AMS-U-Net: automatic mass segmentation in digital breast tomosynthesis via U-Net.

IF 1.9 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Journal of Medical Imaging Pub Date : 2024-03-01 Epub Date: 2024-03-23 DOI:10.1117/1.JMI.11.2.024005

Ahmad Qasem, Genggeng Qin, Zhiguo Zhou

{"title":"AMS-U-Net: automatic mass segmentation in digital breast tomosynthesis via U-Net.","authors":"Ahmad Qasem, Genggeng Qin, Zhiguo Zhou","doi":"10.1117/1.JMI.11.2.024005","DOIUrl":null,"url":null,"abstract":"Purpose: The objective of this study was to develop a fully automatic mass segmentation method called AMS-U-Net for digital breast tomosynthesis (DBT), a popular breast cancer screening imaging modality. The aim was to address the challenges posed by the increasing number of slices in DBT, which leads to higher mass contouring workload and decreased treatment efficiency.Approach: The study used 50 slices from different DBT volumes for evaluation. The AMS-U-Net approach consisted of four stages: image pre-processing, AMS-U-Net training, image segmentation, and post-processing. The model performance was evaluated by calculating the true positive ratio (TPR), false positive ratio (FPR), F-score, intersection over union (IoU), and 95% Hausdorff distance (pixels) as they are appropriate for datasets with class imbalance.Results: The model achieved 0.911, 0.003, 0.911, 0.900, 5.82 for TPR, FPR, F-score, IoU, and 95% Hausdorff distance, respectively.Conclusions: The AMS-U-Net model demonstrated impressive visual and quantitative results, achieving high accuracy in mass segmentation without the need for human interaction. This capability has the potential to significantly increase clinical efficiency and workflow in DBT for breast cancer screening.","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"11 2","pages":"024005"},"PeriodicalIF":1.9000,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10960181/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Medical Imaging","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1117/1.JMI.11.2.024005","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/3/23 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}

引用次数: 0

Abstract

Purpose: The objective of this study was to develop a fully automatic mass segmentation method called AMS-U-Net for digital breast tomosynthesis (DBT), a popular breast cancer screening imaging modality. The aim was to address the challenges posed by the increasing number of slices in DBT, which leads to higher mass contouring workload and decreased treatment efficiency.

Approach: The study used 50 slices from different DBT volumes for evaluation. The AMS-U-Net approach consisted of four stages: image pre-processing, AMS-U-Net training, image segmentation, and post-processing. The model performance was evaluated by calculating the true positive ratio (TPR), false positive ratio (FPR), F-score, intersection over union (IoU), and 95% Hausdorff distance (pixels) as they are appropriate for datasets with class imbalance.

Results: The model achieved 0.911, 0.003, 0.911, 0.900, 5.82 for TPR, FPR, F-score, IoU, and 95% Hausdorff distance, respectively.

Conclusions: The AMS-U-Net model demonstrated impressive visual and quantitative results, achieving high accuracy in mass segmentation without the need for human interaction. This capability has the potential to significantly increase clinical efficiency and workflow in DBT for breast cancer screening.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

AMS-U-Net：通过 U-Net 在数字乳腺断层合成中自动分割肿块。

目的：本研究的目的是为数字乳腺断层合成（DBT）这种流行的乳腺癌筛查成像模式开发一种名为 AMS-U-Net 的全自动质量分割方法。其目的是解决 DBT 中切片数量不断增加所带来的挑战，因为切片数量增加会导致质量轮廓工作量增加和治疗效率降低：研究使用了不同 DBT 容量的 50 张切片进行评估。AMS-U-Net 方法包括四个阶段：图像预处理、AMS-U-Net 训练、图像分割和后处理。模型的性能通过计算真阳性率（TPR）、假阳性率（FPR）、F-score、交集大于联合（IoU）和 95% Hausdorff 距离（像素）来评估，因为它们适用于类不平衡的数据集：该模型的 TPR、FPR、F-score、IoU 和 95% Hausdorff 距离分别达到 0.911、0.003、0.911、0.900 和 5.82：AMS-U-Net 模型展示了令人印象深刻的视觉和定量结果，无需人工交互即可实现高精度的质量分割。这种能力有望显著提高乳腺癌筛查 DBT 的临床效率和工作流程。

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分钟内获得全文去求助

来源期刊

Journal of Medical Imaging RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING-

CiteScore

4.10

自引率

4.20%

发文量

期刊介绍： JMI covers fundamental and translational research, as well as applications, focused on medical imaging, which continue to yield physical and biomedical advancements in the early detection, diagnostics, and therapy of disease as well as in the understanding of normal. The scope of JMI includes: Imaging physics, Tomographic reconstruction algorithms (such as those in CT and MRI), Image processing and deep learning, Computer-aided diagnosis and quantitative image analysis, Visualization and modeling, Picture archiving and communications systems (PACS), Image perception and observer performance, Technology assessment, Ultrasonic imaging, Image-guided procedures, Digital pathology, Biomedical applications of biomedical imaging. JMI allows for the peer-reviewed communication and archiving of scientific developments, translational and clinical applications, reviews, and recommendations for the field.