在CT图像上对无监督和深度学习方法进行腹腔大动脉动脉瘤自动细分的比较研究:初步结果
D Arampatzis1, E Athanasiadis2, E Kontopodis3
1Intelligent Data Exploration and Analysis Laboratory, Department of Statistics and Actuarial - Financial Mathematics, University of the Aegean, Karlovasi, Samos, Greece.
Advances in experimental medicine and biology
|November 18, 2025
概括
这项研究比较了两种使用CT扫描的腹腔大动脉动脉瘤 (AAA) 分段算法. 深度学习 (TotalSegmentor) 与传统方法相比,在AAA检测和划分方面显示出更高的准确性.
科学领域:
- 医疗成像医学成像
- 人工智能在医学中的应用
- 心血管外科心血管外科
背景情况:
- 腹腔大动脉瘤 (AAA) 是一个重要的全球健康问题,往往无症状,直到破裂.
- 从CT图像中精确细分AAA对于及时的临床干预和改善患者结果至关重要.
研究的目的:
- 为了比较评估深度学习算法 (TotalSegmentor) 与AAA细分的传统图像分析方法的性能.
- 评估这些算法的准确性和稳定性,使用患者CT扫描的新型数据集.
主要方法:
- 利用了18名被诊断患有AAA的患者的CT扫描,并使用临床医生手册的注释作为基本事实.
- 实现并将内部无监督的细分算法与TotalSegmentor深度学习模型 (nnU-Net框架) 进行比较.
主要成果:
- 总分段实现了更高的准确性,平均索伦森-迪斯 (0.89) 和贾卡德 (0.81) 指数.
- 公司内部的算法得到的得分略低一些 (戴斯:0.85,贾卡德:0.77).
- 这两种方法都在细分腹腔大动脉动脉瘤方面表现出强大.
结论:
- 深度学习模型,以TotalSegmentor为例,为AAA细分提供了更高的准确性.
- 这些发现支持整合人工智能驱动的工具,以改善早期AAA检测和监测的临床工作流程.
相关概念视频
Aneurysm II: Clinical Manifestations and Diagnostic Studies
176
Thoracic, aortic arch and abdominal aneurysms are significant vascular conditions that can present with various clinical manifestations and lead to serious complications. Understanding these manifestations and the appropriate diagnostic studies is essential for effective management and treatment.Thoracic Aortic AneurysmsThoracic aortic aneurysms often remain asymptomatic until they reach a size that impinges on adjacent structures. They typically cause deep, diffuse chest pain that radiates to...
176
Imaging Studies for Cardiovascular System V: CT
248
Cardiac computed tomography (CT) scanning is an advanced cardiac imaging technique that utilizes CT technology, with or without intravenous (IV) contrast, to produce accurate cross-sectional virtual slices of specific areas of the heart, coronary circulation, and major blood vessels such as the aorta, pulmonary veins, and arteries. The computer processes these slices to generate three-dimensional images. Multidetector CT (MDCT) is a rapid form of CT scanning that captures multiple slices...
248


