相关实验视频

Updated: Jul 28, 2025

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

在动态对比增强MRI中弱监督的乳腺损伤检测

Rong Sun¹, Chuanling Wei¹, Zhuoyun Jiang¹

¹School of Health Science and Engineering, University of Shanghai for Science and Technology, No. 516 Jun-Gong Road, Shanghai, 200093, China.

Journal of digital imaging

|May 30, 2023

概括

这项研究引入了一种弱监督的学习模型,用于MRI中检测乳腺病变,大大减少了对手册注释的需求. 该模型实现了高精度,使得乳腺瘤的有效和自动识别成为可能.

科学领域:

放射学放射学是一门学科.
医疗成像医学成像
人工智能在医学中的应用

背景情况:

准确的医疗注释用于瘤检测是劳动密集型的,阻碍了监督学习的发展.
动态对比增强型MRI (DCE-MRI) 对于乳腺损伤可视化至关重要.
弱监督学习为注释限制提供了一个潜在的解决方案.

研究的目的:

开发和评估一个弱监督的学习模型,用于乳腺病变检测,仅使用DCE-MRI中的图像级标签.
在分类和定位准确性方面评估模型的性能.
在这种情况下,研究特征金字塔网络 (FPN) 和层CAM的实用性.

主要方法:

使用了652例DCE-MRI病例 (254例正常,398例异常) 的数据集.
用于特征提取,使用了与VGG16集成的卷积块注意模块 (CBAM) 的特征金字塔网络 (FPN).
层CAM生成了初始定位热图,并通过条件随机场 (CRF) 进行了改进.

主要成果:

该模型展示了高图像级分类性能:95.2%的准确性,91.6%的灵敏性,99.2%的特异性和0.986 AUC.
乳腺病变定位使用弱监督学习实现了84.1%的平均精度 (AP).
结合了FPN和Layer-CAM的方法,便于自动检测乳腺病变.

结论:

使用FPN和Layer-CAM的弱监督学习有效地检测DCE-MRI中的乳腺病变,使用图像级标签.
这种方法显著减少了对大量手册注释的依赖,加速了乳腺癌诊断中的AI发展.
该模型的高精度和局部化性能显示出其在乳腺病变检测中的临床应用的前景.

关键词:

类激活映射的映射类激活映射计算机辅助检测计算机辅助检测功能金字塔网络的特点是:磁共振成像技术磁共振成像技术缺乏监督的学习学习.

更多相关视频

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Dynamic Contrast Enhanced Magnetic Resonance Imaging of an Orthotopic Pancreatic Cancer Mouse Model

Dynamic Contrast Enhanced Magnetic Resonance Imaging of an Orthotopic Pancreatic Cancer Mouse Model

Published on: April 18, 2015

相关概念视频

Magnetic Resonance Imaging

Magnetic Resonance Imaging

Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...