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

Abstract

BackgroundProgrammed 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.MethodsWe 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.ResultsThe 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).ConclusionA 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.

What does radiomics do in PD‐L1 blockade therapy of NSCLC patients?

“…In order to simultaneously construct a prediction model of PD‐L1 expression and prognosis, Wang et al also used radiomics combined with 3D ResNet to construct a PD‐L1ES model based on the information of 1135 patients to complete the three‐classification task and prognosis prediction. Its AUCs for PD‐L1ES <1%, 1%–49%, and ≥50% in the prediction validation cohort were 0.950, 0.934, and 0.946, respectively 57 …”

“…Its AUCs for PD-L1ES <1%, 1%-49%, and ≥50% in the prediction validation cohort were 0.950, 0.934, and 0.946, respectively. 57 In addition, there are two studies in which the cutoff value for evaluating PD-L1 expression by immunohistochemical staining of pathological tissues of NSCLC patients was not noted. Wang et al combined traditional radiomic methods with convolutional neural networks to simultaneously predict PD-L1 and EGFR expression to complete the fourclassification task.…”

“…Its AUCs for PD‐L1ES <1%, 1%–49%, and ≥50% in the prediction validation cohort were 0.950, 0.934, and 0.946, respectively. 57 …”

Advances in artificial intelligence to predict cancer immunotherapy efficacy

“…Additionally, AI-based predictive models can provide reliable non-invasive biomarkers for evaluating immunotherapeutic response. Among various biomarkers, PD-L1 expression has been well validated in immunotherapy, and a combined model based on CT radiomics and clinical features can assess PD-L1 expression levels non-invasively (28) (30) analyzed baseline PET/CT data of 194 patients with stage IIIB-IV NSCLC treated with PD-1/PD-L1 inhibitors, and they developed multiparametric imaging histological signature models which successfully predict whether patients would receive sustained clinical benefit from immunotherapy. However, further research is still required to determine whether models utilizing several data sources can perform better than models that simply use radiomics.…”

The Application of Artificial Intelligence in the Diagnosis and Drug Resistance Prediction of Pulmonary Tuberculosis

“…The prosperity of AI applied to the medical field, especially in respiratory system, has attracted substantial attention with promising results, such as detection of pulmonary nodules (21) and prediction of treatment response or outcome of lung cancer (22,23). Meanwhile, we have made excellent achievements, including diagnosis and discrimination of 2019 novel coronavirus pneumonia (24), predetermination of epidermal growth factor receptor (EGFR) gene mutation status, programmed death ligand-1 (PD-L1) expression level, and target therapy effect in patients with lung cancer (25)(26)(27).…”