深度学习用于恶性瘤和瘤起源预测,使用细胞学或组织病理学全幻灯片图像
Ching-Wei Wang1, Tzu-Chiao Chu2, Tzu-Kang Wu2
1Graduate Institute of Biomedical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, ROC. cweiwang@mail.ntust.edu.tw.
一个新的深度学习框架,MAMILE-UNI,准确地检测癌症恶性和细胞学图像中的起源. 这种人工智能工具可以提高肺和流的诊断准确度,帮助病理学家.
科学领域:
- 计算病理学计算病理学
- 数字细胞学数字细胞学
- 人工智能在瘤学中的应用
背景情况:
- 胸腔和性细胞学的显微镜分析在诊断转移性癌症和确定瘤起源方面具有准确性和一致性的局限性.
- 深度学习在细胞病理学中的应用,特别是对于输液,尽管有潜力,但仍未得到充分探索.
研究的目的:
- 开发和评估一个数据效率高的深度学习框架 (MAMILE-UNI),用于细胞学中自动检测恶性瘤和瘤起源识别.
- 评估MAMILE-UNI在从膜和膜液以及基因病理样本的整片图像 (WSI) 上的性能.
主要方法:
- MAMILE-UNI框架是在细胞学涂抹和从膜和液流出的细胞块的整片图像 (WSI) 上进行训练和评估的.
- 使用包括AUROC (接收器操作特征曲线下的面积),平均灵敏度和特异性 (MeanSS),准确性,精度和F1分数在内的指标来评估性能.
- 通过使用费舍尔的精确测试进行了统计验证.
主要成果:
- MAMILE-UNI显示出高AUROC,MeanSS和检测恶性瘤的精确性,在多发性和性溢出 (1250 WSIs) 中.
- 该框架实现了高精度,MeanSS和AUROC在鉴定细胞学涂抹的初级癌症来源.
- 对于基因病理图像 (1196 WSIs),该方法在准确度,精度,灵敏度,F1分数,特异性,MeanSS和AUROC方面表现出色.
- 模型预测得到了统计验证 (p < 0.001).
结论:
- MAMILE-UNI提供了一个强大的,数据效率高的深度学习解决方案,用于改善细胞病理学中的癌症诊断和起源确定.
- 该框架显示出显著的潜力,可以提高诊断的准确性,并减少观察者在输出细胞学和组织病理学分析的变异性.
- 这种人工智能驱动的方法可以帮助病理学家在转移性癌症的临床决策中.
更多相关视频
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
09:31High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning
Published on: April 28, 2022
相关概念视频
Predicting Molecular Geometry
Design Example: Designing Water Slide
Bernoulli's principle determines the water's velocity along the slide....
Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
Avoidance Learning and Learned Helplessness
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Cancers Originate from Somatic Mutations in a Single Cell
End Point Prediction: Gran Plot
For potentiometric titration, the Gran plot is created by plotting...
