Image Classification with Consistent Supporting Evidence

Peiqi Wang, Ruizhi Liao, Daniel Moyer, Seth Berkowitz, Steven Horng, Polina Golland
Proceedings of Machine Learning for Health, PMLR 158:168-180, 2021.

Abstract

Adoption of machine learning models in healthcare requires end users’ trust in the system. Models that provide additional supportive evidence for their predictions promise to facilitate adoption. We define consistent evidence to be both compatible and sufficient with respect to model predictions. We propose measures of model inconsistency and regularizers that promote more consistent evidence. We demonstrate our ideas in the context of edema severity grading from chest radiographs. We demonstrate empirically that consistent models provide competitive performance while supporting interpretation.

Cite this Paper

BibTeX
@InProceedings{pmlr-v158-wang21a, title = {Image Classification with Consistent Supporting Evidence}, author = {Wang, Peiqi and Liao, Ruizhi and Moyer, Daniel and Berkowitz, Seth and Horng, Steven and Golland, Polina}, booktitle = {Proceedings of Machine Learning for Health}, pages = {168--180}, year = {2021}, editor = {Roy, Subhrajit and Pfohl, Stephen and Rocheteau, Emma and Tadesse, Girmaw Abebe and Oala, Luis and Falck, Fabian and Zhou, Yuyin and Shen, Liyue and Zamzmi, Ghada and Mugambi, Purity and Zirikly, Ayah and McDermott, Matthew B. A. and Alsentzer, Emily}, volume = {158}, series = {Proceedings of Machine Learning Research}, month = {04 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v158/wang21a/wang21a.pdf}, url = {https://proceedings.mlr.press/v158/wang21a.html}, abstract = {Adoption of machine learning models in healthcare requires end users’ trust in the system. Models that provide additional supportive evidence for their predictions promise to facilitate adoption. We define consistent evidence to be both compatible and sufficient with respect to model predictions. We propose measures of model inconsistency and regularizers that promote more consistent evidence. We demonstrate our ideas in the context of edema severity grading from chest radiographs. We demonstrate empirically that consistent models provide competitive performance while supporting interpretation.} }
Endnote
%0 Conference Paper %T Image Classification with Consistent Supporting Evidence %A Peiqi Wang %A Ruizhi Liao %A Daniel Moyer %A Seth Berkowitz %A Steven Horng %A Polina Golland %B Proceedings of Machine Learning for Health %C Proceedings of Machine Learning Research %D 2021 %E Subhrajit Roy %E Stephen Pfohl %E Emma Rocheteau %E Girmaw Abebe Tadesse %E Luis Oala %E Fabian Falck %E Yuyin Zhou %E Liyue Shen %E Ghada Zamzmi %E Purity Mugambi %E Ayah Zirikly %E Matthew B. A. McDermott %E Emily Alsentzer %F pmlr-v158-wang21a %I PMLR %P 168--180 %U https://proceedings.mlr.press/v158/wang21a.html %V 158 %X Adoption of machine learning models in healthcare requires end users’ trust in the system. Models that provide additional supportive evidence for their predictions promise to facilitate adoption. We define consistent evidence to be both compatible and sufficient with respect to model predictions. We propose measures of model inconsistency and regularizers that promote more consistent evidence. We demonstrate our ideas in the context of edema severity grading from chest radiographs. We demonstrate empirically that consistent models provide competitive performance while supporting interpretation.
APA
Wang, P., Liao, R., Moyer, D., Berkowitz, S., Horng, S. & Golland, P.. (2021). Image Classification with Consistent Supporting Evidence. Proceedings of Machine Learning for Health, in Proceedings of Machine Learning Research 158:168-180 Available from https://proceedings.mlr.press/v158/wang21a.html.

Related Material