LAVA HyperSense and deep-learning reconstruction for near-isotropic (3D) enhanced magnetic resonance enterography in patients with Crohn's disease: utility in noise reduction and image quality improvement

Deep learning enabled near-isotropic CAIPIRINHA VIBE in the nephrogenic phase improves image quality and renal lesion conspicuity

Background

Deep learning (DL) accelerated controlled aliasing in parallel imaging results in higher acceleration (CAIPIRINHA)-volumetric interpolated breath-hold examination (VIBE), provides high spatial resolution T1-weighted imaging of the upper abdomen. We aimed to investigate whether DL-CAIPIRINHA-VIBE can improve image quality, vessel conspicuity, and lesion detectability compared to a standard CAIPIRINHA-VIBE in renal imaging at 3 Tesla.

Methods

In this prospective study, 50 patients with 23 solid and 45 cystic renal lesions underwent MRI with clinical MR sequences, including standard CAIPIRINHA-VIBE and DL-CAIPIRINHA-VIBE sequences in the nephrographic phase at 3 Tesla. Two experienced radiologists independently evaluated both sequences and multiplanar reconstructions (MPR) of the sagittal and coronal planes for image quality with a Likert scale ranging from 1 to 5 (5 =best). Quantitative measurements including the size of the largest lesion and renal lesion contrast ratios were evaluated.

Results

DL-CAIPIRINHA-VIBE compared to standard CAIPIRINHA-VIBE showed significantly improved overall image quality, higher scores for renal border delineation, renal sinuses, vessels, adrenal glands, reduced motion artifacts and reduced perceived noise in nephrographic phase images (all p < 0.001). DL-CAIPIRINHA-VIBE with MPR showed superior lesion conspicuity and diagnostic confidence compared to standard CAIPIRINHA-VIBE. However, DL-CAIPIRINHA-VIBE presented a more synthetic appearance and more aliasing artifacts (p < 0.023). The mean size and signal intensity of renal lesions for DL-CAIPIRINHA-VIBE showed no significant differences compared to standard CAIPIRINHA-VIBE (p > 0.9).

Conclusions

DL-CAIPIRINHA-VIBE is well suited for kidney imaging in the nephrographic phase, provides good image quality, improved delineation of anatomic structures and renal lesions.

Deep learning image enhancement for confident diagnosis of TMJ osteoarthritis in zero-TE MR imaging

OBJECTIVES

This study aimed to evaluate the effectiveness of deep learning method for denoising and artefact reduction (AR) in zero echo time MRI (ZTE-MRI). Also, clinical applicability was evaluated by comparing image diagnosis to the temporomandibular joint (TMJ) cone-beam CT (CBCT).

METHODS

CBCT and routine ZTE-MRI data were collected for 30 patients, along with an additional ZTE-MRI obtained with reduced scan time. Scan time-reduced image sets were processed into denoised and AR images based on a deep learning technique. The image quality of the routine sequence, denoised, and AR image sets was compared quantitatively using the signal-to-noise ratio (SNR) and qualitatively using a 3-point grading system (0: poor, 1: good, 2: excellent). The presence of osteoarthritis was assessed in each imaging protocol. Diagnostic accuracy of each protocol was compared against the CBCT results, which served as the reference standard. The SNR and the qualitative scores were compared using analysis of variance test and Kruskal-Wallis test, respectively. The diagnostic accuracy was assessed using Cohen's κ (<0.5 = poor; 0.5 to <0.75 = moderate; 0.75 to <0.9 = good; ≥0.9 = excellent).

RESULTS

Both the denoised and AR protocols resulted in significantly enhanced SNR compared to the routine protocol, with the AR protocol showing a higher SNR than the denoised one. The qualitative assessment also showed highest grade in AR protocol with statistical significance. The osteoarthritis diagnosis showed enhanced agreement with CBCT in denoised (κ = 0.928) and AR images (κ = 0.929) than routine images (κ = 0.707).

CONCLUSIONS

A newly developed deep learning technique for both denoising and artefact reduction in ZTE-MRI presented clinical usefulness. Specifically, AR protocol showed significantly improved image quality and comparable diagnostic accuracy comparable to CBCT. It can be expected that this novel technique would help overcome the current limitation of ZTE-MRI for replacing CBCT in bone imaging of TMJ.

Artificial Intelligence in Gastrointestinal Imaging: Advances and Applications

While artificial intelligence (AI) has shown considerable progress in many areas of medical imaging, applications in abdominal imaging, particularly for the gastrointestinal (GI) system, have notably lagged behind advancements in other body regions. This article reviews foundational concepts in AI and highlights examples of AI applications in GI tract imaging. The discussion on AI applications includes acute & emergent GI imaging, inflammatory bowel disease, oncology, and other miscellaneous applications. It concludes with a discussion of important considerations for implementing AI tools in clinical practice, and steps we can take to accelerate future developments in the field.

Evaluation of Image Quality and Scan Time Efficiency in Accelerated 3D T1-Weighted Pediatric Brain MRI Using Deep Learning-Based Reconstruction

OBJECTIVE

This study evaluated the effect of an accelerated three-dimensional (3D) T1-weighted pediatric brain MRI protocol using a deep learning (DL)-based reconstruction algorithm on scan time and image quality.

MATERIALS AND METHODS

This retrospective study included 46 pediatric patients who underwent conventional and accelerated, pre- and post-contrast, 3D T1-weighted brain MRI using a 3T scanner (SIGNA Premier; GE HealthCare) at a single tertiary referral center between March 1, 2023, and April 30, 2023. Conventional scans were reconstructed using intensity Filter A (Conv), whereas accelerated scans were reconstructed using intensity Filter A (Fast_A) and a DL-based algorithm (Fast_DL). Image quality was assessed quantitatively based on the coefficient of variation, relative contrast, apparent signal-to-noise ratio (aSNR), and apparent contrast-to-noise ratio (aCNR) and qualitatively according to radiologists' ratings of overall image quality, artifacts, noisiness, gray-white matter differentiation, and lesion conspicuity.

RESULTS

The acquisition times for the pre- and post-contrast scans were 191 and 135 seconds, respectively, for the conventional scan. With the accelerated protocol, these were reduced to 135 and 80 seconds, achieving time reductions of 29.3% and 40.7%, respectively. DL-based reconstruction significantly reduced the coefficient of variation, improved the aSNR, aCNR, and overall image quality, and reduced the number of artifacts compared with the conventional acquisition method (all P < 0.05). However, the lesion conspicuity remained similar between the two protocols.

CONCLUSION

Utilizing a DL-based reconstruction algorithm in accelerated 3D T1-weighted pediatric brain MRI can significantly shorten the acquisition time, enhance image quality, and reduce artifacts, making it a viable option for pediatric imaging.

Deep learning in magnetic resonance enterography for Crohn's disease assessment: a systematic review

Crohn's disease (CD) poses significant morbidity, underscoring the need for effective, non-invasive inflammatory assessment using magnetic resonance enterography (MRE). This literature review evaluates recent publications on the role of deep learning in improving MRE for CD assessment. We searched MEDLINE/PUBMED for studies that reported the use of deep learning algorithms for assessment of CD activity. The study was conducted according to the PRISMA guidelines. The risk of bias was evaluated using the QUADAS-2 tool. Five eligible studies, encompassing 468 subjects, were identified. Our study suggests that diverse deep learning applications, including image quality enhancement, bowel segmentation for disease burden quantification, and 3D reconstruction for surgical planning are useful and promising for CD assessment. However, most of the studies are preliminary, retrospective studies, and have a high risk of bias in at least one category. Future research is needed to assess how deep learning can impact CD patient diagnostics, particularly when considering the increasing integration of such models into hospital systems.

Deep learning-based reconstruction for 3-dimensional heavily T2-weighted fat-saturated magnetic resonance (MR) myelography in epidural fluid detection: image quality and diagnostic performance

Background

Heavily T2-weighted fat-saturated (HT2W-FS) magnetic resonance myelography (MRM) is useful for diagnosing the cause of intracranial hypotension. Recently, deep learning-based reconstruction (DLR) has been utilized to improve image signal-to-noise ratios and sharpness while reducing artifacts, all without lengthening acquisition times. This study aimed to compare the diagnostic performance and image quality of conventional reconstruction (CR) and DLR of 3-dimensional (3D) HT2W-FS MRM applied to detecting epidural fluid in patients with clinically suspected intracranial hypotension.

Methods

This retrospective study included 21 magnetic resonance myelography examinations using both CR and DLR in 21 patients who experienced orthostatic headache between April 2021 and September 2022. Quantitative image quality evaluation was performed by comparing signal-to-noise ratios at the lower thoracic levels. The image quality and artifacts were graded by three readers. The presence of epidural fluid was reported with a confidence score by two readers, and the area under the receiver operating curve, interobserver agreement, and inter-image-set agreement were evaluated. The conspicuity of the dura mater where the epidural fluid was detected was also investigated.

Results

Quantitative and subjective image quality, and artifacts significantly improved with DLR (all P<0.001). Diagnostic performance of DLR was higher for both readers [reader 1: area under the curve (AUC) of CR =0.929; 95% confidence interval (CI): 0.902-0.950, AUC of DLR =0.965 (95% CI: 0.944-0.979), P=0.007; reader 2: AUC of CR =0.834 (95% CI: 0.798-0.866), AUC of DLR =0.877 (0.844-0.905), P=0.040]. Correlation with standard care of MRM in CR and DLR were both strong in reader 1 (rho =0.868-0.919, P<0.001), but was respectively strong and moderate in reader 2 (rho =0.734-0.805, P<0.001). Interobserver agreement was substantial (κ=0.708-0.762). The inter-image-set agreement was almost perfect for reader 1 (κ=0.907) and was substantial for reader 2 (κ=0.750). Dura mater conspicuity significantly improved with DLR (P<0.014, reader 1; P<0.001, readers 2 and 3).

Conclusions

HT2W-FS magnetic resonance myelography with DLR demonstrates substantial improvements in image quality and may improve confidence in detecting epidural fluid.

Improved image quality in contrast-enhanced 3D-T1 weighted sequence by compressed sensing-based deep-learning reconstruction for the evaluation of head and neck

PURPOSE

To assess the utility of deep learning (DL)-based image reconstruction with the combination of compressed sensing (CS) denoising cycle by comparing images reconstructed by conventional CS-based method without DL in fat-suppressed (Fs)-contrast enhanced (CE) three-dimensional (3D) T1-weighted images (T1WIs) of the head and neck.

MATERIALS AND METHODS

We retrospectively analyzed the cases of 39 patients who had undergone head and neck Fs-CE 3D T1WI applying reconstructions based on conventional CS and CS augmented by DL, respectively. In the qualitative assessment, we evaluated overall image quality, visualization of anatomical structures, degree of artifacts, lesion conspicuity, and lesion edge sharpness based on a five-point system. In the quantitative assessment, we calculated the signal-to-noise ratios (SNRs) of the lesion and the posterior neck muscle and the contrast-to-noise ratio (CNR) between the lesion and the adjacent muscle.

RESULTS

For all items of the qualitative analysis, significantly higher scores were awarded to images with DL-based reconstruction (p < 0.001). In the quantitative analysis, DL-based reconstruction resulted in significantly higher values for both the SNR of lesions (p < 0.001) and posterior neck muscles (p < 0.001). Significantly higher CNRs were also observed in images with DL-based reconstruction (p < 0.001).

CONCLUSION

DL-based image reconstruction integrating into the CS-based denoising cycle offered superior image quality compared to the conventional CS method. This technique will be useful for the assessment of patients with head and neck disease.

Application of a deep learning algorithm for three-dimensional T1-weighted gradient-echo imaging of gadoxetic acid-enhanced MRI in patients at a high risk of hepatocellular carcinoma

PURPOSE

To evaluate the efficacy of a vendor-specific deep learning reconstruction algorithm (DLRA) in enhancing image quality and focal lesion detection using three-dimensional T1-weighted gradient-echo images in gadoxetic acid-enhanced liver magnetic resonance imaging (MRI) in patients at a high risk of hepatocellular carcinoma.

MATERIALS AND METHODS

In this retrospective analysis, 83 high-risk patients with hepatocellular carcinoma underwent gadoxetic acid-enhanced liver MRI using a 3-T scanner. Triple arterial phase, high-resolution portal venous phase, and high-resolution hepatobiliary phase images were reconstructed using conventional reconstruction techniques and DLRA (AIRTM Recon DL; GE Healthcare) for subsequent comparison. Image quality and solid focal lesion detection were assessed by three abdominal radiologists and compared between conventional and DL methods. Focal liver lesion detection was evaluated using figures of merit (FOMs) from a jackknife alternative free-response receiver operating characteristic analysis on a per-lesion basis.

RESULTS

DLRA-reconstructed images exhibited significantly improved overall image quality, image contrast, lesion conspicuity, vessel conspicuity, and liver edge sharpness and reduced subjective image noise, ringing artifacts, and motion artifacts compared to conventionally reconstructed images (all P < 0.05). Although there was no significant difference in the FOMs of non-cystic focal liver lesions between the conventional and DL methods, DLRA-reconstructed images showed notably higher pooled sensitivity than conventionally reconstructed images (P < 0.05) in all phases and higher detection rates for viable post-treatment HCCs in the arterial and hepatobiliary phases (all P < 0.05).

CONCLUSIONS

Implementing DLRA can enhance the image quality in 3D T1-weighted gradient-echo sequences of gadoxetic acid-enhanced liver MRI examinations, leading to improved detection of viable post-treatment HCCs.

Advanced Abdominal MRI Techniques and Problem-Solving Strategies

MRI plays an important role in abdominal imaging because of its ability to detect and characterize focal lesions. However, MRI examinations have several challenges, such as comparatively long scan times and motion management through breath-holding maneuvers. Techniques for reducing scan time with acceptable image quality, such as parallel imaging, compressed sensing, and cutting-edge deep learning techniques, have been developed to enable problem-solving strategies. Additionally, free-breathing techniques for dynamic contrast-enhanced imaging, such as extra-dimensional-volumetric interpolated breath-hold examination, golden-angle radial sparse parallel, and liver acceleration volume acquisition Star, can help patients with severe dyspnea or those under sedation to undergo abdominal MRI. We aimed to present various advanced abdominal MRI techniques for reducing the scan time while maintaining image quality and free-breathing techniques for dynamic imaging and illustrate cases using the techniques mentioned above. A review of these advanced techniques can assist in the appropriate interpretation of sequences.

Impact of deep learning-based reconstruction and anti-peristaltic agent on the image quality and diagnostic performance of magnetic resonance enterography comparing single breath-hold single-shot fast spin echo with and without anti-peristaltic agent

Background

While anti-peristaltic agents are beneficial for high quality magnetic resonance enterography (MRE), their use is constrained by potential side effects and increased examination complexity. We explored the potential of deep learning-based reconstruction (DLR) to compensate for the absence of anti-peristaltic agent, improve image quality and reduce artifact. This study aimed to evaluate the need for an anti-peristaltic agent in single breath-hold single-shot fast spin-echo (SSFSE) MRE and compare the image quality and artifacts between conventional reconstruction (CR) and DLR.

Methods

We included 45 patients who underwent MRE for Crohn's disease between October 2021 and September 2022. Coronal SSFSE images without fat saturation were acquired before and after anti-peristaltic agent administration. Four sets of data were generated: SSFSE CR with and without an anti-peristaltic agent (CR-A and CR-NA, respectively) and SSFSE DLR with and without an anti-peristaltic agent (DLR-A and DLR-NA, respectively). Two radiologists independently reviewed the images for overall quality and artifacts, and compared the three images with DLR-A. The degree of distension and inflammatory parameters were scored on a 5-point scale in the jejunum and ileum, respectively. Signal-to-noise ratio (SNR) levels were calculated in superior mesenteric artery (SMA) and iliac bifurcation level.

Results

In terms of overall quality, DLR-NA demonstrated no significant difference compared to DLR-A, whereas CR-NA and CR-A demonstrated significant differences (P<0.05, both readers). Regarding overall artifacts, reader 1 rated DLR-A slightly better than DLR-NA in four cases and rated them as identical in 41 cases (P=0.046), whereas reader 2 demonstrated no difference. Bowel distension was significantly different in the jejunum (Reader 1: P=0.046; Reader 2: P=0.008) but not in the ileum. Agreements between the images (Reader 1: ĸ=0.73-1.00; Reader 2: ĸ=1.00) and readers (ĸ=0.66 for all comparisons) on inflammation were considered good to excellent. The sensitivity, specificity, and accuracy in diagnosing inflammation in the terminal ileum were the same among DLR-NA, DLR-A, CR-NA and CR-A (94.42%, 81.83%, and 89.69 %; and 83.33%, 90.91%, and 86.21% for Readers 1 and 2, respectively). In both SMA and iliac bifurcation levels, SNR of DLR images exhibited no significant differences. CR images showed significantly lower SNR compared with DLR images (P<0.001).

Conclusions

SSFSE without anti-peristaltic agents demonstrated nearly equivalent quality to that with anti-peristaltic agents. Omitting anti-peristaltic agents before SSFSE and adding DLR could improve the scanning outcomes and reduce time.