Anomaly-aware multiple instance learning for rare anemia disorder classification
This work addresses the challenge of rare anemia disorder classification for medical diagnostics, but it is incremental as it builds on existing MIL and attention mechanisms.
The paper tackled the problem of classifying rare anemia disorders from blood samples using deep learning, which suffers from limited data and annotations, by proposing an interpretable pooling method for Multiple Instance Learning that increases the contribution of anomalous instances, resulting in outperformance over standard MIL algorithms and the ability to denote unseen anomalous instances.
Deep learning-based classification of rare anemia disorders is challenged by the lack of training data and instance-level annotations. Multiple Instance Learning (MIL) has shown to be an effective solution, yet it suffers from low accuracy and limited explainability. Although the inclusion of attention mechanisms has addressed these issues, their effectiveness highly depends on the amount and diversity of cells in the training samples. Consequently, the poor machine learning performance on rare anemia disorder classification from blood samples remains unresolved. In this paper, we propose an interpretable pooling method for MIL to address these limitations. By benefiting from instance-level information of negative bags (i.e., homogeneous benign cells from healthy individuals), our approach increases the contribution of anomalous instances. We show that our strategy outperforms standard MIL classification algorithms and provides a meaningful explanation behind its decisions. Moreover, it can denote anomalous instances of rare blood diseases that are not seen during the training phase.