Transformer-based biomarker prediction from colorectal cancer histology: A large-scale multicentric study.

Deep learning (DL) can accelerate the prediction of prognostic biomarkers from routine pathology slides in colorectal cancer (CRC). However, current approaches rely on convolutional neural networks (CNNs) and have mostly been validated on small patient cohorts. Here, we develop a new transformer-based pipeline for end-to-end biomarker prediction from pathology slides by combining a pre-trained transformer encoder with a transformer network for patch aggregation. Our transformer-based approach substantially improves the performance, generalizability, data efficiency, and interpretability as compared with current state-of-the-art algorithms. After training and evaluating on a large multicenter cohort of over 13,000 patients from 16 colorectal cancer cohorts, we achieve a sensitivity of 0.99 with a negative predictive value of over 0.99 for prediction of microsatellite instability (MSI) on surgical resection specimens. We demonstrate that resection specimen-only training reaches clinical-grade performance on endoscopic biopsy tissue, solving a long-standing diagnostic problem.

Artificial Intelligence-Assisted Score Analysis for Predicting the Expression of the Immunotherapy Biomarker PD-L1 in Lung Cancer.

Programmed cell death ligand 1 (PD-L1) is a critical biomarker for predicting the response to immunotherapy. However, traditional quantitative evaluation of PD-L1 expression using immunohistochemistry staining remains challenging for pathologists. Here we developed a deep learning (DL)-based artificial intelligence (AI) model to automatically analyze the immunohistochemical expression of PD-L1 in lung cancer patients. A total of 1,288 patients with lung cancer were included in the study. The diagnostic ability of three different AI models (M1, M2, and M3) was assessed in both PD-L1 (22C3) and PD-L1 (SP263) assays. M2 and M3 showed improved performance in the evaluation of PD-L1 expression in the PD-L1 (22C3) assay, especially at 1% cutoff. Highly accurate performance in the PD-L1 (SP263) was also achieved, with accuracy and specificity of 96.4 and 96.8% in both M2 and M3, respectively. Moreover, the diagnostic results of these three AI-assisted models were highly consistent with those from the pathologist. Similar performances of M1, M2, and M3 in the 22C3 dataset were also obtained in lung adenocarcinoma and lung squamous cell carcinoma in both sampling methods. In conclusion, these results suggest that AI-assisted diagnostic models in PD-L1 expression are a promising tool for improving the efficiency of clinical pathologists.

Dual-scale categorization based deep learning to evaluate programmed cell death ligand 1 expression in non-small cell lung cancer.

ABSTRACT: In precision oncology, immune check point blockade therapy has quickly emerged as novel strategy by its efficacy, where programmed death ligand 1 (PD-L1) expression is used as a clinically validated predictive biomarker of response for the therapy. Automating pathological image analysis and accelerating pathology evaluation is becoming an unmet need. Artificial Intelligence and deep learning tools in digital pathology have been studied in order to evaluate PD-L1 expression in PD-L1 immunohistochemistry image. We proposed a Dual-scale Categorization (DSC)-based deep learning method that employed 2 VGG16 neural networks, 1 network for 1 scale, to critically evaluate PD-L1 expression. The DSC-based deep learning method was tested in a cohort of 110 patients diagnosed as non-small cell lung cancer. This method showed a concordance of 88% with pathologist, which was higher than concordance of 83% of 1-scale categorization-based method. Our results show that the DSCbased method can empower the deep learning application in digital pathology and facilitate computer-aided diagnosis.