Transformer- and joint learning-based dual-domain networks for undersampled MRI segmentation

IF 3.2 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Medical physics Pub Date : 2024-08-22 DOI:10.1002/mp.17358

Jizhong Duan, Zhenyu Huang, Yunshuang Xie, Junfeng Wang, Yu Liu

{"title":"Transformer- and joint learning-based dual-domain networks for undersampled MRI segmentation","authors":"Jizhong Duan, Zhenyu Huang, Yunshuang Xie, Junfeng Wang, Yu Liu","doi":"10.1002/mp.17358","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>Recently, magnetic resonance imaging (MRI) has become a crucial medical imaging technology widely used in clinical practice. However, MRI faces challenges such as the lengthy acquisition time for k-space data and the need for time-consuming manual annotation by radiologists. Traditionally, these challenges have been addressed individually through undersampled MRI reconstruction and automatic segmentation algorithms. Whether undersampled MRI segmentation can be enhanced by treating undersampled MRI reconstruction and segmentation as an end-to-end task, trained simultaneously, rather than as serial tasks should be explored.</p>\n </section>\n \n <section>\n \n <h3> Purpose</h3>\n \n <p>We introduce a novel Transformer- and Joint Learning-based Dual-domain Network (TJLD-Net) for undersampled MRI segmentation.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>This method significantly enhances feature recognition in the segmentation process by fully utilizing the rich detail obtained during the image reconstruction phase. Consequently, the method can achieve precise and reliable image segmentation even with undersampled k-space data. Additionally, it incorporates an attention mechanism for feature enhancement, which improves the representation of shared features by learning the contextual information in MR images.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>Simulation experiments demonstrate that the segmentation performance of TJLD-Net on three datasets is significantly higher than that of the joint model (RecSeg) and six baseline models (where reconstruction and segmentation are regarded as serial tasks). On the CHAOS dataset, the Dice scores of TJLD-Net are, on average, 9.87%, 2.17%, 1.90%, 1.80%, 9.60%, 0.80%, and 6.50% higher than those of the seven compared models. On the ATLAS challenge dataset, the average Dice scores of TJLD-Net improve by 4.23%, 5.63%, 2.30%, 1.53%, 3.57%, 0.93%, and 6.60%. Similarly, on the SKM-TEA dataset, the average Dice scores of TJLD-Net improve by 4.73%, 12.80%, 14.83%, 8.67%, 4.53%, 11.60%, and 12.10%. The novel TJLD-Net model provides a promising solution for undersampled MRI segmentation, overcoming the poor performance issues encountered by automated segmentation algorithms in low-quality accelerated imaging.</p>\n </section>\n </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"51 11","pages":"8108-8123"},"PeriodicalIF":3.2000,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Medical physics","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/mp.17358","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}

引用次数: 0

Abstract

Background

Recently, magnetic resonance imaging (MRI) has become a crucial medical imaging technology widely used in clinical practice. However, MRI faces challenges such as the lengthy acquisition time for k-space data and the need for time-consuming manual annotation by radiologists. Traditionally, these challenges have been addressed individually through undersampled MRI reconstruction and automatic segmentation algorithms. Whether undersampled MRI segmentation can be enhanced by treating undersampled MRI reconstruction and segmentation as an end-to-end task, trained simultaneously, rather than as serial tasks should be explored.

Purpose

We introduce a novel Transformer- and Joint Learning-based Dual-domain Network (TJLD-Net) for undersampled MRI segmentation.

Methods

This method significantly enhances feature recognition in the segmentation process by fully utilizing the rich detail obtained during the image reconstruction phase. Consequently, the method can achieve precise and reliable image segmentation even with undersampled k-space data. Additionally, it incorporates an attention mechanism for feature enhancement, which improves the representation of shared features by learning the contextual information in MR images.

Results

Simulation experiments demonstrate that the segmentation performance of TJLD-Net on three datasets is significantly higher than that of the joint model (RecSeg) and six baseline models (where reconstruction and segmentation are regarded as serial tasks). On the CHAOS dataset, the Dice scores of TJLD-Net are, on average, 9.87%, 2.17%, 1.90%, 1.80%, 9.60%, 0.80%, and 6.50% higher than those of the seven compared models. On the ATLAS challenge dataset, the average Dice scores of TJLD-Net improve by 4.23%, 5.63%, 2.30%, 1.53%, 3.57%, 0.93%, and 6.60%. Similarly, on the SKM-TEA dataset, the average Dice scores of TJLD-Net improve by 4.73%, 12.80%, 14.83%, 8.67%, 4.53%, 11.60%, and 12.10%. The novel TJLD-Net model provides a promising solution for undersampled MRI segmentation, overcoming the poor performance issues encountered by automated segmentation algorithms in low-quality accelerated imaging.

查看原文本刊更多论文

基于变压器和联合学习的双域网络，用于欠采样磁共振成像分割。

背景：近年来，磁共振成像（MRI）已成为广泛应用于临床的重要医学成像技术。然而，核磁共振成像面临着一些挑战，如 k 空间数据的采集时间较长，放射科医生需要耗时的人工标注。传统上，这些挑战都是通过欠采样磁共振成像重建和自动分割算法单独解决的。目的：我们介绍了一种新型的基于变压器和联合学习的双域网络（TJLD-Net），用于欠采样磁共振成像分割：方法：该方法充分利用图像重建阶段获得的丰富细节，大大提高了分割过程中的特征识别能力。因此，该方法即使在 K 空间数据采样不足的情况下，也能实现精确可靠的图像分割。此外，该方法还加入了用于特征增强的注意力机制，通过学习磁共振图像中的上下文信息来改进共享特征的表示：模拟实验表明，TJLD-Net 在三个数据集上的分割性能明显高于联合模型（RecSeg）和六个基线模型（重建和分割被视为串行任务）。在 CHAOS 数据集上，TJLD-Net 的 Dice 分数分别比七个比较模型平均高出 9.87%、2.17%、1.90%、1.80%、9.60%、0.80% 和 6.50%。在 ATLAS 挑战数据集上，TJLD-Net 的平均 Dice 分数分别提高了 4.23%、5.63%、2.30%、1.53%、3.57%、0.93% 和 6.60%。同样，在 SKM-TEA 数据集上，TJLD-Net 的平均 Dice 分数分别提高了 4.73%、12.80%、14.83%、8.67%、4.53%、11.60% 和 12.10%。新颖的 TJLD-Net 模型为采样不足的磁共振成像分割提供了一种有前途的解决方案，克服了自动分割算法在低质量加速成像中遇到的性能不佳问题。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Medical physics 医学-核医学

CiteScore

6.80

自引率

15.80%

发文量

660

审稿时长

1.7 months

期刊介绍： Medical Physics publishes original, high impact physics, imaging science, and engineering research that advances patient diagnosis and therapy through contributions in 1) Basic science developments with high potential for clinical translation 2) Clinical applications of cutting edge engineering and physics innovations 3) Broadly applicable and innovative clinical physics developments Medical Physics is a journal of global scope and reach. By publishing in Medical Physics your research will reach an international, multidisciplinary audience including practicing medical physicists as well as physics- and engineering based translational scientists. We work closely with authors of promising articles to improve their quality.