FCP-Net: A Feature-Compression-Pyramid Network Guided by Game-Theoretic Interactions for Medical Image Segmentation

Liu, Yexin, Zhou, Jian, Liu, Lizhu, Zhan, Zhengjia, Hu, Yueqiang, Fu, Yong Qing and Duan, Huiguo (2022) FCP-Net: A Feature-Compression-Pyramid Network Guided by Game-Theoretic Interactions for Medical Image Segmentation. IEEE Transactions on Medical Imaging, 41 (6). pp. 1482-1496. ISSN 0278-0062

IEEE Biomedical Imaging Clean Copy new.pdf - Accepted Version

Download (2MB) | Preview
Official URL: https://doi.org/10.1109/TMI.2021.3140120


Medical image segmentation is a crucial step in diagnosis and analysis of diseases for clinical applications. Deep neural network methods such as DeepLabv3+ have successfully been applied for medical image segmentation, but multi-level features are seldom integrated seamlessly into different attention mechanisms, and few studies have explored the interactions between medical image segmentation and classification tasks. Herein, we propose a feature-compression-pyramid network (FCP-Net) guided by game-theoretic interactions with a hybrid loss function (HLF) for the medical image segmentation. The proposed approach consists of segmentation branch, classification branch and interaction branch. In the encoding stage, a new strategy is developed for the segmentation branch by applying three modules, e.g., embedded feature ensemble, dilated spatial mapping and channel attention (DSMCA), and branch layer fusion. These modules allow effective extraction of spatial information, efficient identification of spatial correlation among various features, and fully integration of multireceptive field features from different branches. In the decoding stage, a DSMCA module and a multi-scale feature fusion module are used to establish multiple skip connections for enhancing fusion features. Classification and interaction branches are introduced to explore the potential benefits of the classification information task to the segmentation task. We further explore the interactions of segmentation and classification branches from a game theoretic view, and design an HLF. Based on this HLF, the segmentation, classification and interaction branches can collaboratively learn and teach each other throughout the training process, thus applying the conjoint information between the segmentation and classification tasks and improving the generalization performance. The proposed model has been evaluated using several datasets, including ISIC2017, ISIC2018, REFUGE, Kvasir-SEG, BUSI, and PH2, and the results prove its competitiveness compared with other state-of-the-art techniques.

Item Type: Article
Additional Information: Funding information: This work was supported by the General Program of National Natural Science Foundation of China (NSFC No. 52075162), Innovation Leading Program of New and High-tech Industry of Hunan Province (2020GK2015), the Natural Science Foundation of Hunan Province (2021jj20018), the Natural Science Foundation of Changsha (kq2007026), the Key Research Project of Guangdong Province (2020B0101040002), and International Exchange Grant (IEC/NSFC/201078) through the Royal Society, UK and the NSFC.
Uncontrolled Keywords: Hybrid loss function, game theory, embedded feature ensemble module, dilated spatial mapping and channel attention module, branch layer fusion module
Subjects: B900 Others in Subjects allied to Medicine
G400 Computer Science
G600 Software Engineering
Department: Faculties > Engineering and Environment > Mathematics, Physics and Electrical Engineering
Depositing User: Rachel Branson
Date Deposited: 04 Jan 2022 12:17
Last Modified: 28 Jun 2022 14:00
URI: http://nrl.northumbria.ac.uk/id/eprint/48067

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics