Assessing Generalization Capabilities of Malaria Diagnostic Models from Thin Blood Smears

2024/08/16 by Louise Guillon, Soheib Biga, Guillon, Louise +21 · 1 citation
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Digital Imaging for Blood Diseases #FOS: Biological sciences #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Quantitative Methods (q-bio.QM) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2408.08792

openalex publication_date 2024/08/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Cited by

• Towards Field-Ready AI-based Malaria Diagnosis: A Continual Learning Approach

Related

• Towards Field-Ready AI-based Malaria Diagnosis: A Continual Learning Approach
• Metrics to guide development of machine learning algorithms for malaria diagnosis
• A CNN-Based Malaria Diagnosis from Blood Cell Images with SHAP and LIME Explainability
• Automatic Diagnosis of Malaria from Thin Blood Smear Images using Deep\n Convolutional Neural Network with Multi-Resolution Feature Fusion
• Fully-automated patient-level malaria assessment on field-prepared thin blood film microscopy images, including Supplementary Information