Research progress of artificial intelligence and radiomics in ovarian cancer
QI Luying
ZHAO Hongxing
BIAN Hupo
XUE Jingnan
CHEN Jieqiong
Abstract：Ovarian cancer(OC)is the deadliest malignant tumour of female reproductive system,which is mostly found in end stage with poor prognosis and easy to recur.Current diagnostic methods for ovarian cancer are mainly imaging and pathologi-cal examinations,but,with limited sensitivity and specificity.The emerging radiomics technology is able to extract quantitative imaging features from medical images and transform visual image information into deeper features to quantitatively assess lesions.The combination of artificial intelligence,a computer algorithm capable of simulating computers and surpassing human intelli-gence,and radiomics further promotes the development of ovarian cancer in terms of identification,segmentation,diagnosis,classification,lymph node metastasis,efficacy evaluation,survival prediction and recurrence monitoring.At present,3D U-Net can achieve automated segmentation of OC,and the combination of radiomics and deep learning(DL)can non-invasively distinguish between benign and malignant OC before surgery.The combination of radiomics and clinical indicators can assist in preoperative diagnosis of lymph node metastasis,and radiomics and convolutional neural networks(CNNs)can improve the ac-curacy of survival prediction and recurrence risk.In this paper,we review the progress of the application of artificial intelligence and radiomics in the field of ovarian cancer.
Keywords：Ovarian cancerArtificial intelligenceRadiomicsDeep learning
Publication Date：2025-12-30
Online Publishing Date：2026-02-04(First online date of this platform, not the publication date of the document)
Pages：5( 153-157 )