What type of study is this?

September 10, 2025Engineering Technology & Applied Science ResearchOpen Access

CNN-Based Automated Detection of Metastatic Cancer in Histopathology Images

View Full Paper

Ask AI

Bookmark

Authors

OAOmaia Al-OmariPrince Sultan University OAOmar AlkhatibFreeman Hospital TATariq Al-OmariJordan University of Science and Technology

Discussion

Member takes

Overview

This analysis demonstrates an enhanced deep learning framework improving diagnostic accuracy for breast cancer, indicating vital advancements in AI-assisted histopathology.

Key Points

The proposed CNN framework achieved a test accuracy of 92.33% on the BreaKHis dataset, significantly outperforming traditional classifiers.
Gradient-weighted class activation mapping (Grad-CAM) successfully visualized malignant regions in over 95% of test samples, enhancing interpretability.
Employing dimensionality reduction techniques improved separability between benign and malignant feature clusters, confirming the model's effectiveness.
This work illustrates the potential of EfficientNet-based CNNs for providing reliable and explainable AI solutions in cancer diagnostics.

Cite This Study

Al-Omari et al. (2025) studied this question.

synapsesocial.com/papers/68c1ac0954b1d3bfb60e4995 https://doi.org/10.48084/etasr.10888

View Full Paper

Ask AI

Bookmark

September 10, 2025Engineering Technology & Applied Science ResearchOpen Access

CNN-Based Automated Detection of Metastatic Cancer in Histopathology Images

View Full Paper

Ask AI

Bookmark

Authors

OAOmaia Al-OmariPrince Sultan University OAOmar AlkhatibFreeman Hospital TATariq Al-OmariJordan University of Science and Technology

Discussion

Member takes

Overview

This analysis demonstrates an enhanced deep learning framework improving diagnostic accuracy for breast cancer, indicating vital advancements in AI-assisted histopathology.

Key Points

The proposed CNN framework achieved a test accuracy of 92.33% on the BreaKHis dataset, significantly outperforming traditional classifiers.
Gradient-weighted class activation mapping (Grad-CAM) successfully visualized malignant regions in over 95% of test samples, enhancing interpretability.
Employing dimensionality reduction techniques improved separability between benign and malignant feature clusters, confirming the model's effectiveness.
This work illustrates the potential of EfficientNet-based CNNs for providing reliable and explainable AI solutions in cancer diagnostics.

Cite This Study

Al-Omari et al. (2025) studied this question.

synapsesocial.com/papers/68c1ac0954b1d3bfb60e4995 https://doi.org/10.48084/etasr.10888

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark