Browsing by Author "Woloshuk, Andre"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    A case of ureteral fungal mass removal in a patient taking empagliflozin
    (SpringerLink, 2021-11) Woloshuk, Andre; Lee, Matthew; Assmus, Mark; Agarwal, Deepak; Krambeck, Amy; Large, Tim; Urology, School of Medicine
    With increased use of sodium-glucose co-transporter 2 (SGLT2) inhibitors as antidiabetic agents, the risk of serious fungal urinary tract infection (UTI) may be increased. We present the case of a 67-year-old Caucasian female who was admitted for emphysematous pyelitis and found to have a fungal ball in the renal pelvis. Candida glabrata was cultured and the patient was managed with percutaneous nephrostomy tube placement and antifungal treatment. The fungal ball persisted and required surgical removal with ureteroscopy and basket extraction. Fungal balls can be a difficult sequelae of UTIs requiring a combination of antifungal and surgical intervention for definitive management.
  • Thumbnail Image
    Item
    In Situ Classification of Cell Types in Human Kidney Tissue Using 3D Nuclear Staining
    (Wiley, 2021) Woloshuk, Andre; Khochare, Suraj; Almulhim, Aljohara F.; McNutt, Andrew T.; Dean, Dawson; Barwinska, Daria; Ferkowicz, Michael J.; Eadon, Michael T.; Kelly, Katherine J.; Dunn, Kenneth W.; Hasan, Mohammad A.; El-Achkar, Tarek M.; Winfree, Seth; Medicine, School of Medicine
    To understand the physiology and pathology of disease, capturing the heterogeneity of cell types within their tissue environment is fundamental. In such an endeavor, the human kidney presents a formidable challenge because its complex organizational structure is tightly linked to key physiological functions. Advances in imaging-based cell classification may be limited by the need to incorporate specific markers that can link classification to function. Multiplex imaging can mitigate these limitations, but requires cumulative incorporation of markers, which may lead to tissue exhaustion. Furthermore, the application of such strategies in large scale 3-dimensional (3D) imaging is challenging. Here, we propose that 3D nuclear signatures from a DNA stain, DAPI, which could be incorporated in most experimental imaging, can be used for classifying cells in intact human kidney tissue. We developed an unsupervised approach that uses 3D tissue cytometry to generate a large training dataset of nuclei images (NephNuc), where each nucleus is associated with a cell type label. We then devised various supervised machine learning approaches for kidney cell classification and demonstrated that a deep learning approach outperforms classical machine learning or shape-based classifiers. Specifically, a custom 3D convolutional neural network (NephNet3D) trained on nuclei image volumes achieved a balanced accuracy of 80.26%. Importantly, integrating NephNet3D classification with tissue cytometry allowed in situ visualization of cell type classifications in kidney tissue. In conclusion, we present a tissue cytometry and deep learning approach for in situ classification of cell types in human kidney tissue using only a DNA stain. This methodology is generalizable to other tissues and has potential advantages on tissue economy and non-exhaustive classification of different cell types.