提高结直肠病变分类的准确性和可解释性,使用注意监督视觉转换器
Luca Carlini1, Luca Di Stefano1, Chiara Lena1
1Dipartimento di Elettronica, Informazione, Bioingegneria (DEIB), Politecnico di Milano, Piazza Leonardo da Vinci, 32, Milano, 20133, Italy.
Computer methods and programs in biomedicine
|January 25, 2026
概括
监督视觉变压器 (ViT) 注意地图与专家注释可以提高结直肠病变分类的准确性和可解释性. 这种方法提高了巴黎分类的性能,并为更好的临床决策提供了更清晰,以病变为重点的注意模式.
科学领域:
- 人工智能在医学中的应用
- 计算机视觉用于内镜.
- 医学图像分析 医学图像分析
背景情况:
- 准确的结直肠病变评估对于治疗和癌症风险分层至关重要.
- 巴黎分类有助于此评估,但面临着观察者之间的变化.
- 视觉转换器 (ViT) 提供了潜力,但可以表现出分散的注意力,阻碍了可解释性.
研究的目的:
- 调查是否监督ViT关注地图与专家注释提高巴黎分类准确性.
- 通过关注相关损伤区域来提高ViT模型的可解释性.
- 开发一种方法,同时提高分类性能和模型可解释性.
主要方法:
- 提出了一个损伤集中注意力丧失 (LLFA) 预训练目标.
- 使用专家的息肉界限框来引导ViT关注注释的损伤区域.
- 在六个ViT架构中应用LLFA,然后在SUN数据集上对巴黎分类进行交叉微调.
主要成果:
- 在ViT模型中,注意力监督预训始终提高了准确性和病变集中注意力.
- LLFA提高了三类巴黎分类准确度,高达7个百分点.
- LFA的表现优于Grad-CAM的一致性基线的5-13个百分点,集中注意力和正确预测之间存在显著的关联.
结论:
- 使用LFA直接监督ViT关注,有效地利用专家知识.
- 这种方法共同提高了巴黎分类的准确性和空间解释性.
- 与基于Grad-CAM的解释规范化相比,LFA表现出更高的性能.
相关概念视频
01:24Vision
59.5K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
59.5K
02:07Improving Translational Accuracy
14.1K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
14.1K
02:07Improving Translational Accuracy
3.6K
3.6K
03:37Uncertainty in Measurement: Accuracy and Precision
100.6K
Scientists typically make repeated measurements of a quantity to ensure the quality of their findings and to evaluate both the precision and the accuracy of their results. Measurements are said to be precise if they yield very similar results when repeated in the same manner. A measurement is considered accurate if it yields a result that is very close to the true or the accepted value. Precise values agree with each other; accurate values agree with a true value.
100.6K
01:24Color Vision
1.4K
Color perception begins in the retina, the light-sensitive layer at the back of the eye. Two main theories explain how colors are seen: the trichromatic theory and the opponent-process theory. The trichromatic theory, proposed by Thomas Young in 1802 and extended by Hermann von Helmholtz in 1852, suggests that color vision is based on three types of cone receptors in the retina. These cones are sensitive to different but overlapping ranges of wavelengths corresponding to red, blue, and green.
1.4K
01:33Bacterial Transformation
59.5K
In 1928, bacteriologist Frederick Griffith worked on a vaccine for pneumonia, which is caused by Streptococcus pneumoniae bacteria. Griffith studied two pneumonia strains in mice: one pathogenic and one non-pathogenic. Only the pathogenic strain killed host mice.
Griffith made an unexpected discovery when he killed the pathogenic strain and mixed its remains with the live, non-pathogenic strain. Not only did the mixture kill host mice, but it also contained living pathogenic bacteria that...
Griffith made an unexpected discovery when he killed the pathogenic strain and mixed its remains with the live, non-pathogenic strain. Not only did the mixture kill host mice, but it also contained living pathogenic bacteria that...
59.5K