What question did this study set out to answer?

This research aims to improve breast cancer diagnosis through effective image classification using CNNs.

June 1, 2017PLoS ONEOpen Access

Classification of breast cancer histology images using Convolutional Neural Networks

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates effective classification of breast cancer images in patients, suggesting improved diagnostic accuracy.

This research aims to improve breast cancer diagnosis through effective image classification using CNNs.
Proposed a classification method using Convolutional Neural Networks (CNNs) for breast biopsy images.
Classified images into four classes: normal tissue, benign lesion, in situ carcinoma, and invasive carcinoma.
Utilized Support Vector Machine for additional classification training using features extracted by the CNN.
Achieved accuracy of 77.8% for four-class classification.
Achieved accuracy of 83.3% for carcinoma vs non-carcinoma classification.
Sensitivity for cancer detection was 95.6%.

Araújo et al. (2017) studied this question.

View Full Paper

Ask AI

Bookmark