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

Abstract

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.

The Role of Genomics and Proteomics in Lung Cancer Early Detection and Treatment

“…They used three different AI models (M1, M2, and M3) assessed in both PDL1 (22C3) and PD-L1 (SP263) assays. Their models improved the evaluation of PD-L1 expression, and diagnostic results were consistent with the pathologist’s [ 177 , 178 ]. In the study of Wu et al, TPS of PD-L1 expression was also assessed in whole slide images (WSIs) of the 22c3 assay by the DL model.…”

Tumor microenvironment features decipher the outperformance of neoadjuvant immunochemotherapy over chemotherapy in resectable non-small cell lung cancer

“…Unstained and monoplex stained slide images were applied to extract tissue autofluorescence and the spectrum of each fluorophore, respectively. Fluorescence images were imported and analyzed using the AP-TIME image analysis software (3D Medicines Inc.) ( 17 ). Tumor parenchyma and stroma were differentiated according to CK staining.…”

Identifying Serum Small Extracellular Vesicle MicroRNA as a Noninvasive Diagnostic and Prognostic Biomarker for Ovarian Cancer

“…8 The accuracy of CA125 in the diagnosis of OC is affected by the age of patients. 9 Moreover, CA125 does not always show significant changes in the early stages of OC, and was only elevated in approximately 50% of patients. 10 HE4 is a complementary and validated biomarker for CA125 during the OC diagnosis.…”

“…However, there is currently no noninvasive method available to accurately detect early stage EOC. , As tumor biomarkers, carbohydrate antigen 125 (CA125) and human epididymis 4 (HE4) have limited diagnostic utility . The accuracy of CA125 in the diagnosis of OC is affected by the age of patients . Moreover, CA125 does not always show significant changes in the early stages of OC, and was only elevated in approximately 50% of patients .…”