# Information Gain Sampling for Active Learning in Medical Image Classification

arXiv: https://arxiv.org/abs/2208.00974 · HTML: https://mlsanity.com/paper/2208.00974/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 1 Aug 2022.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [What makes ImageNet good for transfer learning?](https://mlsanity.com/paper/1608.08614/) (2016)
- [Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation](https://mlsanity.com/paper/1502.02734/) (2015)
- [Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis](https://mlsanity.com/paper/1804.06353/) (2018)
- [A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1910.02923/) (2019)
- [Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation](https://mlsanity.com/paper/1706.04737/) (2017)
- [Synthetic Data Augmentation using GAN for Improved Liver Lesion Classification](https://mlsanity.com/paper/1801.02385/) (2018)
- [Constrained Convolutional Neural Networks for Weakly Supervised Segmentation](https://mlsanity.com/paper/1506.03648/) (2015)
- [Deep Active Learning: Unified and Principled Method for Query and Training](https://mlsanity.com/paper/1911.09162/) (2019)
- [Constrained-CNN losses for weakly supervised segmentation](https://mlsanity.com/paper/1805.04628/) (2018)
- [Posterior Re-calibration for Imbalanced Datasets](https://mlsanity.com/paper/2010.11820/) (2020)
- [How useful is photo-realistic rendering for visual learning?](https://mlsanity.com/paper/1603.08152/) (2016)
- [An Active Learning Approach for Reducing Annotation Cost in Skin Lesion Analysis](https://mlsanity.com/paper/1909.02344/) (2019)
- [Confident Coreset for Active Learning in Medical Image Analysis](https://mlsanity.com/paper/2004.02200/) (2020)

## Built on by (most cited first, 2 of 2)

- [Benchmarking of Query Strategies: Towards Future Deep Active Learning](https://mlsanity.com/paper/2312.05751/) (2023)
- [Team, Then Trim: An Assembly-Line LLM Framework for High-Quality Tabular Data Generation](https://mlsanity.com/paper/2602.04785/) (2026)

## Abstract (arXiv)

Large, annotated datasets are not widely available in medical image analysis due to the prohibitive time, costs, and challenges associated with labelling large datasets. Unlabelled datasets are easier to obtain, and in many contexts, it would be feasible for an expert to provide labels for a small subset of images. This work presents an information-theoretic active learning framework that guides the optimal selection of images from the unlabelled pool to be labeled based on maximizing the expected information gain (EIG) on an evaluation dataset. Experiments are performed on two different medical image classification datasets: multi-class diabetic retinopathy disease scale classification and multi-class skin lesion classification. Results indicate that by adapting EIG to account for class-imbalances, our proposed Adapted Expected Information Gain (AEIG) outperforms several popular baselines including the diversity based CoreSet and uncertainty based maximum entropy sampling. Specifically, AEIG achieves ~95% of overall performance with only 19% of the training data, while other active learning approaches require around 25%. We show that, by careful design choices, our model can be integrated into existing deep learning classifiers.