基于形变残差和级联编码的胰腺分割模型

doi:10.3969/j.issn.1006-2475.2024.06.014

摘要/Abstract

摘要：
摘要：为解决深度卷积神经网络进行胰腺分割时存在的胰腺形状位置变化大、噪声干扰、部分小目标等问题，提出一种结合可形变收缩残差块（Deformable Shrinkage Residual Block，DSRB）与级联编码模块（Cascading Encoding Module，CEM）的胰腺分割模型DC U-net。该模型利用2个可形变卷积、注意力机制以及残差结构设计了DSRB，通过可形变卷积来解决胰腺形状位置变化大的问题，使用软阈值化来减少噪声干扰；采用CEM来进行特征融合，对编码特征进行复用以降低编解码阶段的特征差异度，加强对小目标特征的学习。在NIH公开数据集上的实验结果表明，本文模型DC U-net的平均Dice相似系数（Dice Similarity Coefficient， DSC）达到87.26%，平均交并比（Intersection Over Union， IOU）达到77.98%，分割精度优于对比模型。

关键词: 关键词：图像分割, 胰腺分割, 可形变收缩残差块, 级联编码模块, 特征融合

Abstract: Abstract： In order to solve the problems of large pancreatic shape and position change， noise interference， and some small targets in pancreas segmentation by deep convolutional neural networks， a pancreatic segmentation model DC U-net combining deformable shrinkage residual block （DSRB） and cascading encoding module （CEM） is proposed. The DSRB is designed by using two deformable convolutions， an attention mechanism， and a residual structure. This method solves the problem of large changes in pancreatic shape and position through deformable convolution， and uses soft thresholding to reduce noise interference. CEM is used to fuse features， and the coding features are multiplexed to reduce the feature differentiation in the encoding and decoding stage， and strengthen the learning of small target features. The experimental results on the NIH public dataset show that the proposed DC U-net model achieves an average Dice similarity coefficient （DSC） of 87.26%， the average section over union （IOU） of 77.98%， and the segmentation accuracy is better than that of the comparison model.

Key words: Key words： image segmentation, pancreas segmentation, deformable shrinkage residual block, cascading encoding module, feature fusion

中图分类号:

TP391.41

朱纷, 何立风, 孙爽, 张梦颖, 于佳佳. 基于形变残差和级联编码的胰腺分割模型[J]. 计算机与现代化, 2024, 0(06): 83-88.

ZHU Fen, HE Lifeng, SUN Shuang, ZHANG Mengying, YU Jiajia. Pancreas Segmentation Model Based on Deformable Residual and Cascading Encoding[J]. Computer and Modernization, 2024, 0(06): 83-88.

参考文献

［1］ SINDHU A， RADHA V. Pancreatic tumour segmentation in recent medical imaging–an overview［J］. Computational Vision and Bio-Inspired Computing： ICCVBIC 2019， 2020：514-522.
［2］ YAO X， SONG Y Q， LIU Z. Advances on pancreas segmentation： a review［J］. Multimedia Tools and Applications， 2020，79：6799-6821.
［3］ CARDOBI N， DAL Palù A， PEDRINI F， et al. An overview of artificial intelligence applications in liver and pancreatic imaging［J］. Cancers， 2021，13（9）：2162.
［4］ CAI L， GAO J Y， ZHAO D. A review of the application of deep learning in medical image classification and segmentation［J］. Annals of Translational Medicine， 2020，8（11）：713-727.
［5］ KUMAR H， DESOUZA S V， PETROV M S. Automated pancreas segmentation from computed tomography and magnetic resonance images： A systematic review［J］. Computer Methods and Programs in Biomedicine， 2019，178：319-328.
［6］马豪，刘彦，张俊然. 基于模型压缩与重构U-net的胰腺分割［J］. 计算机工程与设计， 2022，43（7）：1998-2006.
［7］ LI M Y， LIAN F H， WANG C Y， et al. Dual adversarial convolutional networks with multilevel cues for pancreatic segmentation［J］. Physics in Medicine & Biology， 2021，66（17）：175025.
［8］曹路洋，李建微. 面向深度学习的胰腺医学图像分割方法研究进展［J］. 小型微型计算机系统， 2022，43（12）：2591-2604.
［9］ LONG J， SHELHAMER E， DARRELL T. Fully convolutional networks for semantic segmentation［C］// Proceedings of the IEEE conference on computer vision and pattern recognition. 2015：3431-3440.
［10］ 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， Springer， 2015：234-241.
［11］ ZHOU Z， RAHMAN Siddiquee M M， TAJBAKHSH N， et al. Unet++： A nested u-net architecture for medical image segmentation［C］// Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support： 4th International Workshop， DLMIA 2018， and 8th International Workshop， Springer， 2018：3-11.
［12］ OKTAY O， SCHLEMPER J， FOLGOC L L， et al. Attention U-Net： Learning where to look for the pancreas［J］. arXiv preprint arXiv：1804.03999， 2018.
［13］ VASWANI A， SHAZEER N， PARMAR N， et al. Attention is all you need［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Curran Associates Inc， 2017：6000-6010.
［14］ DIAKOGIANNIS F I， WALDNER F， CACCETTA P， et al. ResUNet-a： A deep learning framework for semantic segmentation of remotely sensed data［J］. ISPRS Journal of Photogrammetry and Remote Sensing， 2020，162：94-114.
［15］毕秀丽，陆猛，肖斌，等. 基于双解码U型卷积神经网络的胰腺分割［J］. 软件学报， 2022，33（5）：1947-1958.
［16］ DAI J， QI H， XIONG Y， et al. Deformable convolutional networks［C］// Proceedings of the IEEE International Conference on Computer Vision. IEEE， 2017：764-773.
［17］ ZHAO M H， ZHONG S S， FU X Y， et al. Deep residual shrinkage networks for fault diagnosis［J］. IEEE Transactions on Industrial Informatics， IEEE， 2019，16（7）：4681-4690.
［18］ LI W S， QIN S Y， LI F， et al. MAD-UNet： A deep U-shaped network combined with an attention mechanism for pancreas segmentation in CT images［J］. Medical Physics， 2021，48（1）：329-341.
［19］ QIU C J， SONG Y Q， LIU Z， et al. CMFCUNet： Cascaded multi-scale feature calibration UNet for pancreas segmentation［J］. Multimedia Systems， 2023，29（2）：871-886.
［20］ LIU H， FOYGEL Barber R. Between hard and soft thresholding： optimal iterative thresholding algorithms［J］. Information and Inference： A Journal of the IMA， 2020，9（4）：899-933.
［21］ FAN D P， ZHOU T， JI G P， et al. Inf-net： Automatic covid-19 lung infection segmentation from ct images［J］. IEEE Transactions on Medical Imaging， 2020，39（8）：2626-2637.
［22］ TRINH M N， NGUYEN N T， TRAN T T， et al. A deep learning-based approach with image-driven active contour loss for medical image segmentation［C］// Proceedings of International Conference on Data Science and Applications： ICDSA 2021. Springer Singapore， 2022：1-12.
［23］ WANG G， PENG Y， ZHANG S， et al. Pyramid self-attention mechanism-based change detection in hyperspectral imagery［J］. Journal of Applied Remote Sensing， 2021，15（4）：042611-042611.
［24］ MAN Y， HUANG Y， FENG J， et al. Deep Q learning driven CT pancreas segmentation with geometry-aware U-Net［J］. IEEE transactions on medical imaging， 2019，38（8）：1971-1980.
［25］ HASAN S M K， LINTE C A. A modified U-Net convolutional network featuring a nearest-neighbor re-sampling-based elastic-transformation for brain tissue characterization and segmentation［C］// 2018 IEEE Western New York Image and Signal Processing Workshop （WNYISPW）. IEEE， 2018：1-5.
［26］ SANFORD T H， ZHANG L， HARMON S A， et al. Data augmentation and transfer learning to improve generalizability of an automated prostate segmentation model［J］. AJR. American journal of roentgenology， 2020，215（6）：1403.
［27］ ROSEBROCK A. Intersection over Union （IoU） for object detection［EB/OL］.［2016-11-07］［2023-05-03］. https//www.pyimagesearch.com/2016/11/07/intersection-over-union-iou-for-object-detection.
［28］向智霆，刘剑聪，魏柳，等. 基于全局特征U-net的胰腺图像分割［J］. 重庆邮电大学学报（自然科学版）， 2022，34（02）：216-222.

[1]	张思敏, 刘新妹, 殷俊龄, 李宝玲. 基于YOLOv7改进的PCB缺陷检测方法[J]. 计算机与现代化, 2024, 0(12): 45-52.
[2]	马钰, 杨勇, 任鸽, 帕力旦·吐尔逊. 基于GCN和微调BERT的作文自动评分方法[J]. 计算机与现代化, 2024, 0(09): 33-37.
[3]	陈俊义. 基于图节点动静态特征的健康事件预测模型[J]. 计算机与现代化, 2023, 0(10): 39-44.