European radiology
-
Relevance and penetration of machine learning in clinical practice is a recent phenomenon with multiple applications being currently under development. Deep learning-and especially convolutional neural networks (CNNs)-is a subset of machine learning, which has recently entered the field of thoracic imaging. The structure of neural networks, organized in multiple layers, allows them to address complex tasks. ⋯ The role of these methods is likely to increase in clinical practice as a complement of the radiologist's expertise. The objective of this review is to provide definitions for understanding the methods and their potential applications for thoracic imaging. KEY POINTS: • Deep learning outperforms other machine learning techniques for number of tasks in radiology. • Convolutional neural network is the most popular deep learning architecture in medical imaging. • Numerous deep learning algorithms are being currently developed; some of them may become part of clinical routine in the near future.
-
To assess the discriminative power of a 5-min quantitative double-echo steady-state (qDESS) sequence for simultaneous T2 measurements of cartilage and meniscus, and structural knee osteoarthritis (OA) assessment, in a clinical OA population, using radiographic knee OA as reference standard. ⋯ • Quantitative T2values of cartilage and meniscus as well as structural assessment of the knee with a single 5-min quantitative double-echo steady-state (qDESS) scan can distinguish between different grades of knee osteoarthritis (OA). • Quantitative and structural qDESS-based measurements correlate significantly with the reference standard, radiographic degree of OA, for all cartilage and meniscus regions. • By providing quantitative measurements and diagnostic image quality in one rapid MRI scan, qDESS has great potential for application in large-scale clinical trials in knee OA.
-
This study was conducted in order to determine the optimal timing of diffusion-weighted magnetic resonance imaging (DW-MRI) for prediction of pathologic complete response (pCR) to neoadjuvant chemoradiotherapy (nCRT) for esophageal cancer. ⋯ • DW-MRI during the second week of neoadjuvant chemoradiotherapy is most predictive for pathologic complete response in esophageal cancer. • A model including ΔADCweek 2was able to discriminate between pathologic complete responders and non-pathologic complete responders in 87%. • Improvements in future MRI studies for esophageal cancer may be obtained by incorporating motion management techniques.
-
To build a dual-energy CT (DECT)-based deep learning radiomics nomogram for lymph node metastasis (LNM) prediction in gastric cancer. ⋯ • This study investigated the value of deep learning dual-energy CT-based radiomics in predicting lymph node metastasis in gastric cancer. • The dual-energy CT-based radiomics nomogram outweighed the single-energy model and the clinical model. • The nomogram also exhibited a significant prognostic ability for patient survival and enriched radiomics studies.
-
To qualitatively and quantitatively compare the image quality between single-shot echo-planar (SS-EPI) and multi-shot echo-planar (IMS-EPI) diffusion-weighted imaging (DWI) in female pelvis METHODS: This was a prospective study involving 80 females who underwent 3.0T pelvic magnetic resonance imaging (MRI). SS-EPI and IMS-EPI DWI were acquired with 3 b values (0, 400, 800 s/mm2). Two independent reviewers assessed the overall image quality, artifacts, sharpness, and lesion conspicuity based on a 5-point Likert scale. Regions of interest (ROI) were placed on the endometrium and the gluteus muscles to quantify the signal intensities and apparent diffusion coefficient (ADC). Signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and geometric distortion were quantified on both sequences. Inter-rater agreement was assessed using κ statistics and Kendall test. Qualitative scores were compared using Wilcoxon signed-rank test and quantitative parameters were compared with paired t test and Bland-Altman analysis. ⋯ • IMS-EPI showed better image quality than SS-EPI. • IMS-EPI showed lower geometric distortion without affecting ADC compared with SS-EPI. • The SNR and CNR of IMS-EPI decreased due to post-processing limitations.