Interpretable CRAM‑Enhanced Lightweight Dual‑Branch CNN for Real‑Time Breast Cancer Histopathology in Internet‑of‑Medical‑Things Environments
Small · 2026-05 · 22 (26)
DOI: 10.1002/smll.202509066 ↗Kurz gefasst
Fachartikel in der Zeitschrift Small, online erschienen am 19.03.2026. Verfasst von Roseline Oluwaseun Ogundokun und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Multimedia Engineering, Kaunas University of Technology, Kaunas, Lithuania. Hauptthemen laut MEDLINE: Breast Neoplasms, Internet of Things, Internet. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Breast cancer remains a primary global health concern, with histopathological image analysis serving as the diagnostic gold standard. However, manual microscopy is time‐consuming and often subjective. While deep learning offers a powerful solution, existing models are typically too complex and opaque for real‐time use in Internet of Medical Things (IoMT) environments. To address this, we propose an interpretable and lightweight hybrid deep learning model that combines MobileNetV2 and EfficientNet‐B0, enhanced by a novel contextual recurrent attention module (CRAM). CRAM refines fused features through attention‐based weighting, improving focus on diagnostically relevant regions. The model achieved 99.9% classification accuracy and an AUC of 1.00, outperforming standalone baselines while remaining efficient (∼12 M parameters) and suitable for IoMT deployment. Interpretability is ensured through integrated Grad‐CAM and SHAP analyses, which visually and quantitatively explain predictions by highlighting malignant tissue features that align with pathologist judgment. This balance of accuracy, efficiency, and transparency enables real‐time, trustworthy diagnostics for resource‐limited and point‐of‐care settings. Future work includes extending to multi‐class tumor subtypes and clinical validation in real‐world workflows. The proposed system represents a significant step toward making AI in digital pathology more accessible and explainable.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Multimedia Engineering, Kaunas University of Technology, Kaunas, Lithuania.
- Department of Computer Systems Engineering, Tshwane University of Technology, Pretoria, South Africa.
- Department of Computer Science, Redeemer's University, Ede, Osun, Nigeria.
- Department of Software Engineering, Kaunas University of Technology, Kaunas, Lithuania.
- Business Management Department, Catholic University in Erbil, Erbil, Kurdistan, Iraq.
ORCID-Profile: Roseline Oluwaseun Ogundokun
Zitieren
APA
Ogundokun, R. O., Bello, R. W., Owolawi, P. A., Maskeliūnas, R., & Sultan, A. A. (2026). Interpretable CRAM‑Enhanced Lightweight Dual‑Branch CNN for Real‑Time Breast Cancer Histopathology in Internet‑of‑Medical‑Things Environments. Small, 22(26). https://doi.org/10.1002/smll.202509066
Vancouver
Ogundokun RO, Bello RW, Owolawi PA, Maskeliūnas R, Sultan AA. Interpretable CRAM‑Enhanced Lightweight Dual‑Branch CNN for Real‑Time Breast Cancer Histopathology in Internet‑of‑Medical‑Things Environments. Small. 2026;22(26). doi:10.1002/smll.202509066
BibTeX
@article{Ogundokun2026,
author = {Ogundokun, Roseline Oluwaseun and Bello, Rotimi-Williams and Owolawi, Pius Adewale and Maskeliūnas, Rytis and Sultan, Abdulsatar Abduljabbar},
title = {Interpretable CRAM‑Enhanced Lightweight Dual‑Branch CNN for Real‑Time Breast Cancer Histopathology in Internet‑of‑Medical‑Things Environments},
journal = {Small},
year = {2026},
volume = {22},
number = {26},
doi = {10.1002/smll.202509066}
}
EUVIMED