European journal of radiology
-
To develop and externally validate an MR-based radiomics nomogram from retrospective multicenter datasets for pretreatment prediction of early relapse (≤ 1 year) in osteosarcoma after surgical resection. ⋯ The proposed MRI-based radiomics nomogram could provide a non-invasive tool to predict early relapse of osteosarcoma, which has the potential to improve personalized pretreatment management of osteosarcoma.
-
Artificial intelligence (AI) will continue to cause substantial changes within the field of radiology, and it will become increasingly important for clinicians to be familiar with several concepts behind AI algorithms in order to effectively guide their clinical implementation. This review aims to give medical professionals the basic information needed to understand AI development and research. The general concepts behind several AI algorithms, including their data requirements, training, and evaluation methods are explained. The potential legal implications of using AI algorithms in clinical practice are also discussed.
-
Randomized Controlled Trial
The effect of injection volume on long-term outcomes of US-guided subacromial bursa injections.
Limited data exist on the efficacy of high- compared to low-volume US-guided corticosteroid injections (CI) in the subacromial-subdeltoid (SA-SD) bursa. Our purpose was to compare the short- and long-term efficacy of low- and high-volume injections, by using a capacity reference of SA-SD bursa volume, as assessed on cadaveric specimens. ⋯ High-compared to low-volume US-guided CI are superior for achieving early pain recovery.
-
Adenocarcinoma (ADC) is the most common histological subtype of lung cancers in non-small cell lung cancer (NSCLC) in which ground glass opacifications (GGOs) found on computed tomography (CT) scans are the most common lesions. However, the presence of a micropapillary or a solid component is identified as an independent predictor of prognosis, suggesting a more extensive resection. The purpose of our study is to explore imaging phenotyping using a method combining radiomics with deep learning (RDL) to predict high-grade patterns within lung ADC. ⋯ High-grade lung ADC based on histologic pattern spectrum in GGO lesions might be predicted by the framework combining radiomics with deep learning, which reveals advantage over radiomics alone.
-
To evaluate the efficacy of optimized T1-Perfusion MRI protocol (protocol-2) with whole brain coverage and improved spatial resolution using Compressed-SENSE (CSENSE) to differentiate high-grade-glioma (HGG) and low-grade-glioma (LGG) and to compare it with the conventional protocol (protocol-1) with partial brain coverage used in our center. ⋯ CSENSE (R = 4) can be used to improve the resolution and brain coverage for T1-Perfusion analysis used to differentiate gliomas.