您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（工学版）》

山东大学学报 (工学版) ›› 2024, Vol. 54 ›› Issue (6): 8-18.doi: 10.6040/j.issn.1672-3961.0.2023.174

• 机器学习与数据挖掘 • 上一篇    

基于双解码器的医学图像分割模型

刘全金1,嵇文1,胡浪涛1,黄汇磊1,杨瑞1,李翔2,3,高泽文2,3,魏本征2,3*   

  1. 1.安庆师范大学电子工程与智能制造学院, 安徽 安庆 246133;2.山东中医药大学医学人工智能研究中心, 山东 青岛 266112;3.山东中医药大学青岛中医药科学院, 山东 青岛 266112
  • 发布日期:2024-12-26
  • 作者简介:刘全金(1971— ),男,安徽寿县人,教授,硕士生导师,博士,主要研究方向为机器学习、医学图像处理、智能无线通信. E-mail:liuquanjin@aqnu.edu.cn. *通信作者简介:魏本征(1976— ),男,山东临沂人,教授,博士生导师,博士,主要研究方向为医学人工智能、计算医学、机器学习等. E-mail:wbz99@sina.com
  • 基金资助:
    国家自然科学基金资助项目(62372280,61872225);山东省自然科学基金资助项目(ZR2020KF013,ZR2020ZD44,ZR2019ZD04,ZR2020QF043);山东省高校青创引才育才计划资助项目(2019-173);青岛市科技惠民示范专项资助项目(23-2-8-smjk-2-nsh)

Medical image segmentation model based on double decoder

LIU Quanjin1, JI Wen1, HU Langtao1, HUANG Huilei1, YANG Rui1, LI Xiang2,3, GAO Zewen2,3, WEI Benzheng2,3*   

  1. 1. School of Electronic Engineering and Intelligent Manufacturing, Anqing Normal University, Anqing 246133, Anhui, China;
    2. Center for Medical Artificial Intelligence, Shandong University of Traditional Chinese Medicine, Qingdao 266112, Shandong, China;
    3. Qingdao Academy of Chinese Medical Sciences, Shandong University of Traditional Chinese Medicine, Qingdao 266112, Shandong, China
  • Published:2024-12-26

PDF (PC)

13

摘要： 针对医学图像目标区域尺度不一及有标签医学图像样本少的问题,提出一种基于双解码器的医学图像分割模型(dual-decoding Swin-Unet, DDS-UNet)。DDS-UNet模型以Swin Transformer模块构建编码器,提取医学图像多尺度特征;解码器1利用Swin Transformer模块全局和远程语义特征提取优势,在上采样过程中逐级恢复并聚合编码器输出的对应尺度特征信息;解码器2利用卷积神经网络(convolutional neural networks, CNN)的局部特征提取优势,在上采样过程中逐级恢复医学图像空间信息;特征融合模块利用空洞卷积分解编码器输出的深层语义特征信息,并在上采样过程中协同融合双解码器输出的多尺度特征信息,重建医学图像目标区域的空间细节信息。脊柱和脑胶质瘤图像分割试验结果表明,DDS-UNet模型对目标区域具有优异的特征提取和分割能力。消融试验进一步验证DDS-UNet模型对医学图像分割的有效性。

关键词: 医学图像分割, 双解码器, Swin Transformer, 空洞卷积, 多尺度特征融合

中图分类号: 

  • TP391
[1] SHAMSHAD F, KHAN S, ZAMIR S W, et al. Transformers in medical imaging: a survey[J]. Medical Image Analysis, 2023, 88: 102802.
[2] BAUR D, KROBOTH K, HEYDE C, et al. Convolutional neural networks in spinal magnetic resonance imaging: a systematic review[J]. World Neurosurgery, 2022, 166: 60-70.
[3] AHIR B K, NGELHARD H H, AKKA S S. Tumor development and angiogenesis in adult brain tumor: glioblastoma[J]. Molecular Neurobiology, 2020, 57: 2461-2478.
[4] LOUIS D N, PERRY A, WESSELING P, et al. The 2021 WHO classification of tumors of the central nervous system: a summary[J]. Neuro-Oncology, 2021, 23(8): 1231-1251.
[5] OLAF R, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C] //Proceedings of the 18th Medical Image Computing and Computer-Assisted Intervention. Munich, Germany: MICCAI, 2015: 234-241.
[6] VALANARASU J M J, OZA P, HACIHALILOGLU I, et al. Medical Transformer: gated axial-attention for medical image segmentation[C] //Proceedings of the 24th Medical Image Computing and Computer Assisted Intervention. Strasbourg, France: MICCAI, 2021: 36-46.
[7] OKTAY O, SCHLEMPER J, FOLGOC L L, et al. Attention U-Net: learning where to look for the pancreas[EB/OL].(2018-05-20)[2023-07-08]. https://arxiv.org/abs/1804.03999.
[8] HUANG X, CHEN J, CHEN M, et al. TDD-UNet: Transformer with double decoder UNet for COVID-19 lesions segmentation[J]. Computers in Biology and Medicine, 2022, 151: 106306.
[9] 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. BI Xiuli, LU Meng, XIAO Bin, et al. Pancreas segmentation based on dual-decoding U-Net[J]. Journal of Software, 2022, 33(5): 1947-1958.
[10] 苏赋, 方东, 王龙业, 等. 基于双解码路径DD-UNet的脑肿瘤图像分割算法[J]. 光电子激光, 2023(3): 328-336. SU Fu, FANG Dong, WANG Longye, et al. Brain tumor image segmentation algorithm based on dual decoding path DD-UNet[J]. Journal of Optoelectronics Laser, 2023(3): 328-336.
[11] 侯月武, 刘兆英, 张婷, 等. 基于改进的DUNet遥感图像道路提取[J]. 山东大学学报(工学版), 2022, 52(4): 29-37. HOU Yuewu, LIU Zhaoying, ZHANG Ting, et al. Road extraction from remote sensing images based on improved DUNet[J]. Journal of Shandong University(Engineering Science), 2022, 52(4): 29-37.
[12] 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. Long Beach, USA: NIPS, 2017: 6000-6010.
[13] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16×16 words: Transformers for image recognition at scale[EB/OL].(2021-06-03)[2023-07-08]. https://arxiv.org/abs/2010.11929.
[14] ZHU X, SU W, LU L, et al. Deformable DETR:deformable Transformers for end-to-end object detection[EB/OL].(2021-05-18)[2023-07-08]. https://arxiv.org/abs/2010.04159.
[15] LIU Z, LIN Y, CAO Y, et al. Swin Transformer: hierarchical vision Transformer using shifted windows[C] //Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Montreal, Canada: IEEE, 2021: 10012-10022.
[16] CHEN J, LU Y, YU Q, et al. TransUNet: Transformers make strong encoders for medical image segmentation[EB/OL].(2021-02-08)[2023-07-08]. https://arxiv.org/abs/2102.04306.
[17] ZHANG Y, LIU H, HU Q. TransFuse: fusing transformers and CNNs for medical image segmentation[C] //Proceedings of the 24th Medical Image Computing and Computer Assisted Intervention. Strasbourg, France: MICCAI, 2021: 14-24.
[18] CAO H, WANG Y, CHEN J, et al. Swin-Unet: Unet-like pure Transformer for medical image segmentation[C] //European Conference on Computer Vision. Tel Aviv, Israel: Springer, 2022: 205-218.
[19] D'ASCOLI S, TOUVRON H, LEAVITT M L, et al. ConViT: improving vision Transformers with soft convolutional inductive biases[C] //Proceedings of the 38th International Conference on Machine Learning. [S.l.] : PMLR, 2021: 2286-2296.
[20] LOFFLER M, SEKUBOYINA A, JAKOB A, et al. A vertebral segmentation dataset with fracture grading[J]. Radiology: Artificial Intelligence, 2020, 2(4): e190138.
[21] SEKUBOYINA A, HUSSEINI M, BAYAT A, et al. VerSe: a vertebrae labelling and segmentation benchmark for multi-detector CT images[J]. Medical Image Analysis, 2021, 73: 102166.
[22] BAKAS S, REYES M, JAKAB A, et al. Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge[EB/OL].(2021-04-23)[2023-07-08]. https://arxiv.org/abs/1811.02629.
[23] 刘方旭, 王建, 魏本征. 基于多空间注意力的小儿肺炎辅助诊断算法[J]. 山东大学学报(工学版), 2023, 53(2): 135-142. LIU Fangxu, WANG Jian, WEI Benzheng. Auxiliary diagnosis algorithm for pediatric pneumonia based on multi-spatial attention[J]. Journal of Shandong University(Engineering Science), 2023, 53(2): 135-142.
[24] 陆猛. 基于全卷积神经网络的医学图像分割[D]. 重庆: 重庆邮电大学, 2021. LU Meng. Medical image segmentation based on full convolutional neural network[D]. Chongqing: Chongqing University of Posts and Telecommunications, 2021.
[25] HE X, ZHOU Y, ZHAO J, et al. Swin Transformer embedding UNet for remote sensing image semantic segmentation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-15.
[26] LIN T, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C] //Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017: 2117-2125.
[27] LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C] //Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA: IEEE, 2015: 3431-3440.
[28] CHEN L, PAPANDREOU G, SCHROFF F, et al. Rethinking atrous convolution for semantic image segmentation[EB/OL].(2017-12-05)[2023-11-08]. https://arxiv.org/abs/1706.05587.
[29] DDS-UNet医学图像分割算法源代码[EB/OL].(2023-07-20)[2023-11-08]. https://github.com/DeepPicEI/DDS-UNet.
[1] 袁钺,王艳丽,刘勘. 基于空洞卷积块架构的命名实体识别模型[J]. 山东大学学报 (工学版), 2022, 52(6): 105-114.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2018 《山东大学学报(工学版)》编辑部　
地址: 济南市山大南路27号（250100）　 电话: 0531-88366735　 E-mail: xbgxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发