Embedded deep-learning based sample-to-answer device for on-site malaria diagnosis

Abstract Improvements in digital microscopy are critical for the development of a malaria diagnosis method that is accurate at the cellular level and exhibits satisfactory clinical performance. Digital microscopy can be enhanced by improving deep learning algorithms and achieving consistent staining results. In this study, a novel miLab TM device incorporating the solid hydrogel staining method was proposed for consistent blood film preparation, eliminating the use of complex equipment and liquid reagent maintenance. By leveraging deformable staining patches, miLab TM ensures consistent, high-quality, and reproducible blood films across various hematocrits. Embedded-deep-learning-enabled miLab TM was used to detect and classify malarial parasites from the autofocused images of stained blood cells by using an internal optical system. The results of this method were consistent with manual microscopy images. This method not only minimizes human error but also facilitates remote assistance and review by experts through digital image transmission. This method can set new paradigm for on-site malaria diagnosis. The miLab TM algorithm for malaria detection achieved a total accuracy of 98.86% for infected red blood cell (RBCs) classification. Clinical validation performed in Malawi demonstrated an overall percent agreement of 92.21%. Thus, miLab TM can become a reliable and efficient tool for decentralized malaria diagnosis.