Real-World Outcomes of Inoperable and Metastatic Cutaneous Head and Neck Melanoma Patients.

OBJECTIVE: This study aims to describe the overall survival (OS) and to identify associated prognostic factors in patients with inoperable and metastatic cutaneous melanoma of the head and neck (H&N) region, undergoing modern systemic treatments. METHODS: This is a retrospective single institutional study. Data on all consecutive H&N melanoma patients treated with systemic oncologic treatments between 2015 and 2022 were collected from electronic medical files. Kaplan-Meier curves were used to describe survival and Cox regression analysis was used to identify patient and tumor factors associated with prognosis. RESULTS: A total of 144 patients were included. Median OS was 45 months (95% confidence interval [CI] 28-65 m). On univariable analysis for OS, the primary disease site, specifically the nape and neck (hazard ratio [HR] 3.3, 95% CI 1.4-7.7, p = 0.007), high Eastern Cooperative Oncology Group Performance Status ([ECOG-PS], HR 2.5, 95% CI = 1.9-3.3, p < 0.001), high lactate dehydrogenase (LDH) levels (HR 2.8, 95% CI = 1.7-4.6, p < 0.001), and treatment with targeted therapy (TT) as compared with immunotherapy (HR 2.6, 95% CI = 1.06-6.3, p = 0.03) were all associated with shorter OS. High-grade adverse events (AEs) were associated with a longer OS (HR 0.41, 95% CI = 0.25-0.68, p = 0.001). On multivariable analysis for OS, the ECOG-PS, LDH levels, site of disease, and the development of moderate-severe AEs remained significant. CONCLUSIONS: In the era of modern oncologic treatments, the prognosis of inoperable and metastatic cutaneous H&N melanoma aligns with other cutaneous melanomas. Primary tumor site of the nape and neck region emerges as a significant prognostic factor. LEVEL OF EVIDENCE: 3 Laryngoscope, 134:2762-2770, 2024.

Differentiating spinal pathologies by deep learning approach.

BACKGROUND CONTEXT: Spinal pathologies are diverse in nature and, excluding trauma and degenerative diseases, includes infectious, neoplastic (either extradural or intradural), and inflammatory conditions. The preoperative diagnosis is made with clinical judgment incorporating lab findings and radiological studies. When the diagnosis is uncertain, a biopsy is almost always mandatory since the treatment is dictated by the type of pathology. This is an invasive, timely, and costly process. PURPOSE: The aim of this study was to develop a deep learning (DL) algorithm, based on preoperative MRI and post-operative pathological results, to differentiate between leading spinal pathologies. STUDY DESIGN: We retrospectively collected and analyzed clinical, radiological, and pathological data of patients who underwent spinal surgery or biopsy for various spinal pathologies between 2008 and 2022 at a tertiary center. The patients were stratified according to their pathological reports (the threshold for inclusion was set to 25 patients per diagnosis). METHODS: Preoperative MRI, clinical data, and pathological results were processed by a deep learning model built on the Fast.ai framework on top of the PyTorch environment. RESULTS: A total of 231 patients diagnosed with carcinoma (80), infection (57), meningioma (52), or schwannoma (42), were included in our model. The mean overall accuracy was 0.78±0.06 for the validation, and 0.93±0.03 for the test dataset. CONCLUSION: Deep learning algorithm for differentiation between the aforementioned spinal pathologies, based solely on clinical MRI, proves as a feasible primary diagnostic modality. Larger studies should be performed to validate and improve this algorithm for clinical use. CLINICAL SIGNIFICANCE: This study provides a proof-of-concept for predicting spinal pathologies solely by MRI based DL technology, allowing for a rapid, targeted, and cost-effective work-up and subsequent treatment.