Automatic liver segmentation with CT images based on 3D U-net deep learning approach

Ting Yu Su, Wei Tse Yang, Tsu Chi Cheng, Yi Fei He, Yu Hua Fang

研究成果: Conference contribution


The detection and the evaluation of the shape of liver from abdominal computed tomography (CT) images are fundamental tasks in the computer-assisted liver surgery planning such as radiation therapy. However, the segmentation of the liver still remains many challenges to be solved, such as ambiguous boundaries, heterogeneous appearances and highly varied shapes of the liver. To address these difficulties, we developed an automatic liver segmentation model based on 3D U-net network. Some preprocessing steps were done to elevate the performance of our protocol first. Also, an approximate liver map was generated by calculating the gradient of CT images. The area which had high possibility to be liver was select as the training set to make sure the balance of data. Then, a deep learning U-net structure was applied for the processed training data. Finally, some post-processing methods, which include k-means clustering and morphology algorithms, was applied in our protocol. Our protocol showed the results with high structure similarity index (SSIM), dice score coefficient and peak signal-to noise ratio (PSNR) of liver segmentation model, demonstrating the potential clinical applicability of the proposed approach.

主出版物標題International Forum on Medical Imaging in Asia 2019
編輯Jong Hyo Kim, Hiroshi Fujita, Feng Lin
出版狀態Published - 2019
事件International Forum on Medical Imaging in Asia 2019 - Singapore, Singapore
持續時間: 2019 一月 72019 一月 9


名字Proceedings of SPIE - The International Society for Optical Engineering


ConferenceInternational Forum on Medical Imaging in Asia 2019

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

指紋 深入研究「Automatic liver segmentation with CT images based on 3D U-net deep learning approach」主題。共同形成了獨特的指紋。