Automatic fine-grained glomerular lesion recognition in kidney pathology

•This paper proposed an efficient scheme for fine-grained lesion recognition in kidney pathology to help pathologists make more objective and effective clinical diagnoses.•The proposed method has improved segmentation performance by optimizing the structural integrity through instance.•The proposed method has addressed the fine-grained lesion classification by incorporating uncertainty assessment and data reconstitution, without any bounding box annotation or adversarial model.