3D-SPRNet: 一种基于并行解码器和双注意力机制的胆囊癌分割模型

doi:10.3969/j.issn.1006-2475.2023.12.011

计算机与现代化 ›› 2023, Vol. 0 ›› Issue (12): 59-66.doi: 10.3969/j.issn.1006-2475.2023.12.011

3D-SPRNet: 一种基于并行解码器和双注意力机制的胆囊癌分割模型

（1.上海理工大学健康科学与工程学院，上海 200093; 2.上海交通大学医学院附属新华医院普外科，上海 200092）

出版日期:2023-12-24 发布日期:2024-01-29
作者简介:张浩洋（2000—），男，山东临沂人，本科生，研究方向:医学图像处理，E-mail: 331361966@qq.com；通信作者:尹梓名（1986—），男，辽宁沈阳人，副教授，博士，研究方向:医学人工智能，医学图像处理，E-mail: yinziming1@163.com；乐珺怡（2000—），女，浙江宁波人，本科生，研究方向:医学图像处理，E-mail: GypsophilaL7@163.com；沈达聪（1997—），男，浙江宁波人，硕士研究生，研究方向:医学图像处理，E-mail: 1842853105@qq.com；束翌俊（1988—），男，上海人，副主任医师，博士，研究方向:消化系统恶性肿瘤的诊治，E-mail: shuyijun19881125@163.com；杨自逸（1992—），男，四川乐山人，住院医师，博士，研究方向:消化系统恶性肿瘤的诊治，E-mail: alvin_yzy@foxmail.com；孔祥勇（1979—），男，山东曲阜人，讲师，硕士，研究方向:智能医疗，E-mail: kxy@usst.edu.cn；龚伟（1969—），男，上海人，主任医师，博士生导师，博士，研究方向:肝胆胰恶性肿瘤的诊治，E-mail: gongwei@xinhuamed.com.cn。
基金资助:
上海市市级科技重大专项项目（2021SHZDZX）；国家重点研发计划项目（2022YFC3601101）

3D-SPRNet: Segmentation Model of Gallbladder Cancer Based on Parallel Decoder and Double Attention Mechanism

（1. School of Health Science and Engineering， University of Shanghai for Science and Technology， Shanghai 200093， China；
2. Department of General Surgery， Xinhua Hospital Affiliated to Shanghai Jiaotong University School of Medicine， Shanghai 200092， China）

Online:2023-12-24 Published:2024-01-29

摘要/Abstract

摘要： 摘要：利用深度学习对胆囊CT癌变部分进行分割，能够为临床医生提供诊断参考。现有方法均采用二维影像切片作为输入，缺少空间上下文信息以及对癌变边界区域的细化。为提高边界分割的准确性，保证空间信息的连续性，本文提出3D-SPRNet胆囊癌分割模型：采用并行解码器提取多尺度高级特征并解码；使用通道注意力帮助网络强调特征提取信息；利用反向注意力关注未被预测的区域，逐步细化癌变边界。选取304位来自上海交通大学医学院附属新华医院胆囊癌患者的CT影像进行实验，得到的MIoU、IoU及Dice系数分别为0.85、0.70、0.83，优于大多数主流分割网络，通过消融实验验证各模块的有效性。实验结果表明，本文提出的网络模型能够改善分割边界粗糙的问题，提高胆囊癌变部分的分割精度。

关键词: 关键词：计算机断层扫描, 胆囊癌, 通道注意力机制, 并行解码器, 反向注意力机制

Abstract: Abstract: The segmentation of cancerous part of gallbladder CT based on deep learning could be used as a diagnostic reference for clinicians. In existing methods， two-dimensional image slices that lack spatial context information are universally adopted as input. Meanwhile， the boundary segmentation is not accurate enough because of lacking the refinement of the cancer boundary region. In order to increase the accuracy of boundary segmentation and guarantee the continuity of spatial information， a 3D-SPRNet segmentation model for gallbladder carcinoma is proposed. A parallel decoder is used to extract and decode multi-scale advanced features. Channel attention is used to help network emphasize feature extraction information. Reverse attention is used to focus on the unpredicted region and gradually refine the cancer boundary. The CT images of 304 patients with gallbladder cancer from Xinhua Hospital Affiliated to Shanghai Jiaotong University School of Medicine are selected for the experiment. The MIoU， IoU and Dice coefficients obtained are 0.85， 0.70 and 0.83， respectively， which are better than those of most mainstream segmentation networks. The effectiveness of each module has been verified by ablation experiment. The experimental results show that the network model proposed in this paper can improve the problem of rough segmentation boundaries and increase the segmentation accuracy of gallbladder carcinoma.

Key words: Key words: computed tomography, gallbladder cancer, channel attention mechanism, parallel decoder, reverse attention mechanism

中图分类号:

TP391

张浩洋, 尹梓名, 乐珺怡, 沈达聪, 束翌俊, 杨自逸, 孔祥勇, 龚伟. 3D-SPRNet: 一种基于并行解码器和双注意力机制的胆囊癌分割模型[J]. 计算机与现代化, 2023, 0(12): 59-66.

ZHANG Hao-yang, YIN Zi-ming, LE Jun-yi, SHEN Da-cong, SHU Yi-jun, YANG Zi-yi, . 3D-SPRNet: Segmentation Model of Gallbladder Cancer Based on Parallel Decoder and Double Attention Mechanism[J]. Computer and Modernization, 2023, 0(12): 59-66.

参考文献［26］

［1］	RAWLA P， SUNKARA T， THANDRA K C， et al. Epidemiology of gallbladder cancer［J］. Clinical and Experimental Hepatology， 2019，5（2）:93-102.
［2］	李永盛，李茂岚，刘颖斌. 胆囊癌相关基础研究现状与展望［J］. 中国实用外科杂志， 2021，41（1）:52-55.
［3］	FITZMAURICE C， ABATE D， ABBASI N， et al. Global， regional， and national cancer incidence， mortality， years of life lost， years lived with disability， and disability-adjusted life-years for 29 cancer groups， 1990 to 2017: A systematic analysis for the global burden of disease study［J］. JAMA Oncology， 2019，5（12）:1749-1768.
［4］	KRELL R W， WEI A C. Gallbladder cancer: Surgical management［J］. Chinese Clinical Oncology， 2019，8（4）. DOI: 10.21037/cco.2019.06.06.
［5］	MAJI D， SIGEDAR P， SINGH M. Attention res-UNet with guided decoder for semantic segmentation of brain tumors［J］. Biomedical Signal Processing and Control， 2022，71（Part A）. DOI: 10.1016/j.bspc.2021.103077.
［6］	LEE H， PARK J， HWANG J Y. Channel attention module with multiscale grid average pooling for breast cancer segmentation in an ultrasound image［J］. IEEE Transactions on Ultrasonics， Ferroelectrics， and Frequency Control， 2020，67（7）:1344-1353.
［7］	FAN D P， JI G P， ZHOU T， et al. PraNet: Parallel reverse attention network for polyp segmentation［C］// Proceedings of the 2020 International Conference on Medical Image Computing and Computer-Assisted Intervention. 2020:263-273.
［8］	HUANG Y F， XU Z Z， YAN C R. Automatic gallbladder location and segmentation based on anatomical knowledge［J］. Applied Mechanics and Materials， 2014，556-562:4697-4700.
［9］	LIAN J， MA Y D， MA Y R， et al. Automatic gallbladder and gallstone regions segmentation in ultrasound image［J］. International Journal of Computer Assisted Radiology and Surgery， 2017，12（4）:553-568.
［10］	SHEN N Y， WANG Z Y， LI J， et al. Multi-organ segmentation network for abdominal CT images based on spatial attention and deformable convolution［J］. Expert Systems with Applications， 2023，211. DOI: 10.1016/j.eswa.2022.
	118625.
［11］	金哲川，李起，张东，等. 基于nnU-Net的临床影像组学模型对胆囊癌预后的预测价值［J］. 中华消化外科杂志， 2022，21（5）:656-664.
［12］	尹梓名，刘颖斌，束翌俊，等. 基于深度神经网络Mask R-CNN胆囊癌辅助识别系统临床应用价值研究［J］. 中国实用外科杂志， 2021，41（3）:310-314.
［13］	BASU S， GUPTA M， RANA P， et al. Surpassing the human accuracy: Detecting gallbladder cancer from USG images with curriculum learning［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. 2022:20854-20864.
［14］	HE K M， ZHANG X Y， REN S Q， et al. Deep residual learning for image recognition［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. 2016:770-778.
［15］	ULYANOV D， VEDALDI A， LEMPITSKY V. Improved texture networks: Maximizing quality and diversity in feed-forward stylization and texture synthesis［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. 2017:4105-4113.
［16］	XU J， LI Z S， DU B W， et al. Reluplex made more practical: Leaky ReLU［C］// Proceedings of the 2020 IEEE Symposium on Computers and communications （ISCC）. 2020. DOI: 10.1109/ISCC50000.2020.9219587.
［17］	ABRAHAM N， KHAN N M. A novel focal Tversky loss function with improved attention U-Net for lesion segmentation［C］// Proceedings of the 2019 IEEE 16th International Symposium on Biomedical Imaging （ISBI 2019）. 2019:683-687.
［18］	CAI Y T， WANG Y. MA-Unet: An improved version of Unet based on multi-scale and attention mechanism for medical image segmentation［C］// Proceedings of the 3rd International Conference on Electronics and Communication； Network and Computer Technology （ECNCT 2021）. 2022:205-211.
［19］	HU J， SHEN L， SUN G. Squeeze-and-excitation networks［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. 2018:7132-7141.
［20］	ZEILER M D， FERGUS R. Visualizing and understanding convolutional networks［C］// Proceedings of the 2014 European Conference on Computer Vision （ECCV）. 2014:818-833.
［21］	WU Z， SU L， HUANG Q M. Cascaded partial decoder for fast and accurate salient object detection［C］// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. 2019:3902-3911.
［22］	LIU S T， HUANG D， WANG Y H. Receptive field block net for accurate and fast object detection［C］// Proceedings of the 2018 European Conference on Computer Vision （ECCV）. 2018:404-419.
［23］	CHEN S H， TAN X L， WANG B， et al. Reverse attention for salient object detection［C］// Proceedings of the 2018 European Conference on Computer Vision （ECCV）. 2018:236-252.
［24］	CICEK O， ABDULKADIR A， LIENKAMP S S， et al. 3D U-Net: Learning dense volumetric segmentation from sparse annotation［C］// Proceedings of the 2016 International Conference on Medical Image Computing and Computer-Assisted Intervention. 2016:424-432.
［25］	YU L Q， YANG X， CHEN H， et al. Volumetric convNets with mixed residual connections for automated prostate segmentation from 3D MR images［C］// Proceedings of the 31st AAAI Conference on Artificial Intelligence. 2017:66-72.
［26］	RUIZ J， MAHMUD M， MODASSHIR M， et al. 3D DenseNet ensemble in 4-way classification of Alzheimer’s disease［C］// Proceedings of the 2020 International Conference on Brain Informatics. 2020:85-96.

[1]	梁正友, 耿经邦, 孙宇. 基于改进残差网络的交通标志识别算法[J]. 计算机与现代化, 2022, 0(04): 52-57.
[2]	李传栋, 邱磊, 于雁. 基于改进残差密集网络的心律失常自动分类[J]. 计算机与现代化, 2021, 0(11): 106-111.
[3]	李国进, 荣誉. 基于DCN-SERes-YOLOv3的人脸佩戴口罩检测算法[J]. 计算机与现代化, 2021, 0(09): 12-20.

3D-SPRNet: 一种基于并行解码器和双注意力机制的胆囊癌分割模型

3D-SPRNet: Segmentation Model of Gallbladder Cancer Based on Parallel Decoder and Double Attention Mechanism

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献［26］

相关文章 3

编辑推荐

Metrics

本文评价

3D-SPRNet: 一种基于并行解码器和双注意力机制的胆囊癌分割模型

3D-SPRNet: Segmentation Model of Gallbladder Cancer Based on Parallel Decoder and Double Attention Mechanism

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 ［26］

相关文章 3

编辑推荐

Metrics

本文评价

参考文献［26］