October 12, 2025Open Access

Advancing Breast Cancer Detection: A Comprehensive Evaluation of Machine Learning Models on Mammogram Imaging

View Full Paper

Ask AI

Bookmark

Authors

RMReshad Al MuttakiBRAC University SASadia AfrinAmerican International University-Bangladesh AAAlvi Ibn Amzad AnilBRAC University

Discussion

Member takes

Implication

Observational analysis assessed diagnostic accuracy of machine learning models in mammogram imaging, suggesting potential for improving patient outcomes.

Key Points

Hybrid and KAN models achieved promising accuracy and discriminative power in breast cancer diagnosis.
Hybrid model has an impressive accuracy of 0.9667 and F1 Score of 0.9444, while KAN model excels with ROC AUC of 0.9760.
Random Forest demonstrated the lowest false negatives, enhancing its reliability for clinical screening applications.
Future research should focus on optimizing inference speed and enhancing interpretability across diverse datasets.

Cite This Study

Muttaki et al. (2025) studied this question.

synapsesocial.com/papers/68ebe3d6becc64ad52fdaefd https://doi.org/10.1101/2025.10.08.25337620

View Full Paper

Ask AI

Bookmark

Implication

Observational analysis assessed diagnostic accuracy of machine learning models in mammogram imaging, suggesting potential for improving patient outcomes.

Advancing Breast Cancer Detection: A Comprehensive Evaluation of Machine Learning Models on Mammogram Imaging

Discussion

Member takes

Implication

Key Points

Cite This Study

Advancing Breast Cancer Detection: A Comprehensive Evaluation of Machine Learning Models on Mammogram Imaging

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider