European journal of radiology
-
To verify the feasibility of synthetic MRI in quantitative evaluation of lumbar intervertebral disk (IVD) degeneration, as compared to the conventional CarrPurcell-Meiboom-Gill (CPMG) T2 mapping approach. ⋯ The synthetic MRI may be used to provide quantitative biomarkers for assessing the level of lumbar intervertebral disc degeneration.
-
To develop and evaluate the performance of a fully-automated convolutional neural network (CNN)-based algorithm to evaluate hepatobiliary phase (HBP) adequacy of gadoxetate disodium (EOB)-enhanced MRI. Secondarily, we explored the potential of the proposed CNN algorithm to reduce examination length by applying it to EOB-MRI examinations. ⋯ A proposed CNN-based algorithm achieves higher than 95 % AUC for classifying HBP images as adequate versus suboptimal. The application of this algorithm could potentially shorten examination time and aid radiologists in recognizing technically suboptimal images, avoiding diagnostic pitfalls.
-
To propose an automatic approach based on a convolutional neural network (CNN) to evaluate the quality of T2-weighted liver magnetic resonance (MR) images as nondiagnostic (ND) or diagnostic (D). ⋯ The proposed two-step patch-based model achieved excellent performance when assessing the quality of liver MR images.
-
To investigate the role of a quantitative analysis software (CALIPER) in identifying HRCT thresholds predicting IPF patients' survival and lung function decline and its role in detecting changes of HRCT abnormalities related to treatment and their correlation with Forced Vital Capacity (FVC). ⋯ CALIPER quantification of fibrosis and vascular involvement could distinguish disease progression in treated versus untreated patients and predict the survival. The changes in CALIPER-derived variables over time were significantly correlated to changes in FVC.
-
Artificial intelligence is a hot topic in medical imaging. The development of deep learning methods and in particular the use of convolutional neural networks (CNNs), have led to substantial performance gain over the classic machine learning techniques. Multiple usages are currently being evaluated, especially for thoracic imaging, such as such as lung nodule evaluation, tuberculosis or pneumonia detection or quantification of diffuse lung diseases. ⋯ Such a perspective requires understanding new terms and concepts associated with machine learning. The objective of this paper is to provide useful definitions for understanding the methods used and their possibilities, and report current and future developments for thoracic imaging. Prospective validation of AI tools will be required before reaching routine clinical implementation.