Robust whole slide image analysis for cervical cancer screening using deep learning
| Autor: | Gong Rao, Wenjie Zhu, Shaoqun Zeng, Ziquan Wei, Jiabo Ma, Ning Li, Wei Han, Xiuli Liu, Li Chen, Xu Li, Jing Cai, Xi Feng, Shenghua Cheng, Tingwei Quan, Sibo Liu, Xiebo Geng, Zehua Wang, Xiao Yuwei, Xueying Zhang, Xiaohua Lv, Jingya Yu, Fei Yang, Junbo Hu |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Computer science
Cytodiagnosis Science General Physics and Astronomy Uterine Cervical Neoplasms Image processing Cervical cancer screening General Biochemistry Genetics and Molecular Biology Article Cancer screening Deep Learning Machine learning Image Processing Computer-Assisted Humans Diagnosis Computer-Assisted Recognition algorithm Early Detection of Cancer Multidisciplinary Artificial neural network business.industry Deep learning Reproducibility of Results Pattern recognition General Chemistry Translational research Recurrent neural network ROC Curve Whole slide image Female Artificial intelligence Neural Networks Computer business |
| Zdroj: | Nature Communications, Vol 12, Iss 1, Pp 1-10 (2021) Nature Communications |
| ISSN: | 2041-1723 |
| Popis: | Computer-assisted diagnosis is key for scaling up cervical cancer screening. However, current recognition algorithms perform poorly on whole slide image (WSI) analysis, fail to generalize for diverse staining and imaging, and show sub-optimal clinical-level verification. Here, we develop a progressive lesion cell recognition method combining low- and high-resolution WSIs to recommend lesion cells and a recurrent neural network-based WSI classification model to evaluate the lesion degree of WSIs. We train and validate our WSI analysis system on 3,545 patient-wise WSIs with 79,911 annotations from multiple hospitals and several imaging instruments. On multi-center independent test sets of 1,170 patient-wise WSIs, we achieve 93.5% Specificity and 95.1% Sensitivity for classifying slides, comparing favourably to the average performance of three independent cytopathologists, and obtain 88.5% true positive rate for highlighting the top 10 lesion cells on 447 positive slides. After deployment, our system recognizes a one giga-pixel WSI in about 1.5 min. Computer-assisted diagnosis is key for scaling up cervical cancer screening, but current algorithms perform poorly on whole slide image analysis and generalization. Here, the authors present a WSI classification and top lesion cell recommendation system using deep learning, and achieve comparable results with cytologists. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink