Figure 3
From: A deep learning model for gastric diffuse-type adenocarcinoma classification in whole slide images
Representative true positive diffuse-type gastric ADC cases from endoscopic biopsy test set. Case-1 (a–d) is a poorly-differentiated ADC and Case-2 (e–g) is a SRCC. Heatmap images (b and f) show true positive predictions of poorly-differentiated ADC (b) and SRCC (f) cells and they correspond respectively to (a) and (e) H&E histopathology. The high magnification images (c, d, and g) show representative poorly-differentiated ADC (c and d) and SRCC (g) cellular morphology. Model applied at \(\times \) 20, where the 224 \(\times \) 224px heatmap square represents 112 \(\times \) 112 \({\upmu }\)m\(^2\).
