Assessing Generalization Capabilities of Malaria Diagnostic Models from Thin Blood Smears

TL;DR

This study evaluates how well deep learning models for malaria diagnosis from blood smears perform across different clinical sites and explores methods to improve their generalization capabilities.

Contribution

It provides an assessment of model generalization across diverse settings and introduces strategies like fine-tuning to enhance performance.

Findings

Site-specific data improves model accuracy

Fine-tuning enhances generalization

Incremental learning benefits model adaptability

Abstract

Malaria remains a significant global health challenge, necessitating rapid and accurate diagnostic methods. While computer-aided diagnosis (CAD) tools utilizing deep learning have shown promise, their generalization to diverse clinical settings remains poorly assessed. This study evaluates the generalization capabilities of a CAD model for malaria diagnosis from thin blood smear images across four sites. We explore strategies to enhance generalization, including fine-tuning and incremental learning. Our results demonstrate that incorporating site-specific data significantly improves model performance, paving the way for broader clinical application.