Speeding up the clinical routine: Compressed sensing for 2D imaging of lumbar spine disc herniation

Deep Learning-based Image Enhancement Techniques for Fast MRI in Neuroimaging

Despite its superior soft tissue contrast and non-invasive nature, MRI requires long scan times due to its intrinsic signal acquisition principles, a main drawback which technological advancements in MRI have been focused on. In particular, scan time reduction is a natural requirement in neuroimaging due to detailed structures requiring high resolution imaging and often volumetric (3D) acquisitions, and numerous studies have recently attempted to harness deep learning (DL) technology in enabling scan time reduction and image quality improvement. Various DL-based image reconstruction products allow for additional scan time reduction on top of existing accelerated acquisition methods without compromising the image quality.

Reconstruction of shoulder MRI using deep learning and compressed sensing: a validation study on healthy volunteers

BACKGROUND

To investigate the potential of combining compressed sensing (CS) and deep learning (DL) for accelerated two-dimensional (2D) and three-dimensional (3D) magnetic resonance imaging (MRI) of the shoulder.

METHODS

Twenty healthy volunteers were examined using at 3-T scanner with a fat-saturated, coronal, 2D proton density-weighted sequence with four acceleration levels (2.3, 4, 6, and 8) and a 3D sequence with three acceleration levels (8, 10, and 13), all accelerated with CS and reconstructed using the conventional algorithm and a new DL-based algorithm (CS-AI). Subjective image quality was evaluated by two blinded readers using 6 criteria on a 5-point Likert scale (overall impression, artifacts, and delineation of the subscapularis tendon, bone, acromioclavicular joint, and glenoid labrum). Objective image quality was measured by calculating signal-to-noise-ratio, contrast-to-noise-ratio, and a structural similarity index measure. All reconstructions were compared to the clinical standard (CS 2D acceleration factor 2.3; CS 3D acceleration factor 8). Additionally, subjective and objective image quality were compared between CS and CS-AI with the same acceleration levels.

RESULTS

Both 2D and 3D sequences reconstructed with CS-AI achieved on average significantly better subjective and objective image quality compared to sequences reconstructed with CS with the same acceleration factor (p ≤ 0.011). Comparing CS-AI to the reference sequences showed that 4-fold acceleration for 2D sequences and 13-fold acceleration for 3D sequences without significant loss of quality (p ≥ 0.058).

CONCLUSIONS

For MRI of the shoulder at 3 T, a DL-based algorithm allowed additional acceleration of acquisition times compared to the conventional approach.

RELEVANCE STATEMENT

The combination of deep-learning and compressed sensing hold the potential for further scan time reduction in 2D and 3D imaging of the shoulder while providing overall better objective and subjective image quality compared to the conventional approach.

TRIAL REGISTRATION

DRKS00024156.

KEY POINTS

• Combination of compressed sensing and deep learning improved image quality and allows for significant acceleration of shoulder MRI. • Deep learning-based algorithm achieved better subjective and objective image quality than conventional compressed sensing. • For shoulder MRI at 3 T, 40% faster image acquisition for 2D sequences and 38% faster image acquisition for 3D sequences may be possible.

Non-contrast enhancement of brachial plexus magnetic resonance imaging with compressed sensing

PURPOSE

To observe the quality of brachial plexus (BP) images obtained from magnetic resonance imaging (MRI) with 3D T2 STIR SPACE sequence and compressed sensing (CS) and to compare the results with BP images from the same sequence without CS.

METHODS

In this study, compressed sensing was applied to acquire non-contrast BP images from ten healthy volunteers with 3D T2 STIR SPACE sequence to shorten acquisition time without sacrificing image quality. The acquisition time of scanning with CS was compared to that without CS. The quantitative signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated and compared using paired t-test to determine the quality of images with and without CS. The qualitative assessment by three experienced radiologists was performed using a scoring scale from 1 (poor) to 5 (excellent) and analyzed for interobserver agreement on image quality.

RESULTS

The increasing SNR and CNR of images with CS were found in nine regions of BP images (p < 0.001) with faster acquisition time. The result of paired t-test (p < 0.001) illustrates the significant difference between images with CS compared to images without CS. The assessment of observers also shows higher scores for images with CS compared to images without CS.

CONCLUSIONS

This study demonstrates that CS can effectively increase the visibility of images and image boundaries, SNR, and CNR of BP images obtained with 3D T2 STIR SPACE sequence with the good interobserver agreement and within clinically optimal acquisition time compared to images from similar sequence without CS.

Conventional and Deep-Learning-Based Image Reconstructions of Undersampled K-Space Data of the Lumbar Spine Using Compressed Sensing in MRI: A Comparative Study on 20 Subjects

Compressed sensing accelerates magnetic resonance imaging (MRI) acquisition by undersampling of the k-space. Yet, excessive undersampling impairs image quality when using conventional reconstruction techniques. Deep-learning-based reconstruction methods might allow for stronger undersampling and thus faster MRI scans without loss of crucial image quality. We compared imaging approaches using parallel imaging (SENSE), a combination of parallel imaging and compressed sensing (COMPRESSED SENSE, CS), and a combination of CS and a deep-learning-based reconstruction (CS AI) on raw k-space data acquired at different undersampling factors. 3D T2-weighted images of the lumbar spine were obtained from 20 volunteers, including a 3D sequence (standard SENSE), as provided by the manufacturer, as well as accelerated 3D sequences (undersampling factors 4.5, 8, and 11) reconstructed with CS and CS AI. Subjective rating was performed using a 5-point Likert scale to evaluate anatomical structures and overall image impression. Objective rating was performed using apparent signal-to-noise and contrast-to-noise ratio (aSNR and aCNR) as well as root mean square error (RMSE) and structural-similarity index (SSIM). The CS AI 4.5 sequence was subjectively rated better than the standard in several categories and deep-learning-based reconstructions were subjectively rated better than conventional reconstructions in several categories for acceleration factors 8 and 11. In the objective rating, only aSNR of the bone showed a significant tendency towards better results of the deep-learning-based reconstructions. We conclude that CS in combination with deep-learning-based image reconstruction allows for stronger undersampling of k-space data without loss of image quality, and thus has potential for further scan time reduction.

Practical Aspects of novel MRI Techniques in Neuroradiology: Part 2 - Acceleration Methods and Implications for Individual Regions

BACKGROUND

 Recently introduced MRI techniques facilitate accelerated examinations or increased resolution with the same duration. Further techniques offer homogeneous image quality in regions with anatomical transitions. The question arises whether and how these techniques can be adopted for routine diagnostic imaging.

METHODS

 Narrative review with an educational focus based on current literature research and practical experiences of different professions involved (physicians, MRI technologists/radiographers, physics/biomedical engineering). Different hardware manufacturers are considered.

RESULTS AND CONCLUSIONS

 Compressed sensing and simultaneous multi-slice imaging are novel acceleration techniques with different yet complimentary applications. They do not suffer from classical signal-to-noise-ratio penalties. Combining 3 D and acceleration techniques facilitates new broader examination protocols, particularly for clinical brain imaging. In further regions of the nervous systems mainly specific applications appear to benefit from recent technological improvements.

KEY POINTS

  · New acceleration techniques allow for faster or higher resolution examinations.. · New brain imaging approaches have evolved, including more universal examination protocols.. · Other regions of the nervous system are dominated by targeted applications of recently introduced MRI techniques..

CITATION FORMAT

· Sundermann B, Billebaut B, Bauer J et al. Practical Aspects of novel MRI Techniques in Neuroradiology: Part 2 - Acceleration Methods and Implications for Individual Regions. Fortschr Röntgenstr 2022; DOI: 10.1055/a-1800-8789.