{"title":"HRGUNet:新型高分辨率生成对抗网络与改进的 UNet 方法相结合用于脑肿瘤分割","authors":"Dongmei Zhou, Hao Luo, Xingyang Li, Shengbing Chen","doi":"10.1016/j.jvcir.2024.104345","DOIUrl":null,"url":null,"abstract":"<div><div>Brain tumor segmentation in MRI images is challenging due to variability in tumor characteristics and low contrast. We propose HRGUNet, which combines a high-resolution generative adversarial network with an improved UNet architecture to enhance segmentation accuracy. Our proposed GAN model uses an innovative discriminator design that is able to process complete tumor labels as input. This approach can better ensure that the generator produces realistic tumor labels compared to some existing GAN models that only use local features. Additionally, we introduce a Multi-Scale Pyramid Fusion (MSPF) module to improve fine-grained feature extraction and a Refined Channel Attention (RCA) module to enhance focus on tumor regions. In comparative experiments, our method was verified on the BraTS2020 and BraTS2019 data sets, and the average Dice coefficient increased by 1.5% and 1.2% respectively, and the Hausdorff distance decreased by 23.9% and 15.2% respectively, showing its robustness and generalization for segmenting complex tumor structures.</div></div>","PeriodicalId":54755,"journal":{"name":"Journal of Visual Communication and Image Representation","volume":"105 ","pages":"Article 104345"},"PeriodicalIF":2.6000,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"HRGUNet: A novel high-resolution generative adversarial network combined with an improved UNet method for brain tumor segmentation\",\"authors\":\"Dongmei Zhou, Hao Luo, Xingyang Li, Shengbing Chen\",\"doi\":\"10.1016/j.jvcir.2024.104345\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Brain tumor segmentation in MRI images is challenging due to variability in tumor characteristics and low contrast. We propose HRGUNet, which combines a high-resolution generative adversarial network with an improved UNet architecture to enhance segmentation accuracy. Our proposed GAN model uses an innovative discriminator design that is able to process complete tumor labels as input. This approach can better ensure that the generator produces realistic tumor labels compared to some existing GAN models that only use local features. Additionally, we introduce a Multi-Scale Pyramid Fusion (MSPF) module to improve fine-grained feature extraction and a Refined Channel Attention (RCA) module to enhance focus on tumor regions. In comparative experiments, our method was verified on the BraTS2020 and BraTS2019 data sets, and the average Dice coefficient increased by 1.5% and 1.2% respectively, and the Hausdorff distance decreased by 23.9% and 15.2% respectively, showing its robustness and generalization for segmenting complex tumor structures.</div></div>\",\"PeriodicalId\":54755,\"journal\":{\"name\":\"Journal of Visual Communication and Image Representation\",\"volume\":\"105 \",\"pages\":\"Article 104345\"},\"PeriodicalIF\":2.6000,\"publicationDate\":\"2024-11-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Visual Communication and Image Representation\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1047320324003018\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Visual Communication and Image Representation","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1047320324003018","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
HRGUNet: A novel high-resolution generative adversarial network combined with an improved UNet method for brain tumor segmentation
Brain tumor segmentation in MRI images is challenging due to variability in tumor characteristics and low contrast. We propose HRGUNet, which combines a high-resolution generative adversarial network with an improved UNet architecture to enhance segmentation accuracy. Our proposed GAN model uses an innovative discriminator design that is able to process complete tumor labels as input. This approach can better ensure that the generator produces realistic tumor labels compared to some existing GAN models that only use local features. Additionally, we introduce a Multi-Scale Pyramid Fusion (MSPF) module to improve fine-grained feature extraction and a Refined Channel Attention (RCA) module to enhance focus on tumor regions. In comparative experiments, our method was verified on the BraTS2020 and BraTS2019 data sets, and the average Dice coefficient increased by 1.5% and 1.2% respectively, and the Hausdorff distance decreased by 23.9% and 15.2% respectively, showing its robustness and generalization for segmenting complex tumor structures.
期刊介绍:
The Journal of Visual Communication and Image Representation publishes papers on state-of-the-art visual communication and image representation, with emphasis on novel technologies and theoretical work in this multidisciplinary area of pure and applied research. The field of visual communication and image representation is considered in its broadest sense and covers both digital and analog aspects as well as processing and communication in biological visual systems.