PRECISe : Prototype-Reservation for Explainable classification under Imbalanced and Scarce-Data Settings

Vaibhav Ganatra, Drishti Goel
Proceedings of the 9th Machine Learning for Healthcare Conference, PMLR 252, 2024.

Abstract

Deep learning models used for medical image classification tasks are often constrained by the limited amount of training data along with severe class imbalance. Despite these problems, models should be explainable to enable human trust in the models’ decisions to ensure wider adoption in high risk situations. In this paper, we propose PRECISe, an explainable-by-design model meticulously constructed to concurrently address all three challenges. Evaluation on 2 imbalanced medical image datasets reveals that PRECISe outperforms the current state-of-the-art methods on data efficient generalization to minority classes, achieving an accuracy of  87% in detecting pneumonia in chest x-rays upon training on <60 images only. Additionally, a case study is presented to highlight the model’s ability to produce easily interpretable predictions, reinforcing its practical utility and reliability for medical imaging tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v252-ganatra24a, title = {{PRECIS}e : Prototype-Reservation for Explainable classification under Imbalanced and Scarce-Data Settings}, author = {Ganatra, Vaibhav and Goel, Drishti}, booktitle = {Proceedings of the 9th Machine Learning for Healthcare Conference}, year = {2024}, editor = {Deshpande, Kaivalya and Fiterau, Madalina and Joshi, Shalmali and Lipton, Zachary and Ranganath, Rajesh and Urteaga, Iñigo}, volume = {252}, series = {Proceedings of Machine Learning Research}, month = {16--17 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v252/main/assets/ganatra24a/ganatra24a.pdf}, url = {https://proceedings.mlr.press/v252/ganatra24a.html}, abstract = {Deep learning models used for medical image classification tasks are often constrained by the limited amount of training data along with severe class imbalance. Despite these problems, models should be explainable to enable human trust in the models’ decisions to ensure wider adoption in high risk situations. In this paper, we propose PRECISe, an explainable-by-design model meticulously constructed to concurrently address all three challenges. Evaluation on 2 imbalanced medical image datasets reveals that PRECISe outperforms the current state-of-the-art methods on data efficient generalization to minority classes, achieving an accuracy of  87% in detecting pneumonia in chest x-rays upon training on <60 images only. Additionally, a case study is presented to highlight the model’s ability to produce easily interpretable predictions, reinforcing its practical utility and reliability for medical imaging tasks.} }
Endnote
%0 Conference Paper %T PRECISe : Prototype-Reservation for Explainable classification under Imbalanced and Scarce-Data Settings %A Vaibhav Ganatra %A Drishti Goel %B Proceedings of the 9th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2024 %E Kaivalya Deshpande %E Madalina Fiterau %E Shalmali Joshi %E Zachary Lipton %E Rajesh Ranganath %E Iñigo Urteaga %F pmlr-v252-ganatra24a %I PMLR %U https://proceedings.mlr.press/v252/ganatra24a.html %V 252 %X Deep learning models used for medical image classification tasks are often constrained by the limited amount of training data along with severe class imbalance. Despite these problems, models should be explainable to enable human trust in the models’ decisions to ensure wider adoption in high risk situations. In this paper, we propose PRECISe, an explainable-by-design model meticulously constructed to concurrently address all three challenges. Evaluation on 2 imbalanced medical image datasets reveals that PRECISe outperforms the current state-of-the-art methods on data efficient generalization to minority classes, achieving an accuracy of  87% in detecting pneumonia in chest x-rays upon training on <60 images only. Additionally, a case study is presented to highlight the model’s ability to produce easily interpretable predictions, reinforcing its practical utility and reliability for medical imaging tasks.
APA
Ganatra, V. & Goel, D.. (2024). PRECISe : Prototype-Reservation for Explainable classification under Imbalanced and Scarce-Data Settings. Proceedings of the 9th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 252 Available from https://proceedings.mlr.press/v252/ganatra24a.html.

Related Material