Comparison of malignancy‐prediction efficiency between contrast and non‐contract CT‐based radiomics features in gastrointestinal stromal tumors: A multicenter study

• Published in: Clinical and translational medicine Vol. 10; no. 3; pp. e291 - n/a
• Main Authors: Zhang, Qing‐Wei, Zhou, Xiao‐Xuan, Zhang, Ran‐Ying, Chen, Shuang‐Li, Liu, Qiang, Wang, Jian, Zhang, Yan, Lin, Jiang, Xu, Jian‐Rong, Gao, Yun‐Jie, Ge, Zhi‐Zheng
• Format: Journal Article
• Language: English
• Published: United States John Wiley and Sons Inc 01.07.2020; Wiley
• Subjects: gastrointestinal stromal tumor; malignant potential; prediction; radiomics signature; Short Communication; radiomics signature; prediction; gastrointestinal stromal tumor; malignant potential
• DOI: 10.1002/ctm2.91
• ISSN: 2001-1326

This work seeks the development and validation of radiomics signatures from nonenhanced computed tomography (CT, NE‐RS) to preoperatively predict the malignancy degree of gastrointestinal stromal tumors (GISTs) and the comparison of these signatures with those from contrast‐enhanced CT. A dataset for 370 GIST patients was collected from four centers. This dataset was divided into cohorts for training, as well as internal and external validation. The minimum‐redundancy maximum‐relevance algorithm and the least absolute shrinkage and selection operator (LASSO) algorithm were used to filter unstable features. (a) NE‐RS and radiomics signature from contrast‐enhanced CT (CE‐RS) were built and compared for the prediction of malignancy potential of GIST based on the area under the receiver operating characteristic curve (AUC). (b) The radiomics model was also developed with both the tumor size and NE‐RS. The AUC values were comparable between NE‐RS and CE‐RS in the training (.965 vs .936; P = .251), internal validation (.967 vs .960; P = .801), and external validation (.941 vs .899; P = .173) cohorts in diagnosis of high malignancy potential of GISTs. We next focused on the NE‐RS. With 0.185 selected as the cutoff of NE‐RS for diagnosis of the malignancy potential of GISTs, accuracy, sensitivity, and specificity for diagnosis high‐malignancy potential GIST was 90.0%, 88.2%, and 92.3%, respectively, in the training cohort. For the internal validation set, the corresponding metrics are 89.1%, 94.9%, and 80.0%, respectively. The corresponding metrics for the external cohort are 84.6%, 76.1%, and 91.0%, respectively. Compared with only NE‐RS, the radiomics model increased the sensitivity in the diagnosis of GIST with high‐malignancy potential by 5.9% (P = .025), 2.5% (P = .317), 10.5% (P = .008) for the training set, internal validation set, and external validation set, respectively. The NE‐RS had comparable prediction efficiency in the diagnosis of high‐risk GISTs to CE‐RS. The NE‐RS and radiomics model both had excellent accuracy in predicting malignancy potential of GISTs. A dataset for 370 GIST patients was collected from four centers and was divided into cohorts for training, as well as internal and external validation. The minimum‐redundancy maximum‐relevance (mRMR) algorithm, and the least absolute shrinkage and selection operator (LASSO) algorithm were used to filter unstable features. The area under the curve (AUC) values were comparable between radiomics signatures from non‐enhanced CT (NE‐RS) and radiomics signatures from enhanced CT (CE‐RS) in the three cohorts in diagnosis of high malignancy potential of GISTs. With 0.185 selected as the cut‐off of NE‐RS for diagnosis of the malignancy potential of GISTs, accuracy for diagnosis high‐malignancy potential GIST was 89%, 85% for the internal validation and external validation cohort. Compared with only NE‐RS, the radiomics model with combination of radiomic signature and tumor size, had increased accuracy of 91%, 89% for the internal validation and external validation cohort. The NE‐RS and radiomics model both had excellent accuracy in predicting malignancy potential of GISTs.