Fig. 6From: Reverse active learning based atrous DenseNet for pathological image classificationExamples from the Cervical Carcinoma Grade dataset (CCG). a Normal slice, b Cancer-level I slice, c Cancer-level II slice, d Cancer-level III slice. The resolution of the slices is in gigapixels, i.e., 16,473×21,163. The areas in red squares have been enlarged for illustrationBack to article page