RESUMEN
BACKGROUND AND AIMS: Evaluation of the programmed cell death ligand-1 (PD-L1) combined positive score (CPS) is vital to predict the efficacy of the immunotherapy in triple-negative breast cancer (TNBC), but pathologists show substantial variability in the consistency and accuracy of the interpretation. It is of great importance to establish an objective and effective method which is highly repeatable. METHODS: We proposed a model in a deep learning-based framework, which at the patch level incorporated cell analysis and tissue region analysis, followed by the whole-slide level fusion of patch results. Three rounds of ring studies (RSs) were conducted. Twenty-one pathologists of different levels from four institutions evaluated the PD-L1 CPS in TNBC specimens as continuous scores by visual assessment and our artificial intelligence (AI)-assisted method. RESULTS: In the visual assessment, the interpretation results of PD-L1 (Dako 22C3) CPS by different levels of pathologists have significant differences and showed weak consistency. Using AI-assisted interpretation, there were no significant differences between all pathologists (P = 0.43), and the intraclass correlation coefficient (ICC) value was increased from 0.618 [95% confidence interval (CI) = 0.524-0.719] to 0.931 (95% CI = 0.902-0.955). The accuracy of interpretation result is further improved to 0.919 (95% CI = 0.886-0.947). Acceptance of AI results by junior pathologists was the highest among all levels, and 80% of the AI results were accepted overall. CONCLUSION: With the help of the AI-assisted diagnostic method, different levels of pathologists achieved excellent consistency and repeatability in the interpretation of PD-L1 (Dako 22C3) CPS. Our AI-assisted diagnostic approach was proved to strengthen the consistency and repeatability in clinical practice.
RESUMEN
Background: Most of its issues are still undecided on the relationship between tumour mutation burden (TMB) and immune-related genes in the breast cancer. This study explores their relationship based on gene mutation and transcription data in The Cancer Genome Atlas (TCGA) database, and the effects of immune cells in TMB and tumour microenvironments on prognosis of breast cancer patients. Methods: Cases were divided into low-TMB and high-TMB subgroups. Differentially expressed immune-related genes were identified in different TMB subgroups, and patient prognosis was predicted by gene function enrichment analysis, invasive immune cells and different clinical pathological features were compared among different TMB subgroups. Results: A total of 986 mutation data from breast cancer patients were obtained. Compared with low-TMB group, the survival period of high-TMB group was relatively longer. A total of 337 differential expression genes were identified in this study. Of these genes, seven differentially expressed immune-related genes were associated with prognosis. In the high-TMB group, activated CD4+ memory T cells and other cells had high expression, the expression ratio of memory B cells and other cells in low-TMB group was high. Conclusions: TMB-related immunological infiltration characteristics showed meaningful value for prognosis prediction for breast cancer patients. Differentially expressed immune-related genes in TMB subgroups provide important information on the survival prediction.