METHOD: Retrospective study at a tertiary care hospital between 2004 and 2009 in patients over 18 years with RRP. RESULTS: Eighty-seven patients were identified. Sixty (69%) were male and 27 (31%) were female (mean age 48 years). Eighty of the 87 patients (92%) had biopsy data. Dysplasia was identified in 53.7% (43/80). The mean number of operations for patients with dysplasia was 5 and without was 3. Of the 80 patients, 46.3% had no dysplasia, 31.2% had mild dysplasia (grade 1), 10.0% had moderate dysplasia (grade 2), 2.5% had severe dysplasia (grade 3), 5.0% had carcinoma in situ, and 5.0% had squamous cell carcinoma as the highest noted degree of dysplasia. Twenty-seven patients (27/80, 34%) developed a higher dysplastic grade with 8/80 (10.0%) developing carcinoma in situ or squamous cell carcinoma. Most patients who developed dysplasia progression were older (mean age 50 vs. 47 in non-progressors) and male (15/27), while only nine (9/27) had a history of smoking. HPV 6 was the most common subtype found with dysplasia progression (15/27, 56%). Cidofovir was utilized in 24/80 patients (30%). Twelve patients (12/24, 50%) had progression of dysplasia despite cidofovir usage. CONCLUSION: This study delineates the natural progression of dysplasia in adult RRP. Progression of dysplasia was associated with older age, male gender, and HPV 6. These data reveal the significance of dysplasia progression in adult RRP and the necessity of accurate monitoring.

Alakai Defense Systems has developed several standoff ultra-violet (UV) Raman systems over the years to enable detection of hazardous chemicals from a safe distance. These systems have traditionally used classical non-machinelearning-based algorithms, but Alakai together with its partner Systems & Technology Research (STR) are currently developing the Agnostic Machine learning Platform for Spectroscopy (AMPS). AMPS, implemented using PyTorch, automatically creates and optimizes tailored one-dimensional (1D) convolutional neural networks (CNN) when trained on simulated or measured data. Several emerging and novel techniques, including advanced domain adaptation approaches, have been implemented to increase model robustness and minimize training data requirements. While the created models are optimized for a specific modality, AMPS itself is agnostic-it can be used for any spectroscopic modality that produces 1D spectra. AMPS has shown promising results for long-wave infrared (LWIR) reflectance spectroscopy as well as UV and near-infrared (NIR) Raman. This talk will focus on AMPS models created using both simulated UV Raman data as well as measured UV Raman data taken with Alakai's Portable Raman Improvised Explosives Detection (PRIED) system. Performance between AMPS and Alakai's legacy algorithms will be compared.