Overview

Breast cancer detection from ultrasound imaging is a challenging classification problem. This project systematically compares the transfer learning performance of four state-of-the-art CNN architectures on a curated ultrasound dataset.

Architectures Compared

ModelParametersTop Accuracy
VGG16138M91.2%
VGG19143M90.8%
InceptionV323M93.7%
DenseNet16914M94.1%
Inception-ResNetV256M95.3%

Approach

  • Fine-tuned pretrained ImageNet weights on medical ultrasound dataset
  • Applied class-weighted loss to handle benign/malignant imbalance
  • Evaluated with 5-fold cross-validation

Outcome

Inception-ResNetV2 achieved the best performance with 95.3% accuracy and 0.97 AUC, demonstrating strong generalization for clinical screening support.