期刊
HELIYON
卷 8, 期 12, 页码 -出版社
CELL PRESS
DOI: 10.1016/j.heliyon.2022.e11981
关键词
Lung adenocarcinoma; Adenocarcinoma subtype classification; Transfer learning; Weak supervised learning; The cancer genome atlas; Squamous cell carcinoma; NSCLC
资金
- National Key Research and Development Program of China
- [2017YFC0909903]
Confirming histological patterns of lung carcinoma is crucial for patient treatment and prognosis. However, this task is challenging and requires the input of experienced pathologists. Computer-aided diagnosis has the potential to speed up the diagnosis process by reducing the need for manual annotation by pathologists.
Confirming histological patterns of lung carcinoma is important for determining the prognosis and the next steps of treatment for a patient. Confirming the histologic patterns (subtype) of lung adenocarcinoma is important for determining the prognosis and treatment options for a patient. The task is challenging, and often requires the input of experienced pathologists, who by themselves lack interobserver concordance. A computer-aided diag-nosis holds the potential to accelerate the time to diagnosis. As many adenocarcinoma tissue samples contain multiple histologic patterns, accurate computer-aided diagnosis requires annotations manually labeled by pa-thologists. We propose a method that merges weak supervised learning and Integrated Learning using Transfer Learning using two datasets: The Cancer Genome Atlas (TCGA), and the Clinical Proteomic Tumor Analysis Consortium (CPTAC) to reduce the need for manual annotation by a pathologist while maintaining accuracy. Whole-slide images (WSI) are first determined to be either adenocarcinoma or squamous cell carcinoma, then further identify the subtypes by generating weak classifiers for each subtype, then using integrated learning to create a strong classifier.Our model was evaluated with independent datasets from the CPTAC dataset and a dataset from a private hospital. It can achieve AUC values of 0.86, 0.91, 0.82, 0.77, 0.96, 0.98 in Acinar, LPA, Micropapillary, Papillary, Solid, and Normal, respectively.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据