Ultrafast Brain MRI with Deep Learning Reconstruction for Suspected Acute Ischemic Stroke

Assessment of AI-accelerated T2-weighted brain MRI, based on clinical ratings and image quality evaluation

OBJECTIVE

To compare clinical ratings and signal-to-noise ratio (SNR) measures of a commercially available Deep Learning-based MRI reconstruction method (T2(DR)) against conventional T2- turbo spin echo brain MRI (T2(CN)).

MATERIALS AND METHODS

100 consecutive patients with various neurological conditions underwent both T2(DR) and T2(CN) on a Siemens Vida 3 T scanner with a 64-channel head coil in the same examination. Acquisition times were 3.33 min for T2(CN) and 1.04 min for T2(DR). Four neuroradiologists evaluated overall image quality (OIQ), diagnostic safety (DS), and image artifacts (IA), blinded to the acquisition mode. SNR and SNReff (adjusted for acquisition time) were calculated for air, grey- and white matter, and cerebrospinal fluid.

RESULTS

The mean patient age was 43.6 years (SD 20.3), with 54 females. The distribution of non-diagnostic ratings did not differ significantly between T2(CN) and T2(DR) (IA p = 0.108; OIQ: p = 0.700 and DS: p = 0.652). However, when considering the full spectrum of ratings, significant differences favouring T2(CN) emerged in OIQ (p = 0.003) and IA (p < 0.001). T2(CN) had higher SNR (157.9, SD 123.4) than T2(DR) (112.8, SD 82.7), p < 0.001, but T2(DR) demonstrated superior SNReff (14.1, SD 10.3) compared to T2(CN) (10.8, SD 8.5), p < 0.001.

CONCLUSION

Our results suggest that while T2(DR) may be clinically applicable for a diagnostic setting, it does not fully match the quality of high-standard conventional T2(CN), MRI acquisitions.

Region-guided focal adversarial learning for CT-to-MRI translation: A proof-of-concept and validation study in hepatocellular carcinoma

BACKGROUND

Generative adversarial networks (GANs) have recently demonstrated significant potential for producing virtual images with the same characteristics as real-life landscapes, thereby enhancing various medical tasks.

PURPOSE

To design a region-guided focal GAN (Focal-GAN) for translating images between CT and MRI and test its clinical applicability in patients with hepatocellular carcinoma (HCC).

METHODS

Between January 2012 and October 2021, two cohorts of patients with HCC who underwent contrast-enhanced CT (Center 1, n = 685) and MRI (Center 1, n = 516; Center 2, n = 318) were retrospectively enrolled. We trained the Focal-GAN model by adding tumor regions to a baseline Cycle-GAN framework to steer the model toward focal attention learning. The quality of the images generated was assessed using an open-source MRQy tool. The clinical applicability of the Focal-GAN was evaluated by applying the nnUNet and ResNet-50 model for tumor segmentation and microvascular invasion (MVI) prediction in HCC on the generated images.

RESULTS

In the ablation tests, Focal-GAN achieved a higher fidelity than the conventional Cycle-GAN in the generated image quality assessment with MRQy. Regarding applicability, regardless of tumor size, nnUNet trained with focal-GAN-generated images achieved higher Dice scores than nnUNet trained using Cycle-GAN-generated images for HCC segmentation in both internal (0.607 vs. 0.341, p < 0.01) and external (0.796 vs. 0.753, p < 0.001) validation. Additionally, ResNet-50 trained with Focal-GAN-generated images produced higher areas-under-curve (AUCs) than ResNet-50 trained with real images for MVI prediction in both internal (0.754 vs. 0.665, p = 0.048) and external (0.670 vs. 0.579, p < 0.001) validation.

CONCLUSIONS

The designed Focal-GAN model can generate virtual MR images from unpaired CT images, thereby extending the clinical applicability of CT in the liver tumor diagnostic pathway.

Prediction of prognosis in acute ischemic stroke after mechanical thrombectomy based on multimodal MRI radiomics and deep learning

Background

Acute ischemic stroke (AIS) is a major global health threat associated with high rates of disability and mortality, highlighting the need for early prognostic assessment to guide treatment. Currently, there are no reliable methods for the early prediction of poor prognosis in AIS, especially after mechanical thrombectomy. This study aimed to explore the value of radiomics and deep learning based on multimodal magnetic resonance imaging (MRI) in predicting poor prognosis in patients with AIS who underwent mechanical thrombectomy. This study aimed to provide a more accurate and comprehensive tool for stroke prognosis.

Methods

This study retrospectively analyzed the clinical data and multimodal MRI images of patients with stroke at admission. Logistic regression was employed to identify the risk factors associated with poor prognosis and to construct a clinical model. Radiomics features of the stroke-affected regions were extracted from the patients' baseline multimodal MRI images, and the optimal radiomics features were selected using a least absolute shrinkage and selection operator regression model combined with five-fold cross-validation. The radiomics score was calculated based on the feature weights, and machine learning techniques were applied using a logistic regression classifier to develop the radiomics model. In addition, a deep learning model was devised using ResNet101 and transfer learning. The clinical, radiomics, and deep learning models were integrated to establish a comprehensive multifactorial logistic regression model, termed the CRD (Clinic-Radiomics-Deep Learning) model. The performance of each model in predicting poor prognosis was assessed using receiver operating characteristic (ROC) curve analysis, with the optimal model visualized as a nomogram. A calibration curve was plotted to evaluate the accuracy of nomogram predictions.

Results

A total of 222 patients with AIS were enrolled in this study in a 7:3 ratio, with 155 patients in the training cohort and 67 in the validation cohort. Statistical analysis of clinical data from the training and validation cohorts identified two independent risk factors for poor prognosis: the National Institutes of Health Stroke Scale score at admission and the occurrence of intracerebral hemorrhage. Of the 1,197 radiomic features, 16 were selected to develop the radiomics model. Area under the ROC curve (AUC) analysis of specific indicators demonstrated varying performances across methods and cohorts. In the training cohort, the clinical, radiomics, deep learning, and integrated CRD models achieved AUC values of 0.762, 0.755, 0.689, and 0.834, respectively. In the validation cohort, the clinical model exhibited an AUC of 0.874, the radiomics model achieved an AUC of 0.805, the deep learning model attained an AUC of 0.757, and the CRD model outperformed all models, with an AUC of 0.908. Calibration curves indicated that the CRD model showed exceptional consistency and accuracy in predicting poor prognosis in patients with AIS. Decision curve analysis revealed that the CRD model offered the highest net benefit compared with the clinical, radiomics, and deep learning models.

Conclusion

The CRD model based on multimodal MRI demonstrated high diagnostic efficacy and reliability in predicting poor prognosis in patients with AIS who underwent mechanical thrombectomy. This model holds considerable potential for assisting clinicians with risk assessment and decision-making for patients experiencing ischemic stroke.

A 3-Minute Ultrafast MRI and MRA Protocol for Screening of Acute Ischemic Stroke

OBJECTIVE

To evaluate the diagnostic performance of a 3-min ultrafast brain MRI and MRA protocol for screening of acute ischemic stroke.

METHODS

This study involved 67 adult patients who underwent ultrafast and reference MRI and MRA scans from September 2023 to June 2024 for stroke evaluation. Two readers independently assessed the ultrafast and reference MRI and MRA images in a masked and randomized manner for acute and chronic infarct and hemorrhage as well as large-vessel occlusion and severe stenosis. A 3-point Likert scale was used to evaluate diagnostic quality of the ultrafast sequences and Cohen's κ was used to assess interrater agreement.

RESULTS

The ultrafast MRI and MRA protocol showed high diagnostic quality, with 98% of sequences rated as diagnostic. Raters showed perfect agreement in identifying acute infarcts, aneurysms, and vascular occlusions using both ultrafast and reference protocols and near-perfect agreement (>95%) for detecting acute hemorrhage and severe stenosis. For chronic conditions such as chronic infarction and chronic hemorrhage, there was substantial agreement with κ values ranging from 0.73 to 0.76.

DISCUSSION

The screening ultrafast MRI and MRA protocol can effectively identify acute ischemic stroke and intracranial large-vessel occlusion with high diagnostic accuracy while significantly reducing acquisition time, making it suitable for initial stroke triage. Evaluation for chronic pathologies on the ultrafast protocol is inferior compared with standard MRI and MRA imaging.

Deep Learning Reconstruction Combined With Conventional Acceleration Improves Image Quality of 3 T Brain MRI and Does Not Impact Quantitative Diffusion Metrics

OBJECTIVES

Deep learning reconstruction of magnetic resonance imaging (MRI) allows to either improve image quality of accelerated sequences or to generate high-resolution data. We evaluated the interaction of conventional acceleration and Deep Resolve Boost (DRB)-based reconstruction techniques of a single-shot echo-planar imaging (ssEPI) diffusion-weighted imaging (DWI) on image quality features in cerebral 3 T brain MRI and compared it with a state-of-the-art DWI sequence.

MATERIALS AND METHODS

In this prospective study, 24 patients received a standard of care ssEPI DWI and 5 additional adapted ssEPI DWI sequences, 3 of those with DRB reconstruction. Qualitative analysis encompassed rating of image quality, noise, sharpness, and artifacts. Quantitative analysis compared apparent diffusion coefficient (ADC) values region-wise between the different DWI sequences. Intraclass correlations, paired sampled t test, Wilcoxon signed rank test, and weighted Cohen κ were used.

RESULTS

Compared with the reference standard, the acquisition time was significantly improved in accelerated DWI from 75 seconds up to 50% (39 seconds; P < 0.001). All tested DRB-reconstructed sequences showed significantly improved image quality, sharpness, and reduced noise (P < 0.001). Highest image quality was observed for the combination of conventional acceleration and DL reconstruction. In singular slices, more artifacts were observed for DRB-reconstructed sequences (P < 0.001). While in general high consistency was found between ADC values, increasing differences in ADC values were noted with increasing acceleration and application of DRB. Falsely pathological ADCs were rarely observed near frontal poles and optic chiasm attributable to susceptibility-related artifacts due to adjacent sinuses.

CONCLUSIONS

In this comparative study, we found that the combination of conventional acceleration and DRB reconstruction improves image quality and enables faster acquisition of ssEPI DWI. Nevertheless, a tradeoff between increased acceleration with risk of stronger artifacts and high-resolution with longer acquisition time needs to be considered, especially for application in cerebral MRI.

Clinical Evaluation of 3D Motion-Correction Via Scout Accelerated Motion Estimation and Reduction Framework Versus Conventional T1-Weighted MRI at 1.5 T in Brain Imaging

OBJECTIVES

The aim of this study was to investigate the occurrence of motion artifacts and image quality of brain magnetic resonance imaging (MRI) T1-weighted imaging applying 3D motion correction via the Scout Accelerated Motion Estimation and Reduction (SAMER) framework compared with conventional T1-weighted imaging at 1.5 T.

MATERIALS AND METHODS

A preliminary study involving 14 healthy volunteers assessed the impact of the SAMER framework on induced motion during 3 T MRI scans. Participants performed 3 different motion patterns: (1) step up, (2) controlled breathing, and (3) free motion. The patient study included 82 patients who required clinically indicated MRI scans. 3D T1-weighted images (MPRAGE) were acquired at 1.5 T. The MRI data were reconstructed using either regular product reconstruction (non-Moco) or the 3D motion correction SAMER framework (SAMER Moco), resulting in 145 image sequences. For the preliminary and the patient study, 3 experienced radiologists evaluated the image data using a 5-point Likert scale, focusing on overall image quality, artifact presence, diagnostic confidence, delineation of pathology, and image sharpness. Interrater agreement was assessed using Gwet's AC2, and an exploratory analysis (non-Moco vs SAMER Moco) was performed.

RESULTS

Compared with non-Moco, the preliminary study demonstrated significant improvements across all imaging parameters and motion patterns with SAMER Moco (P < 0.001). Odds ratios favoring SAMER Moco were >999.999 for freedom of artifact and overall image quality (P < 0.0001). Excellent or good ratings for freedom of artifact were 52.4% with SAMER Moco, compared with 21.4% for non-Moco. Similarly, 66.7% of SAMER Moco images were rated excellent or good for overall image quality versus 21.4% for non-Moco. Multireader interrater agreement was excellent across all parameters.The patient study confirmed that SAMER Moco provided significantly superior image quality across all evaluated imaging parameters, particularly in the presence of motion (P < 0.001). Diagnostic confidence was rated as excellent or good in 95.1% of SAMER Moco cases, compared with 78.1% for non-Moco cases. Similarly, overall image quality was rated as excellent or good in 89.8% of SAMER Moco cases versus 65.9% for non-Moco cases. The odds ratios for diagnostic confidence and for overall image quality were 6.698 and 6.030, respectively, both favoring SAMER Moco (P < 0.0001). Multireader interrater agreement was excellent across all parameters.

CONCLUSIONS

The application of SAMER in T1-weighted imaging datasets is feasible in clinical routine and significantly increases image quality and diagnostic confidence in 1.5 T brain MRI by effectively reducing motion artifacts.

Beyond the Conventional Structural MRI: Clinical Application of Deep Learning Image Reconstruction and Synthetic MRI of the Brain

ABSTRACT

Recent technological advancements have revolutionized routine brain magnetic resonance imaging (MRI) sequences, offering enhanced diagnostic capabilities in intracranial disease evaluation. This review explores 2 pivotal breakthrough areas: deep learning reconstruction (DLR) and quantitative MRI techniques beyond conventional structural imaging. DLR using deep neural networks facilitates accelerated imaging with improved signal-to-noise ratio and spatial resolution, enhancing image quality with short scan times. DLR focuses on supervised learning applied to clinical implementation and applications. Quantitative MRI techniques, exemplified by 2D multidynamic multiecho, 3D quantification using interleaved Look-Locker acquisition sequences with T2 preparation pulses, and magnetic resonance fingerprinting, enable precise calculation of brain-tissue parameters and further advance diagnostic accuracy and efficiency. Potential DLR instabilities and quantification and bias limitations will be discussed. This review underscores the synergistic potential of DLR and quantitative MRI, offering prospects for improved brain imaging beyond conventional methods.

NeuroMix with MRA: A Fast MR Protocol to Reduce Head and Neck CTA for Patients with Acute Neurologic Presentations

BACKGROUND AND PURPOSE

Overuse of CT-based cerebrovascular imaging in the emergency department and inpatient settings, notably CTA of the head and neck for minor and nonfocal neurologic presentations, stresses imaging services and exposes patients to radiation and contrast. Furthermore, such CT-based imaging is often insufficient for definitive diagnosis, necessitating additional MR imaging. Recent advances in fast MRI may allow timely assessment and a reduced need for head and neck CTA in select populations.

MATERIALS AND METHODS

We identified inpatients or patients in the emergency department who underwent CTAHN (including noncontrast and postcontrast head CT, with or without CTP imaging) followed within 24 hours by a 3T MRI study that included a 2.5-minute unenhanced multicontrast sequence (NeuroMix) and a 5-minute intracranial time of flight MRA) during a 9-month period (April to December 2022). Cases were classified by 4 radiologists in consensus as to whether NeuroMix and NeuroMix + MRA detected equivalent findings, detected unique findings, or missed findings relative to CTAHN.

RESULTS

One hundred seventy-four cases (mean age, 67 [SD, 16] years; 56% female) met the inclusion criteria. NeuroMix alone and NeuroMix + MRA protocols were determined to be equivalent or better compared with CTAHN in 71% and 95% of patients, respectively. NeuroMix always provided equivalent or better assessment of the brain parenchyma, with unique findings on NeuroMix and NeuroMix + MRA in 35% and 36% of cases, respectively, most commonly acute infarction or multiple microhemorrhages. In 8/174 cases (5%), CTAHN identified vascular abnormalities not seen on the NeuroMix + MRA protocol due to the wider coverage of the cervical arteries by CTAHN.

CONCLUSIONS

A fast MR imaging protocol consisting of NeuroMix + MRA provided equivalent or better information compared with CTAHN in 95% of cases in our population of patients with an acute neurologic presentation. The findings provide a deeper understanding of the benefits and challenges of a fast unenhanced MR-first approach with NeuroMix + MRA, which could be used to design prospective trials in select patient groups, with the potential to reduce radiation dose, mitigate adverse contrast-related patient and environmental effects, and lessen the burden on radiologists and health care systems.

A dynamic approach for MR T2-weighted pelvic imaging

Objective. T2-weighted 2D fast spin echo sequence serves as the standard sequence in clinical pelvic MR imaging protocols. However, motion artifacts and blurring caused by peristalsis present significant challenges. Patient preparation such as administering antiperistaltic agents is often required before examination to reduce artifacts, which discomfort the patients. This work introduce a novel dynamic approach for T2 weighted pelvic imaging to address peristalsis-induced motion issue without any patient preparation.Approach. A rapid dynamic data acquisition strategy with complementary sampling trajectory is designed to enable highly undersampled motion-resistant data sampling, and an unrolling method based on deep equilibrium model is leveraged to reconstruct images from the dynamic sampled k-space data. Moreover, the fix-point convergence of the equilibrium model ensures the stability of the reconstruction. The high acceleration factor in each temporal phase, which is much higher than that in traditional static imaging, has the potential to effectively freeze pelvic motion, thereby transforming the imaging problem from conventional motion prevention or removal to motion reconstruction.Main results. Experiments on both retrospective and prospective data have demonstrated the superior performance of the proposed dynamic approach in reducing motion artifacts and accurately depicting structural details compared to standard static imaging.Significance. The proposed dynamic approach effectively captures motion states through dynamic data acquisition and deep learning-based reconstruction, addressing motion-related challenges in pelvic imaging.

Ultrafast Brain MRI at 3 T for MS: Evaluation of a 51-Second Deep Learning-Enhanced T2-EPI-FLAIR Sequence

In neuroimaging, there is no equivalent alternative to magnetic resonance imaging (MRI). However, image acquisitions are generally time-consuming, which may limit utilization in some cases, e.g., in patients who cannot remain motionless for long or suffer from claustrophobia, or in the event of extensive waiting times. For multiple sclerosis (MS) patients, MRI plays a major role in drug therapy decision-making. The purpose of this study was to evaluate whether an ultrafast, T2-weighted (T2w), deep learning-enhanced (DL), echo-planar-imaging-based (EPI) fluid-attenuated inversion recovery (FLAIR) sequence (FLAIRUF) that has targeted neurological emergencies so far might even be an option to detect MS lesions of the brain compared to conventional FLAIR sequences. Therefore, 17 MS patients were enrolled prospectively in this exploratory study. Standard MRI protocols and ultrafast acquisitions were conducted at 3 tesla (T), including three-dimensional (3D)-FLAIR, turbo/fast spin-echo (TSE)-FLAIR, and FLAIRUF. Inflammatory lesions were grouped by size and location. Lesion conspicuity and image quality were rated on an ordinal five-point Likert scale, and lesion detection rates were calculated. Statistical analyses were performed to compare results. Altogether, 568 different lesions were found. Data indicated no significant differences in lesion detection (sensitivity and positive predictive value [PPV]) between FLAIRUF and axially reconstructed 3D-FLAIR (lesion size ≥3 mm × ≥2 mm) and no differences in sensitivity between FLAIRUF and TSE-FLAIR (lesion size ≥3 mm total). Lesion conspicuity in FLAIRUF was similar in all brain regions except for superior conspicuity in the occipital lobe and inferior conspicuity in the central brain regions. Further findings include location-dependent limitations of signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) as well as artifacts such as spatial distortions in FLAIRUF. In conclusion, FLAIRUF could potentially be an expedient alternative to conventional methods for brain imaging in MS patients since the acquisition can be performed in a fraction of time while maintaining good image quality.

Deep learning reconstruction for turbo spin echo to prospectively accelerate ankle MRI: A multi-reader study

PURPOSE

To evaluate a deep learning reconstruction for turbo spin echo (DLR-TSE) sequence of ankle magnetic resonance imaging (MRI) in terms of acquisition time, image quality, and lesion detectability by comparing with conventional TSE.

METHODS

Between March 2023 and May 2023, patients with an indication for ankle MRI were prospectively enrolled. Each patient underwent a conventional TSE protocol and a prospectively undersampled DLR-TSE protocol. Four experienced radiologists independently assessed image quality using a 5-point scale and reviewed structural abnormalities. Image quality assessment included overall image quality, differentiation of anatomic details, diagnostic confidence, artifacts, and noise. Interchangeability analysis was performed to evaluate the equivalence of DLR-TSE relative to conventional TSE for detection of structural pathologies.

RESULTS

In total, 56 patients were included (mean age, 32.6 ± 10.6 years; 35 men). The DLR-TSE (233 s) protocol enabled a 57.4 % reduction in total acquisition time, compared with the conventional TSE protocol (547 s). DLR-TSE images had superior overall image quality, fewer artifacts, and less noise (all P < 0.05), compared with conventional TSE images, according to mean ratings by the four readers. Differentiation of anatomic details, diagnostic confidence, and assessments of structural abnormalities showed no differences between the two techniques (P > 0.05). Furthermore, DLR-TSE demonstrated diagnostic equivalence with conventional TSE, based on interchangeability analysis involving all analyzed structural abnormalities.

CONCLUSION

DLR can prospectively accelerate conventional TSE to a level comparable with a 4-minute comprehensive examination of the ankle, while providing superior image quality and similar lesion detectability in clinical practice.

Application of Artificial Intelligence in Acute Ischemic Stroke: A Scoping Review

Artificial intelligence (AI) is revolutionizing stroke care by enhancing diagnosis, treatment, and outcome prediction. This review examines 505 original studies on AI applications in ischemic stroke, categorized into outcome prediction, stroke risk prediction, diagnosis, etiology prediction, and complication and comorbidity prediction. Outcome prediction, the most explored category, includes studies predicting functional outcomes, mortality, and recurrence, often achieving high accuracy and outperforming traditional methods. Stroke risk prediction models effectively integrate clinical and imaging data, improving assessments of both first-time and recurrent stroke risks. Diagnostic tools, such as automated imaging analysis and lesion segmentation, streamline acute stroke workflows, while AI models for large vessel occlusion detection demonstrate clinical utility. Etiology prediction focuses on identifying causes such as atrial fibrillation or cancer-associated thrombi, using imaging and thrombus analysis. Complication and comorbidity prediction models address stroke-associated pneumonia and acute kidney injury, aiding in risk stratification and resource allocation. While significant advancements have been made, challenges such as limited validation, ethical considerations, and the need for better data collection persist. This review highlights the advancements in AI applications for addressing key challenges in stroke care, demonstrating its potential to enhance precision medicine and improve patient outcomes.