European radiology
-
To develop a proof-of-concept "interpretable" deep learning prototype that justifies aspects of its predictions from a pre-trained hepatic lesion classifier. ⋯ • An interpretable deep learning system prototype can explain aspects of its decision-making by identifying relevant imaging features and showing where these features are found on an image, facilitating clinical translation. • By providing feedback on the importance of various radiological features in performing differential diagnosis, interpretable deep learning systems have the potential to interface with standardized reporting systems such as LI-RADS, validating ancillary features and improving clinical practicality. • An interpretable deep learning system could potentially add quantitative data to radiologic reports and serve radiologists with evidence-based decision support.
-
To develop and validate a proof-of-concept convolutional neural network (CNN)-based deep learning system (DLS) that classifies common hepatic lesions on multi-phasic MRI. ⋯ • Deep learning demonstrates high performance in the classification of liver lesions on volumetric multi-phasic MRI, showing potential as an eventual decision-support tool for radiologists. • Demonstrating a classification runtime of a few milliseconds per lesion, a deep learning system could be incorporated into the clinical workflow in a time-efficient manner.
-
To develop a radiomic nomogram for preoperative prediction of axillary lymph node (LN) metastasis in breast cancer patients. ⋯ • ALNM is an important factor affecting breast cancer patients' treatment and prognosis. • Traditional imaging examinations have limited value for evaluating axillary LNs status. • We developed a radiomic nomogram based on MR imagings to predict LN metastasis.
-
Observational Study
Pain reduction after lumbar epidural injections using particulate versus non-particulate steroids: intensity of the baseline pain matters.
To compare pain relief after CT-guided lumbar epidural steroid injections (ESI) using particulate (triamcinolone) and non-particulate (dexamethasone) steroids, and to explore factors affecting the effectiveness of both steroid types. ⋯ • Triamcinolone is superior to dexamethasone for epidural treatment of severe lumbar radiculopathy. • For mild to moderate pain, dexamethasone could be equally effective. • Dexamethasone reduces pain caused by disc herniation much better than it does to pain caused by fixed stenotic spinal lesions.
-
Comparative Study
Ultrasound- versus fluoroscopy-guided injections in the lower back for the management of pain: a systematic review.
Ultrasound-guided spinal injections are less common than fluoroscopy-guided injections. Although unable to penetrate bones, ultrasound guidance has a number of advantages including convenience and reduced exposure to ionizing radiation. However, it is not known how ultrasound-guided injections compare to fluoroscopy-guided injections in the management of lower back pain. Our objective is to systematically review the literature comparing ultrasound-guided injections to fluoroscopy-guided injections for the management of lower back pain. ⋯ • There were no differences in pain relief, procedure time, number of needle passes, changes in disability indices, complications or adverse events, post-procedure opioid consumption, or patient satisfaction between ultrasound- and fluoroscopy-guided injections for the management of lower back pain. • Given the lack of evidence to demonstrate superior efficacy and the added harms with fluoroscopic guidance, ultrasound guidance may be the preferred method of guidance for injections to manage lower back pain in appropriate patients. Further study is required to understand the exact role of ultrasound in image-guided injections.