Non-Invasive Measurement Using Deep Learning Algorithm Based on Multi-Source Features Fusion to Predict PD-L1 Expression and Survival in NSCLC

• Published in: Frontiers in immunology Vol. 13; p. 828560
• Main Authors: Wang, Chengdi, Ma, Jiechao, Shao, Jun, Zhang, Shu, Li, Jingwei, Yan, Junpeng, Zhao, Zhehao, Bai, Congchen, Yu, Yizhou, Li, Weimin
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Media S.A 07.04.2022
• Subjects: Algorithms; Artificial Intelligence; B7-H1 Antigen - metabolism; Carcinoma, Non-Small-Cell Lung - pathology; Deep Learning; Humans; Immunology; lung cancer; Lung Neoplasms - pathology; PD-L1 expression; radiomics; survival; lung cancer; PD-L1 expression; deep learning; radiomics; survival
• ISSN: 1664-3224; 1664-3224
• DOI: 10.3389/fimmu.2022.828560

Programmed death-ligand 1 (PD-L1) assessment of lung cancer in immunohistochemical assays was only approved diagnostic biomarker for immunotherapy. But the tumor proportion score (TPS) of PD-L1 was challenging owing to invasive sampling and intertumoral heterogeneity. There was a strong demand for the development of an artificial intelligence (AI) system to measure PD-L1 expression signature (ES) non-invasively. We developed an AI system using deep learning (DL), radiomics and combination models based on computed tomography (CT) images of 1,135 non-small cell lung cancer (NSCLC) patients with PD-L1 status. The deep learning feature was obtained through a 3D ResNet as the feature map extractor and the specialized classifier was constructed for the prediction and evaluation tasks. Then, a Cox proportional-hazards model combined with clinical factors and PD-L1 ES was utilized to evaluate prognosis in survival cohort. The combination model achieved a robust high-performance with area under the receiver operating characteristic curves (AUCs) of 0.950 (95% CI, 0.938-0.960), 0.934 (95% CI, 0.906-0.964), and 0.946 (95% CI, 0.933-0.958), for predicting PD-L1ES <1%, 1-49%, and ≥50% in validation cohort, respectively. Additionally, when combination model was trained on multi-source features the performance of overall survival evaluation (C-index: 0.89) could be superior compared to these of the clinical model alone (C-index: 0.86). A non-invasive measurement using deep learning was proposed to access PD-L1 expression and survival outcomes of NSCLC. This study also indicated that deep learning model combined with clinical characteristics improved prediction capabilities, which would assist physicians in making rapid decision on clinical treatment options.