A research team has employed contrast-enhanced computed tomography (CECT) to develop a radiomics nomogram that predicts Ki-67 expression levels and prognosis in patients with gastrointestinal stromal tumors (GISTs).

The study, published in the International Journal of Computer Assisted Radiology and Surgery, validated the nomogram by comparing its predicted Ki-67 level with the pathological Ki-67 level in estimating the prognoses of 382 patients with GIST.

“Radiomics features extracted from [CECT] images were selected and classified to build a radiomics signature,” the authors explained. “This radiomics nomogram based on CECT had a satisfactory performance in predicting both the Ki-67 expression level and prognosis noninvasively in patients with GISTs, which may serve as an effective imaging tool that can assist in guiding personalized clinical treatment.”

Continue Reading

Read more about GIST prognosis

Ki-67 antigen expression levels are known markers of cell proliferation in various tumor types, including breast, liver, and lung cancers. Prior to developing the radiomics nomogram, the patients included in this study were divided into high Ki-67 and low Ki-67 groups based on postoperative pathological sample categorization.

The research team obtained abdominal CT scans and used the CT characteristics to develop 3 prediction models (a subjective CT model, radiomics signature, and combined model). The model with the best diagnostic performance was employed as the nomogram to preoperatively predict Ki-67 expression levels and therefore the prognosis.

Given that GISTs have widely varying behaviors ranging from small lesions that can simply be monitored to aggressive tumors that require resection, approaches to accurately predict the malignancy of GISTs have become important. The authors found that the radiomics nomogram achieved good discrimination in predicting the Ki-67 expression level of GISTs and that it was a potentially effective noninvasive approach to evaluate prognosis and make clinical decisions for these patients.


Feng Q, Tang B, Zhang Y, Liu X. Prediction of the Ki-67 expression level and prognosis of gastrointestinal stromal tumors based on CT radiomics nomogram. Int J Comput Assist Radiol Surg. Published online February 23, 2022. doi:10.1007/s11548-022-02575-6