Region Proposals for Saliency Map Refinement for Weakly-supervised Disease Localisation and Classification
This work addresses the challenge of justifying automated disease diagnoses in medical imaging for clinicians, though it is incremental as it builds on existing weakly-supervised methods.
The paper tackles the problem of weakly-supervised disease localization and classification in medical images, where training sets lack detailed annotations, by introducing a model that combines region proposals with saliency detection. The result is a new state-of-the-art performance on the ChestX-ray14 dataset for both diagnosis and localization.
The deployment of automated systems to diagnose diseases from medical images is challenged by the requirement to localise the diagnosed diseases to justify or explain the classification decision. This requirement is hard to fulfil because most of the training sets available to develop these systems only contain global annotations, making the localisation of diseases a weakly supervised approach. The main methods designed for weakly supervised disease classification and localisation rely on saliency or attention maps that are not specifically trained for localisation, or on region proposals that can not be refined to produce accurate detections. In this paper, we introduce a new model that combines region proposal and saliency detection to overcome both limitations for weakly supervised disease classification and localisation. Using the ChestX-ray14 data set, we show that our proposed model establishes the new state-of-the-art for weakly-supervised disease diagnosis and localisation.