Minimalist Histopathology image analysis dataset
The minimalist histopathology image analysis dataset (MHIST) is a binary classification dataset of 3,152 fixed-size images of colorectal polyps, each with a gold-standard label determined by the majority vote of seven board-certified gastrointestinal pathologists. MHIST also includes each image’s annotator agreement level. As a minimalist dataset, MHIST occupies less than 400 MB of disk space, and a ResNet-18 baseline can be trained to convergence on MHIST in just 6 minutes using approximately 3.5 GB of memory on a NVIDIA RTX 3090. As example use cases, the authors use MHIST to study natural questions that arise in histopathology image classification such as how dataset size, network depth, transfer learning, and high-disagreement examples affect model performance.
Source: Wei et al.
Image source: Wei et al.
Variants: MHIST
This dataset is used in 1 benchmark:
Task | Model | Paper | Date |
---|---|---|---|
Classification | MoCo-v2 (ResNet-50) | Benchmarking Self-Supervised Learning on Diverse … | 2022-12-09 |
Classification | Supervised (ViT-S/16) | Benchmarking Self-Supervised Learning on Diverse … | 2022-12-09 |
Classification | Barlow Rwins (ResNet-50) | Benchmarking Self-Supervised Learning on Diverse … | 2022-12-09 |
Classification | DINO (ViT-S/16) | Benchmarking Self-Supervised Learning on Diverse … | 2022-12-09 |
Classification | Supervised (ResNet-50) | Benchmarking Self-Supervised Learning on Diverse … | 2022-12-09 |
Classification | SwAV (ResNet-50) | Benchmarking Self-Supervised Learning on Diverse … | 2022-12-09 |
Recent papers with results on this dataset: