The polymorphism of cutaneous leishmaniasis (CL) complicates diagnosis in health care services because lesions may be confused with other dermatoses such as sporotrichosis, paracocidiocomycosis, and venous insufficiency. Automated identification of skin diseases based on deep learning (DL) has been applied to assist diagnosis. In this study, we evaluated the performance of AlexNet, a DL algorithm, to identify pictures of CL lesions in patients from Midwest Brazil. We used a set of 2458 pictures (up to 10 of each lesion) obtained from patients treated between 2015 and 2022 in the Leishmaniasis Clinic at the University Hospital of Brasilia. We divided the picture database into training (80%), internal validation (10%), and testing sets (10%), and trained and tested AlexNet to identify pictures of CL lesions. We performed three simulations and trained AlexNet to differentiate CL from 26 other dermatoses (e.g., chromomycosis, ecthyma, venous insufficiency). We obtained an average accuracy of 95.04% (Confidence Interval 95%: 93.81–96.04), indicating an excellent performance of AlexNet in identifying pictures of CL lesions. We conclude that automated CL identification using AlexNet has the potential to assist clinicians in diagnosing skin lesions. These results contribute to the development of a mobile application to assist in the diagnosis of CL in health care services.

This study evaluated total mercury (THg) distribution and accumulation in soil, litter, and surface-active soil invertebrates at the Águas Emendadas Ecological Station (ESECAE), a savanna reserve in central Brazil. We assessed whether THg differed between soil and litter; whether soil pH and organic matter influenced soil THg, the degree of THg accumulation in invertebrates relative to soil and litter; whether feeding habits structured epigeic soil fauna according to THg concentrations; and whether biomagnification could be inferred within the local trophic network. THg concentrations were significantly higher in litter (51.7 ± 5.6 ng g⁻ ¹ ) than in soil (34.9 ± 13.5 ng g⁻ ¹ ; t = 4.402, df = 7, p = 0.0032). Soil organic matter was positively associated with soil THg ( R ² = 0.455, p = 0.039), whereas pH showed no significant relationship. Invertebrate THg concentrations ranged from 0.095 to 970.70 ng g⁻ ¹ , reaching values approximately 15 times higher than those in soil or litter. Overall, 83.75% of samples showed bioaccumulation potential, and macroaccumulation predominated relative to both soil (80.38%) and litter (68.53%). Grouping by feeding habits revealed consistent accumulation patterns, indicating trophic-level biomagnification. Predator frequency increased from 9.1% in the lowest THg group to 45.5% in the highest, while phytophagous organisms decreased from 26.1% to 2.3%. Our results underscore the complexity of mercury cycling in terrestrial food webs and highlight the role of ecological traits and environmental parameters in modulating mercury bioavailability and transfer.