FetSAM：超声图像中胎儿头部生物识别的高级分割技术

IF 2.7 Q3 ENGINEERING, BIOMEDICAL

IEEE Open Journal of Engineering in Medicine and Biology Pub Date : 2024-03-27 DOI:10.1109/OJEMB.2024.3382487

Mahmood Alzubaidi;Uzair Shah;Marco Agus;Mowafa Househ

{"title":"FetSAM：超声图像中胎儿头部生物识别的高级分割技术","authors":"Mahmood Alzubaidi;Uzair Shah;Marco Agus;Mowafa Househ","doi":"10.1109/OJEMB.2024.3382487","DOIUrl":null,"url":null,"abstract":"<italic>Goal:\n FetSAM represents a cutting-edge deep learning model aimed at revolutionizing fetal head ultrasound segmentation, thereby elevating prenatal diagnostic precision. \n<italic>Methods:\n Utilizing a comprehensive dataset–the largest to date for fetal head metrics–FetSAM incorporates prompt-based learning. It distinguishes itself with a dual loss mechanism, combining Weighted DiceLoss and Weighted Lovasz Loss, optimized through AdamW and underscored by class weight adjustments for better segmentation balance. Performance benchmarks against prominent models such as U-Net, DeepLabV3, and Segformer highlight its efficacy. \n<italic>Results:\n FetSAM delivers unparalleled segmentation accuracy, demonstrated by a DSC of 0.90117, HD of 1.86484, and ASD of 0.46645. \n<italic>Conclusion:\n FetSAM sets a new benchmark in AI-enhanced prenatal ultrasound analysis, providing a robust, precise tool for clinical applications and pushing the envelope of prenatal care with its groundbreaking dataset and segmentation capabilities.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":null,"pages":null},"PeriodicalIF":2.7000,"publicationDate":"2024-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10480532","citationCount":"0","resultStr":"{\"title\":\"FetSAM: Advanced Segmentation Techniques for Fetal Head Biometrics in Ultrasound Imagery\",\"authors\":\"Mahmood Alzubaidi;Uzair Shah;Marco Agus;Mowafa Househ\",\"doi\":\"10.1109/OJEMB.2024.3382487\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<italic>Goal:\\n FetSAM represents a cutting-edge deep learning model aimed at revolutionizing fetal head ultrasound segmentation, thereby elevating prenatal diagnostic precision. \\n<italic>Methods:\\n Utilizing a comprehensive dataset–the largest to date for fetal head metrics–FetSAM incorporates prompt-based learning. It distinguishes itself with a dual loss mechanism, combining Weighted DiceLoss and Weighted Lovasz Loss, optimized through AdamW and underscored by class weight adjustments for better segmentation balance. Performance benchmarks against prominent models such as U-Net, DeepLabV3, and Segformer highlight its efficacy. \\n<italic>Results:\\n FetSAM delivers unparalleled segmentation accuracy, demonstrated by a DSC of 0.90117, HD of 1.86484, and ASD of 0.46645. \\n<italic>Conclusion:\\n FetSAM sets a new benchmark in AI-enhanced prenatal ultrasound analysis, providing a robust, precise tool for clinical applications and pushing the envelope of prenatal care with its groundbreaking dataset and segmentation capabilities.\",\"PeriodicalId\":33825,\"journal\":{\"name\":\"IEEE Open Journal of Engineering in Medicine and Biology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.7000,\"publicationDate\":\"2024-03-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10480532\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Open Journal of Engineering in Medicine and Biology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10480532/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, BIOMEDICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Open Journal of Engineering in Medicine and Biology","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10480532/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}

引用次数: 0

摘要

目标：FetSAM 是一种尖端的深度学习模型，旨在彻底改变胎儿头部超声波分割，从而提高产前诊断的精确度。方法：利用迄今为止最大的胎儿头部指标综合数据集，FetSAM 结合了基于提示的学习。它采用了双重损失机制，结合了加权骰子损失和加权洛瓦斯损失，通过 AdamW 进行优化，并通过类权重调整实现更好的分割平衡。与 U-Net、DeepLabV3 和 Segformer 等著名模型的性能基准对比凸显了它的功效。结果FetSAM 的 DSC 为 0.90117、HD 为 1.86484、ASD 为 0.46645，显示了无与伦比的分割准确性。结论FetSAM 树立了人工智能增强产前超声分析的新标杆，为临床应用提供了强大、精确的工具，并以其开创性的数据集和分割功能推动了产前护理的发展。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

FetSAM: Advanced Segmentation Techniques for Fetal Head Biometrics in Ultrasound Imagery

Goal: FetSAM represents a cutting-edge deep learning model aimed at revolutionizing fetal head ultrasound segmentation, thereby elevating prenatal diagnostic precision. Methods: Utilizing a comprehensive dataset–the largest to date for fetal head metrics–FetSAM incorporates prompt-based learning. It distinguishes itself with a dual loss mechanism, combining Weighted DiceLoss and Weighted Lovasz Loss, optimized through AdamW and underscored by class weight adjustments for better segmentation balance. Performance benchmarks against prominent models such as U-Net, DeepLabV3, and Segformer highlight its efficacy. Results: FetSAM delivers unparalleled segmentation accuracy, demonstrated by a DSC of 0.90117, HD of 1.86484, and ASD of 0.46645. Conclusion: FetSAM sets a new benchmark in AI-enhanced prenatal ultrasound analysis, providing a robust, precise tool for clinical applications and pushing the envelope of prenatal care with its groundbreaking dataset and segmentation capabilities.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

IEEE Open Journal of Engineering in Medicine and Biology ENGINEERING, BIOMEDICAL-

CiteScore

9.50

自引率

3.40%

发文量

审稿时长

10 weeks

期刊介绍： The IEEE Open Journal of Engineering in Medicine and Biology (IEEE OJEMB) is dedicated to serving the community of innovators in medicine, technology, and the sciences, with the core goal of advancing the highest-quality interdisciplinary research between these disciplines. The journal firmly believes that the future of medicine depends on close collaboration between biology and technology, and that fostering interaction between these fields is an important way to advance key discoveries that can improve clinical care.IEEE OJEMB is a gold open access journal in which the authors retain the copyright to their papers and readers have free access to the full text and PDFs on the IEEE Xplore® Digital Library. However, authors are required to pay an article processing fee at the time their paper is accepted for publication, using to cover the cost of publication.