# Beyond Fine-tuning: Classifying High Resolution Mammograms using Function-Preserving Transformations

arXiv: https://arxiv.org/abs/2101.07945 · HTML: https://mlsanity.com/paper/2101.07945/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 59 references that are in the map.
- First posted on arXiv 20 Jan 2021.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning](https://mlsanity.com/paper/1711.05225/) (2017)
- [Net2Net: Accelerating Learning via Knowledge Transfer](https://mlsanity.com/paper/1511.05641/) (2015)
- [Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening](https://mlsanity.com/paper/1903.08297/) (2019)
- [End-to-end Training for Whole Image Breast Cancer Diagnosis using An All Convolutional Design](https://mlsanity.com/paper/1711.05775/) (2017)
- [Network Morphism](https://mlsanity.com/paper/1603.01670/) (2016)
- [Comparison of Deep Learning Approaches for Multi-Label Chest X-Ray Classification](https://mlsanity.com/paper/1803.02315/) (2018)
- [Detecting and classifying lesions in mammograms with Deep Learning](https://mlsanity.com/paper/1707.08401/) (2017)
- [An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization](https://mlsanity.com/paper/2002.07613/) (2020)
- [Learning to diagnose from scratch by exploiting dependencies among labels](https://mlsanity.com/paper/1710.10501/) (2017)
- [Learning to recognize Abnormalities in Chest X-Rays with Location-Aware Dense Networks](https://mlsanity.com/paper/1803.04565/) (2018)
- [High-Resolution Breast Cancer Screening with Multi-View Deep Convolutional Neural Networks](https://mlsanity.com/paper/1703.07047/) (2017)
- [Weakly Supervised Medical Diagnosis and Localization from Multiple Resolutions](https://mlsanity.com/paper/1803.07703/) (2018)
- [AUNet: Attention-guided dense-upsampling networks for breast mass segmentation in whole mammograms](https://mlsanity.com/paper/1810.10151/) (2018)
- [GraphXNET- Chest X-Ray Classification Under Extreme Minimal Supervision](https://mlsanity.com/paper/1907.10085/) (2019)
- [Breast Mass Classification from Mammograms using Deep Convolutional Neural Networks](https://mlsanity.com/paper/1612.00542/) (2016)
- [Learning on the Edge: Explicit Boundary Handling in CNNs](https://mlsanity.com/paper/1805.03106/) (2018)
- [Abnormality Detection in Mammography using Deep Convolutional Neural Networks](https://mlsanity.com/paper/1803.01906/) (2018)

## Built on by (most cited first, 5 of 5)

- [Breast Cancer Diagnosis in Two-View Mammography Using End-to-End Trained EfficientNet-Based Convolutional Network](https://mlsanity.com/paper/2110.01606/) (2021)
- [MammoDG: Generalisable Deep Learning Breaks the Limits of Cross-Domain Multi-Center Breast Cancer Screening](https://mlsanity.com/paper/2308.01057/) (2023)
- [Optimizing Breast Cancer Detection in Mammograms: A Comprehensive Study of Transfer Learning, Resolution Reduction, and Multi-View Classification](https://mlsanity.com/paper/2503.19945/) (2025)
- [Hybrid Deep Learning and Handcrafted Feature Fusion for Mammographic Breast Cancer Classification](https://mlsanity.com/paper/2507.19843/) (2025)
- [Is ChatGPT-5 Ready for Mammogram VQA?](https://mlsanity.com/paper/2508.11628/) (2025)

## Abstract (arXiv)

The task of classifying mammograms is very challenging because the lesion is usually small in the high resolution image. The current state-of-the-art approaches for medical image classification rely on using the de-facto method for ConvNets - fine-tuning. However, there are fundamental differences between natural images and medical images, which based on existing evidence from the literature, limits the overall performance gain when designed with algorithmic approaches. In this paper, we propose to go beyond fine-tuning by introducing a novel framework called MorphHR, in which we highlight a new transfer learning scheme. The idea behind the proposed framework is to integrate function-preserving transformations, for any continuous non-linear activation neurons, to internally regularise the network for improving mammograms classification. The proposed solution offers two major advantages over the existing techniques. Firstly and unlike fine-tuning, the proposed approach allows for modifying not only the last few layers but also several of the first ones on a deep ConvNet. By doing this, we can design the network front to be suitable for learning domain specific features. Secondly, the proposed scheme is scalable to hardware. Therefore, one can fit high resolution images on standard GPU memory. We show that by using high resolution images, one prevents losing relevant information. We demonstrate, through numerical and visual experiments, that the proposed approach yields to a significant improvement in the classification performance over state-of-the-art techniques, and is indeed on a par with radiology experts. Moreover and for generalisation purposes, we show the effectiveness of the proposed learning scheme on another large dataset, the ChestX-ray14, surpassing current state-of-the-art techniques.