Anomaly-aware multiple instance learning for rare anemia disorder classification

TL;DR

This paper introduces an interpretable pooling method for multiple instance learning that improves rare anemia disorder classification accuracy and explainability by leveraging negative bag information, even for unseen anomalies.

Contribution

It proposes a novel MIL pooling approach that enhances anomaly detection and interpretability using negative bag instance-level data, addressing data scarcity and explainability issues.

Findings

Outperforms standard MIL algorithms in classification accuracy.

Provides meaningful explanations for model decisions.

Detects unseen anomalous instances in rare blood diseases.

Abstract

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.