Machine learning method for breast cancer diagnostics
2018
Radboud University Medical Center, Nijmegen, Netherlands
This method is based on machine learning techniques to gain insights into stromal changes associated with breast cancer. Using deep convolutional neural networks, the algorithm was trained to discriminate between invasive breast cancer-related stroma from benign biopsies from patients. Afterwards, the algorithm could perform correctly and even could be used to detect ductal carcinoma. These results show that algorithms can be powerful tools to classify breast biopsies and understand breast insults.
Using deep convolutional neural networks to identify and classify tumor-associated stroma in diagnostic breast biopsies
Jeroen A W M van der Laak
Added on: 07-22-2021
[1] https://www.nature.com/articles/s41379-018-0073-z[2] https://data.jrc.ec.europa.eu/dataset/ffebe454-ed9a-47cf-8a33-8cf70c1b7d38
