ER2Net: an evidential reasoning rule–enabled neural network for reliable triple-negative breast cancer tumor segmentation in magnetic resonance imaging
ER<sup>2</sup>Net introduces WR segmentation and BF as enhanced fusion techniques and PWRE as a uncertainty metric. Together, these advances improve segmentation accuracy, sensitivity, confidence calibration, and uncertainty estimation, paving the way for reliable MRI-based tools to support personalized treatment planning and response assessment in TNBC.
Authors
- Ahmad Qasem (ORCID: https://orcid.org/0000-0003-3740-6963)
- Rachel Yoder (ORCID: https://orcid.org/0009-0008-6800-1743)
- Joshua M. Staley (ORCID: https://orcid.org/0000-0001-9273-0286)
- Allison Aripoli (ORCID: https://orcid.org/0000-0002-7379-6025)
- Priyanka Sharma (ORCID: https://orcid.org/0000-0001-9270-8492)
- Shane Richard Stecklein (ORCID: https://orcid.org/0000-0001-8322-5886)
- Zhiguo Zhou (ORCID: https://orcid.org/0000-0003-4031-3178)
- Kazi Md Farhad Mahmud
Institutions
- The University of Kansas Cancer Center (US)
- University of Kansas Medical Center (US)
Publication Details
- Journal
- Journal of Medical Imaging
- Published
- 2026-01-29
- DOI
- https://doi.org/10.1117/1.jmi.13.1.014005
- Primary Topic
- MRI in cancer diagnosis
- Type
- article
- Field-Weighted Citation Impact
- 0.00