AUTHOR=Zhang Yingfeng , Qin Qin 

TITLE=Prospects and challenges of deep learning in gynecologic malignancies

JOURNAL=Frontiers in Oncology

VOLUME=Volume 15 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2025.1592078

DOI=10.3389/fonc.2025.1592078

ISSN=2234-943X

ABSTRACT=Artificial intelligence (AI) is revolutionizing oncology, with deep learning (DL) emerging as a pivotal technology for addressing gynecologic malignancies (GMs). DL-based models are now widely applied to assist in clinical diagnosis and prognosis prediction, demonstrating excellent performance in tasks such as tumor detection, segmentation, classification, and necrosis assessment for both primary and metastatic GMs. By leveraging radiological (e.g., X-ray, CT, MRI, and Single Photon Emission Computed Tomography (SPECT)) and pathological images, these approaches show significant potential for enhancing diagnostic accuracy and prognostic evaluation. This review provides a concise overview of deep learning techniques for medical image analysis and their current applications in GM diagnosis and outcome prediction. Furthermore, it discusses key challenges and future directions in the field. AI-based radiomics presents a non-invasive and cost-effective tool for gynecologic practice, and the integration of multi-omics data is recommended to further advance precision medicine in oncology.