Learning distance metrics for interactive search-assisted diagnosis of mammograms

Abstract

The goal of interactive search-assisted diagnosis (ISAD) is to enable doctors to make more informed decisions about a given case by providing a selection of similar annotated cases. For instance, a radiologist examining a suspicious mass could study labeled mammograms with similar conditions and weigh the outcome of their biopsy results before determining whether to recommend a biopsy. The fundamental challenge in developing ISAD systems is the identification of similar cases, not simply in terms of superficial image characteristics, but in a medically-relevant sense. This task involves three aspects: extraction of a representative set of features, identifying an appropriate measure of similarity in the high-dimensional feature space, and return the most similar matches at interactive speed. The first has been an active research area for several decades. The second has largely been ignored by the medical imaging community. The third can be achieved using the Diamond framework, an open-source platform that enables efficient exploration of large distributed complex data repositories. This paper focuses on the second aspect. We show that the choice of distance metric affects the accuracy of an ISAD system and that machine learning enables the construction of effective domain-specific distance metrics. In the learned distance, data points with the same labels (e.g., malignant masses) are closer than data points with different labels (e.g., malignant vs. benign). Thus, the labels of the near neighbors of a new case are likely to be informative. We present and evaluate several novel methods for distance metric learning and evaluate them on a database involving 2522 mass regions of interest (ROI) extracted from digital mammograms, with ground truth defined by biopsy results (1800 malignant, 722 benign). Our results show that learned distance metrics improve both classification (ROC curve) and retrieval performance.

Interactive Computer-Aided Diagnosis of Breast Masses: Computerized Selection of Visually Similar Image Sets From a Reference Library

“…In this study, we only focused on the improvement of visual similarity between the queried masses and the ICAD-selected reference lesions with a fully-automated scheme. Because the reference library and the 14 image features used in this study were already used in our previous studies, the overall ICAD performance in classification between true-positive and false-positive (or malignant and benign) mass lesions should remain the similar level (e.g., the areas under ROC curves = 0.87) as we reported in two previously independent studies using the KNN classifiers with different learning methods and conditions [14,37].…”

A Boosting Framework for Visuality-Preserving Distance Metric Learning and Its Application to Medical Image Retrieval

“…This is done by retrieving medically relevant cases from the reference library and displaying their outcomes. Earlier work [2] has demonstrated that learning domain-specific distance metrics significantly improves the quality of such searches.…”

“…However, the value of CAD in clinical practice is controversial, due to their "blackbox" nature and lack of reasoning ability [7], [8], [9], [10], [11], despite significant recent progress [12], [13], [14], [15], [16], [17], [18], [19], [20] both in automated detection and characterization of breast masses. An alternative approach, espoused by efforts such as ISADS [2], eschews automated diagnosis in favor of providing medical professionals with additional context about the current case that could enable them to make a more informed decision. This is done by retrieving medically relevant cases from the reference library and displaying their outcomes.…”

“…In this section, we present a novel boosting framework, termed BDM (we follow the terminology from [2]), that automatically learns a distance function from a given set of pairwise constraints. The main idea is to iteratively generate a set of binary features from the side information.…”

“…The neighborhood of a point is defined by a distance metric, such as the euclidean distance. Our previous work showed that the choice of distance metric affects the accuracy of an ISADS system and that machine learning enables the construction of effective domain-specific distance metrics [2]. In a learned distance metric, data points with the same labels (e.g., malignant masses) are closer than data points with different labels (e.g., malignant versus benign).…”