Deep learning trained on lymph node status predicts outcome from gastric cancer histopathology: a retrospective multicentric study

Gastric cancer (GC) is a tumor entity with highly variant outcomes. Lymph node metastasis is a prognostically adverse biomarker. We hypothesized that GC primary tissue contains information that is predictive of lymph node status and patient prognosis and that this information can be extracted using Deep Learning (DL). Using three patient cohorts comprising 1146 patients, we trained and validated a DL system to predict lymph node status directly from hematoxylin-and-eosin stained GC tissue sections. We investigated the concordance between the DL-based prediction from the primary tumor slides (aiN score) and the histopathological lymph node status (pN). Furthermore, we assessed the prognostic value of the aiN score alone and when combined with the pN status. The aiN score predicted the pN status reaching Area Under the Receiver Operating Characteristic curves (AUROCs) of 0.71 in the training cohort and 0.69 and 0.65 in the two test cohorts. In a multivariate Cox analysis, the aiN score was an independent predictor of patient survival with Hazard Ratios (HR) of 1.5 in the training cohort and of 1.3 and 2.2 in the two test cohorts. A combination of the aiN score and the pN status prognostically stratified patients by survival with p-values <0.05 in log-rank tests. GC primary tumor tissue contains additional prognostic information that is accessible using the aiN score. In combination with the pN status, this can be used for personalized management of gastric cancer patients after prospective validation.