Visceral Leishmaniasis (VL) is a neglected disease that affects between 50,000 and 90,000 new cases annually worldwide. In Brazil, VL causes about 3500 cases/per year. This chronic disease can lead to death in 90% of untreated cases. Thus, it is necessary to study safe technologies for diagnosing, treating, and controlling VL. Specialized laboratories carry out the VL diagnosis, and this step has a significant automation power through methods based on computational tools. The gold standard for detecting VL is the microscopy of material aspirated from the bone marrow to search for amastigotes. This work aims to assist in detecting amastigotes from microscopy images using deep learning techniques. The proposed methodology consists of segmenting the Leishmania parasites in the images, precisely indicating the location of the amastigotes in the image. In the detection of VL parasites, in this methodology, a Dice of 80.4% was obtained, Intersection over Union (IoU) of 75.2%, Accuracy of 99.1%, Precision of 81.5%, Sensitivity of 72.2%, Specificity of 99.6%, and Area under the Receiver Operating Characteristics Curve (AUC) of 86.5%. The results are promising and demonstrate that deep learning models trained with images of microscopy slides of biological material can precisely help the specialist detect VL in humans.
11 January 2023 in IEEE Latin America Transactions
Visceral Leishmaniasis (VL) is a neglected disease that affects 1 billion people in tropical and subtropical countries. In Brazil, VL causes about 3,500 cases/year. Although this disease is lethal when left untreated, the number of cases is increasing. Thus, it is necessary to study current and safety technologies for VL diagnosis, treatment, and control. Specialized laboratories carry out the LV diagnosis, and this step has great automation power through automatic methods based on computer vision to aid in diagnosis. This work aims to present state-of-the-art research on computer vision techniques to detect VL in humans and provide a theoretical basis for developing computational systems to aid in diagnosing VL. This work's contributions are finding the methodologies and algorithms used in VL automatic detection and listing the gaps in developing those systems. As a result, we find out the lack of image databases and the use of deep learning techniques is still scarce. We conclude that methodologies that use the segmentation procedure perform better in terms of accuracy and that it is possible to develop a CAD system to help diagnose VL in humans.
Anais do 3rd (ICAIC) International Conference for Academia and Industry Co-operation & 3rd (IMMSEM) International Meeting in Materials Science and Engineering of Maranhão (978-85-5722-477-3) - Caracterização Microestrutural De Nanotubos De Tio2 Crescidos Por Anodização Na Superficie Da Liga Ti-35Nb-5Ta