Citations

BACKGROUND There is a scarcity of artificial intelligence models trained on frozen pathology. One way to expand the clinical utility of models trained on permanent pathology is by applying them to frozen sections and fine-tune based on weaknesses. OBJECTIVE To qualitatively evaluate a deep learning model trained on permanent pathology to classify squamous cell carcinoma on Mohs surgery frozen sections to learn model shortcomings and inform retraining and fine-tuning. MATERIALS AND METHODS The authors trained a model for classification of tumor on 746 skin biopsy slides and tested it on 15 Mohs surgery frozen sections. The authors estimated performance metrics and compared the regions of interest generated by the model with the original H&E slides. RESULTS The model achieved an AUC-ROC of 0.985 and 0.796 for tumor classification in permanent pathology and in frozen sections, respectively. Regions of interest for frozen sections with scarce tumor areas were inaccurate, focusing on normal tissue for slides classified as false negative, or highlighting structures different from tumor (e.g., inflammation, muscle, and nerves) for slides classified as true positive. CONCLUSION Deep anatomical structures more commonly present in Mohs frozen pathology might represent data out-of-distribution for models trained on permanent pathology, potentially leading to inadequate model outputs.

BACKGROUND Cutaneous lichen planus (LP) is a recalcitrant, difficult-to-treat, inflammatory skin disease characterized by pruritic, flat-topped, violaceous papules on the skin. Baricitinib is an oral Janus kinase (JAK) 1/2 inhibitor that interrupts the signaling pathway of IFN-γ, a cytokine implicated in the pathogenesis of LP. METHODS In this phase II trial, 12 patients with cutaneous LP received 2 mg daily baricitinib for 16 weeks, accompanied by in-depth spatial, single-cell, and bulk transcriptomic profiling of pre- and posttreatment samples. RESULTS An early and sustained clinical response was seen, with 83.3% of patients responsive at week 16. Our molecular data identified a unique, oligoclonal IFN-γ, CD8 + , and CXCL13 + cytotoxic T cell population in LP skin and demonstrated a rapid decrease in IFN signature within 2 weeks of treatment, most prominently in the basal layer of the epidermis. CONCLUSION This study demonstrates the efficacy and molecular mechanisms of JAK inhibition in LP. TRIAL REGISTRATION NCT05188521 FUNDING Eli Lilly, Appignani Benefactor Funds, 5P30AR075043, Mayo Clinic Clinical Trials Stimulus Funds.

Reactive granulomatous dermatitis (RGD) is an umbrella term to describe a reaction pattern characterized by skin-colored to erythematous papules, plaques, and nodules although other morphologies have been described. RGD has rarely been reported in children, and in this report, we present the case of a 3-year-old girl with acute lymphoblastic leukemia (ALL) who presented with firm, tender nodules, and ulcerated plaques on her extremities. Histopathologic examination showed foci of dense granulomatous inflammatory infiltrates composed of histiocytes, neutrophils, and multinucleate giant cells. The constellation of clinical symptoms, negative infectious workup, and histopathology support the diagnosis of RGD.