Atypical Squamous Verrucous Lesions of the Oral Cavity: Challenges in Interpretation of Small Incisional Biopsies.

BACKGROUND: Squamous verrucous proliferative lesions of oral cavity can pose a diagnostic challenge for the general pathologist, especially on small biopsies. The superficial nature of incisional biopsies and inconsistent histologic terminologies used for these lesions contribute to often-discrepant clinical diagnosis, resulting in delayed treatment. This study aims to explore the proliferative squamous lesions of oral cavity, correlate biopsy & resection diagnoses, and evaluate possible reasons for discrepant diagnosis (if any). DESIGN: A retrospective review of oral verrucous squamous lesions was undertaken. Pathology database was searched for oral cavity biopsies from January2018 through August2022 with the keywords: atypical, verrucous, squamous, and proliferative. Cases with follow-up were included in this study. A blinded review of the biopsy slides was performed and documented by a single head and neck pathologist. Demographic data, biopsy and final diagnosis were recorded. RESULTS: Twenty-three cases met criteria for inclusion. The mean patient age was 61.1 years with a male: female ratio of 1.09. Most frequent site was lateral border of tongue (36%) followed by buccal mucosa and retromolar trigone. The most common biopsy diagnosis was "Atypical squamoproliferative lesion, excision recommended" (n = 16/23, 69%) with 13/16 showing conventional squamous cell carcinoma (SCC) on follow-up resection. 2/16 atypical cases underwent repeat biopsy for confirmation of diagnosis. Overall, conventional SCC was the most prevalent final diagnosis (73%, n = 17), followed by verrucous carcinoma (17%, n = 4). On slide review, six initial biopsies were reclassified as SCC, while one final diagnosis was reclassified as a hybrid carcinoma (on resection specimen). Diagnostic concordance (biopsy and resection) was observed in three cases, all three were recurrences. The primary reasons for discrepant diagnosis on initial biopsies were found to be 1. Obscuring inflammation, 2. Superficial biopsies, and 3. Under recognition of morphologic features (e.g., tear shaped rete, loss of polarity, dyskeratotic cells, paradoxical maturation) that help differentiate dysplasia from reactive atypia. CONCLUSION: This study highlights the rampant interobserver variability in diagnosis of oral cavity squamous lesions and emphasizes importance of identifying morphologic clues that can aid in correct diagnosis, thereby helping in adequate clinical management.

Bladder cancer prognosis using deep neural networks and histopathology images.

Background: Recent studies indicate that bladder cancer is among the top 10 most common cancers in the world (Saginala et al. 2022). Bladder cancer frequently reoccurs, and prognostic judgments may vary among clinicians. As a favorable prognosis may help to inform less aggressive treatment plans, classification of histopathology slides is essential for the accurate prognosis and effective treatment of bladder cancer patients. Developing automated and accurate histopathology image analysis methods can help pathologists determine the prognosis of patients with bladder cancer. Materials and methods: In this study, we introduced Bladder4Net, a deep learning pipeline, to classify whole-slide histopathology images of bladder cancer into two classes: low-risk (combination of PUNLMP and low-grade tumors) and high-risk (combination of high-grade and invasive tumors). This pipeline consists of four convolutional neural network (CNN)-based classifiers to address the difficulties of identifying PUNLMP and invasive classes. We evaluated our pipeline on 182 independent whole-slide images from the New Hampshire Bladder Cancer Study (NHBCS) (Karagas et al., 1998; Sverrisson et al., 2014; Sverrisson et al., 2014) collected from 1994 to 2004 and 378 external digitized slides from The Cancer Genome Atlas (TCGA) database (https://www.cancer.gov/tcga). Results: The weighted average F1-score of our approach was 0.91 (95% confidence interval (CI): 0.86-0.94) on the NHBCS dataset and 0.99 (95% CI: 0.97-1.00) on the TCGA dataset. Additionally, we computed Kaplan-Meier survival curves for patients who were predicted as high risk versus those predicted as low risk. For the NHBCS test set, patients predicted as high risk had worse overall survival than those predicted as low risk, with a log-rank p-value of 0.004. Conclusions: If validated through prospective trials, our model could be used in clinical settings to improve patient care.

Primary Pulmonary Round Cell Sarcomas: Multiple Potential Pitfalls for the Pathologist.

Primary sarcomas of the lung are extremely uncommon. A diverse group of round cell sarcomas has been reported to originate in this location, including Ewing sarcoma, desmoplastic small round cell tumor, rhabdomyosarcoma, and poorly differentiated synovial sarcoma. The rarity of these tumors presents a potential pitfall; without careful study, they may easily be misidentified as the significantly more common poorly differentiated carcinoma. While histomorphology is a key aspect of correctly identifying a sarcoma, ancillary testing has become increasingly important in making a definitive diagnosis, as more and more recurrent genetic alterations are discovered and new entities are defined. We present three cases of primary round cell sarcomas of the lung that proved diagnostically challenging, describe the features and ancillary testing that led to the correct diagnoses, and discuss classic and evolving entities among sarcomas with round cell morphology.

Retrospective Evaluation of the Antibody Prevalence in Epilepsy and Encephalopathy (APE2) Score.

BACKGROUND: Autoimmune encephalitis (AE) is a rare collection of disorders that present with a diverse and often nebulous set of clinical symptoms. Indiscriminate use of multi-antibody panels decreases their overall utility and predictive value. Application of a standardized scoring system may help reduce the number of specimens that generate misleading or uninformative results. METHODS: The results of autoimmune encephalopathy, epilepsy, or dementia autoantibody panels performed on serum (n = 251) or cerebrospinal fluid (CSF) (n = 235) specimens from October 9th, 2016 to October 11th, 2019 were collected. Retrospective chart review was performed to calculate the Antibody Prevalence in Epilepsy and Encephalopathy (APE2) score for patients with an antibody above the assay-specific reference interval and to classify results as true or false positive. RESULTS: Of the 486 specimens, 60 (12.3%) generated positive results for any AE antibody (6 CSF and 54 serum). After removing 2 duplicate specimens collected from a single patient, 10 of the remaining 58 were determined to be true positives and 8 contained neural-specific antibodies. Application of the APE2 score revealed that 89% of all true positives and 86% of specimens with neural-specific antibodies had a score ≥4. In contrast, 76% of false positives, 74% of clinically nonspecific antibodies, and 85% of the negative specimens had an APE2 score <4. CONCLUSION: The APE2 score can improve the diagnostic utility of autoimmune encephalopathy evaluation panels.

Development and evaluation of a deep neural network for histologic classification of renal cell carcinoma on biopsy and surgical resection slides.

Renal cell carcinoma (RCC) is the most common renal cancer in adults. The histopathologic classification of RCC is essential for diagnosis, prognosis, and management of patients. Reorganization and classification of complex histologic patterns of RCC on biopsy and surgical resection slides under a microscope remains a heavily specialized, error-prone, and time-consuming task for pathologists. In this study, we developed a deep neural network model that can accurately classify digitized surgical resection slides and biopsy slides into five related classes: clear cell RCC, papillary RCC, chromophobe RCC, renal oncocytoma, and normal. In addition to the whole-slide classification pipeline, we visualized the identified indicative regions and features on slides for classification by reprocessing patch-level classification results to ensure the explainability of our diagnostic model. We evaluated our model on independent test sets of 78 surgical resection whole slides and 79 biopsy slides from our tertiary medical institution, and 917 surgical resection slides from The Cancer Genome Atlas (TCGA) database. The average area under the curve (AUC) of our classifier on the internal resection slides, internal biopsy slides, and external TCGA slides is 0.98 (95% confidence interval (CI): 0.97-1.00), 0.98 (95% CI: 0.96-1.00) and 0.97 (95% CI: 0.96-0.98), respectively. Our results suggest that the high generalizability of our approach across different data sources and specimen types. More importantly, our model has the potential to assist pathologists by (1) automatically pre-screening slides to reduce false-negative cases, (2) highlighting regions of importance on digitized slides to accelerate diagnosis, and (3) providing objective and accurate diagnosis as the second opinion.

Educational Case: Aspiration Pneumonia.

The following fictional case is intended as a learning tool within the Pathology Competencies for Medical Education (PCME), a set of national standards for teaching pathology. These are divided into three basic competencies: Disease Mechanisms and Processes, Organ System Pathology, and Diagnostic Medicine and Therapeutic Pathology. For additional information, and a full list of learning objectives for all three competencies, see http://journals.sagepub.com/doi/10.1177/2374289517715040.1.