基于深度关联机制的肝胆管超分辨率分割

doi:10.12052/gdutxb.220197

广东工业大学学报 ›› 2023, Vol. 40 ›› Issue (05): 41-46.doi: 10.12052/gdutxb.220197

基于深度关联机制的肝胆管超分辨率分割

郑煜¹, 蔡念¹, 欧阳文生¹, 谢依颖¹, 王平²

1. 广东工业大学信息工程学院，广东广州 510006;
2. 广州医科大学附属第一医院肝胆外科，广东广州 510120

收稿日期:2022-12-27 出版日期:2023-09-25 发布日期:2023-09-26
通信作者: 蔡念 (1976-),男,教授,博士生导师,主要研究方向为机器视觉、机器学习、数字信号处理等,E-mail:cainian@sina.com
作者简介:郑煜 (1998-),男,硕士研究生,主要研究方向为深度学习、医学图像处理等
基金资助:
国家自然科学基金资助项目 (82172019)；广州市科技计划项目 (202102010251)

Super-resolution Segmentation of Hepatobiliary Ducts Based on Deep Correlation Mechanism

Zheng Yu¹, Cai Nian¹, Ouyang Wen-sheng¹, Xie Yi-ying¹, Wang Ping²

1. School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China;
2. Department of Hepatobiliary Surgery, the First Affiliated Hospital of Guangzhou Medical University, Guangzhou 510120, China

Received:2022-12-27 Online:2023-09-25 Published:2023-09-26

摘要/Abstract

摘要： 肝胆管结石是常见的肝脏疾病，已成为我国非肿瘤性胆道疾病死亡的主要原因，实现对肝胆管层间插值分割重建具有重要意义。针对肝胆管等此类树状型组织器官在分割重建过程中出现断层、不连续等现象，本文提出一种基于深度关联机制的肝胆管CT(Computed Tomography)层间超分辨率分割的端到端级联框架，将层间插值网络和分割网络级联起来进行端到端训练，引入ConvLSTM来加强切片间肝胆管的高维特征信息提取，提出一种新损失函数联合插值网络和分割网络进行整个框架的优化训练。实验结果表明，相比于其他现有深度学习方法，本文方法取得了更好的肝胆管分割性能，更有利于肝胆管三维重建。

关键词: 肝胆管, 超分辨率分割, 深度关联机制, ConvLSTM

Abstract: Hepatobiliary stone disease is a common liver disease and has become the main cause of death from non-neoplastic biliary diseases in China, and it is important to achieve interpolated segmentation reconstruction between slices of hepatobiliary ducts. In this research, an end-to-end framework for super-resolution abdominal CT image processing is proposed based on deep correlation mechanism. The framework cascades an inter-slice interpolation network and a segmentation network, in which the ConvLSTM is introduced to enhance the extraction of high-dimensional feature information of hepatobiliary ducts between slices. A novel loss is designed by combining the loss of the interpolation network and the loss of the segmentation network. Experimental results show that the proposed framework is superior to the existing deep learning methods for the segmentation of hepatobiliary ducts, which is beneficial for the 3D reconstruction of hepatobiliary ducts.

Key words: hepatobiliary ducts, super-resolution segmentation, deep correlation mechanism, ConvLSTM

中图分类号:

TP391

郑煜, 蔡念, 欧阳文生, 谢依颖, 王平. 基于深度关联机制的肝胆管超分辨率分割[J]. 广东工业大学学报, 2023, 40(05): 41-46.

Zheng Yu, Cai Nian, Ouyang Wen-sheng, Xie Yi-ying, Wang Ping. Super-resolution Segmentation of Hepatobiliary Ducts Based on Deep Correlation Mechanism[J]. Journal of Guangdong University of Technology, 2023, 40(05): 41-46.

参考文献

[1] PEREIRA-LIMA J C, JAKOBS R, WINTER U H, et al. Long-term results (7 to 10 years) of endoscopic papillotomy for choledocholithiasis. Multivariate analysis of prognostic factors for the recurrence of biliary symptoms [J]. Gastrointestinal Endoscopy, 1998, 48(5): 457-464.
[2] UENO N, OZAWA Y, AIZAWA T. Prognostic factors for recurrence of bile duct stones after endoscopic treatment by sphincter dilation [J]. Gastrointestinal Endoscopy, 2003, 58(3): 336-340.
[3] 李江, 刘斌. 肝胆管结石初始外科治疗的规范化研究[J]. 临床肝胆病杂志, 2015, 31(10): 1612-1614.
LI J, LIU B. More attention to initial surgical treatment of hepatolithiasis [J]. Journal of Clinical Hepatol, 2015, 31(10): 1612-1614.
[4] 王平, 刘成成, 陶海粟, 等. 经皮肝Ⅰ期胆道造瘘取石治疗有胆道手术史患者的肝内胆管结石[J]. 中华肝胆外科杂志, 2019, 25(2): 106-110.
WANG P, LIU C C, TAO H S, et al. Percutaneous transhepatic one-step biliary fistulation for patients with hepatolithiasis and hepatobiliary surgery history [J]. Chinese Journal of Hepatobiliary Surgery, 2019, 25(2): 106-110.
[5] NAKAGAWA Y, ROSENFELD A. Some experiments on variable thresholding [J]. Pattern Recognition, 1979, 11(3): 191-204.
[6] MORE M D, ANDURKAR G K. Edge detection techniques: a comparative approach [J]. World Journal of Science and Technology, 2012, 2(4): 142-145.
[7] ZENG Y, LIAO S, TANG P, et al. Automatic liver vessel segmentation using 3D region growing and hybrid active contour model [J]. Computers in Biology and Medicine, 2018, 97: 63-73.
[8] SHEN D, WU G, SUK H I. Deep learning in medical image analysis [J]. Annual Review of Biomedical Engineering, 2017, 19(5): 221-248.
[9] FU X, CAI N, HUANG K, et al. M-net: a novel U-net with multi-stream feature fusion and multi-scale dilated convolutions for bile ducts and hepatolith segmentation [J]. IEEE Access, 2019, 7: 148645-148657.
[10] RONNEBERGER O, FISCHER P, BROX T. U-net: convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention. Munich: MICCAI, 2015: 234-241.
[11] 陈芝涛. 基于多尺度上下文特征学习的胆管及胆结石图像分割[J]. 现代计算机, 2021, 27(25): 74-78.
CHEN Z T. Bile ducts and hepatoliths segmentation via multi-scale context feature learning [J]. Modern Computer, 2021, 27(25): 74-78.
[12] KITRUNGROTSAKUL T, HAN X H, IWAMOTO Y, et al. VesselNet: a deep convolutional neural network with multi pathways for robust hepatic vessel segmentation [J]. Computerized Medical Imaging and Graphics, 2019, 75: 74-83.
[13] YAN Q, WANG B, ZHANG W, et al. Attention-guided deep neural network with multi-scale feature fusion for liver vessel segmentation [J]. IEEE Journal of Biomedical and Health Informatics, 2020, 25(7): 2629-2642.
[14] SU J, LIU Z, ZHANG J, et al. DV-Net: accurate liver vessel segmentation via dense connection model with D-BCE loss function [J]. Knowledge-Based Systems, 2021, 232: 107471.
[15] HAO W, ZHANG J, SU J, et al. HPM-Net: hierarchical progressive multiscale network for liver vessel segmentation in CT images [J]. Computer Methods and Programs in Biomedicine, 2022, 224: 107003.
[16] 杨柳, 李德玉, 何爱军, 等. 医学图像多维重建中的插值问题研究进展[J]. 生物医学工程学杂志, 2003(4): 728-732.
YANG L, LI D Y, HE A J, et al. A review of interpolation in multi-dimensional reconstruction of medical images [J]. Journal of Biomedical Engineering, 2003(4): 728-732.
[17] 闫芳. 医学影像重建算法研究及应用[D]. 济南: 山东师范大学, 2021.
[18] NIKLAUS S, MAI L, LIU F. Video frame interpolation via adaptive separable convolution[C]//IEEE/CVF International Conference on Computer Vision (ICCV). Venice: IEEE, 2017: 261-270.
[19] JIANG H, SUN D, JAMPANI V, et al. Super slomo: high quality estimation of multiple intermediate frames for video interpolation[C]// IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City: IEEE, 2018: 9000-9008.
[20] LU L, WU R, LIN H, et al. Video frame interpolation with transformer[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans: IEEE, 2022: 3532-3542.
[21] LUO Y, PAN J, TANG J. Bi-directional pseudo-three-dimensional network for video frame interpolation [J]. IEEE Transactions on Image Processing, 2022, 31: 6773-6788.
[22] OKTAY O, SCHLEMPER J, FOLGOC L L, et al. Attention u-net: learning where to look for the pancreas[EB/OL]. (2018-05-20) [2022-12-26].https://doi.org/10.48550/arXiv.1804.03999.
[23] 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.
[24] CAO H, WANG Y, CHEN J, et al. Swin-unet: unet-like pure transformer for medical image segmentation[EB/OL]. (2021-05-12) [2022-12-26]. https://doi.org/10.48550/arXiv.2105.05537.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于深度关联机制的肝胆管超分辨率分割

Super-resolution Segmentation of Hepatobiliary Ducts Based on Deep Correlation Mechanism

HTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	甘孟坤, 曾安, 张小波. 基于Swin-Unet的主动脉再缩窄预测研究[J]. 广东工业大学学报, 2023, 40(05): 34-40.
[2]	吴圳桦, 唐文艳, 吕文阁, 陈汝杰, 侯梦华, 李德源. 基于ISSA和积分图的二维熵图像多阈值分割快速算法[J]. 广东工业大学学报, 2023, 40(05): 47-55.
[3]	李杨, 周莹. 基于方向控制的差分隐私轨迹数据发布方法[J]. 广东工业大学学报, 2023, 40(05): 56-63.
[4]	梁宇辰, 蔡念, 欧阳文生, 谢依颖, 王平. 基于切片关联信息的慢性阻塞性肺疾病CT诊断[J]. 广东工业大学学报, 0, (): 2-7.
[5]	戴彬, 曾碧, 魏鹏飞, 黄永健. 改进判别式深度Dyna-Q的任务对话策略学习方法[J]. 广东工业大学学报, 2023, 40(04): 9-17,23.
[6]	钟耿君, 李东. 基于通道分离机制的双分支点云处理网络[J]. 广东工业大学学报, 2023, 40(04): 18-23.
[7]	张家悦, 张灵. 基于增量式类激活知识的蒸馏学习方法[J]. 广东工业大学学报, 2023, 40(04): 24-30,36.
[8]	吴亚迪, 陈平华. 基于用户长短期偏好和音乐情感注意力的音乐推荐模型[J]. 广东工业大学学报, 2023, 40(04): 37-44.
[9]	林哲煌, 李东. 语义引导下自适应拓扑推理图卷积网络的人体动作识别[J]. 广东工业大学学报, 2023, 40(04): 45-52.
[10]	黄晓湧, 李伟彤. 基于TSSI和STB-CNN的跌倒检测算法[J]. 广东工业大学学报, 2023, 40(04): 53-59.
[11]	陈晓荣, 杨雪荣, 成思源, 刘国栋. 基于改进Unet网络的锂电池极片表面缺陷检测[J]. 广东工业大学学报, 2023, 40(04): 60-66,93.
[12]	曹智雄, 吴晓鸰, 骆晓伟, 凌捷. 融合迁移学习与YOLOv5的安全帽佩戴检测算法[J]. 广东工业大学学报, 2023, 40(04): 67-76.
[13]	赖东升, 冯开平, 罗立宏. 基于多特征融合的表情识别算法[J]. 广东工业大学学报, 2023, 40(03): 10-16.
[14]	谢国波, 林立, 林志毅, 贺笛轩, 文刚. 基于YOLOv4-MP的绝缘子爆裂缺陷检测方法[J]. 广东工业大学学报, 2023, 40(02): 15-21.
[15]	陈靖宇, 吕毅. 基于脉冲神经网络的冷链制冷机结霜检测方法[J]. 广东工业大学学报, 2023, 40(01): 29-38.