ProMIL: Probabilistic Multiple Instance Learning for Medical Imaging
This addresses the problem of more accurate weakly-supervised learning for medical imaging tasks, but it is incremental as it builds on existing instance-based MIL methods.
The paper tackles the problem of Multiple Instance Learning (MIL) in medical imaging, where standard models assume a bag is positive if at least one instance is positive, which does not hold in many real-life scenarios requiring a certain percentage of positive instances. The result is that ProMIL, a method based on deep neural networks and Bernstein polynomial estimation, outperforms standard instance-based MIL in real-world medical applications.
Multiple Instance Learning (MIL) is a weakly-supervised problem in which one label is assigned to the whole bag of instances. An important class of MIL models is instance-based, where we first classify instances and then aggregate those predictions to obtain a bag label. The most common MIL model is when we consider a bag as positive if at least one of its instances has a positive label. However, this reasoning does not hold in many real-life scenarios, where the positive bag label is often a consequence of a certain percentage of positive instances. To address this issue, we introduce a dedicated instance-based method called ProMIL, based on deep neural networks and Bernstein polynomial estimation. An important advantage of ProMIL is that it can automatically detect the optimal percentage level for decision-making. We show that ProMIL outperforms standard instance-based MIL in real-world medical applications. We make the code available.