Smooth Attention for Deep Multiple Instance Learning: Application to CT Intracranial Hemorrhage Detection

TL;DR

This paper introduces a smooth attention mechanism for deep Multiple Instance Learning, improving intracranial hemorrhage detection in CT scans by modeling spatial dependencies and outperforming existing methods.

Contribution

The study proposes a novel smooth attention deep MIL model with first and second order constraints, enhancing spatial dependency modeling in medical imaging diagnosis.

Findings

Outperforms non-smooth MIL in ICH detection

Learns spatial dependencies between slices

Achieves state-of-the-art results on ICH dataset

Abstract

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.