Search

In recent years, it has become clear that artificial intelligence (AI) models can achieve high accuracy in specific pathology‐related tasks. An example is our deep‐learning model, designed to automatically detect serous tubal intraepithelial carcinoma (STIC), the precursor lesion to high‐grade serous ovarian carcinoma, found in the fallopian tube. However, the standalone performance of a model is insufficient to determine its value in the diagnostic setting. To evaluate the impact of the use of this model on pathologists' performance, we set up a fully crossed multireader, multicase study, in which 26 participants, from 11 countries, reviewed 100 digitalized H&E‐stained slides of fallopian tubes (30 cases/70 controls) with and without AI assistance, with a washout period between the sessions. We evaluated the effect of the deep‐learning model on accuracy, slide review time and (subjectively perceived) diagnostic certainty, using mixed‐models analysis. With AI assistance, we found a significant increase in accuracy (p < 0.01) whereby the average sensitivity increased from 82% to 93%. Further, there was a significant 44 s (32%) reduction in slide review time (p < 0.01). The level of certainty that the participants felt versus their own assessment also significantly increased, by 0.24 on a 10‐point scale (p < 0.01). In conclusion, we found that, in a diverse group of pathologists and pathology residents, AI support resulted in a significant improvement in the accuracy of STIC diagnosis and was coupled with a substantial reduction in slide review time. This model has the potential to provide meaningful support to pathologists in the diagnosis of STIC, ultimately streamlining and optimizing the overall diagnostic process. [ABSTRACT FROM AUTHOR]

Endometrial carcinoma is a heterogeneous group of malignancies characterized by distinct histopathological features and genetic underpinnings. The 2020 WHO classification has provided a comprehensive framework for the categorization of endometrial carcinoma. However, it has not fully addressed the spectrum of uncommon entities that are currently not recognized by the 2020 WHO and have only been described in the form of small case series and case reports. These neoplasms represent a real diagnostic challenge for pathologists; furthermore, their therapeutic management still remains controversial and information regarding tumor prognosis is very limited. This review aims to elucidate these lesser-known variants of endometrial carcinoma. We discuss the challenges of identifying these rare subtypes and the molecular alterations associated with them. Furthermore, we propose the need for expanded classification systems that include these variants to enhance clinical outcomes and research efforts. We believe that a better histological typing characterization of these entities may lead to more reproducible and accurate diagnoses and more personalized treatments. By raising awareness of these rare entities, we also hope to encourage further investigation and integration into clinical practice to improve patient care in endometrial carcinoma. [ABSTRACT FROM AUTHOR]

Objective: The introduction of cytological screening with the Papanicolau smear significantly reduced cervical cancer mortality. However, Pap smear examination can be challenging, being based on the observer ability to decode different cytological and architectural features. This study aims to evaluate the malignancy rate of AGC (atypical glandular cells) category, investigating the relationships between cytological and histological diagnosis. Methods: Eighty‐nine patients, diagnosed as AGC at cytological evaluation and followed up with biopsy or surgical procedure at Policlinico Gemelli Hospital, Rome, Italy, were included in the study. The cytopathological architectural (feathering, rosette formation, overlapping, loss of polarity, papillary formation, three‐dimensional formation) and nuclear (N/C ratio, nuclear enlargement and hyperchromasia, mitoses, nuclei irregularity, evident nucleoli) features of AGC were evaluated. Statistical analyses were performed to assess cyto‐histological correlation and determine the relevance of architectural and nuclear features in the diagnosis of malignancy. Results: Of the 89 AGC patients, 48 cases (53.93%) were diagnosed as AGC‐NOS and 41 (46.07%) were diagnosed as AGC‐FN, according to the Bethesda classification system. The follow‐up biopsies or surgical resections revealed malignancy in 46 patients (51.69%). The rates of malignancy for AGC‐NOS and AGC‐FN were 35.41% and 70.73% respectively. Furthermore, analysing cytopathological features, we found that both architectural and nuclear criteria were statistically significant (p < 0.05). Only overlapping, nuclear irregularity and increased N/C ratio were not found to be statistically significant for detecting malignancy. Conclusions: Cytological diagnosis of glandular lesions remains a valid tool, when appropriate clinical correlation and expert evaluation are available. [ABSTRACT FROM AUTHOR]

Microscopic heterotopic extraovarian sex cord-stromal proliferations were first reported in the literature in 2015 by McCluggege. Afterwards, few similar cases have been described. Herein, we report the fourteenth case of microscopic heterotopic sex cord-stromal proliferation and the third case sited in the pelvic peritoneum. The clinical history of these rare cases suggests their benign nature. Knowledge of this histological pattern is important for differential diagnoses such as malignant pathologies and metastatic diseases., Competing Interests: Declaration of Competing Interest The authors declare no conflict of interest., (Copyright © 2024 The Authors. Published by Elsevier GmbH.. All rights reserved.)