深度学习的神经网络在输出细胞学中检测腺癌
Katsuhide Ikeda1, Nanako Sakabe1, Kenta Fukuda1
1Pathophysiology Sciences, Department of Integrated Health Sciences, Nagoya University Graduate School of Medicine, Nagoya, Aichi, Japan.
American journal of clinical pathology
|July 30, 2025
概括
一个新的深度学习模型有效地检测出液细胞学图像中的恶性细胞,有助于癌症查. 这种自动化系统显示出高精度和灵敏度,旨在减少细胞学检查中的假阴性结果.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 细胞病理学 细胞病理学
背景情况:
- 细胞学检查对于检测恶性细胞至关重要,腺癌是常见的类型.
- 输液细胞学有助于诊断来自各种器官的癌症.
- 准确检测恶性细胞对于有效的癌症查至关重要.
研究的目的:
- 开发一种深度学习模型,用于检测输液细胞学图像中的恶性细胞.
- 评估YOLOv8对象检测算法在识别腺癌细胞中的性能.
主要方法:
- 使用YOLOv8对象检测算法开发了一个深度学习模型.
- 该模型在275例腺癌病例 (12,182张图像) 和188例恶性瘤阴性病例 (1,980张图像) 上进行了训练.
主要成果:
- 该模型实现了高性能指标,包括精度 (0.909),回忆 (0.911),F1得分 (0.910) 和腺癌的平均精度 (0.955).
- 总体准确度,灵敏度和特异性分别为96.3%,98.5%和92.7%.
- 在非腺癌数据集中观察到高灵敏度 (97.1%),在负恶性瘤数据集中,假阳性率为7.3%.
结论:
- 开发的深度学习模型显示出足够的准确性,以协助在输出细胞学中的癌症查.
- 虽然存在细胞注释挑战,但该模型的性能支持其实用性.
- 预计自动化系统的进一步开发将提高恶性细胞的可靠检测,并减少假阴性率.
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.
02:26Protein Networks
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...