Faculty Bibliography

OBJECTIVE/UNASSIGNED:Early detection and removal of suspicious polyps during routine colonoscopies play an important role in reducing the risk of colorectal cancer. Patient management and follow-up are determined by the type of polyps removed and the degree of dysplasia present on histological evaluation. Whereas discerning between a benign polyp and a dysplastic one is a trivial task, distinguishing between tubular adenomas with low-grade dysplasia (LGD) and high-grade dysplasia (HGD) is a challenging task. In this study, we trained a deep learning model to distinguish between colorectal adenomas with LGD and HGD. DESIGN/UNASSIGNED:We retrieved 259 slides of adenomatous polyps taken between January 2011 and October 2024. Slides with HGD were reviewed by a subspecialty-trained GI pathologist. After excluding discordant and duplicate cases, 200 slides remained: 71 (35.5%) with HGD and 129 (64.5%) with LGD. The slides were divided into training (160 slides, 80%) and test (40 slides, 20%) sets. After patch generation and stain normalization, a ResNet34 model (pre-trained on ImageNet) was trained using 5-fold cross-validation. Slide classification was determined by aggregating patch-level predictions. RESULTS/UNASSIGNED:The model's slide-level prediction accuracy was 95.0%, correctly classifying all but 2 out of 40 slides. The model achieved an area under the receiver operating characteristic curve score of 0.981 and an F1 score of 0.923. CONCLUSIONS/UNASSIGNED:This study demonstrates that deep learning models can accurately distinguish between colonic adenomas with LGD and HGD. Training on a larger dataset could increase the accuracy and generalizability of the model and should be a focus of further studies.

OBJECTIVES/OBJECTIVE:Fine needle aspiration (FNA) plays a crucial role in their initial assessment of salivary gland neoplasms. In the Milan System for Reporting Salivary Gland Cytopathology (MSRSGC), the category of Salivary Gland Neoplasm of Uncertain Malignant Potential (SUMP) categorizes lesions with ambiguous features. This study aims to investigate the risk of neoplasm (RON) and risk of malignancy (ROM) within different subgroups of SUMP lesions using data from three large academic institutions. METHODS:We analyzed salivary gland (FNA) cases from three academic institutions post-MSRSGC implementation. Salivary gland FNA cases categorized as Milan IVB (SUMP) with subsequent surgical pathology follow-up were analyzed. Cases were divided into basaloid, oncocytic, and clear cell SUMP subtypes, with RON and ROM assessed and compared. RESULTS:Out of 1377 MSRSGC cases, 231 were SUMP (16.8%), with 101 subjected to surgical pathology follow-up. The overall ROM for SUMP was 20.8%, with variations of 10% to 29.5% observed amongst institutions, but no significant difference was observed among three institutions (p = 0.15). Basaloid and oncocytic SUMP displayed 17.1% and 20.5% ROM, respectively, without significant disparity. However, all clear cell SUMP cases were malignant on surgical resection. CONCLUSIONS:This study highlights the variability in ROM for SUMP lesions and the significantly higher ROM in SUMP cases with clear cell features. These findings emphasize the importance of accurately subcategorizing SUMP lesions, particularly those with clear cell features, for appropriate clinical management.

This study presents two cases of lipid-rich pancreatic neuroendocrine tumors (PanNETs), a rare variant posing significant diagnostic challenges in fine needle aspiration (FNA) cytology and small biopsies. The first case involves an elderly male with a pancreatic tumor, displaying distinct cytoplasmic vacuoles, while the second case is a middle-aged male present with a pancreatic tail mass exhibiting foamy cytoplasm and eccentric nuclei, infiltrating in the stroma. Both cases did not exhibit typical morphologic features of PanNET but demonstrated cytomorphologic features and infiltrative growth patterns that mimicked adenocarcinoma. Further work-up demonstrated that both tumors were immunoreactive for synaptophysin and chromogranin, and were interpreted as well-differentiated, PanNET, lipid-rich variant. The study highlights the overlapping morphological features between lipid-rich PanNETs and other pancreatic neoplasms and underscores the importance of comprehensive cytological and immunohistochemical analysis for accurately diagnosing this variant, particularly due to the risk of misinterpreting it as pancreatic adenocarcinoma. Recognizing lipid-rich PanNETs is crucial for appropriate clinical management, as their identification can significantly impact treatment decisions and patient outcomes.

OBJECTIVES/OBJECTIVE:We studied the prevalence and prognostic significance of mismatch repair deficient (MMRD) and p53 aberrant ovarian clear cell carcinoma (CCO) and their association with other prognostic and theranostic biomarkers (p16, HER2, PD-L1). We also aimed to identify morphologic features to serve as screening tools for immunohistochemical testing for these biomarkers. METHODS:Tissue microarrays with 3-mm cores from 71 pure CCOs were immunostained with PMS2, MSH6, p53, p16, HER2, and PD-L1. Expression status was correlated with tumor recurrence/disease progression and survival. It was also correlated with morphologic features (tumor size, nuclear grade, tumor architecture, mitotic activity, presence of endometriosis, tumor budding, and tumor inflammation). RESULTS:p53 aberrant tumors were associated with shorter overall and recurrence-free survivals (P = .002 and P = .01, respectively). In multivariate analysis, p53 aberrant status and tumor stage were independently associated with recurrence/disease progression (hazard ratio [HR] = 3.31, P = .037 and HR = 1.465, P = .004, respectively). p53 aberrant status was associated with tumor budding (P = .037). MMRD, p16, HER2, and PD-L1 expression had no prognostic significance. HER2 and PD-L1 were expressed in 56% and 35% of tumors, respectively. MMRD was associated with tumor expression of PD-L1 (P > .05) but not with tumor inflammation. CONCLUSIONS:Aberrant p53 in CCO is infrequent but associated with poor prognosis independent of stage. Presence of tumor budding could be a screening tool for p53 testing. High prevalence of HER2 and PD-L1 expression indicates the eligibility of patients with CCO for ongoing clinical trials using these therapeutic targets.