Transformer Skip-Fusion Based SwinUNet for Liver Segmentation From CT Images

IF 3 4区计算机科学 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

International Journal of Imaging Systems and Technology Pub Date : 2024-06-24 DOI:10.1002/ima.23126

S. S. Kumar, R. S. Vinod Kumar

{"title":"Transformer Skip-Fusion Based SwinUNet for Liver Segmentation From CT Images","authors":"S. S. Kumar, R. S. Vinod Kumar","doi":"10.1002/ima.23126","DOIUrl":null,"url":null,"abstract":"<div>\n \n <p>Liver segmentation is a crucial step in medical image analysis and is essential for diagnosing and treating liver diseases. However, manual segmentation is time-consuming and subject to variability among observers. To address these challenges, a novel liver segmentation approach, SwinUNet with transformer skip-fusion is proposed. This method harnesses the Swin Transformer's capacity to model long-range dependencies efficiently, the U-Net's ability to preserve fine spatial details, and the transformer skip-fusion's effectiveness in enabling the decoder to learn intricate features from encoder feature maps. In experiments using the 3DIRCADb and CHAOS datasets, this technique outperformed traditional CNN-based methods, achieving a mean DICE coefficient of 0.988% and a mean Jaccard coefficient of 0.973% by aggregating the results obtained from each dataset, signifying outstanding agreement with ground truth. This remarkable accuracy in liver segmentation holds significant promise for improving liver disease diagnosis and enhancing healthcare outcomes for patients with liver conditions.</p>\n </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"34 4","pages":""},"PeriodicalIF":3.0000,"publicationDate":"2024-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Imaging Systems and Technology","FirstCategoryId":"94","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/ima.23126","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}

引用次数: 0

Abstract

Liver segmentation is a crucial step in medical image analysis and is essential for diagnosing and treating liver diseases. However, manual segmentation is time-consuming and subject to variability among observers. To address these challenges, a novel liver segmentation approach, SwinUNet with transformer skip-fusion is proposed. This method harnesses the Swin Transformer's capacity to model long-range dependencies efficiently, the U-Net's ability to preserve fine spatial details, and the transformer skip-fusion's effectiveness in enabling the decoder to learn intricate features from encoder feature maps. In experiments using the 3DIRCADb and CHAOS datasets, this technique outperformed traditional CNN-based methods, achieving a mean DICE coefficient of 0.988% and a mean Jaccard coefficient of 0.973% by aggregating the results obtained from each dataset, signifying outstanding agreement with ground truth. This remarkable accuracy in liver segmentation holds significant promise for improving liver disease diagnosis and enhancing healthcare outcomes for patients with liver conditions.

查看原文本刊更多论文

基于变压器跃迁融合的 SwinUNet 用于 CT 图像的肝脏分割

肝脏分割是医学图像分析的关键步骤，对于诊断和治疗肝脏疾病至关重要。然而，人工分割不仅耗时，而且观察者之间的差异也很大。为了应对这些挑战，我们提出了一种新颖的肝脏分割方法--SwinUNet 与变压器跳过融合。这种方法利用了 Swin 变换器高效建立长距离依赖关系模型的能力、U-Net 保存精细空间细节的能力，以及变换器跳过融合使解码器从编码器特征图中学习复杂特征的有效性。在使用 3DIRCADb 和 CHAOS 数据集进行的实验中，该技术的表现优于传统的基于 CNN 的方法，通过汇总从每个数据集获得的结果，平均 DICE 系数达到 0.988%，平均 Jaccard 系数达到 0.973%，这表明该技术与地面实况的一致性非常出色。这种出色的肝脏分割准确性为改善肝病诊断和提高肝病患者的医疗效果带来了巨大希望。

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

International Journal of Imaging Systems and Technology 工程技术-成像科学与照相技术

CiteScore

6.90

自引率

6.10%

发文量

138

审稿时长

3 months

期刊介绍： The International Journal of Imaging Systems and Technology (IMA) is a forum for the exchange of ideas and results relevant to imaging systems, including imaging physics and informatics. The journal covers all imaging modalities in humans and animals. IMA accepts technically sound and scientifically rigorous research in the interdisciplinary field of imaging, including relevant algorithmic research and hardware and software development, and their applications relevant to medical research. The journal provides a platform to publish original research in structural and functional imaging. The journal is also open to imaging studies of the human body and on animals that describe novel diagnostic imaging and analyses methods. Technical, theoretical, and clinical research in both normal and clinical populations is encouraged. Submissions describing methods, software, databases, replication studies as well as negative results are also considered. The scope of the journal includes, but is not limited to, the following in the context of biomedical research: Imaging and neuro-imaging modalities: structural MRI, functional MRI, PET, SPECT, CT, ultrasound, EEG, MEG, NIRS etc.; Neuromodulation and brain stimulation techniques such as TMS and tDCS; Software and hardware for imaging, especially related to human and animal health; Image segmentation in normal and clinical populations; Pattern analysis and classification using machine learning techniques; Computational modeling and analysis; Brain connectivity and connectomics; Systems-level characterization of brain function; Neural networks and neurorobotics; Computer vision, based on human/animal physiology; Brain-computer interface (BCI) technology; Big data, databasing and data mining.