Deep learning approach for automated cancer detection and tumor proportion score estimation of PD-L1 expression in lung adenocarcinoma
Wu, J.; Liu, C.; Liu, X.; Sun, W.; Li, L.; Zhang, Y.; Zhang, J.; Wang, H.; Liu, X.; Yang, X.; Huang, X.; Lin, D.; Ling, S.
Show abstract
Background This study proposed a computational method to detect the cancer areas and calculate the tumor proportion score (TPS) of PD-L1 immunohistochemistry (IHC) expression for lung adenocarcinoma based on deep learning and transfer learning.Patients and methods PD-L1 22C3 and SP142 IHC slides of lung adenocarcinoma samples on digitized whole-slide images (WSI) database were employed. We build a deep convolutional neural network (DCNN) to automatically segment cancer regions. TPS was calculated based on segmented areas and then compared with the interpretations of pathologists.Results We trained a DCNN model based on 22C3 dataset and fine-tuned it with SP142 dataset. We obtain a robust performance on cancer region detection on both datasets, with a sensitivity of 93.36% (22C3) and 92.80% (SP142) and a specificity of 93.97% (22C3) and 89.25% (SP142). With all the coefficient of determinations larger than 0.9 and Fleiss’ and Cohen’s Kappa larger than 0.8 (between mean or median of pathologists and TPS calculated by our method), we also found out the strong correlation between the TPS estimated by our computational method and estimation from multiple pathologists’ interpretations of 22C3 and SP142 respectively.Conclusion We provide an AI method to efficiently predict cancer region and calculate TPS in PD-L1 IHC slide of lung adenocarcinoma on two different antibodies. It demonstrates the potential of using deep learning methods to conveniently access PD-L1 IHC status. In the future, we will further validate the AI tool for automated scoring PD-L1 in large volume samples.Competing Interest StatementThe authors have declared no competing interest.View Full Text
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Using an Anomaly Detection Approach for the Segmentation of Colorectal Cancer Tumors in Whole Slide Images 95%
- Bladder Cancer Prognosis Using Deep Neural Networks and Histopathology Images 95%
- Spatial heterogeneity and organization of tumor mutation burden and immune infiltrates within tumors based on whole slide images correlated with patient survival in bladder cancer 94%
Similar papers in this journal
- Weakly supervised learning for multi-organ adenocarcinoma classification in whole slide images 97%
- Pixelwise H-score: a novel digital image analysis based-metric to quantify membrane biomarker expression from immunohistochemistry images 96%
- Predicting cancer origins with a DNA methylation-based deep neural network model 95%
Similar papers in this journal
- Deep learning models for poorly differentiated colorectal adenocarcinoma classification in whole slide images using transfer learning 94%
- Analytical performance of a highly sensitive system to detect gene variants using next-generation sequencing for lung cancer companion diagnostics 93%
- Demarcation line determination for diagnosis of gastric cancer disease range using unsupervised machine learning in magnifying narrow-band imaging 92%
Similar papers in this journal
- Performance and efficiency of machine learning algorithms for analyzing rectangular biomedical data 93%
- Comparison of QuPath and HALO platforms for analysis of the tumor microenvironment in prostate cancer 91%
- Alternative protocols of tissue fixation dramatically reduces the impact of DNA artifacts, unraveling the interpretation of clinical Comprehensive Genomic Profiling 91%
Similar papers in this journal
- A deep learning approach for Pan-Renal Cell Carcinoma classification and survival prediction from histopathology images 94%
- Novel cancer subtyping method based on patient-specific gene regulatory network 94%
- CluSA: Clustering-based Spatial Analysis framework through Graph Neural Network for Chronic Kidney Disease Prediction using Histopathology Images 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.