Cerebrovascular segmentation from mesoscopic optical images using Swin Transformer

被引:7
作者
Li, Yuxin [1 ]
Zhang, Qianlong [1 ]
Zhou, Hang [2 ]
Li, Junhuai [1 ]
Li, Xiangning [3 ,4 ]
Li, Anan [3 ,4 ]
机构
[1] Xian Univ Technol, Sch Comp Sci & Engn, Shaanxi Key Lab Network Comp & Secur Technol, Xian 710048, Peoples R China
[2] Chengdu Univ Informat Technol, Sch Comp Sci, Chengdu 610225, Peoples R China
[3] Huazhong Univ Sci & Technol, Britton Chance Ctr Biomed Photon, Wuhan Natl Lab Optoelect, MoE Key Lab Biomed Photon, Wuhan 430074, Peoples R China
[4] HUST, Suzhou Inst Brainsmat, Suzhou 215123, Peoples R China
基金
中国国家自然科学基金;
关键词
Vascular segmentation; Swin Transformer; mesoscopic optical imaging; fMOST; VESSEL SEGMENTATION; ENHANCEMENT;
D O I
10.1142/S1793545823500098
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
Vascular segmentation is a crucial task in biomedical image processing, which is significant for analyzing and modeling vascular networks under physiological and pathological states. With advances in fluorescent labeling and mesoscopic optical techniques, it has become possible to map the whole-mouse-brain vascular networks at capillary resolution. However, segmenting vessels from mesoscopic optical images is a challenging task. The problems, such as vascular signal discontinuities, vessel lumens, and background fluorescence signals in mesoscopic optical images, belong to global semantic information during vascular segmentation. Traditional vascular segmentation methods based on convolutional neural networks (CNNs) have been limited by their insufficient receptive fields, making it challenging to capture global semantic information of vessels and resulting in inaccurate segmentation results. Here, we propose SegVesseler, a vascular segmentation method based on Swin Transformer. SegVesseler adopts 3D Swin Transformer blocks to extract global contextual information in 3D images. This approach is able to maintain the connectivity and topology of blood vessels during segmentation. We evaluated the performance of our method on mouse cerebrovascular datasets generated from three different labeling and imaging modalities. The experimental results demonstrate that the segmentation effect of our method is significantly better than traditional CNNs and achieves state-of-the-art performance.
引用
收藏
页数:14
相关论文
共 35 条
  • [1] Neuronal and Vascular Interactions
    Andreone, Benjamin J.
    Lacoste, Baptiste
    Gu, Chenghua
    [J]. ANNUAL REVIEW OF NEUROSCIENCE, VOL 38, 2015, 38 : 25 - 46
  • [2] Aydin O. U., 2020, ARXIV
  • [3] Cao Hu, 2023, Computer Vision - ECCV 2022 Workshops: Proceedings. Lecture Notes in Computer Science (13803), P205, DOI 10.1007/978-3-031-25066-8_9
  • [4] Generative Consistency for Semi-Supervised Cerebrovascular Segmentation From TOF-MRA
    Chen, Cheng
    Zhou, Kangneng
    Wang, Zhiliang
    Xiao, Ruoxiu
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2023, 42 (02) : 346 - 353
  • [5] VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images
    Chen, Hao
    Dou, Qi
    Yu, Lequan
    Qin, Jing
    Heng, Pheng-Ann
    [J]. NEUROIMAGE, 2018, 170 : 446 - 455
  • [6] Chen J, 2021, ARXIV
  • [7] Accurate Vessel Segmentation With Constrained B-Snake
    Cheng, Yuanzhi
    Hu, Xin
    Wang, Ji
    Wang, Yadong
    Tamura, Shinichi
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2015, 24 (08) : 2440 - 2455
  • [8] Cicek Ozgun, 2016, Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016. 19th International Conference. Proceedings: LNCS 9901, P424, DOI 10.1007/978-3-319-46723-8_49
  • [9] Automatic Graph-Based Modeling of Brain Microvessels Captured With Two-Photon Microscopy
    Damseh, Rafat
    Pouliot, Philippe
    Gagnon, Louis
    Sakadzic, Sava
    Boas, David
    Cheriet, Farida
    Lesage, Frederic
    [J]. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2019, 23 (06) : 2551 - 2562
  • [10] Frangi AF, 1998, LECT NOTES COMPUT SC, V1496, P130, DOI 10.1007/BFb0056195