# Knowledge Distillation to Ensemble Global and Interpretable Prototype-Based Mammogram Classification Models

arXiv: https://arxiv.org/abs/2209.12420 · HTML: https://mlsanity.com/paper/2209.12420/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Distillation for medical imaging, one of 12 directions in Knowledge distillation.
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 26 Sep 2022.

## Placed in

- Knowledge distillation / [Distillation for medical imaging](https://mlsanity.com/distill/distillation-for-medical-imaging/)

## Builds on (most cited first, 12 of 12)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening](https://mlsanity.com/paper/1903.08297/) (2019)
- [XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations](https://mlsanity.com/paper/2103.10663/) (2021)
- [An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization](https://mlsanity.com/paper/2002.07613/) (2020)
- [Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification](https://mlsanity.com/paper/1612.05968/) (2016)
- [Region Proposals for Saliency Map Refinement for Weakly-supervised Disease Localisation and Classification](https://mlsanity.com/paper/2005.10550/) (2020)
- [Learning Interpretable Features via Adversarially Robust Optimization](https://mlsanity.com/paper/1905.03767/) (2019)
- [Meta-repository of screening mammography classifiers](https://mlsanity.com/paper/2108.04800/) (2021)

## Built on by (most cited first, 11 of 11)

- [Learning Support and Trivial Prototypes for Interpretable Image Classification](https://mlsanity.com/paper/2301.04011/) (2023)
- [Interpretable Image Classification with Adaptive Prototype-based Vision Transformers](https://mlsanity.com/paper/2410.20722/) (2024)
- [Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlooks](https://mlsanity.com/paper/2410.02331/) (2024)
- [The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers](https://mlsanity.com/paper/2307.14517/) (2023)
- [Deep Learning in Breast Cancer Imaging: A Decade of Progress and Future Directions](https://mlsanity.com/paper/2304.06662/) (2023)
- [Mixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable and Trustworthy Image Recognition](https://mlsanity.com/paper/2312.00092/) (2023)
- [Don't PANIC: Prototypical Additive Neural Network for Interpretable Classification of Alzheimer's Disease](https://mlsanity.com/paper/2303.07125/) (2023)
- [Cross- and Intra-image Prototypical Learning for Multi-label Disease Diagnosis and Interpretation](https://mlsanity.com/paper/2411.04607/) (2024)
- [Prototype-based Interpretable Breast Cancer Prediction Models: Analysis and Challenges](https://mlsanity.com/paper/2403.20260/) (2024)
- [XAI for Skin Cancer Detection with Prototypes and Non-Expert Supervision](https://mlsanity.com/paper/2402.01410/) (2024)
- [ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question Answering](https://mlsanity.com/paper/2509.16680/) (2025)

## Abstract (arXiv)

State-of-the-art (SOTA) deep learning mammogram classifiers, trained with weakly-labelled images, often rely on global models that produce predictions with limited interpretability, which is a key barrier to their successful translation into clinical practice. On the other hand, prototype-based models improve interpretability by associating predictions with training image prototypes, but they are less accurate than global models and their prototypes tend to have poor diversity. We address these two issues with the proposal of BRAIxProtoPNet++, which adds interpretability to a global model by ensembling it with a prototype-based model. BRAIxProtoPNet++ distills the knowledge of the global model when training the prototype-based model with the goal of increasing the classification accuracy of the ensemble. Moreover, we propose an approach to increase prototype diversity by guaranteeing that all prototypes are associated with different training images. Experiments on weakly-labelled private and public datasets show that BRAIxProtoPNet++ has higher classification accuracy than SOTA global and prototype-based models. Using lesion localisation to assess model interpretability, we show BRAIxProtoPNet++ is more effective than other prototype-based models and post-hoc explanation of global models. Finally, we show that the diversity of the prototypes learned by BRAIxProtoPNet++ is superior to SOTA prototype-based approaches.