人工智能称之为虚张声势:区分良性病变与三阴性乳腺癌病例
João Mendes1,2, Ana M Mota3, Ana T Teixeira4
1Instituto de Biofísica e Engenharia Biomédica, Faculdade de Ciências da Universidade de Lisboa, 1749-016, Lisbon, Portugal. jpmendes@ciencias.ulisboa.pt.
La Radiologia medica
|January 6, 2026
概括
一个新的卷积神经网络 (CNN) 模型准确地区分了三阴性乳腺癌 (TNBC) 和乳房影像上的良性病变. 这种人工智能工具显示了改善TNBC早期诊断和减少虚假阴性结果的潜力.
科学领域:
- 医疗成像医学成像
- 在瘤学中使用人工智能
- 乳腺癌研究研究 乳腺癌研究
背景情况:
- 三阴性乳腺癌 (TNBC) 是一种具有攻击性的乳腺癌亚型,缺乏向治疗.
- 乳腺癌经常在乳房影像上表现出良性特征,阻碍了早期诊断,导致结果不佳.
- 有效的TNBC早期检测方法对于改善患者存活率至关重要.
研究的目的:
- 开发和验证一个卷积神经网络 (CNN) 模型,以区分TNBC与乳腺良性病变在乳房影像上.
- 与专家放射科医生相比,评估CNN模型的诊断性能.
- 使用GRAD-CAM.探索CNN模型预测的可解释性.
主要方法:
- 这是一项回顾性多中心研究,涉及来自英国三所机构的566张乳房镜 (277张良性,289张TNBC).
- 使用总变化最小化过和对比本地自适应性图表平衡 (CLAHE) 的图像质量提升.
- 开发和测试CNN模型,使用AUC,灵敏度和特异性来评估性能. 使用GRAD-CAM进行的可解释性分析.
主要成果:
- 在CNN模型的测试中,AUC达到0.984,具有94.2%的灵敏度和91.9%的特异性.
- GRAD-CAM分析表明,该模型利用病变特征和瘤微环境进行预测.
- 在相同的测试组中,CNN模型显著超过了专家放射科医生 (71%的灵敏度,60%的特异性).
结论:
- 开发的CNN模型在分辨TNBC与乳房图片上的良性病变方面表现出高度准确性.
- 该模型分析瘤微环境区域的能力表明了诊断的综合方法.
- 这种人工智能工具显示出作为TNBC早期检测的补充诊断辅助的巨大潜力,可能减少误诊.
相关概念视频
01:37Neural Regulation
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
02:23Abnormal Proliferation
Under normal conditions, most adult cells remain in a non-proliferative state unless stimulated by internal or external factors to replace lost cells. Abnormal cell proliferation is a condition in which the cell's growth exceeds and is uncoordinated with normal cells. In such situations, cell division persists in the same excessive manner even after cessation of the stimuli, leading to persistent tumors. The tumor arises from the damaged cells that replicate to pass the damage to the daughter...
01:31Respiratory System Abnormal Finding II: Palpation and Auscultation
In assessing respiratory abnormalities, palpation and auscultation are critical tools for detecting and interpreting various pathophysiological changes. These techniques provide insight into underlying disorders by evaluating tactile sensations and sounds produced by the respiratory system.
Palpation Findings
During a respiratory assessment, palpation can reveal several vital abnormalities:
Palpation Findings
During a respiratory assessment, palpation can reveal several vital abnormalities: