What question did this study set out to answer?

The study aims to develop a deep learning method for automatic detection of invasive ductal carcinoma in whole slide images.

Automatic detection of invasive ductal carcinoma in whole slide images with convolutional neural networks

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates improved IDC detection in breast cancer tissue regions, highlighting the potential of deep learning methods.

The study aims to develop a deep learning method for automatic detection of invasive ductal carcinoma in whole slide images.
Trained a convolutional neural network on image patches from whole slide images.
Evaluated classifier accuracy using a dataset of 162 patient slides, with training on 113 and testing on 49 slides.
Ground truth provided by expert pathologist delineation for quantitative evaluation.
Achieved an F-measure of 71.80% and balanced accuracy of 84.23% for automatic IDC detection.
Outperformed traditional approaches using handcrafted image features, achieving 67.53% and 78.74% accuracy for fuzzy color histogram.
Results indicated that classification errors were often tied to limitations in expert annotations rather than the method itself.

Cruz-Roa et al. (2014) studied this question.

View Full Paper

Ask AI

Bookmark

Randomized trial demonstrates improved IDC detection in breast cancer tissue regions, highlighting the potential of deep learning methods.