Sickle-cell disease diagnosis support selecting the most appropriate machinelearning method: Towards a general and interpretable approach for cellmorphology analysis from microscopy images

TL;DR

This paper presents a method for selecting the most effective and interpretable machine learning classifiers for diagnosing sickle-cell disease from microscopy images, emphasizing feature quality, parameter optimization, and interpretability.

Contribution

It introduces a systematic approach for choosing optimal, interpretable classifiers and features for blood cell morphology analysis, validated on a public dataset with improved results.

Findings

Achieved better classification performance than state-of-the-art methods.

Provided a comprehensive parameter set and code library for reproducibility.

Enhanced interpretability of models for diagnostic support.

Abstract

In this work we propose an approach to select the classification method and features, based on the state-of-the-art, with best performance for diagnostic support through peripheral blood smear images of red blood cells. In our case we used samples of patients with sickle-cell disease which can be generalized for other study cases. To trust the behavior of the proposed system, we also analyzed the interpretability. We pre-processed and segmented microscopic images, to ensure high feature quality. We applied the methods used in the literature to extract the features from blood cells and the machine learning methods to classify their morphology. Next, we searched for their best parameters from the resulting data in the feature extraction phase. Then, we found the best parameters for every classifier using Randomized and Grid search. For the sake of scientific progress, we published parameters for each classifier, the implemented code library, the confusion matrices with the raw data, and we used the public erythrocytesIDB dataset for validation. We also defined how to select the most important features for classification to decrease the complexity and the training time, and for interpretability purpose in opaque models. Finally, comparing the best performing classification methods with the state-of-the-art, we obtained better results even with interpretable model classifiers.