Predicting Lymph Node Metastasis Status from Primary Muscle-Invasive Bladder Cancer Histology Slides Using Deep Learning: A Retrospective Multicenter Study

SIMPLE SUMMARY: Accurate prediction of lymph node metastasis (LNM) status in patients with muscle-invasive bladder cancer (MIBC) before radical cystectomy can guide the use of neoadjuvant chemotherapy and the extent of pelvic lymph node dissection. However, there are no reliable tools available for achieving this goal. Data-driven deep-learning techniques have been widely used in disease diagnosis, prognosis assessment, and treatment response prediction by identifying subtle patterns in digitized histopathological images. In this study, we developed a weakly-supervised model based on multiple instance learning and attention mechanism for predicting LNM status in MIBC patients, demonstrating decent performance in three independent cohorts. The visualization technique revealed that the stroma surrounding the tumor with lymphocytic inflammation seemed to be the critical feature for predicting LNM. This deep learning-based study provides a non-invasive and low-cost preoperative prediction tool for identifying MIBC patients with a high risk of LNM. ABSTRACT: Background: Accurate prediction of lymph node metastasis (LNM) status in patients with muscle-invasive bladder cancer (MIBC) before radical cystectomy can guide the use of neoadjuvant chemotherapy and the extent of pelvic lymph node dissection. We aimed to develop and validate a weakly-supervised deep learning model to predict LNM status from digitized histopathological slides in MIBC. Methods: We trained a multiple instance learning model with an attention mechanism (namely SBLNP) from a cohort of 323 patients in the TCGA cohort. In parallel, we collected corresponding clinical information to construct a logistic regression model. Subsequently, the score predicted by the SBLNP was incorporated into the logistic regression model. In total, 417 WSIs from 139 patients in the RHWU cohort and 230 WSIs from 78 patients in the PHHC cohort were used as independent external validation sets. Results: In the TCGA cohort, the SBLNP achieved an AUROC of 0.811 (95% confidence interval [CI], 0.771–0.855), the clinical classifier achieved an AUROC of 0.697 (95% CI, 0.661–0.728) and the combined classifier yielded an improvement to 0.864 (95% CI, 0.827–0.906). Encouragingly, the SBLNP still maintained high performance in the RHWU cohort and PHHC cohort, with an AUROC of 0.762 (95% CI, 0.725–0.801) and 0.746 (95% CI, 0.687–0.799), respectively. Moreover, the interpretability of SBLNP identified stroma with lymphocytic inflammation as a key feature of predicting LNM presence. Conclusions: Our proposed weakly-supervised deep learning model can predict the LNM status of MIBC patients from routine WSIs, demonstrating decent generalization performance and holding promise for clinical implementation.