Objective:

To propose a two-step deep learning method for breast cancer detection in mammograms, focusing on its application in low-resource settings like Palestine.

Approach:

Key Findings:

• The U-Net segmentation model achieved a mean IoU of 0.70, Dice coefficient of 0.74, precision of 0.78, and recall of 0.71 on the CBIS-DDSM test set.
• The VGG16 classifier achieved 91% accuracy, 0.91 precision, 0.95 recall for the malignant class, and AUC of 0.97 on the Palestine evaluation subset.
• The proposed approach outperformed ResNet50 (85% accuracy) and MobileNet (82% accuracy).

Interpretation:

Limitations:

• The framework requires validation on a larger annotated local dataset before deployment.

Conclusion:

Attribution Notice

This content is an AI-generated, fully rewritten summary based on a published scholarly article. It does not reproduce the original text and is not a substitute for the original publication. Readers are encouraged to consult the source for full context, data, and methodology.