# Less is More: Selective Reduction of CT Data for Self-Supervised Pre-Training of Deep Learning Models with Contrastive Learning Improves Downstream Classification Performance

arXiv: https://arxiv.org/abs/2410.14524 · HTML: https://mlsanity.com/paper/2410.14524/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 68 references that are in the map.
- First posted on arXiv 18 Oct 2024.

## Builds on (most cited first, 13 of 13)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [Understanding Dimensional Collapse in Contrastive Self-supervised Learning](https://mlsanity.com/paper/2110.09348/) (2021)
- [Transfusion: Understanding Transfer Learning for Medical Imaging](https://mlsanity.com/paper/1902.07208/) (2019)
- [Selection via Proxy: Efficient Data Selection for Deep Learning](https://mlsanity.com/paper/1906.11829/) (2019)
- [A Cookbook of Self-Supervised Learning](https://mlsanity.com/paper/2304.12210/) (2023)
- [COVID-CT-Dataset: A CT Scan Dataset about COVID-19](https://mlsanity.com/paper/2003.13865/) (2020)
- [Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling](https://mlsanity.com/paper/2301.03580/) (2023)
- [Coresets for Data-efficient Training of Machine Learning Models](https://mlsanity.com/paper/1906.01827/) (2019)
- [Comparison of 2D vs. 3D U-Net Organ Segmentation in abdominal 3D CT images](https://mlsanity.com/paper/2107.04062/) (2021)

## Abstract (arXiv)

Self-supervised pre-training of deep learning models with contrastive learning is a widely used technique in image analysis. Current findings indicate a strong potential for contrastive pre-training on medical images. However, further research is necessary to incorporate the particular characteristics of these images. We hypothesize that the similarity of medical images hinders the success of contrastive learning in the medical imaging domain. To this end, we investigate different strategies based on deep embedding, information theory, and hashing in order to identify and reduce redundancy in medical pre-training datasets. The effect of these different reduction strategies on contrastive learning is evaluated on two pre-training datasets and several downstream classification tasks. In all of our experiments, dataset reduction leads to a considerable performance gain in downstream tasks, e.g., an AUC score improvement from 0.78 to 0.83 for the COVID CT Classification Grand Challenge, 0.97 to 0.98 for the OrganSMNIST Classification Challenge and 0.73 to 0.83 for a brain hemorrhage classification task. Furthermore, pre-training is up to nine times faster due to the dataset reduction. In conclusion, the proposed approach highlights the importance of dataset quality and provides a transferable approach to improve contrastive pre-training for classification downstream tasks on medical images.