Multiple Instance Learning with Auxiliary Task Weighting for Multiple Myeloma Classification
This work addresses the challenge of efficient and accurate diagnosis of multiple myeloma for radiologists, but it is incremental as it builds on existing multiple instance learning and multi-task learning techniques.
The authors tackled the problem of automating multiple myeloma classification from whole-body MRI scans, which is time-consuming and requires expertise, by proposing an auxiliary task-based multiple instance learning approach (ATMIL) that localizes disease sites and improves performance with adaptive reweighting, achieving validation on synthetic and real multi-center clinical data.
Whole body magnetic resonance imaging (WB-MRI) is the recommended modality for diagnosis of multiple myeloma (MM). WB-MRI is used to detect sites of disease across the entire skeletal system, but it requires significant expertise and is time-consuming to report due to the great number of images. To aid radiological reading, we propose an auxiliary task-based multiple instance learning approach (ATMIL) for MM classification with the ability to localize sites of disease. This approach is appealing as it only requires patient-level annotations where an attention mechanism is used to identify local regions with active disease. We borrow ideas from multi-task learning and define an auxiliary task with adaptive reweighting to support and improve learning efficiency in the presence of data scarcity. We validate our approach on both synthetic and real multi-center clinical data. We show that the MIL attention module provides a mechanism to localize bone regions while the adaptive reweighting of the auxiliary task considerably improves the performance.