 2022