We report a case of pulmonary Rhizopus microsporus infection in a patient with untreated diabetes following brush clearing. The patient was successfully treated with a combined medical and surgical approach with complete resolution of the lung lesions and remains asymptomatic at 11-month follow-up.

Fine needle aspiration (FNA) biopsy of thyroid nodules is a safe, cost-effective, and accurate diagnostic method for detecting thyroid cancer. However, about 10% of initial FNA biopsy samples from patients are non-diagnostic and require repeated FNA, which delays the diagnosis and appropriate care. On-site evaluation of the FNA sample can be performed to filter out non-diagnostic FNA samples. Unfortunately, it involves a time-consuming staining process, and a cytopathologist has to be present at the time of FNA. To bypass the staining process and expert interpretation of FNA specimens at the clinics, we developed a deep learning-based ensemble model termed FNA-Net that allows in situ screening of adequacy of unstained thyroid FNA samples smeared on a glass slide which can decrease the non-diagnostic rate in thyroid FNA. FNA-Net combines two deep learning models, a patch-based whole slide image classifier and Faster R-CNN, to detect follicular clusters with high precision. Then, FNA-Net classifies sample slides to be non-diagnostic if the total number of detected follicular clusters is less than a predetermined threshold. With bootstrapped sampling, FNA-Net achieved a 0.81 F1 score and 0.84 AUC in the precision-recall curve for detecting the non-diagnostic slides whose follicular clusters are less than six. We expect that FNA-Net can dramatically reduce the diagnostic cost associated with FNA biopsy and improve the quality of patient care.

Although the overall prognosis for patients with non-small cell lung cancer (NSCLC) has improved over the past several decades, there are still survival differences that are not accurately defined by clinicopathological factors. Thus, there is an unmet clinical need to develop novel approaches to enhance prognostic accuracy for these patients. Keratin 17 (K17) is a negative prognostic biomarker in a wide range of cancer types, including pancreatic ductal adenocarcinoma, head and neck squamous cell carcinoma, and pulmonary adenocarcinoma (LUAD), but has yet to be investigated as a prognostic biomarker in primary lung squamous cell carcinoma (LSCC). Based on TCGA RNA-seq data, alpha-2-macroglobulin like 1 (A2ML1), a protease inhibitor, is highly correlated with K17 in other solid tumors, including pancreatic ductal adenocarcinoma and is also a prognostic biomarker for LSCC, although the prognostic accuracy of A2ML1 for LUAD has not been tested. Thus, we hypothesized that A2ML1 expression correlates with K17 expression and that K17/A2ML1 co-testing could provide complementary prognostic data for NSCLC. The aims of this study were to explore K17 and A2ML1 as dual prognostic biomarkers, using publicly available gene expression databases [The Cancer Genome Atlas (TCGA)] LSCC (n=266), LUAD (n=271)] and multiplexed immunohistochemistry (mIHC) on representative sections of LSCC (n=104) and LUAD (n=107) from two major academic medical centers. Our results suggest that using either mRNA or mIHC-based methods, combined K17 and A2ML1 testing provides information, independent of other clinicopathologic variables, that could impact treatment decisions for patients with NSCLC.