Brain tumour segmentation framework with deep nuanced reasoning and Swin-T

作者全名："Xu, Yang; Yu, Kun; Qi, Guanqiu; Gong, Yifei; Qu, Xiaolong; Yin, Li; Yang, Pan"

作者地址："[Xu, Yang; Yu, Kun] Chongqing Univ Posts & Telecommun, Coll Automat, Chongqing, Peoples R China; [Yu, Kun; Yang, Pan] Chongqing Med Univ, Emergency Dept, Affiliated Hosp 2, Chongqing, Peoples R China; [Qi, Guanqiu] SUNY Buffalo State, Comp Informat Syst Dept, Buffalo, NY 14222 USA; [Gong, Yifei] Univ Toronto, Fac Appl Sci & Engn, Edward S Rogers Sr Dept Elect & Comp Engn ECE, Toronto, ON, Canada; [Qu, Xiaolong] Army Med Univ, Southwest Hosp, Dept Cardiovasc Med, Chongqing, Peoples R China; [Yin, Li] Chongqing Univ Canc Hosp, Dept Chongqing Key Lab Translat Res Canc Metastasi, Chongqing, Peoples R China; [Yang, Pan] Univ Chinese Acad Sci, Chongqing Gen Hosp, Dept Cardiovasc Surg, Chongqing, Peoples R China"

通信作者："Qu, XL (通讯作者)，Army Med Univ, Southwest Hosp, Dept Cardiovasc Med, Chongqing, Peoples R China.; Yin, L (通讯作者)，Chongqing Univ Canc Hosp, Dept Chongqing Key Lab Translat Res Canc Metastasi, Chongqing, Peoples R China.; Yang, P (通讯作者)，Univ Chinese Acad Sci, Chongqing Gen Hosp, Dept Cardiovasc Surg, Chongqing, Peoples R China."

来源：IET IMAGE PROCESSING

ESI学科分类：ENGINEERING

WOS号：WOS:001180233700001

JCR分区：Q3

影响因子：2

年份：2024

卷号：　

期号：　

开始页：　

结束页：　

文献类型：Article; Early Access

关键词：image segmentation; medical image processing

摘要："Tumour medical image segmentation plays a crucial role in clinical imaging diagnosis. Existing research has achieved good results, enabling the segmentation of three tumour regions in MRI brain tumour images. Existing models have limited focus on the brain tumour areas, and the long-term dependency of features is weakened as the network depth increases, resulting in blurred edge segmentation of the targets. Additionally, considering the excellent segmentation performance of the Swin Transformer(Swin-T) network, its network structure and parameters are relatively large. To address these limitations, this paper proposes a brain tumour segmentation framework with deep nuanced reasoning and Swin-T. It is mainly composed of the backbone hybrid network (BHN) and the deep micro texture extraction module (DMTE). The BHN combines the Swin-T stage with a new downsampling transition module called dual path feature reasoning (DPFR). The entire network framework is designed to extract global and local features from multi-modal data, enabling it to capture and analyze deep texture features in multi-modal images. It provides significant optimization over the Swin-T network structure. Experimental results on the BraTS dataset demonstrate that the proposed method outperforms other state-of-the-art models in terms of segmentation performance. The corresponding source codes are available at . This paper proposes a brain tumour segmentation framework with deep nuanced reasoning and Swin-T. It is mainly composed of the backbone hybrid network (BHN) and the deep micro texture extraction module (DMTE). The BHN combines the Swin Transformer stage with a new downsampling transition module called dual path feature reasoning. The entire network framework focuses on for extracting global and local features from multi-modal data and can capture and analyze deep texture features in multi-modal images. It provides significant optimization over the Swin Transformer network structure. Experimental results on the BraTS dataset demonstrate that the proposed method outperforms other state-of-the-art models in terms of segmentation performance. image"

基金机构：Kuanren Talents Program of the Second Affiliated Hospital of Chongqing Medical University

基金资助正文："This research is sponsored by the China Postdoctoral Science Foundation (2020M670111ZX), Development Fund of Key Laboratory of Chongqing University Cancer Hospital(cquchkfjj005), Natural Science Foundation of Chongqing(cstc2021jcyj-bsh0199), Natural Science Foundation of Chongqing (cstc2020jcyj-bshX0068), Senior Medical Tal-ents Program of Chongqing for Young and Middle-aged(yxgdrc20210101), 2021 Science and Technology Plan Project of Yuzhong District in Chongqing (Basic Research and Frontier Exploration Project 20210164), Kuanren Talents Program of the Second Affiliated Hospital of Chongqing Medical University(kryc-yq-2109).r No Statement Availabler No Statement Availabler No Statement Availabler No Statement Availabler No Statement Available"