European radiology
-
The recent explosion of 'big data' has ushered in a new era of artificial intelligence (AI) algorithms in every sphere of technological activity, including medicine, and in particular radiology. However, the recent success of AI in certain flagship applications has, to some extent, masked decades-long advances in computational technology development for medical image analysis. In this article, we provide an overview of the history of AI methods for radiological image analysis in order to provide a context for the latest developments. ⋯ We discuss the unique characteristics of medical data and medical science that set medicine apart from other technological domains in order to highlight not only the potential of AI in radiology but also the very real and often overlooked constraints that may limit the applicability of certain AI methods. Finally, we provide a comprehensive perspective on the potential impact of AI on radiology and on how to evaluate it not only from a technical point of view but also from a clinical one, so that patients can ultimately benefit from it. KEY POINTS: • Artificial intelligence (AI) research in medical imaging has a long history • The functioning, strengths and limitations of more classical AI methods is reviewed, together with that of more recent deep learning methods. • A perspective is provided on the potential impact of AI on radiology and on its evaluation from both technical and clinical points of view.
-
Multicenter Study Clinical Trial
Magnetic resonance enterography, small bowel ultrasound and colonoscopy to diagnose and stage Crohn's disease: patient acceptability and perceived burden.
To compare patient acceptability and burden of magnetic resonance enterography (MRE) and ultrasound (US) to each other, and to other enteric investigations, particularly colonoscopy. ⋯ • MRE and US are rated as acceptable by most patients and superior to colonoscopy. • MRE generates significantly greater burden and longer recovery times than US, particularly in younger patients and those with high levels of emotional distress. • Most patients prefer the experience of undergoing US than MRE; however, patients rate test accuracy as more importance than scan burden.
-
Developmental dysplasia of the hip (DDH) diagnosis by two-dimensional ultrasound (2DUS) can have poor inter-rater reliability. 3D ultrasound (3DUS) may be more reliably performed, particularly by novice users. We compared intra- and inter-rater reliability between expert and novice operators performing 2DUS and 3DUS for DDH. ⋯ • Novice/expert inter-rater reliability improved from poor with 2DUS to moderate/high with 3DUS. • Novice operators using 3DUS correctly classified 57/58 (98%) of infant hips. • DDH can be reliably assessed by novice operators using 3DUS.
-
To quantitatively compare the diagnostic values of various diffusion parameters obtained from mono- and biexponential diffusion-weighted imaging (DWI) models and diffusion kurtosis imaging (DKI) in differentiating between benign and malignant solitary pulmonary lesions (SPLs). ⋯ • Mono- and biexponential DWI and DKI are feasible for differentiating SPLs. • ADC (0, ≥500) has better performance than ADC (0, <500) in assessing SPLs. • IVIM and DKI have similar performance compared with conventional DWI in differentiating SPLs.
-
To determine the diagnostic accuracy of 68gallium prostate-specific membrane antigen (PSMA)-based positron emission tomography/computed tomography (PET/CT) in comparison with 18F-fluoride-based PET/CT (NaF-PET/CT) and whole-body magnetic resonance imaging (WB-MRI) for the detection of bone metastases in patients with prostate cancer. ⋯ • PSMA-PET/CT assessed the presence of bone metastases correctly in all 55 patients • PSMA-PET/CT was more advantageous compared to WB-MRI • No difference was found between PSMA-PET/CT and NaF-PET/CT.