Cytology and small biopsy specimens achieved comparable specificity and accuracy in sub-typing NSCLC and optimal results were obtain when findings from both modalities combine. The advantage of paired specimens is to maximize overall diagnostic yield and the remaining material will be available for ancillary technique like IHC or for molecular testing. Diagn. Cytopathol. 2017;45:598-603. © 2017 Wiley Periodicals, Inc.

Deep-learning (DL)-based image processing has potential to revolutionize the use of smartphones in mobile health (mHealth) diagnostics of infectious diseases. However, the high variability in cellphone image data acquisition and the common need for large amounts of specialist-annotated images for traditional DL model training may preclude generalizability of smartphone-based diagnostics. Here, we employed adversarial neural networks with conditioning to develop an easily reconfigurable virus diagnostic platform that leverages a dataset of smartphonetaken microfluidic chip photos to rapidly generate image classifiers for different target pathogens on-demand. Adversarial learning was also used to augment this real image dataset by generating 16,000 realistic synthetic microchip images, through style generative adversarial networks (StyleGAN). We used this platform, termed smartphone-based pathogen detection resource multiplier using adversarial networks (SPyDERMAN), to accurately detect different intact viruses in clinical samples and to detect viral nucleic acids through integration with CRISPR diagnostics. We evaluated the performance of the system in detecting five different virus targets using 179 patient samples. The generalizability of the system was confirmed by rapid reconfiguration to detect SARS-CoV-2 antigens in nasal swab samples (n = 62) with 100% accuracy. Overall, the SPyDERMAN system may contribute to epidemic preparedness strategies by providing a platform for smartphone-based diagnostics that can be adapted to a given emerging viral agent within days of work.

FNAC plays an important role in the diagnosis of lymph node metastasis in cases of STS.

Context: Malignant peripheral nerve sheath tumor (MPNST) is a rare and aggressive soft-tissue sarcoma. Aims: The aim of this study was to analyze various prognostic factors and treatment outcome of patients with MPNST. Settings and Design: This was a retrospective study. Subjects and Methods: Ninety-two patients, who presented with MPNST at a tertiary care cancer center from 2011 to 2018, were included in this study. The median follow-up of all living patients was 33 months. Neurofibromatosis 1 (NF1) was seen in 12 (13%) patients. Sixty (65.2%) patients received curative-intent treatment. Statistical Analysis Used: Kaplan–Meier method was used for survival analysis. Log-rank test was used for univariate analysis, and multivariate analysis was done by Cox proportional hazard ratio method. Results: The 5-year overall survival (OS) of all patients was 47.2% and the 5-year disease-free survival (DFS) of operated patients was 41.5%. On univariate analysis, association with NF1 (P = 0.009), grade (P = 0.017), and margin status (P = 0.002) had a significant effect on DFS, whereas association with NF1 (P = 0.025), metastatic disease on presentation (P < 0.0001), palliative intent of treatment (P < 0.0001), grade (P = 0.049), and margin status (P = 0.036) had a significant effect on OS. On multivariate analysis for patients who were treated with curative-intent treatment, grade (P = 0.015), and margin status (P = 0.028) had a significant effect on DFS, whereas association with NF1 (P = 0.00026) and location of tumor (P = 0.040) had a significant effect on OS. Conclusions: The presence of distant metastasis, palliative intent of treatment, association with NF1, location of the tumor in the head and neck, high tumor grade, and positive margin status were the risk factors associated with poor survival for the patients with MPNST. Wide local excision with negative resection margin is the highly recommended treatment.