What question did this study set out to answer?

This research aims to develop a computer-aided detection system for classifying breast cancer in mammography images using deep learning techniques.

Breast cancer detection using deep convolutional neural networks and support vector machines

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial examines accuracy of breast cancer classification using deep learning in mammography imaging, suggesting improved detection methods.

This research aims to develop a computer-aided detection system for classifying breast cancer in mammography images using deep learning techniques.
Utilized deep convolutional neural networks (DCNN) with AlexNet architecture for feature extraction.
Implemented two segmentation approaches: manual region of interest (ROI) determination and threshold-based region segmentation.
Employed data augmentation techniques, specifically rotation, to enhance dataset size for improved accuracy.
Achieved an accuracy of 71.01% with DCNN when cropping ROI manually from mammograms.
Highest AUC of 0.88 (88%) was attained across both segmentation techniques.
When using CBIS-DDSM samples, DCNN accuracy increased to 73.6%, leading to SVM accuracy of 87.2% and AUC of 0.94 (94%).

Ragab et al. (2019) studied this question.

View Full Paper

Ask AI

Bookmark

Randomized trial examines accuracy of breast cancer classification using deep learning in mammography imaging, suggesting improved detection methods.