Breast Cancer Ultrasound Image Classification Experiment Results
In this project report, the focus is on classifying breast cancer ultrasound images using various deep learning models like VGG16, ResNet50, and DenseNet201. The dataset consists of 163 images, with 109 benign and 54 malignant cases. Experimentation includes data augmentation techniques like rotation, shift, shear, zoom, and flip. The images are reshaped to a size of 256x256, and convolution layers are retained while adding dense layers for model complexity. Results indicate that using pretrained weights significantly improves accuracy, with ResNet50 and DenseNet201 achieving 88% and 94% accuracy respectively when pretrained on ImageNet. Loss and accuracy details on ResNet50 and DenseNet201 are analyzed. Overall, the project demonstrates the effectiveness of deep learning models in classifying breast cancer ultrasound images.
Uploaded on Feb 18, 2025 | 0 Views
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Breast cancer ultrasound images Classification Dataset Experiment Results
Dataset Breast cancer ultrasound images 163 images, 109 benign, 54 malignant Training 128, validation 18, testing 17 .
Experiment Data augmentation rotation_range=30, width_shift_range=0.05, height_shift_range=0.05, shear_range=0.05, zoom_range=0.05, horizontal_flip=True, fill_mode='nearest'
Experiment VGG16 ResNet50 DenseNet201 Reshape images to size(256, 256, 3) Keep convolution layer. Add dense layers. (2 layers (512, 1) for VGG16, 1 layer (1) for ResNet50 and DenseNet201) Batch size = 32
Results The accuracy of using VGG16 (with or without pretrained weights), ResNet50 (without pretrained weights), DenseNet201 (without pretrained weights) is around 70% - 80%. The accuracy of using, ResNet50, DenseNet201 with pretrained weights on imagenet are 88%, 94%, respectively.
Results Loss and accuracy on DenseNet201
Results Loss and accuracy on ResNet50
