Pengfei Cai, Biyuan Li, Gaowei Sun, Bo Yang, Xiuwei Wang, Chunjie Lv, Jun Yan
{"title":"DEAF-Net:用于视网膜血管分割的细节增强注意力特征融合网络","authors":"Pengfei Cai, Biyuan Li, Gaowei Sun, Bo Yang, Xiuwei Wang, Chunjie Lv, Jun Yan","doi":"10.1007/s10278-024-01207-6","DOIUrl":null,"url":null,"abstract":"<p><p>Retinal vessel segmentation is crucial for the diagnosis of ophthalmic and cardiovascular diseases. However, retinal vessels are densely and irregularly distributed, with many capillaries blending into the background, and exhibit low contrast. Moreover, the encoder-decoder-based network for retinal vessel segmentation suffers from irreversible loss of detailed features due to multiple encoding and decoding, leading to incorrect segmentation of the vessels. Meanwhile, the single-dimensional attention mechanisms possess limitations, neglecting the importance of multidimensional features. To solve these issues, in this paper, we propose a detail-enhanced attention feature fusion network (DEAF-Net) for retinal vessel segmentation. First, the detail-enhanced residual block (DERB) module is proposed to strengthen the capacity for detailed representation, ensuring that intricate features are efficiently maintained during the segmentation of delicate vessels. Second, the multidimensional collaborative attention encoder (MCAE) module is proposed to optimize the extraction of multidimensional information. Then, the dynamic decoder (DYD) module is introduced to preserve spatial information during the decoding process and reduce the information loss caused by upsampling operations. Finally, the proposed detail-enhanced feature fusion (DEFF) module composed of DERB, MCAE and DYD modules fuses feature maps from both encoding and decoding and achieves effective aggregation of multi-scale contextual information. The experiments conducted on the datasets of DRIVE, CHASEDB1, and STARE, achieving Sen of 0.8305, 0.8784, and 0.8654, and AUC of 0.9886, 0.9913, and 0.9911 on DRIVE, CHASEDB1, and STARE, respectively, demonstrate the performance of our proposed network, particularly in the segmentation of fine retinal vessels.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"DEAF-Net: Detail-Enhanced Attention Feature Fusion Network for Retinal Vessel Segmentation.\",\"authors\":\"Pengfei Cai, Biyuan Li, Gaowei Sun, Bo Yang, Xiuwei Wang, Chunjie Lv, Jun Yan\",\"doi\":\"10.1007/s10278-024-01207-6\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Retinal vessel segmentation is crucial for the diagnosis of ophthalmic and cardiovascular diseases. However, retinal vessels are densely and irregularly distributed, with many capillaries blending into the background, and exhibit low contrast. Moreover, the encoder-decoder-based network for retinal vessel segmentation suffers from irreversible loss of detailed features due to multiple encoding and decoding, leading to incorrect segmentation of the vessels. Meanwhile, the single-dimensional attention mechanisms possess limitations, neglecting the importance of multidimensional features. To solve these issues, in this paper, we propose a detail-enhanced attention feature fusion network (DEAF-Net) for retinal vessel segmentation. First, the detail-enhanced residual block (DERB) module is proposed to strengthen the capacity for detailed representation, ensuring that intricate features are efficiently maintained during the segmentation of delicate vessels. Second, the multidimensional collaborative attention encoder (MCAE) module is proposed to optimize the extraction of multidimensional information. Then, the dynamic decoder (DYD) module is introduced to preserve spatial information during the decoding process and reduce the information loss caused by upsampling operations. Finally, the proposed detail-enhanced feature fusion (DEFF) module composed of DERB, MCAE and DYD modules fuses feature maps from both encoding and decoding and achieves effective aggregation of multi-scale contextual information. The experiments conducted on the datasets of DRIVE, CHASEDB1, and STARE, achieving Sen of 0.8305, 0.8784, and 0.8654, and AUC of 0.9886, 0.9913, and 0.9911 on DRIVE, CHASEDB1, and STARE, respectively, demonstrate the performance of our proposed network, particularly in the segmentation of fine retinal vessels.</p>\",\"PeriodicalId\":516858,\"journal\":{\"name\":\"Journal of imaging informatics in medicine\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of imaging informatics in medicine\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1007/s10278-024-01207-6\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of imaging informatics in medicine","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s10278-024-01207-6","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
视网膜血管分割对眼科和心血管疾病的诊断至关重要。然而,视网膜血管分布密集且不规则,许多毛细血管与背景融为一体,而且对比度低。此外,基于编码器-解码器的视网膜血管分割网络会因多次编码和解码而不可逆转地丢失细节特征,导致血管分割错误。同时,单维注意力机制存在局限性,忽略了多维特征的重要性。为了解决这些问题,本文提出了一种用于视网膜血管分割的细节增强注意力特征融合网络(DEAF-Net)。首先,我们提出了细节增强残差块(DERB)模块,以加强细节表示能力,确保在分割精细血管时有效保留复杂特征。其次,提出了多维协同注意编码器(MCAE)模块,以优化多维信息的提取。然后,引入动态解码器(DYD)模块,在解码过程中保留空间信息,减少上采样操作造成的信息损失。最后,由 DERB、MCAE 和 DYD 模块组成的细节增强特征融合(DEFF)模块融合了编码和解码的特征图,实现了多尺度上下文信息的有效聚合。在 DRIVE、CHASEDB1 和 STARE 数据集上进行的实验证明了我们所提出的网络的性能,尤其是在细小视网膜血管的分割上,其 Sen 值分别达到了 0.8305、0.8784 和 0.8654,AUC 值分别达到了 0.9886、0.9913 和 0.9911。
DEAF-Net: Detail-Enhanced Attention Feature Fusion Network for Retinal Vessel Segmentation.
Retinal vessel segmentation is crucial for the diagnosis of ophthalmic and cardiovascular diseases. However, retinal vessels are densely and irregularly distributed, with many capillaries blending into the background, and exhibit low contrast. Moreover, the encoder-decoder-based network for retinal vessel segmentation suffers from irreversible loss of detailed features due to multiple encoding and decoding, leading to incorrect segmentation of the vessels. Meanwhile, the single-dimensional attention mechanisms possess limitations, neglecting the importance of multidimensional features. To solve these issues, in this paper, we propose a detail-enhanced attention feature fusion network (DEAF-Net) for retinal vessel segmentation. First, the detail-enhanced residual block (DERB) module is proposed to strengthen the capacity for detailed representation, ensuring that intricate features are efficiently maintained during the segmentation of delicate vessels. Second, the multidimensional collaborative attention encoder (MCAE) module is proposed to optimize the extraction of multidimensional information. Then, the dynamic decoder (DYD) module is introduced to preserve spatial information during the decoding process and reduce the information loss caused by upsampling operations. Finally, the proposed detail-enhanced feature fusion (DEFF) module composed of DERB, MCAE and DYD modules fuses feature maps from both encoding and decoding and achieves effective aggregation of multi-scale contextual information. The experiments conducted on the datasets of DRIVE, CHASEDB1, and STARE, achieving Sen of 0.8305, 0.8784, and 0.8654, and AUC of 0.9886, 0.9913, and 0.9911 on DRIVE, CHASEDB1, and STARE, respectively, demonstrate the performance of our proposed network, particularly in the segmentation of fine retinal vessels.