Search

Background/Objectives: Proficient colposcopy is crucial for the adequate management of cervical cancer precursor lesions; nonetheless its limitations may impact its cost-effectiveness. The development of artificial intelligence models is experiencing an exponential growth, particularly in image-based specialties. The aim of this study is to develop and validate a Convolutional Neural Network (CNN) for the automatic differentiation of high-grade (HSIL) from low-grade dysplasia (LSIL) in colposcopy. Methods: A unicentric retrospective study was conducted based on 70 colposcopy exams, comprising a total of 22,693 frames. Among these, 8729 were categorized as HSIL based on histopathology. The total dataset was divided into a training (90%, n = 20,423) and a testing set (10%, n = 2270), the latter being used to evaluate the model's performance. The main outcome measures included sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), and the area under the receiving operating curve (AUC-ROC). Results: The sensitivity was 99.7% and the specificity was 98.6%. The PPV and NPV were 97.8% and 99.8%, respectively. The overall accuracy was 99.0%. The AUC-ROC was 0.98. The CNN processed 112 frames per second. Conclusions: We developed a CNN capable of differentiating cervical cancer precursors in colposcopy frames. The high levels of accuracy for the differentiation of HSIL from LSIL may improve the diagnostic yield of this exam [ABSTRACT FROM AUTHOR]

Background and Aims: The presence of portal hypertension in cirrhotic patients is a major prognostic factor associated with the development of severe complications and increased mortality. The gold standard for diagnosing portal hypertension is the hepatic venous pressure gradient. More recently, spleen stiffness has emerged as a new and non-invasive diagnostic tool, and has already been included in the last Baveno VII guidelines. The exact prevalence of Helicobacter pylori infection, pre-malignant lesions and their relation to portal hypertension have never been described. The aim of our study was to evaluate the relationship between the presence of portal hypertension assessed via liver and spleen elastography and Helicobacter pylori infection and pre-malignant gastric lesions. Methods: An observational study was conducted, including consecutive patients admitted from December 2020 to December 2022. All patients underwent upper endoscopy and were also subjected to liver and spleen elastography (using the new probe of 100 Hz) by the same blinded operator in a tertiary center. Results: We included 155 cirrhotic patients, with a mean age of 64.1 years (±8.8), and 81.3% were male. The most common etiology was alcoholic liver disease (72.9%). The median value of liver stiffness measurement was 24.4 kPa [3.1–75.0], and the spleen stiffness measurement was 49.1 kPa [12.8–100.0]. Akin to endoscopic findings, 50.3% presented esophageal varices, 5.2% gastric atrophy, 11.6% gastric metaplasia, and 32.9% portal hypertension gastropathy. Regarding histologic findings, we found that 34.8% presented H. pylori infection, 35.5% gastric atrophy (OLGA 1—58.2%) and 38.7% gastric metaplasia (OLGIM 1—63.3%). Liver stiffness and spleen stiffness measurements were associated with the presence of portal hypertensive gastropathy (p < 0.01), but not with H. pylori infection or pre-malignant gastric lesions. Conclusions: Although present in almost one third of cirrhotic patients, H. pylori infection and pre-malignant gastric lesions are not associated with liver stiffness and spleen stiffness measurements. On the other hand, we found an association between liver stiffness and spleen stiffness measurements and portal hypertensive gastropathy. [ABSTRACT FROM AUTHOR]

Artificial intelligence has yielded remarkably promising results in several medical fields, namely those with a strong imaging component. Gynecology relies heavily on imaging since it offers useful visual data on the female reproductive system, leading to a deeper understanding of pathophysiological concepts. The applicability of artificial intelligence technologies has not been as noticeable in gynecologic imaging as in other medical fields so far. However, due to growing interest in this area, some studies have been performed with exciting results. From urogynecology to oncology, artificial intelligence algorithms, particularly machine learning and deep learning, have shown huge potential to revolutionize the overall healthcare experience for women's reproductive health. In this review, we aim to establish the current status of AI in gynecology, the upcoming developments in this area, and discuss the challenges facing its clinical implementation, namely the technological and ethical concerns for technology development, implementation, and accountability. [ABSTRACT FROM AUTHOR]