Machine learning-based texture analysis for differentiation of large adrenal cortical tumours on CT.

AIM: To compare the efficacy of computed tomography (CT) texture analysis and conventional evaluation by radiologists for differentiation between large adrenal adenomas and carcinomas. MATERIALS AND METHODS: Quantitative CT texture analysis was used to evaluate 54 histopathologically proven adrenal masses (mean size=5.9 cm; range=4.1-10 cm) from 54 patients referred to Anderson Cancer Center from January 2002 through April 2014. The patient group included 32 women (mean age at mass evaluation=59 years) and 22 men (mean age at mass evaluation=61 years). Adrenal lesions seen on precontrast and venous-phase CT images were labelled by three different readers, and the labels were used to generate intensity- and geometry-based textural features. The textural features and the attenuation values were considered as input values for a random forest-based classifier. Similarly, the adrenal lesions were classified by two different radiologists based on morphological criteria. Prediction accuracy and interobserver agreement were compared. RESULTS: The textural predictive model achieved a mean accuracy of 82%, whereas the mean accuracy for the radiologists was 68.5% (p<0.0001). The interobserver agreements between the predictive model and radiologists 1 and 2 were 0.44 (p<0.0005; 95% confidence interval [CI]: 0.25-0.62) and 0.47 (p<0.0005; 95% CI: 0.28-0.66), respectively. The Dice similarity coefficient between the readers' image labels was 0.875±0.04. CONCLUSION: CT texture analysis of large adrenal adenomas and carcinomas is likely to improve CT evaluation of adrenal cortical tumours.

Measuring myocardial perfusion: the role of PET, MRI and CT.

Recently, focus has changed from anatomical assessment of coronary arteries towards functional testing to evaluate the effect of stenosis on the myocardium before intervention. Besides positron-emission tomography (PET), cardiac MRI (CMR), and cardiac CT are able to measure myocardial perfusion. Myocardial perfusion abnormalities are the first sign of the ischaemic cascade in the development of coronary artery disease (CAD). PET is considered the non-invasive clinical reference standard for absolute quantification of myocardial perfusion. The diagnostic and prognostic value of PET is well-known and is used in routine clinical practice. However, PET uses radioactive tracers and has a lower spatial resolution compared to CMR and CT. CMR and CT are emerging techniques in the field of myocardial perfusion imaging. CMR uses magnetic resonance to obtain images, whereas CT uses x-rays during first-pass of non-ionic and ionic contrast agents, respectively. Absolute quantification with CMR has yet to be established in routine clinical practice, while CT has yet to prove its diagnostic and prognostic value. The upcoming years may change the way we diagnose and treat patients suspected of having CAD with more precise methods for measuring myocardial perfusion. The aim of this comprehensive review is to discuss current and emerging imaging techniques used for myocardial perfusion imaging.