BEIJING, Aug. 18 (Xinhua) -- Chinese researchers have developed a non-invasive method to differentiate ovarian cancer subtypes, which could help improve therapeutic plans, according to the Chinese Academy of Sciences (CAS).

Ovarian cancers can be divided into type I and type II according to etiology and prognosis. Accurate subtype differentiation can help improve treatment plans and prognosis.

Researchers from the Suzhou Institute of Biomedical Engineering and Technology under the CAS and Jinshan Hospital of Fudan University conducted a multicenter study involving more than 294 ovarian cancer patients, of which 143 were type I and 151 type II.

They collected the Magnetic Resonance Imaging (MRI) of patients and used machine learning method to build a novel MRI-based radiomics model that can differentiate between type I and type II ovarian cancer. The diagnosis has an average accuracy of 83 percent.

The research was published in the journal European Radiology.