Breast density classification and decision explainability by deep sparse approximations
(2026) Medical Imaging 2026: Computer-Aided Diagnosis In Progress in Biomedical Optics and Imaging - Proceedings of SPIE 13926.- Abstract
Breast density, defined as the proportion of breast tissue composed of dense fibroglandular tissue, is a crucial factor in assessing breast cancer risk and significantly impacts the visibility of lesions during mammography screening. We focus on distinguishing between high and low breast density by fine-tuning deep neural networks and on our joint deep and sparse approximation methodology. We evaluate the performance of these approaches in classifying high versus low breast density. Furthermore, we propose an example-based explainable AI approach denoted as Deep Sparse Reconstruct (DSR), which visualizes the most influential deep features in the corresponding mammogram region of interest, identified by non-negative sparse... (More)
Breast density, defined as the proportion of breast tissue composed of dense fibroglandular tissue, is a crucial factor in assessing breast cancer risk and significantly impacts the visibility of lesions during mammography screening. We focus on distinguishing between high and low breast density by fine-tuning deep neural networks and on our joint deep and sparse approximation methodology. We evaluate the performance of these approaches in classifying high versus low breast density. Furthermore, we propose an example-based explainable AI approach denoted as Deep Sparse Reconstruct (DSR), which visualizes the most influential deep features in the corresponding mammogram region of interest, identified by non-negative sparse representations derived from a training dictionary. We also utilize established explainable AI techniques that visualize model predictions to facilitate comparisons. Our findings support that DSR enhances interpretability by extracting the key training features that contribute to predictions, it is compatible with various deep network architectures, and may contribute towards the development of trustworthy AI diagnostic workflows.
(Less)
- author
- Harris, Chelsea E. ; Liu, Lingling ; Kennady, Dhiwahar Adhithya ; Bakic, Predrag R. LU and Makrogiannis, Sokratis
- organization
- publishing date
- 2026-04-02
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Breast cancer risk, disease diagnosis, explainable AI, mammography
- host publication
- Medical Imaging 2026 : Computer-Aided Diagnosis - Computer-Aided Diagnosis
- series title
- Progress in Biomedical Optics and Imaging - Proceedings of SPIE
- editor
- Wismuller, Axel and Deserno, Thomas Martin
- volume
- 13926
- article number
- 139260P
- publisher
- SPIE
- conference name
- Medical Imaging 2026: Computer-Aided Diagnosis
- conference location
- Vancouver, Canada
- conference dates
- 2026-02-15 - 2026-02-19
- external identifiers
-
- scopus:105041283837
- ISSN
- 2410-9045
- 1605-7422
- ISBN
- 9781510697898
- DOI
- 10.1117/12.3084578
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © COPYRIGHT SPIE.
- id
- 89addc87-ee3d-43b8-97b2-ed99570f730b
- date added to LUP
- 2026-07-23 13:41:44
- date last changed
- 2026-10-02 08:14:08
@inproceedings{89addc87-ee3d-43b8-97b2-ed99570f730b,
abstract = {{<p>Breast density, defined as the proportion of breast tissue composed of dense fibroglandular tissue, is a crucial factor in assessing breast cancer risk and significantly impacts the visibility of lesions during mammography screening. We focus on distinguishing between high and low breast density by fine-tuning deep neural networks and on our joint deep and sparse approximation methodology. We evaluate the performance of these approaches in classifying high versus low breast density. Furthermore, we propose an example-based explainable AI approach denoted as Deep Sparse Reconstruct (DSR), which visualizes the most influential deep features in the corresponding mammogram region of interest, identified by non-negative sparse representations derived from a training dictionary. We also utilize established explainable AI techniques that visualize model predictions to facilitate comparisons. Our findings support that DSR enhances interpretability by extracting the key training features that contribute to predictions, it is compatible with various deep network architectures, and may contribute towards the development of trustworthy AI diagnostic workflows.</p>}},
author = {{Harris, Chelsea E. and Liu, Lingling and Kennady, Dhiwahar Adhithya and Bakic, Predrag R. and Makrogiannis, Sokratis}},
booktitle = {{Medical Imaging 2026 : Computer-Aided Diagnosis}},
editor = {{Wismuller, Axel and Deserno, Thomas Martin}},
isbn = {{9781510697898}},
issn = {{2410-9045}},
keywords = {{Breast cancer risk; disease diagnosis; explainable AI; mammography}},
language = {{eng}},
month = {{04}},
publisher = {{SPIE}},
series = {{Progress in Biomedical Optics and Imaging - Proceedings of SPIE}},
title = {{Breast density classification and decision explainability by deep sparse approximations}},
url = {{http://dx.doi.org/10.1117/12.3084578}},
doi = {{10.1117/12.3084578}},
volume = {{13926}},
year = {{2026}},
}