# Anomaly-aware multiple instance learning for rare anemia disorder classification

Source: [Anomaly-aware multiple instance learning for rare anemia disorder classification](<https://www.sota2.com/research/paper/68fa6cf91e209131cea36fbb>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-01T14:46:21.487Z

Authors: Salome Kazeminia, Ario Sadafi, Asya Makhro, Anna Bogdanova, Shadi Albarqouni, Carsten Marr

Published: 2022-07-04T22:56:09.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Classification on Rare Anemia Disorders (SCD, Thal, Xero, HS, Control) (3-fold cross-validation)](<https://www.sota2.com/research/sota/classification-on-rare-anemia-disorders-scd-thal-xero-hs-control-3-fold-cross-validation.md>): Classification; Rare Anemia Disorders (SCD, Thal, Xero, HS, Control) (3-fold cross-validation); Accuracy: 78.7.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2207.01742>)

[PDF](<https://arxiv.org/pdf/2207.01742.pdf>)

[Implementation](<https://github.com/marrlab/Anomaly-aware-MIL>)