Tumor heterogeneity in gastrointestinal stromal tumors of the small bowel: volumetric CT texture analysis as a potential biomarker for risk stratification

Abstract

BackgroundTo explore whether volumetric CT texture analysis (CTTA) can serve as a potential imaging biomarker for risk stratification of small bowel gastrointestinal stromal tumors (small bowel-GISTs).MethodsA total of 90 patients with small bowel-GISTs were retrospectively reviewed, of these, 26 were rated as high risk, 13 as intermediate risk, and 51 as low or very low risk. Histogram parameters extracted from CT images were compared among small bowel-GISTs with different risk levels by using one-way analysis of variance. Receiver operating characteristics (ROCs) and areas under the curve (AUCs) were analyzed to determine optimal histogram parameters for stratifying tumor risk.ResultsSignificant differences in mean attenuation, 10th, 25th, 50th, 75th and 90th percentile attenuation, and entropy were found among high, intermediate, and low risk small bowel-GISTs (p ≤ 0.001). Mean attenuation, 10th, 25th, 50th, 75th and 90th percentile attenuation, and entropy derived from arterial phase and venous phase images correlated significantly with risk levels (r = 0.403–0.594, r = 0.386–0.593, respectively). Entropy in venous phase reached the highest accuracy (AUC = 0.830, p < 0.001) for differentiating low risk from intermediate to high risk small bowel-GISTs, with a cut-off value of 5.98, and the corresponding sensitivity and specificity were 82.4 and 74.4%, respectively.ConclusionsVolumetric CT texture features, especially entropy, may potentially serve as biomarkers for risk stratification of small bowel-GISTs.

Development of a Malignancy Potential Binary Prediction Model Based on Deep Learning for the Mitotic Count of Local Primary Gastrointestinal Stromal Tumors

“…This approach can yield more information than traditional methods and can overcome the influence of observer subjectivity. A few studies demonstrate that radiomics can capture intra-tumoral heterogeneity, exploit high-level features, assess tumor biological behavior, and improve diagnostic accuracy and disease prognosis (32)(33)(34)(35). Wang et al (27) built radiomic prediction models using CE-CT images to preoperatively predict mitotic count of GIST (sensitivity = 63.3%; specificity = 91.3%; accuracy = 85.4%).…”

Entwicklungen in der Analyse von Tumorheterogenität in computertomografischen Aufnahmen

“…Auch andere Tumorentitäten, wie etwa gastrointestinale Stromatumoren des Dünndarms, wurden hinsichtlich ihrer Heterogenitätscharakteristiken in CT-Datensätzen beurteilt, wobei sich insbesondere die Entropie als möglicher bildmorphologischer Biomarker zur Risikostratifizierung der Tumoren vor Therapiebeginn herausstellte [18].…”

Differential diagnosis of leukoplakia versus lichen planus of the oral mucosa based on digital texture analysis in intraoral photography

“…Texture analysis is used during computed tomography (CT) analysis in the case of bone and soft tissue lesions, but there are no publications about the application of texture analysis in the differential diagnosis of leukoplakia vs LP in the oral mucosa. 7,8 The aim of this study is to attempt to formulate a differential diagnosis of leukoplakia vs LP in the oral mucosa based on digital texture analysis in intraoral macrophotography.…”