Tian, Roland

Abstract In epilepsy patients lacking magnetic resonance imaging‐visible lesions such as focal cortical dysplasia (FCD), surgical resections target regions with abnormal electroencephalographic (EEG) activity. However, histopathological identification of subtle cortical architectural abnormalities in these specimens remains challenging. We investigated whether artificial intelligence (AI)‐based morphometric and spatial analysis of NeuN‐stained cortical sections could detect neuronal architectural disorganization in epilepsy resections, including regions without definitive histologic dysplasia. Whole slide images were generated from 83 FCD regions and 19 neurologically normal autopsy controls. Regions of interest were annotated in QuPath as FCD, FCD‐adjacent, FCD‐distant, apparently normal (abnormal EEG without histologic dysplasia), and true normal (autopsy controls). NeuN‐positive neurons were detected using QuPath (90% sensitivity, 12% false positive rate). Spatial and morphometric features—including neuronal clustering, distribution inhomogeneity, and nuclear morphology—were extracted and used to train a multinomial, Least Absolute Shrinkage and Selection Operator‐regularized regression classifier. The classifier achieved 70.6% accuracy in subregion classification and 88.2% accuracy in overall specimen diagnosis. Notably, regions with abnormal EEG but lacking histologic dysplasia exhibited quantifiable architectural disorganization similar to those seen in areas adjacent to FCD and distinct from control tissue. AI‐driven analysis of neuronal morphology and spatial distribution reveals subtle cortical disorganization in epilepsy resections, including in histologically ambiguous regions. Further investigation is warranted to determine if this methodology can enhance the diagnostic yield of neuropathological evaluation and support more precise surgical targeting in epilepsy.

Context.— Social media is a powerful tool in pathology education and professional networking that connects pathologists and pathology trainees from around the world. Twitter (X) appears to be the most popular social media platform pathologists use to share pathology-related content and connect with other pathologists. Although there has been some published research on pathology-related activity on Twitter during short time frames, to date there has not been published research examining pathology-related Twitter activity in totality from its earliest days of activity to recently. Objective.— To comprehensively evaluate the use of pathology on Twitter (X) during the last 10 years. Design.— Pathology-related tweets were systematically scraped from Twitter from January 2012 to January 2023 using pathology hashtags as a surrogate measure for all pathology content on Twitter. COVID-related tweets were approximated by tweets containing the term “COVID.” Results.— There were 591 812 unique pathology-related tweets identified during the time period, with #pathology being the most common hashtag used and #PathTwitter becoming more popular since 2020. There has been positive annual growth of pathology Twitter, with peaks in use during major pathology conferences. During the initial phases of the COVID-19 pandemic, a sustained increase in pathology tweets was observed. Conclusions.— Pathology Twitter has grown during the last 10 years and has become increasingly popular for pathology education and networking. With the changing landscape of social media platforms, this study provides an understanding of how pathology medical education and professional networking uses of social media happen and evolve over time.