On Combining Multiple-Instance Learning and Active Learning for Computer-Aided Detection of Tuberculosis

The major advantage of multiple-instance learning (MIL) applied to a computer-aided detection (CAD) system is that it allows optimizing the latter with case-level labels instead of accurate lesion outlines as traditionally required for a supervised approach. As shown in previous work, a MIL-based CAD system can perform comparably to its supervised counterpart considering complex tasks such as chest radiograph scoring in tuberculosis (TB) detection. However, despite this remarkable achievement, the uncertainty inherent to MIL can lead to a less satisfactory outcome if analysis at lower levels (e.g., regions or pixels) is needed. This issue may seriously compromise the applicability of MIL to tasks related to quantification or grading, or detection of highly localized lesions. In this paper, we propose to reduce uncertainty by embedding a MIL classifier within an active learning (AL) framework. To minimize the labeling effort, we develop a novel instance selection mechanism that exploits the MIL problem definition through one-class classification. We adapt this mechanism to provide meaningful regions instead of individual instances for expert labeling, which is a more appropriate strategy given the application domain. In addition, and contrary to usual AL methods, a single iteration is performed. To show the effectiveness of our approach, we compare the output of a MIL-based CAD system trained with and without the proposed AL framework. The task is to detect textural abnormalities related to TB. Both quantitative and qualitative evaluations at the pixel level are carried out. In the former case, receiver operating characteristic and precision-recall analyses are used. For completeness, we also compare with a CAD system following a supervised approach and related baselines. The quantitative results show that the proposed method significantly improves the MIL-based classification and narrows the gap with the supervised approach in \%50 and \%75, depending on if 100 or 300 labeled regions are processed, but with only \%5 and \%16 of the labeling effort. In qualitative terms, a substantial improvement in lesion localization and false-positive detections is observed. The proposed method also outperforms the aforementioned baselines.