MENU

Click here to

×

Are you sure ?

Yes, do it No, cancel

Computer-Aided Diagnosis of Hepatic Fibrosis Utilizing Radiomic Features in Phase Contrast X-Ray Computed Tomography

J Duan1*, (1) Shandong Cancer Hospital Affiliated to Shandong University, Jinan, Shandong

Presentations

(Sunday, 7/29/2018) 4:00 PM - 4:30 PM

Room: Exhibit Hall | Forum 9

Purpose: To further explore the diagnostic value of phase contrast imaging with computed tomography for hepatic fibrosis in rats.

Methods: Hepatic fibrosis models were setup in rats induced by human albumin and evaluated by X-ray diffraction enhanced imaging computed tomography (DEI-CT). Histological staging was used to categorize liver fibrosis into mild fibrosis groups, moderate groups and severe groups. The refraction images of hepatic fibrosis sample were extracted from the DEI images. Avoiding large vessels, ten regions of interest (ROIs) were placed in each refraction image. Then, 78 radiomic features were extracted from each ROI using 3D Slicer radiomics software, including 19 first-order statistical features and 59 textural features. Paired Student’s t-tests or Wilcoxon rank tests were used to distinguish different level hepatic fibrosis. P value of less than 0.05 was considered to indicate a significant difference.

Results: DEI-CT produced high-resolution images of the liver parenchyma and the vessel microstructures in hepatic fibrosis. There was a positive correlation between radiomic features and hepatic fibrosis levels. 11 radiomic features (GLSZM-Z.Entropy, GLRLM-R.Entropy, GLCM-SumEntropy, IH-Kurtosis, GLCM-Entropy, GLCM-Homo1, GLCM-DiffEntropy, IH-Entropy, GLRLM-R.Percent, GLRLM-SRE and GLCM-IDMN) showed a significant difference between different stages of fibrosis.

Conclusion: Our study demonstrates that different stages of fibrosis can be clearly differentiated by radiomic features. DEI can be a potential noninvasive technique to diagnose and stage hepatic fibrosis.

Keywords

Not Applicable / None Entered.

Taxonomy

IM- X-ray: Quantitative imaging/analysis

Contact Email