Deep learning-accelerated image reconstruction in back pain-MRI imaging: reduction of acquisition time and improvement of image quality.

INTRODUCTION: Low back pain is a global health issue causing disability and missed work days. Commonly used MRI scans including T1-weighted and T2-weighted images provide detailed information of the spine and surrounding tissues. Artificial intelligence showed promise in improving image quality and simultaneously reducing scan time. This study evaluates the performance of deep learning (DL)-based T2 turbo spin-echo (TSE, T2DLR) and T1 TSE (T1DLR) in lumbar spine imaging regarding acquisition time, image quality, artifact resistance, and diagnostic confidence. MATERIAL AND METHODS: This retrospective monocentric study included 60 patients with lower back pain who underwent lumbar spinal MRI between February and April 2023. MRI parameters and DL reconstruction (DLR) techniques were utilized to acquire images. Two neuroradiologists independently evaluated image datasets based on various parameters using a 4-point Likert scale. RESULTS: Accelerated imaging showed significantly less image noise and artifacts, as well as better image sharpness, compared to standard imaging. Overall image quality and diagnostic confidence were higher in accelerated imaging. Relevant disk herniations and spinal fractures were detected in both DLR and conventional images. Both readers favored accelerated imaging in the majority of examinations. The lumbar spine examination time was cut by 61% in accelerated imaging compared to standard imaging. CONCLUSION: In conclusion, the utilization of deep learning-based image reconstruction techniques in lumbar spinal imaging resulted in significant time savings of up to 61% compared to standard imaging, while also improving image quality and diagnostic confidence. These findings highlight the potential of these techniques to enhance efficiency and accuracy in clinical practice for patients with lower back pain.

Follow-up CT and CT angiography after intracranial aneurysm clipping and coiling-improved image quality by iterative metal artifact reduction.

PURPOSE: This paper aims to evaluate a new iterative metal artifact reduction algorithm for post-interventional evaluation of brain tissue and intracranial arteries. METHODS: The data of 20 patients that underwent follow-up cranial CT and cranial CT angiography after clipping or coiling of an intracranial aneurysm was retrospectively analyzed. After the images were processed using a novel iterative metal artifact reduction algorithm, images with and without metal artifact reduction were qualitatively evaluated by two readers, using a five-point Likert scale. Moreover, artifact strength was quantitatively assessed in terms of CT attenuation and standard deviation alterations. RESULTS: The qualitative analysis yielded a significant increase in image quality (p = 0.0057) in iteratively processed images with substantial inter-observer agreement (ĸ = 0.72), while the CTA image quality did not differ (p = 0.864) and even showed vessel contrast reduction in six cases (30%). The mean relative attenuation difference was 27% without metal artifact reduction vs. 11% for iterative metal artifact reduction images (p = 0.0003). CONCLUSIONS: The new iterative metal artifact reduction algorithm enhances non-enhanced CT image quality after clipping or coiling, but in CT-angiography images, the contrast of adjacent vessels can be compromised.

Deep learning-accelerated image reconstruction in MRI of the orbit to shorten acquisition time and enhance image quality.

BACKGROUND AND PURPOSE: This study explores the use of deep learning (DL) techniques in MRI of the orbit to enhance imaging. Standard protocols, although detailed, have lengthy acquisition times. We investigate DL-based methods for T2-weighted and T1-weighted, fat-saturated, contrast-enhanced turbo spin echo (TSE) sequences, aiming to improve image quality, reduce acquisition time, minimize artifacts, and enhance diagnostic confidence in orbital imaging. METHODS: In a 3-Tesla MRI study of 50 patients evaluating orbital diseases from March to July 2023, conventional (TSES ) and DL TSE sequences (TSEDL ) were used. Two neuroradiologists independently assessed the image datasets for image quality, diagnostic confidence, noise levels, artifacts, and image sharpness using a randomized and blinded 4-point Likert scale. RESULTS: TSEDL significantly reduced image noise and artifacts, enhanced image sharpness, and decreased scan time, outperforming TSES (p < .05). TSEDL showed superior overall image quality and diagnostic confidence, with relevant findings effectively detected in both DL-based and conventional images. In 94% of cases, readers preferred accelerated imaging. CONCLUSION: The study proved that using DL for MRI image reconstruction in orbital scans significantly cut acquisition time by 69%. This approach also enhanced image quality, reduced image noise, sharpened images, and boosted diagnostic confidence.

Image Quality of CT Angiography of Supra-Aortic Arteries : Comparison Between Advanced Modelled Iterative Reconstruction (ADMIRE), Sinogram Affirmed Iterative Reconstruction (SAFIRE) and Filtered Back Projection (FBP) in One Patients' Group.

PURPOSE: To evaluate the potential benefit in image quality of the iterative reconstruction (IR) technique advanced modelled iterative reconstruction (ADMIRE) in CT angiography (CTA) of supra-aortic arteries compared to sinogram affirmed iterative reconstruction (SAFIRE) and standard filtered back projection (FBP) in one patients' group. METHODS: In this study 29 patients underwent standard CTA of supra-aortic arteries. Images were reconstructed using three different reconstruction algorithms, FBP, and IR techniques ADMIRE and SAFIRE. General image quality was assessed by two radiologists in different arterial segments using a 5-point Likert scale. Mean attenuation and noise were measured at different levels of each vessel and signal-to-noise ratio (SNR) was calculated. Interrater variability was determined. RESULTS: Regarding total image quality IR showed only excellent, very good and good results and was more often graded excellent and very good than FBP reconstruction. Image noise levels and SNR were significantly (p < 0.01) improved in IR at the bilateral subclavian arteries (only in SAFIRE), vertebral V1 and V3 segments, common carotid arteries and proximal and distal internal carotid arteries. No significant differences in image quality were found when comparing SAFIRE and ADMIRE reconstructions except for V1 and V3. In these regions ADMIRE showed significantly better image quality than SAFIRE (p < 0.001 and p < 0.01). Interrater agreement was almost perfect (κ = 0.88) for different image quality parameters. CONCLUSION: The CTA of supra-aortic arteries using the IR techniques SAFIRE and ADMIRE was superior to FBP when comparing the objective and subjective image quality and ADMIRE has the potential to overcome SAFIRE.