Visualizing "featureless" regions on mammograms classified as invasive ductal carcinomas by a deep learning algorithm: the promise of AI support in radiology.

Daiju UedaAkira YamamotoTsutomu TakashimaNaoyoshi OnodaSatoru NodaShinichiro KashiwagiTamami MorisakiShinichi TsutsumiTakashi HonjoAkitoshi ShimazakiTakuya GotoYukio Miki

Published in: Japanese journal of radiology (2020)

We successfully showed that features isolated by a DL-based algorithm trained to classify IDCs were indeed those known to be associated with each pathology. Thus, using AI can expand the capacity of radiologists through the discovery of previously unknown findings.

Keyphrases

artificial intelligence
deep learning
big data
machine learning
convolutional neural network
small molecule
high grade
high throughput
resistance training
single cell
high intensity
neural network