Based on the literature data, the incidence of superficial and invasive non-dermatophyte mold infection (NDMI) has increased. Many of these infections are undiagnosed or misdiagnosed, thus causing inadequate treatment procedures followed by critical conditions or even mortality of the patients. Accurate diagnosis of these infections requires complex mycological analyses and operator skills, but simple, fast, and more efficient mycological tests are still required to overcome the limitations of conventional fungal diagnostic procedures. In this study, software has been developed to provide an efficient mycological diagnosis using a trained convolutional neural network (CNN) model as a core classifier. Using EfficientNet-B2 architecture and permanent slides of NDM isolated from patient’s materials (personal archive of Prof. Otašević, Department of Microbiology and Immunology, Medical Faculty, University of Niš, Serbia), a multi-CNN model has been trained and then integrated into the diagnostic tool, with a 93.73% accuracy of the main model. The Grad-CAM visualization model has been used for further validation of the pattern recognition of the model. The software, which makes the final diagnosis based on the rule of the major method, has been tested with images provided by different European laboratories, showing an almost faultless accuracy with different test images.

Superficial fungal infections are one of the most prevalent infections (~20%) in the world, but even knowing dermatophytes are common causative agents, automated classification presents a challenge. This research explores the application of deep learning models for automated classification of dermatophyte species based on microscopy images. Two neural network architectures were implemented, compared and combined: a convolutional neural network (ResNet-50) and a Vision Transformer (ViT). Both models were trained on an image dataset curated from the archives of the Department of Microbiology and Immunology, Medical Faculty, University of Niš, Serbia for the purpose of this research. The evaluation demonstrates that the ResNet-50 model achieved 94.2%, Vision Transformer achieved 93.48%, while the hybrid solution achieved 96,38% accuracy. These results highlight the potential of modern deep learning architectures, including both convolutional and transformer-based approaches, for high-performance image classification tasks in specialized domains.