An evaluation of semiautomatic approaches to contour segmentation applied to fungal hyphae

Segmentation of hyphae and yeast in fungi-infected tissue slice images and its application in analyzing antifungal blue light therapy

Candida albicans is a pathogenic fungus that undergoes morphological transitions between hyphal and yeast forms, adapting to diverse environmental stimuli and exhibiting distinct virulence. Existing research works on antifungal blue light (ABL) therapy have either focused solely on hyphae or neglected to differentiate between morphologies, obscuring potential differential effects. To address this gap, we established a novel dataset of 150 C. albicans-infected mouse skin tissue slice images with meticulously annotated hyphae and yeast. Eleven representative convolutional neural networks were trained and evaluated on this dataset using seven metrics to identify the optimal model for segmenting hyphae and yeast in original high pixel size images. Leveraging the segmentation results, we analyzed the differential impact of blue light on the invasion depth and density of both morphologies within the skin tissue. U-Net-BN outperformed other models in segmentation accuracy, achieving the best overall performance. While both hyphae and yeast exhibited significant reductions in invasion depth and density at the highest ABL dose (180 J/cm2), only yeast was significantly inhibited at the lower dose (135 J/cm2). This novel finding emphasizes the importance of developing more effective treatment strategies for both morphologies.

Image-Processing Scheme to Detect Superficial Fungal Infections of the Skin

The incidence of superficial fungal infections is assumed to be 20 to 25% of the global human population. Fluorescence microscopy of extracted skin samples is frequently used for a swift assessment of infections. To support the dermatologist, an image-analysis scheme has been developed that evaluates digital microscopic images to detect fungal hyphae. The aim of the study was to increase diagnostic quality and to shorten the time-to-diagnosis. The analysis, consisting of preprocessing, segmentation, parameterization, and classification of identified structures, was performed on digital microscopic images. A test dataset of hyphae and false-positive objects was created to evaluate the algorithm. Additionally, the performance for real clinical images was investigated using 415 images. The results show that the sensitivity for hyphae is 94% and 89% for singular and clustered hyphae, respectively. The mean exclusion rate is 91% for the false-positive objects. The sensitivity for clinical images was 83% and the specificity was 79%. Although the performance is lower for the clinical images than for the test dataset, a reliable and fast diagnosis can be achieved since it is not crucial to detect every hypha to conclude that a sample consisting of several images is infected. The proposed analysis therefore enables a high diagnostic quality and a fast sample assessment to be achieved.