Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jan 8, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

LBNet: an optimized lightweight CNN for mammographic breast cancer classification with XAI-based interpretability.

Jalal Ahmmed¹, Faruk Ahmed², Md Alamgir Kabir³

¹Department of Computer Science and Engineering, Daffodil International University, Dhaka, Bangladesh.

Scientific Reports

|December 16, 2025

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Compact on-chip fluorescence microscope for dynamic imaging of cellular processes and biomimetic systems.

JPhys photonics·2026

Same author

Methodological concerns in the comparative evaluation of PORTs and PICCs: limitations of indirect evidence synthesis in a recent meta-analysis.

Expert review of medical devices·2026

Same author

Loss of zinc from zinc-biofortified rice and conventional rice varieties due to various cooking techniques practiced in rural Bangladesh.

Journal of the science of food and agriculture·2026

Same author

LXNet: A lightweight CNN for lung disease classification from Chest X-ray with XAI-based interpretability.

PloS one·2026

Same author

Explainable Text-Based Depression and Suicide Risk Prediction from Social Media Using Deep Learning and Graph Neural Networks.

Healthcare (Basel, Switzerland)·2026

Same author

An integrated CMOS micro search‑coil magnetometer with on‑chip calibration and a low‑noise amplifier.

Microsystems & nanoengineering·2026

A new lightweight deep learning model, LBNet, achieves high accuracy for breast cancer detection. This interpretable convolutional neural network (CNN) offers efficient and generalizable mammographic analysis, outperforming existing methods.

Area of Science:

Medical Imaging
Artificial Intelligence
Oncology

Background:

Breast cancer poses a significant global health challenge.
Current deep learning models for mammography face issues with computational complexity, generalizability, and interpretability.
Resource-constrained settings require efficient and accurate diagnostic tools.

Purpose of the Study:

Introduce LBNet, a lightweight and interpretable convolutional neural network (CNN) for breast cancer detection.
Address the limitations of existing deep learning models in terms of efficiency and interpretability.
Provide an accurate and computationally efficient solution for mammographic analysis.

Main Methods:

Developed LBNet, a CNN with 2.4 million parameters, featuring five convolutional layers, ReLU activation, batch normalization, and max-pooling.

Keywords:

Breast cancer Explainable AI Grad-CAM Lightweight CNN Mammography SHAP Transfer learning

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Related Experiment Videos

Last Updated: Jan 8, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Trained LBNet on the RSNA dataset using the Adam optimizer and five-fold cross-validation.

Integrated SHAP and Grad-CAM for model interpretability, highlighting diagnostically relevant regions.

Main Results:

LBNet achieved 97.28% accuracy on the RSNA dataset, with high precision and recall for both cancer and non-cancer cases.
Demonstrated superior performance compared to baseline models (VGG19, SE-ResNet152, ResNet152V2) and transfer learning approaches.
Validated generalizability with 99.54% accuracy on CBIS-DDSM and 98.50% on MIAS datasets.

Conclusions:

LBNet presents a highly accurate, efficient, and interpretable solution for breast cancer screening.
The model's lightweight design and validated generalizability make it suitable for resource-constrained environments.
Interpretability methods enhance clinical trust and transparency in AI-driven mammographic analysis.