Smooth Attention for Deep Multiple Instance Learning: Application to CT Intracranial Hemorrhage Detection
This work addresses the detection of intracranial hemorrhage in medical imaging, which is critical for patient diagnosis, but it is incremental as it builds on existing MIL methods by adding smoothness constraints.
The paper tackled the problem of detecting intracranial hemorrhage in CT scans using multiple instance learning, proposing a smooth attention model that incorporates spatial dependencies between slices and achieved better performance than non-smooth attention and state-of-the-art methods on the same test set.
Multiple Instance Learning (MIL) has been widely applied to medical imaging diagnosis, where bag labels are known and instance labels inside bags are unknown. Traditional MIL assumes that instances in each bag are independent samples from a given distribution. However, instances are often spatially or sequentially ordered, and one would expect similar diagnostic importance for neighboring instances. To address this, in this study, we propose a smooth attention deep MIL (SA-DMIL) model. Smoothness is achieved by the introduction of first and second order constraints on the latent function encoding the attention paid to each instance in a bag. The method is applied to the detection of intracranial hemorrhage (ICH) on head CT scans. The results show that this novel SA-DMIL: (a) achieves better performance than the non-smooth attention MIL at both scan (bag) and slice (instance) levels; (b) learns spatial dependencies between slices; and (c) outperforms current state-of-the-art MIL methods on the same ICH test set.