MedMNIST v2 - A large-scale lightweight benchmark for 2D and 3D biomedical image classification
By Jiancheng Yang, Rui Shi, Donglai Wei, Zequan Liu, Lin Zhao, B. Ke, Hanspeter Pfister, Bingbing Ni. Scientific Data, 2021
1,391 citations recorded by the source corpus.
Measurement(s) supervised machine learning Technology Type(s) machine learning We introduce MedMNIST v2 , a large-scale MNIST-like dataset collection of standardized biomedical images, including 12 datasets for 2D and 6 datasets for 3D. All images are pre-processed into a small size of 28 × 28 (2D) or 28 × 28 × 28 (3D) with the corresponding classification labels so that no background knowledge is required for users. Covering primary data modalities in biomedical images, MedMNIST v2 is designed to perform classification on lightweight 2D and 3D images with various dataset scales (from 100 to 100,000) and diverse tasks (binary/multi-class, ordinal regression, and multi-label). The resulting dataset, consisting of 708,069 2D images and 9,998 3D images in total, could support numerous research/educational purposes in biomedical image analysis, computer vision, and machine learning. We benchmark several baseline methods on MedMNIST v2, including 2D/3D neural networks and open-source/commercial AutoML tools. The data and code are publicly available at https://medmnist.com/ .
Subfields: Artificial Intelligence, Radiology, Nuclear Medicine and Imaging
View Paper: https://www.semanticscholar.org/paper/a66606a0bb11a1d5a7a14ec09df8a3481121ad6c
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Weidi Xie
- Shahriar Baradaran Shokouhi
- Ahmad Ayatollahi
- Yanfeng Wang
- Omid Nejati Manzari
- Hamid Ahmadabadi
- Ya Zhang
- Hossein Kashiani
Citations in the corpus
- PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents (2023, background): “Spcifically, MedMINIST [31] contains 12 tasks in total, and it covers primary data modalities in biomedical images, including Colon Pathology, Dermatoscope, Retinal OCT, etc.”
- MedViT: A Robust Vision Transformer for Generalized Medical Image Classification (2023, methodology): “The pre-processing and split of the datasets into training, validation and test subsets have been done according to [63].”