Lin Huang1, Wei Xia2, Bo Zhang3, Bensheng Qiu4, Xin Gao5. 1. Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, China; University of Science and Technology of China, Hefei, China. 2. Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, China. 3. Second Affiliated Hospital of Soochow University, Suzhou, China. 4. University of Science and Technology of China, Hefei, China. 5. Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, China. Electronic address: xingaosam@yahoo.com.
Abstract
BACKGROUND AND OBJECTIVE: Automatic osteosarcoma tumor segmentation on computed tomography (CT) images is a challenging problem, as tumors have large spatial and structural variabilities. In this study, an automatic tumor segmentation method, which was based on a fully convolutional networks with multiple supervised side output layers (MSFCN), was presented. METHODS: Image normalization is applied as a pre-processing step for decreasing the differences among images. In the frame of the fully convolutional networks, supervised side output layers were added to three layers in order to guide the multi-scale feature learning as a contracting structure, which was then able to capture both the local and global image features. Multiple feature channels were used in the up-sampling portion to capture more context information, for the assurance of accurate segmentation of the tumor, with low contrast around the soft tissue. The results of all the side outputs were fused to determine the final boundaries of the tumors. RESULTS: A quantitative comparison of the 405 osteosarcoma manual segmentation results from the CT images showed that the average Dice similarity coefficient (DSC), average sensitivity, average Hammoude distance (HM) and F1-measure were 87.80%, 86.88%, 19.81% and 0.908, respectively. It was determined that, when compared with the other learning-based algorithms (for example, the fully convolution networks (FCN), U-Net method, and holistically-nested edge detection (HED) method), the MSFCN had the best performances in terms of DSC, sensitivity, HM and F1-measure. CONCLUSION: The results indicated that the proposed algorithm contributed to the fast and accurate delineation of tumor boundaries, which could potentially assist doctors in making more precise treatment plans.
BACKGROUND AND OBJECTIVE:Automatic osteosarcoma tumor segmentation on computed tomography (CT) images is a challenging problem, as tumors have large spatial and structural variabilities. In this study, an automatic tumor segmentation method, which was based on a fully convolutional networks with multiple supervised side output layers (MSFCN), was presented. METHODS: Image normalization is applied as a pre-processing step for decreasing the differences among images. In the frame of the fully convolutional networks, supervised side output layers were added to three layers in order to guide the multi-scale feature learning as a contracting structure, which was then able to capture both the local and global image features. Multiple feature channels were used in the up-sampling portion to capture more context information, for the assurance of accurate segmentation of the tumor, with low contrast around the soft tissue. The results of all the side outputs were fused to determine the final boundaries of the tumors. RESULTS: A quantitative comparison of the 405 osteosarcoma manual segmentation results from the CT images showed that the average Dice similarity coefficient (DSC), average sensitivity, average Hammoude distance (HM) and F1-measure were 87.80%, 86.88%, 19.81% and 0.908, respectively. It was determined that, when compared with the other learning-based algorithms (for example, the fully convolution networks (FCN), U-Net method, and holistically-nested edge detection (HED) method), the MSFCN had the best performances in terms of DSC, sensitivity, HM and F1-measure. CONCLUSION: The results indicated that the proposed algorithm contributed to the fast and accurate delineation of tumor boundaries, which could potentially assist doctors in making more precise treatment plans.
Authors: Lars C Ebert; Jakob Heimer; Wolf Schweitzer; Till Sieberth; Anja Leipner; Michael Thali; Garyfalia Ampanozi Journal: Forensic Sci Med Pathol Date: 2017-08-18 Impact factor: 2.007
Authors: Botian Xu; Yaqiong Chai; Cristina M Galarza; Chau Q Vu; Benita Tamrazi; Bilwaj Gaonkar; Luke Macyszyn; Thomas D Coates; Natasha Lepore; John C Wood Journal: Proc IEEE Int Symp Biomed Imaging Date: 2018-05-24
Authors: Valentina Pedoia; Berk Norman; Sarah N Mehany; Matthew D Bucknor; Thomas M Link; Sharmila Majumdar Journal: J Magn Reson Imaging Date: 2018-10-10 Impact factor: 4.813