Current status and future potential of radiomics in the management of patients with gastric cancer

Gastric cancer (GC) is one of the most common malignant tumors in the world and has attracted much attention due to its high incidence and mortality. Early detection and accurate diagnosis of GC is very important to improve the survival rate of patients. Traditional imaging techniques, such as computed tomography (CT), have played an important role in the diagnosis and staging of GC, but their accuracy and predictive power are still limited. Radiomics, as an emerging multidisciplinary field, combines medical imaging, computer technology, and bioinformatics to reveal potential biological information in image data through quantitative extraction of image features. To review the current status and future potential of radiomics in the diagnosis, prognosis, and outcome prediction for patients with GC, related studies with keywords such as “radiomics,” “gastric cancer,” and “predict” were retrieved from PubMed (until October 2022). The clinical value of radiomics in GC research, which encompasses diagnosis, clinical staging, and prognostic prediction, was analyzed and summarized. A total of 52 original articles in radiomics were selected for the prediction of diagnostic classification (n = 9), tumor-node-metastasis stages (n = 19), prognosis and response prediction to treatment (n = 20), and the use of deep learning algorithm (n = 4). Among these, 39 (75%) were single-center studies and 13 (25%) were multicenter studies, with sample sizes ranging from 47 to 1,778. In terms of imaging modalities, 44 studies utilized CT-based radiomics, six used positron emission tomography-CT, and a few employed magnetic resonance imaging. With the continuous improvement and development in radiomics, it has great potential in the diagnosis, post-treatment follow-up, and treatment decision for patients with GC.