Mammography Image BI-RADS Classification Using OHPLall

EasyChair Preprint 2270

Abstract

Medical image analysis and classification, using machine learning, particularly Convolutional Neural Networks, have demonstrated a great deal of success.  Research into mammography image classification tended to focus on either binary outcome (malignancy or benign) or nominal (unordered) classification for multiclass labels [1]. The industry standard metric for radiologist’s classification of mammography images is a rating scale called BI-RADS (Breast Imaging Reporting and Data System), where values 1 through 5 are a distinct progression of assessment that are intended to denote higher risk of a malignancy, based on the characteristics of anomalies within an image [1][2][3]. The development of a classifier that predicts BI-RADS 1-5, would provide radiologists with an objective second opinion on image anomalies. In this paper, we applied a novel Deep Learning method called OHPLall (Ordinal Hyperplane Loss - all centroids), which was specifically designed for data with ordinal classes, to the predictions of BI-RADS scales on mammography images. Our experimental study demonstrated promising results generated by OHPLall and great potential of using OHPLall models as a supplemental diagnostic tool.

Keyphrases: BI-RADS, Mammography, deep learning, machine learning, ordinal classification, ordinal hyperplane loss

@booklet{EasyChair:2270,
  author    = {Bob Vanderheyden and Ying Xie},
  title     = {Mammography Image BI-RADS Classification Using OHPLall},
  howpublished = {EasyChair Preprint 2270},
  year      = {EasyChair, 2019}}