Multiple-Instance Learning for Anomaly Detection in Digital Mammography

doi:10.1109/TMI.2016.2521442

Multiple-Instance Learning for Anomaly Detection in Digital Mammography

2016-07-01

60

PRE

AI

DOI：10.1109/TMI.2016.2521442

Original

Original request for help

Save

Abstract

En 中文

This paper describes a computer-aided detection and diagnosis system for breast cancer, the most common form of cancer among women, using mammography. The system relies on the Multiple-Instance Learning (MIL) paradigm, which has proven useful for medical decision support in previous works from our team. In the proposed framework, breasts are first partitioned adaptively into regions. Then, features derived from the detection of lesions (masses and microcalcifications) as well as textural features, are extracted from each region and combined in order to classify mammography examinations as normal or abnormal. Whenever an abnormal examination record is detected, the regions that induced that automated diagnosis can be highlighted. Two strategies are evaluated to define this anomaly detector. In a first scenario, manual segmentations of lesions are used to train an SVM that assigns an anomaly index to each region; local anomaly indices are then combined into a global anomaly index. In a second scenario, the local and global anomaly detectors are trained simultaneously, without manual segmentations, using various MIL algorithms (DD, APR, mi-SVM, MI-SVM and MILBoost). Experiments on the DDSM dataset show that the second approach, which is only weakly-supervised, surprisingly outperforms the first approach, even though it is strongly-supervised. This suggests that anomaly detectors can be advantageously trained on large medical image archives, without the need for manual segmentation.

Keywords:

Anomaly detection

mammography

multiple-instance learning

texture analysis

Multiple-Instance Learning for Anomaly Detection in Digital Mammography

Abstract

AI Summary

Journal

Organization