Tsandmaa Byambadorj MD, Mohammad Rizwan Alam PhD, Yosep Chong MD, PhD
{"title":"Artificial intelligence in nongynecologic cytology: A systematic review of current research and commercial tools","authors":"Tsandmaa Byambadorj MD, Mohammad Rizwan Alam PhD, Yosep Chong MD, PhD","doi":"10.1002/cncy.70092","DOIUrl":"10.1002/cncy.70092","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Nongynecologic (non-GYN) cytology plays an important role in cellular and molecular cancer diagnosis, although its use is limited by variability and interobserver discrepancies. Recent studies suggest that artificial intelligence (AI) may improve diagnostic consistency and performance.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>This systematic review evaluated contemporary AI research in non-GYN cytology and examined commercially available systems.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>MEDLINE, Embase, and the Cochrane Library were searched for English-language studies published from January 2010 to September 2024. Of ∼24,000 records screened, 71 met inclusion criteria. Commercial platforms (KFBIO, Landing Med, VitaDx/VisioCyt, AIxMED, and CellsVision) were assessed using publicly available regulatory documents, technical specifications, and vendor-reported validation data.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Many studies reported high internal diagnostic performance, often exceeding 90% accuracy. Patch-level performance often reached ∼94%, exceeding whole slide image-level metrics. Reduced interobserver variability was frequently observed, with accuracies of 95.9% for senior and 94.4% for junior pathologists. Several studies documented shorter diagnostic time. Thyroid (37%) and urinary bladder (30%) cytology were most frequently studied. AI applications included categorization, segmentation, and atypia detection, with recent work exploring immunocytochemistry support, mutation-associated pattern recognition, and indirect prediction of histologic features.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>AI in non-GYN cytology shows promise but remains limited by data set quality, weak external validation, and regulatory barriers. At present, AI tools function primarily as decision-support systems. Advancing clinical adoption will require multicenter validation, standardized data sets, and careful integration with expert interpretation.</p>\u0000 </section>\u0000 </div>","PeriodicalId":9410,"journal":{"name":"Cancer Cytopathology","volume":"134 4","pages":""},"PeriodicalIF":3.2,"publicationDate":"2026-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13004427/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147490712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Asma Arshia MBBS, David Kalfert MD, PhD, Ivana Kholová MD, PhD, MIAC
{"title":"Navigating the International System for Reporting Serous Fluid Cytopathology in pericardial effusion: A meta-analysis","authors":"Asma Arshia MBBS, David Kalfert MD, PhD, Ivana Kholová MD, PhD, MIAC","doi":"10.1002/cncy.70091","DOIUrl":"10.1002/cncy.70091","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>The International System for Reporting Serous Fluid Cytopathology (TIS) provides a standardized framework for classifying serous fluid cytology into five diagnostic categories: nondiagnostic, negative for malignancy, atypical, suspicious for malignancy, and malignant. Although TIS has been widely adopted for pleural and peritoneal fluids, its application in pericardial effusion cytology remains limited. The objective of this study was to evaluate the use of TIS in pericardial effusion samples and estimate the associated risk of malignancy for each category.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>A systematic review was conducted according to PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Studies published between 2013 and 2023 were identified through a comprehensive PubMed search. Eligible studies applied TIS to pericardial effusion cytology. The analysis excluded case reports, case reviews, abstracts, comparative studies, and non-English publications. Furthermore, the authors omitted studies that did not explicitly categorize pericardial fluid samples using the TIS categorization. Ten studies met inclusion criteria, comprising 2976 pericardial fluid samples.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>The pooled distribution across TIS categories were: nondiagnostic (2.9%), negative for malignancy (60.2%), atypical (5.4%), suspicious for malignancy (2.4%), and malignant (23.4%). Risk of malignancy estimates based on histologic confirmation were: 10.8% for nondiagnostic, 8.7% for negative for malignancy, 34.0% for atypical, 64.1% for suspicious for malignancy, and 78.6% for malignant categories.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>TIS effectively stratifies pericardial effusion cytology samples by malignancy risk. The progressive increase in the risk of malignancy across categories supports its diagnostic utility. However, substantial heterogeneity, particularly in the negative for malignancy and malignant categories, highlights the need for standardized reporting and further prospective validation of TIS.</p>\u0000 </section>\u0000 </div>","PeriodicalId":9410,"journal":{"name":"Cancer Cytopathology","volume":"134 4","pages":""},"PeriodicalIF":3.2,"publicationDate":"2026-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13001633/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147484719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cheng-Chieh Chen MSc, Ke-Yu Hsiao MSc, Hsiu-Ling Lin BS, RN
{"title":"Clinical utility of oral cytology for detecting oral epithelial dysplasia or worse: A diagnostic meta-analysis","authors":"Cheng-Chieh Chen MSc, Ke-Yu Hsiao MSc, Hsiu-Ling Lin BS, RN","doi":"10.1002/cncy.70088","DOIUrl":"10.1002/cncy.70088","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>The majority of oral cancers are diagnosed at an advanced stage. It has been demonstrated that the implementation of screening programs reduces mortality rates. Oral cytology is a technique that is used in these programs. However, the accuracy of oral cytology remains controversial. Therefore, the objective of this meta-analysis was to validate the accuracy of oral cytology.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>A literature search was conducted in the PubMed, Embase, and Cochrane Library databases to identify eligible studies. The inclusion criteria were as follows: studies that evaluated the diagnostic accuracy of oral cytology for low-grade squamous intraepithelial lesion or worse. The article incorporated peer-reviewed articles. In addition, studies that provided sufficient data for conducting a meta-analysis were assessed. The meta-analysis was conducted using a bivariate random-effects model.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>In total, 26 articles comprising 8397 specimens were included in the study. The meta-analysis yielded a pooled sensitivity of 93.8% and a pooled specificity of 87.7% of oral cytology for identifying oral epithelia dysplasia or worse. A subgroup analysis of studies that evaluated oral cytology with Papanicolaou staining demonstrated a pooled sensitivity of 94.8%. The accuracy of oral cytology in detecting high-grade squamous intraepithelial lesion or worse was examined, resulting in a pooled sensitivity of 95.7%.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>This meta-analysis indicated that oral cytology exhibited high sensitivity and specificity in detecting oral epithelia dysplasia or worse, with slightly higher sensitivity for high-grade squamous intraepithelial lesion or worse. A notable advantage of using oral cytology with Papanicolaou staining is the potential for enhanced sensitivity.</p>\u0000 </section>\u0000 </div>","PeriodicalId":9410,"journal":{"name":"Cancer Cytopathology","volume":"134 4","pages":""},"PeriodicalIF":3.2,"publicationDate":"2026-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147472380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A growing brain drain: US policies are spurring medical researchers to pursue other options","authors":"Bryn Nelson PhD, William Faquin MD, PhD","doi":"10.1002/cncy.70081","DOIUrl":"10.1002/cncy.70081","url":null,"abstract":"<p>In March 2025, after weeks of upheaval at the National Institutes of Health (NIH), brewing fights over academic freedom, and increasingly restrictive immigration policies, many researchers in the United States were starting to eye the exits. More than 75% of scientists who responded to a <i>Nature</i> poll said that they were “considering leaving the country following the disruptions to science prompted by the Trump administration.”<span><sup>1</sup></span> Early-career researchers were particularly apt to consider departing. Their top choices were Europe and Canada.</p><p>Other researchers are not even getting in the door or are opting for another entrance to a different career. The disruptions have affected many, including undergraduates who are not receiving internships, graduate students who are encountering closed programs and discontinued fellowships, and postdoctoral fellows and international scholars who are unable to access grants or work visas. “Literally at every single stage of the training spectrum, we have now disincentivized people to pursue these professional trajectories. It’s brain drain by a thousand paper cuts,” says Rachael Sirianni, PhD, a professor of neurological surgery at the University of Massachusetts Chan Medical School in Worcester.</p><p>The rest of the world has taken notice. A growing number of recruitment drives are vying to entice disgruntled or displaced researchers to Canada, China, the United Kingdom, France, Germany, and other countries. Gwen Nichols, MD, chief medical officer of the Leukemia and Lymphoma Society, says that a LinkedIn feed for scientists has been filled with recruitment offers from foreign countries and institutions. “If I’m seeing it, thousands of others are seeing it as well,” she says. Ironically, many of these efforts have been patterned after the past successes of the leader in medical research: the United States itself.</p><p>The United States, observers say, has long been a magnet for research talent from around the world because of its deep investments in research and its reputation as an attractive destination for immigrants. Both of those advantages are now in jeopardy, creating new openings for other countries. “The pullback on support of science, the rise of pseudoscience and that move away from experts and expertise, it’s got people worried; it’s got people thinking about other places,” says Brad Wouters, PhD, executive vice president of science and research at the University Health Network (UHN) in Toronto, Canada.</p><p>In April, UHN launched a program called Canada Leads, which aims to reverse the Toronto region’s own brain drain by recruiting 100 early-career medical researchers to UHN’s institutions, including Toronto General Hospital, Toronto Western Hospital, and the Princess Margaret Cancer Centre. The $30 million initiative is providing money for supplemental salaries as well as laboratory space, mentorship, and partnerships with academic and industry collaborators. ","PeriodicalId":9410,"journal":{"name":"Cancer Cytopathology","volume":"134 3","pages":""},"PeriodicalIF":3.2,"publicationDate":"2026-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://acsjournals.onlinelibrary.wiley.com/doi/epdf/10.1002/cncy.70081","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147347335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
