Adnexal masses can be found in 0.19 to 8.8% of all pregnancies. Most masses are functional and asymptomatic and up to 70% resolve spontaneously in the second trimester. The main predictors of persistence are the size (>5 cm) and the imagiological morphocomplexity. Those that persist carry a low risk of malignancy (0 to 10%). Most malignant masses are diagnosed at early stages and more than 50% are borderline epithelial neoplasms. Ultrasound is the preferred method to stratify the risk of complications and malignancy, allowing medical approach planning. Pregnancy and some gestational disorders may modify the levels of tumor markers, whereby their interpretation during pregnancy should be cautious. Large masses are at increased risk of torsion, rupture, and dystocia. When surgery is indicated, laparoscopy is a safe technique and should ideally be carried out in the second trimester of pregnancy.

Background/Objectives: The integration of artificial intelligence (AI) in medical imaging is rapidly advancing, yet its application in gynecologic use remains limited. This proof-of-concept study presents the development and validation of a convolutional neural network (CNN) designed to automatically detect and classify endometrial polyps. Methods: A multicenter dataset (n = 3) comprising 65 hysteroscopies was used, yielding 33,239 frames and 37,512 annotated objects. Still frames were extracted from full-length videos and annotated for the presence of histologically confirmed polyps. A YOLOv1-based object detection model was used with a 70–20–10 split for training, validation, and testing. Primary performance metrics included recall, precision, and mean average precision at an intersection over union (IoU) ≥ 0.50 (mAP50). Frame-level classification metrics were also computed to evaluate clinical applicability. Results: The model achieved a recall of 0.96 and precision of 0.95 for polyp detection, with a mAP50 of 0.98. At the frame level, mean recall was 0.75, precision 0.98, and F1 score 0.82, confirming high detection and classification performance. Conclusions: This study presents a CNN trained on multicenter, real-world data that detects and classifies polyps simultaneously with high diagnostic and localization performance, supported by explainable AI features that enhance its clinical integration and technological readiness. Although currently limited to binary classification, this study demonstrates the feasibility and potential of AI to reduce diagnostic subjectivity and inter-observer variability in hysteroscopy. Future work will focus on expanding the model’s capabilities to classify a broader range of endometrial pathologies, enhance generalizability, and validate performance in real-time clinical settings.

Introduction: The pathophysiology of endometriosis is not well established. Different theories have been proposed to explain endometriosis, but none alone is able to explain all of the cases described. Case presentation: We report a case of a woman with a congenital polymalformative syndrome, early puberty and primary amenorrhea, in whom an asymptomatic right adnexal nodule was detected at 14 years of age. When she was 18 years old, a laparoscopy was performed, and an ovoid lesion in the right uterine tube was identified and salpingectomy was performed. The pathological examination revealed endometriosis in the muscular layer of the tube. Conclusions: Endometriosis can start early in puberty, even before menarche and in the absence of an obstructive disorder.