武汉科技大学计算机科学与技术学院;武汉科技大学大数据科学与工程研究院;武汉科技大学智能信息处理与实时工业系统湖北省重点实验室;武汉科技大学附属天佑医院;
肝脏器官尺度多样且与周围器官高度相似，很难从腹部计算机影像中准确分割出肝脏区域，现有的很多方法将CNN和Transformer相结合以得到图像局部和全局特征依赖关系，从而取得了更好的性能。然而，简单的组合方法忽视了图像分割中多尺度特征融合和注意力机制的重要性，没有很好地解决肝脏分割问题。该文提出了一种用于肝脏分割的多尺度空间Transformer与交叉自注意机制的三维肝脏影像分割方法。该方法首先采用CNN和Transformer相结合的方式逐步提取不同尺度的特征信息使网络对肝脏及其周围组织的识别更加准确；接着利用多尺度空间Transformer对不同层次和尺度特征的图像在空间维度上融合，提高了网络对肝脏边缘的定位能力；最后在解码器中设计了交叉自注意引导融合模块减少噪声等不相关信息带来的干扰，提高分割质量。在LiTS、CHAOS、Sliver07和某医院MRI数据集上进行了对比和消融实验，实验结果表明，该方法相较于当前的主流网络具有更好的分割性能和临床应用前景。
| 310 | 0 | 309 |
| 下载次数 | 被引频次 | 阅读次数 |
[1] FU M,XU P,LI X,et al.Fast crowd density estimation with convolutional neural networks[J].Engineering Applications of Artificial Intelligence,2015,43:81-88.
[2] RONNEBERGER O,FISCHER P,BROX T.U-net:convolutional networks for biomedical image segmentation[C]//Medical image computing and computer-assisted intervention–MICCAI 2015:18th international conference.Munich:Springer International Publishing,2015:234-241.
[3] ?I?EK ?,ABDULKADIR A,LIENKAMP S S,et al.3D U-Net:learning dense volumetric segmentation from sparse annotation[C]//Medical image computing and computer-assisted intervention–MICCAI 2016:19th international conference.Athens:Springer International Publishing,2016:424-432.
[4] XIAO X,LIAN S,LUO Z,et al.Weighted res-unet for high-quality retina vessel segmentation[C]//2018 9th international conference on information technology in medicine and education (ITME).Hangzhou:IEEE,2018:327-331.
[5] ZHOU Z,SIDDIQUEE M M R,TAJBAKHSH N,et al.Unet++:redesigning skip connections to exploit multiscale features in image segmentation[J].IEEE Transactions on Medical Imaging,2019,39(6):1856-1867.
[6] HAN K,XIAO A,WU E,et al.Transformer in transformer[J].Advances in Neural Information Processing Systems,2021,34:15908-15919.
[7] DOSOVITSKIY A,BEYER L,KOLESNIKOV A,et al.An image is worth 16x16 words:transformers for image recognition at scale[J].arXiv:2010.11929,2020.
[8] LIU Z,LIN Y,CAO Y,et al.Swin transformer:hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF international conference on computer vision.Montreal:IEEE,2021:10012-10022.
[9] WANG W,CHEN C,DING M,et al.Transbts:multimodal brain tumor segmentation using transformer[C]//Medical image computing and computer assisted intervention–MICCAI 2021:24th international conference.Strasbourg:Springer International Publishing,2021:109-119.
[10] ZHANG Y,LIU H,HU Q.Transfuse:fusing transformers and CNNS for medical image segmentation[C]//Medical image computing and computer assisted intervention–MICCAI 2021:24th international conference.Strasbourg:Springer International Publishing,2021:14-24.
[11] CHEN J,LU Y,YU Q,et al.Transunet:transformers make strong encoders for medical image segmentation[J].arXiv:2102.04306,2021.
[12] ZHANG X,PU L,WAN L,et al.DS-MSFF-Net:dual-path self-attention multi-scale feature fusion network for CT image segmentation[J].Applied Intelligence,2024,54(6):4490-4506.
[13] OKTAY O,SCHLEMPER J,FOLGOC L L,et al.Attention u-net:learning where to look for the pancreas[J].arXiv:1804.03999,2018.
[14] WANG H,CAO P,WANG J,et al.Uctransnet:rethinking the skip connections in u-net from a channel-wise perspective with transformer[C]//Proceedings of the AAAI conference on artificial intelligence.Virtual:AAAI,2022:2441-2449.
[15] YANG H,YANG D.CSwin-PNet:a CNN-Swin transformer combined pyramid network for breast lesion segmentation in ultrasound images[J].Expert Systems with Applications,2023,213:119024.
[16] LIU Z,HU H,LIN Y,et al.Swin transformer v2:Scaling up capacity and resolution[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.New Orleans:IEEE,2022:12009-12019.
[17] BILIC P,CHRIST P,LI H B,et al.The liver tumor segmentation benchmark (lits)[J].Medical Image Analysis,2023,84:102680.
[18] 帖军，朱祖桐，郑禄，等.基于混合空洞卷积与特征融合的肝脏肿瘤图像分割[J].电子测量技术，2023,46(22):122-130.
[19] 云飞，殷雁君.改进Attention-UNet的多尺度肝脏CT图像分割[J].内蒙古师范大学学报：自然科学汉文版，2023,52(2):175-180.
[20] LEI T,ZHOU W,ZHANG Y,et al.Lightweight v-net for liver segmentation[C]//ICASSP 2020-2020 IEEE international conference on acoustics,speech and signal processing (ICASSP).Barcelona:IEEE,2020:1379-1383.
[21] LIU L,SU J,LIU H L,et al.MAU-Net:a multiscale attention encoder-decoder network for liver and liver-tumor segmentation[C]//Proceedings of the 2022 5th international conference on image and graphics processing.Beijing:Association for Computing Machinery,2022:202-208.
[22] HATAMIZADEH A,TANG Y,NATH V,et al.Unetr:transformers for 3d medical image segmentation[C]//Proceedings of the IEEE/CVF winter conference on applications of computer vision.Waikoloa:IEEE,2022:574-584.
[23] ZHANG M,ZHANG X,DENG H,et al.A segmentation method of 3D liver image based on multi-scale feature fusion and coordinate attention mechanism[C]//International conference on intelligent computing.Singapore:Springer Nature Singapore,2023:3-15.
[24] 王峰，邹俊忠.一种结合注意力残差的肝脏及肝肿瘤分割算法[J].计算机应用与软件，2024,41(1):183-189.
[25] HATAMIZADEH A,NATH V,TANG Y,et al.Swin unetr:swin transformers for semantic segmentation of brain tumors in MRI images[C]//International MICCAI brainlesion workshop.[s.l.]:Springer International Publishing,2021:272-284.
[26] SHAO S,ZHANG X,CHENG R,et al.Semantic segmentation method of 3D liver image based on contextual attention model[C]//2021 IEEE international conference on systems,man,and cybernetics (SMC).Melbourne:IEEE,2021:3042-3049.
[27] 郑帅，张晓龙，邓鹤，等.基于多尺度特征融合和网格注意力机制的三维肝脏影像分割方法 [J].计算机应用，2023,43(7):2303-2310.
基本信息:
DOI：10.20165/j.cnki.ISSN1673-629X.2024.0302
中图分类号:R816.5;TP18;TP391.41
引用信息:
[1]丁厚林,张晓龙,林晓丽等.基于多尺度空间Transformer的肝脏分割方法[J].计算机技术与发展,2025,35(02):1-8.DOI:10.20165/j.cnki.ISSN1673-629X.2024.0302.
基金信息:
国家自然科学基金项目(61972299,62071456)