MiniDigPath: a New Standard for Pathology Images Few-Shot Learning Classification

EasyChair Preprint 9689

Abstract

 The miniDigPath dataset, which composed by 6 public pathology image datasets, is proposed by our work for few-shot learning (FSL). It consists 67 different diseases and tissue types, and every type has 48-500 tissue image blocks. In total, there are 21165 histopathology images. Importantly, miniDigPath is available publicly for every researcher. It explores a new idea to solve pathological images annotation using FSL, which is the importance and originality of the dataset we proposed. Experimental evaluation on the classical FSL algorithm and our method shows that the miniDigPath dataset can accomplish the task of FSL. Besides, FSL has good advantage for classification of digital pathology images.

Keyphrases: digital pathology images, few-shot learning, miniDigPath

@booklet{EasyChair:9689,
  author    = {Yan-Dong Du and Lin Feng and Xin-Lei Liu},
  title     = {MiniDigPath: a New Standard for Pathology Images Few-Shot Learning Classification},
  howpublished = {EasyChair Preprint 9689},
  year      = {EasyChair, 2023}}