VLM-CPL:来自视觉语言模型的共识伪标签,用于无注释的病理图像分类.
IEEE transactions on medical imaging
|August 4, 2025
概括
这项研究引入了一种新的人类无注释方法,用于使用视觉语言模型 (VLMs) 进行病态图像分类. 这种方法有效地过了杂的伪标签,大大提高了癌症诊断的准确性,而无需手动数据标签.
科学领域:
- 医学图像分析 医学图像分析
- 人工智能的人工智能
- 计算病理学计算病理学
背景情况:
- 癌症诊断的深度学习需要广泛的标记病理图像,这造成了相当大的注释负担.
- 现有的方法与自动化方法固有的噪音标签作斗争.
研究的目的:
- 开发一种人类无注释的方法,用于病态图像分类.
- 利用视觉语言模型 (VLMs) 进行准确的癌症诊断,而无需手动标签.
主要方法:
- 从预先训练的VLM中利用零射击推断来生成初始的伪标签.
- 引入了VLM-CPL,结合了两个噪音标签过技术和半监督学习.
- 开发了基于提示的和基于特征的伪标签,以及不确定性估计和聚类.
- 实现提示功能共识和高信任交叉监督,以实现可靠的学习.
- 采用开放式提示策略,从整个幻灯片中改进补丁选择.
主要成果:
- 提出的方法显著优于病理图像上的直接零射击VLM分类.
- 与现有的噪音标签学习技术相比,实现了更高的性能.
- 在五个公共病理图像数据集中表现出有效性,用于补丁级和幻灯片级分类.
结论:
- VLM-CPL方法为病态图像分类提供了一个强大的,无注释的解决方案.
- 利用先进的标签过策略的VLM可以提高自动化癌症诊断.
- 该方法在减少在数字病理学中依赖手动注释方面显示出希望.
相关概念视频
01:17Classification of Illness
9.4K
The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
9.4K
01:20Labeling Emotion
1.0K
Emotional labeling is a cognitive process that involves identifying and naming one's emotions, such as anger, fear, happiness, or sadness. It allows individuals to recognize and express their internal emotional states, a critical aspect of emotional regulation and communication. Labeling emotions requires more than mere recognition; it also involves drawing upon memory and contextual cues to understand the current situation and apply a corresponding emotional label. For instance, feeling...
1.0K