Artificial neural networks in breast cancer diagnosis: merging of computer-extracted features from breast images
Maryellen Lissak Giger, Zhimin Huo · 2003
We have developed a computer aided diagnosis method for differentiating malignant from benign masses. The computerized method outputs an estimated likelihood of malignancy for eventual use as an aid to radiologists in diagnosing breast cancer. The method incorporates various computer extracted image features and merges them using artificial neural networks and rules. The authors summarize recent progress.