AI Article Synopsis
- The study aimed to utilize deep learning to simultaneously acquire perfusion-weighted imaging (PWI) and MR angiography (MRA) from a single contrast dose during stroke MRI, addressing the common need for multiple doses.
- It involved a retrospective analysis of 60 patients experiencing ischemic symptoms linked to significant artery blockages, where different U-Net architectures were tested to develop accurate perfusion maps.
- The results demonstrated that advanced U-Net configurations yielded high-quality perfusion maps, with the best performance measured using peak signal-to-noise ratio (pSNR) values, signifying successful integration of PWI and MRA in stroke imaging.
Article Abstract
Background: A typical stroke MRI protocol includes perfusion-weighted imaging (PWI) and MR angiography (MRA), requiring a second dose of contrast agent. A deep learning method to acquire both PWI and MRA with single dose can resolve this issue.
Purpose: To acquire both PWI and MRA simultaneously using deep learning approaches.
Study Type: Retrospective.
Subjects: A total of 60 patients (30-73 years old, 31 females) with ischemic symptoms due to occlusion or ≥50% stenosis (measured relative to proximal artery diameter) of the internal carotid artery, middle cerebral artery, or anterior cerebral artery. The 51/1/8 patient data were used as training/validation/test.
Field Strength/sequence: A 3 T, time-resolved angiography with stochastic trajectory (contrast-enhanced MRA) and echo planar imaging (dynamic susceptibility contrast MRI, DSC-MRI).
Assessment: We investigated eight different U-Net architectures with different encoder/decoder sizes and with/without an adversarial network to generate perfusion maps from contrast-enhanced MRA. Relative cerebral blood volume (rCBV), relative cerebral blood flow (rCBF), mean transit time (MTT), and time-to-max (T ) were mapped from DSC-MRI and used as ground truth to train the networks and to generate the perfusion maps from the contrast-enhanced MRA input.
Statistical Tests: Normalized root mean square error, structural similarity (SSIM), peak signal-to-noise ratio (pSNR), DICE, and FID scores were calculated between the perfusion maps from DSC-MRI and contrast-enhanced MRA. One-tailed t-test was performed to check the significance of the improvements between networks. P values < 0.05 were considered significant.
Results: The four perfusion maps were successfully extracted using the deep learning networks. U-net with multiple decoders and enhanced encoders showed the best performance (pSNR 24.7 ± 3.2 and SSIM 0.89 ± 0.08 for rCBV). DICE score in hypo-perfused area showed strong agreement between the generated perfusion maps and the ground truth (highest DICE: 0.95 ± 0.04).
Data Conclusion: With the proposed approach, dynamic angiography MRI may provide vessel architecture and perfusion-relevant parameters simultaneously from a single scan.
Evidence Level: 3 TECHNICAL EFFICACY: Stage 5.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1002/jmri.28315 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Clinical feasibility of deep learning-driven magnetic resonance angiography collateral map in acute anterior circulation ischemic stroke.
Sci Rep
January 2025
DeepClue Inc., Deajeon, Republic of Korea.
To validate the clinical feasibility of deep learning-driven magnetic resonance angiography (DL-driven MRA) collateral map in acute ischemic stroke. We employed a 3D multitask regression and ordinal regression deep neural network, called as 3D-MROD-Net, to generate DL-driven MRA collateral maps. Two raters graded the collateral perfusion scores of both conventional and DL-driven MRA collateral maps and measured the grading time.
View Article and Find Full Text PDFFactors Associated With Prolonged Venous Transit in Large Vessel Occlusion Acute Ischemic Strokes.
J Neuroimaging
January 2025
Department of Radiology, Division of Neuroradiology, Johns Hopkins Medical Center, Baltimore, Maryland, USA.
Background And Purpose: Prolonged venous transit (PVT), derived from computed tomography perfusion (CTP) time-to-maximum (T) maps, reflects compromised venous outflow (VO) in acute ischemic stroke due to large vessel occlusion (AIS-LVO). Poor VO is associated with worse clinical outcomes, but pre-treatment markers predictive of PVT are not well described.
Methods: We conducted a retrospective analysis of 189 patients with anterior circulation AIS-LVO who underwent baseline CT evaluation, including non-contrast CT, CT angiography, and CTP.
Quantitative assessment of transmural remission in Crohn's disease using low dose computed tomography (CT) enterography perfusion imaging: a single-centre study based on intestinal microcirculation.
Clin Radiol
December 2024
Department of Radiology, The First Affiliated Hospital of Soochow University, Suzhou, Jiangsu, 215006, China. Electronic address:
Aim: To assess transmural remission in patients with Crohn's disease using low-dose small bowel computed tomography (CT) perfusion scans.
Materials And Methods: Forty six patients were divided into active and remission phases based on Crohn's Disease Activity Index (CDAI) and C-reactive protein (CRP). Dual-source CT enterography with low-dose perfusion scans was conducted to generate perfusion parameter maps, including blood flow (BF), blood volume (BV), time to peak (TTP), mean transit time (MTT), and permeability of surface (PS).
Comparison and impact of preoperative 3D virtual vascular modelling with intraoperative indocyanine green perfusion angiography for personalized proximal colon cancer surgery.
Eur J Surg Oncol
January 2025
UCD Centre of Precision Surgery, 47 Eccles Street, Dublin 7, Ireland; Department of Surgery, Mater Misericordiae University Hospital, Dublin, Ireland. Electronic address:
Article Synopsis
- The study investigates the effectiveness of 3D virtual modeling (3DVM) and indocyanine green perfusion angiography (ICGPA) in improving surgical planning and outcomes during laparoscopic right hemicolectomy for colon cancer.
- Advanced imaging techniques allowed for precise preoperative planning, showing a high correlation with intraoperative findings, which enabled better decisions regarding vessel management and anastomotic site selection.
- The results indicate that using 3DVM and ICGPA not only enhances the surgical team’s ability to visualize vascular structures but also leads to successful surgeries without postoperative complications.
Evaluating the effect of noise reduction strategies in CT perfusion imaging for predicting infarct core with deep learning.
Neuroradiol J
January 2025
Canon Stroke and Vascular Research Center, University at Buffalo, Buffalo, NY, USA.
This study evaluates the efficacy of deep learning models in identifying infarct tissue on computed tomography perfusion (CTP) scans from patients with acute ischemic stroke due to large vessel occlusion, specifically addressing the potential influence of varying noise reduction techniques implemented by different vendors. We analyzed CTP scans from 60 patients who underwent mechanical thrombectomy achieving a modified thrombolysis in cerebral infarction (mTICI) score of 2c or 3, ensuring minimal changes in the infarct core between the initial CTP and follow-up MR imaging. Noise reduction techniques, including principal component analysis (PCA), wavelet, non-local means (NLM), and a no denoising approach, were employed to create hemodynamic parameter maps.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!