Artificial Intelligence and Hysteroscopy: A Multicentric Study on Automated Classification of Pleomorphic Lesions.
Simple Summary: Hysteroscopy is subject to significant intra- and inter-observer variability due to the wide range of endometrial lesions that can be encountered. The application of artificial intelligence (AI) offers a promising avenue to mitigate this variability; however, its development in gynec...
| Publicado en: | Cancers Vol. 17; no. 15; pp. 2559 - 2569 |
|---|---|
| Autores principales: | , , , , , , , , , , , , , , , |
| Formato: | pictorial research tables/charts Journal Article |
| Publicado: |
MDPI
Aug2025
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=187315778&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 187315778 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 20726694 B74B jtl: Cancers issn: 20726694 maglogo: N pubinfo: dt: Aug2025 vid: 17 iid: 15 pid: 97109 pub: MDPI artinfo: ui: 187315778 187315778 187315778 10.3390/cancers17152559 187315778 ppf: 2559 ppct: 10 formats: tig: atl: Artificial Intelligence and Hysteroscopy: A Multicentric Study on Automated Classification of Pleomorphic Lesions. aug: au: Mascarenhas, Miguel Peixoto, Carla Freire, Ricardo Cavaco Gomes, Joao Cardoso, Pedro Castro, Inês Martins, Miguel Mendes, Francisco Mota, Joana Almeida, Maria João Silva, Fabiana Gutierres, Luis Mendes, Bruno Ferreira, João Mascarenhas, Teresa Zulmira, Rosa affil: Department of Gastroenterology, São João University Hospital, 4200-319 Porto, Portugal (M.M.) sug: subj: Convolutional Neural Networks Classification Algorithms Detection Algorithms Diagnosis, Computer Assisted Hysteroscopy Polyps Diagnosis Polyps Classification Endometrium Pathology Brazil Human Multicenter Studies Artificial Intelligence Descriptive Statistics Sensitivity and Specificity Retrospective Design Female Confidence Intervals Cancer Patients Deep Learning Endometrial Neoplasms Classification Female ab: Simple Summary: Hysteroscopy is subject to significant intra- and inter-observer variability due to the wide range of endometrial lesions that can be encountered. The application of artificial intelligence (AI) offers a promising avenue to mitigate this variability; however, its development in gynecology remains in its early stages compared to other medical imaging fields. In this study, we developed an AI model using a multicentric and diverse dataset, which demonstrated high performance not only in detecting polyps but also in accurately classifying them. Moreover, the use of bounding boxes provides visual localization that can potentially be deployed in real-time clinical procedures. Therefore, while AI adoption in gynecology is still emerging, this study illustrates its feasibility and clinical promise. 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. pubtype: Academic Journal doctype: pictorial research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|