The use of MRI in the diagnosis of ovarian cancer.
Authors
Affiliations (4)
Affiliations (4)
- School of Radiology, Shandong First Medical University, Tai'an, Shandong, China.
- Department of Nuclear Medicine, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, China.
- Department of Oncology, The Affiliated Hospital of Shandong University of Traditional Chinese Medicine, Jinan, China.
- Department of Obstetrics and Gynecology, Shandong Provincial Maternal and Child Health Care Hospital Affiliated to Qingdao University, Jinan, China.
Abstract
Ovarian cancer is a malignant tumor of the female reproductive system with a high mortality rate. Currently, China has the highest number of new ovarian cancer cases worldwide; therefore, preoperative diagnosis is of particular importance. Magnetic resonance imaging (MRI), with its excellent soft tissue resolution and absence of ionizing radiation risk, has become a key imaging modality for the non-invasive diagnosis of ovarian cancer in clinical practice. This article systematically reviews the latest research advances in the application of conventional morphological MRI, multiparametric MRI, and the integration of MRI with radiomics and deep learning technologies in the diagnosis and treatment of ovarian cancer. It focuses on their clinical value in assessing the benign or malignant nature of ovarian tumors, classifying pathological subtypes of epithelial and non-epithelial ovarian cancers, staging ovarian cancer, monitoring treatment efficacy, and predicting prognosis. Additionally, it outlines research directions for emerging technologies such as molecular probes. Existing studies have confirmed that multimodal MRI fusion technology can significantly improve the diagnostic accuracy of ovarian cancer; however, challenges remain, including a lack of model generalizability, insufficient interpretability, difficulty in detecting micro-lesions, and low clinical adoption rates. Future efforts should focus on establishing standardized MRI scanning protocols and data standards, conducting large-scale, multicenter prospective studies, deepening the integrated application of interpretable artificial intelligence and molecular imaging, and constructing an integrated "imaging-biology-clinical" precision assessment system to advance the development of precision preoperative diagnosis and treatment for ovarian cancer.