Automatic PET cervical tumor segmentation by combining deep learning and anatomic prior. (12th April 2019)

• Record Type: Journal Article
• Authors: Chen, Liyuan; Shen, Chenyang; Zhou, Zhiguo; Maquilan, Genevieve; Albuquerque, Kevin; Folkert, Michael R; Wang, Jing
• Is Part Of: Physics in medicine & biology. Volume 64:Number 8(2019:Apr.)
• Publication Date: 2019-04-12
• Subjects: cervical tumor segmentation -- PET image -- CNN -- prior anatomy information; Biophysics -- Periodicals; Medical physics -- Periodicals; 610.153
• DOI: 10.1088/1361-6560/ab0b64
• Languages: English
• ISSNs: 0031-9155

Abstract

Abstract: Cervical tumor segmentation on 3D 18 FDG PET images is a challenging task because of the proximity between cervix and bladder, both of which can uptake 18 FDG tracers. This problem makes traditional segmentation based on intensity variation methods ineffective and reduces overall accuracy. Based on anatomy knowledge, including 'roundness' of the cervical tumor and relative positioning between the bladder and cervix, we propose a supervised machine learning method that integrates convolutional neural network (CNN) with this prior information to segment cervical tumors. First, we constructed a spatial information embedded CNN model (S-CNN) that maps the PET image to its corresponding label map, in which bladder, other normal tissue, and cervical tumor pixels are labeled as −1, 0, and 1, respectively. Then, we obtained the final segmentation from the output of the network by a prior information constrained (PIC) thresholding method. We evaluated the performance of the PIC-S-CNN method on PET images from 50 cervical cancer patients. The PIC-S-CNN method achieved a mean Dice similarity coefficient (DSC) of 0.84 while region-growing, Chan-Vese, graph-cut, fully convolutional neural networks (FCN) based FCN-8 stride, and FCN-2 stride, and U-net achieved 0.55, 0.64, 0.67, 0.71, 0.77, and 0.80 mean DSC, respectively. The proposed PIC-S-CNN provides a more accurate way for segmenting cervical tumors on 3D PET images. Our results suggest that combining deep learning and anatomic prior information may improve segmentation accuracy for cervical tumors.