Background CT texture analysis (CTTA) has been successfully used to assess tissue heterogeneity in multiple diseases. The purpose of this work is to demonstrate the value of three-dimensional CTTA in the evaluation of diffuse liver disease. We aimed to develop CTTA based prediction models, which can be used for staging of fibrosis in different anatomic liver segments irrespective of variations in scanning parameters. Methods We retrospectively collected CT scans of thirty-two chronic hepatitis patients with liver fibrosis. The CT examinations were performed on either a 16- or a 64-slice scanner. Altogether 354 anatomic liver segments were manually highlighted on portal venous phase images, and 1117 three-dimensional texture parameters were calculated from each segment. The segments were divided between groups of low-grade and high-grade fibrosis using shear-wave elastography. The highly-correlated features (Pearson r > 0.95) were filtered out, and the remaining 453 features were normalized and used in a classification with k-means and hierarchical cluster analysis. The segments were split between the train and test sets in equal proportion (analysis I) or based on the scanner type (analysis II) into 64-slice train 16-slice validation cohorts for machine learning classification, and a subset of highly prognostic features was selected with recursive feature elimination. Results A classification with k-means and hierarchical cluster analysis divided segments into four main clusters. The average CT density was significantly higher in cluster-4 (110 HU ± SD = 10.1HU) compared to the other clusters (c1: 96.1 HU ± SD = 11.3HU; p < 0.0001; c2: 90.8 HU ± SD = 16.8HU; p < 0.0001; c3: 93.1 HU ± SD = 17.5HU; p < 0.0001); but there was no difference in liver stiffness or scanner type among the clusters. The optimized random forest classifier was able to distinguish between low-grade and high-grade fibrosis with excellent cross-validated accuracy in both the first and second analysis (AUC = 0.90, CI = 0.85–0.95 vs. AUC = 0.88, CI = 0.84–0.91). The final support vector machine model achieved an excellent prediction rate in the second analysis (AUC = 0.91, CI = 0.88–0.94) and an acceptable prediction rate in the first analysis (AUC = 0.76, CI = 0.67–0.84). Conclusions In conclusion, CTTA-based models can be successfully applied to differentiate high-grade from low-grade fibrosis irrespective of the imaging platform. Thus, CTTA may be useful in the non-invasive prognostication of patients with chronic liver disease.

It has been proven in a few early studies that radiomic analysis offers a promising opportunity to detect or differentiate between organ lesions based on their unique texture parameters. Recently, the utilization of CT texture analysis (CTTA) has been receiving significant attention, especially for response evaluation and prognostication of different oncological diagnoses. In this review article, we discuss the unique ability of radiomics and its subfield CTTA to diagnose lesions in the pancreas and kidney. We review studies in which CTTA was used for the classification of histology grades in pancreas and kidney tumors. We also review the role of radiogenomics in the prediction of the molecular and genetic subtypes of pancreatic tumors. Furthermore, we provide a short report on recent advancements of radiomic analysis in predicting prognosis and survival of patients with pancreatic and renal cancers.

To examine the improvement in the visualisation of bladder and ureteric pathologies next to a hip prosthesis with metallic artefact reduction for orthopaedic implants (O-MAR). MATERIALS AND METHODS: Thirty-four patients who underwent pelvic computed tomography (CT) for non-prosthesis-related causes were enrolled retrospectively. Portal venous phase scans were reconstructed both with standard iterative reconstruction (ITR) and with O-MAR. The density of the ureters and the bladder was measured at both sides in the plane of the prosthesis. A semi-quantitative score was also used to assess visibility. The R (version 3.4.1) package was used for statistical analysis. RESULTS: The average (m) density of the 41 prosthesis side ureters was significantly lower on ITR images (m¼e94.76AE150.48 [AESD] HU) than on O-MAR images (m¼e13.40AE36.37 HU; p<0.0004). The difference between the ITR and O-MAR (m¼e138.62AE182.64 versus e35.55AE40.21 HU; p<0.0003) was also significant at the prosthesis side of the bladder. The visibility of the prosthesis side ureters was improved: 53.7% was obscured on ITR series compared to 4.9% on O-MAR. The visibility score was also better across all levels (p<0.001) with O-MAR. In four cases (13%), the O-MAR images significantly changed the diagnosis: in two cases ureteric stones, in one case each a bladder stone and a bladder tumour were discovered. CONCLUSIONS: O-MAR reconstruction of CT images significantly improves the visibility of the urinary tract adjacent to metallic hip implants. Thus, O-MAR is essential for detecting ureteric and bladder pathologies in patients with a hip prosthesis.

Artificial Intelligence and the use of radiomics analysis have been of great interest in the last decade in the field of imaging. CT texture analysis (CTTA) is a new and emerging field in radiomics, which seems promising in the assessment and diagnosis of both focal and diffuse liver lesions. The utilization of CTTA has only been receiving great attention recently, especially for response evaluation and prognostication of different oncological diagnoses. Radiomics, combined with machine learning techniques, offers a promising opportunity to accurately detect or differentiate between focal liver lesions based on their unique texture parameters. In this review article, we discuss the unique ability of radiomics in the diagnostics and prognostication of both focal and diffuse liver lesions. We also provide a brief review of radiogenomics and summarize its potential role of in the non-invasive diagnosis of malignant liver tumors.