Improvement of image quality in diffusion-weighted imaging with model-based deep learning reconstruction for evaluations of the head and neck.

OBJECTIVES: To investigate the utility of deep learning (DL)-based image reconstruction using a model-based approach in head and neck diffusion-weighted imaging (DWI). MATERIALS AND METHODS: We retrospectively analyzed the cases of 41 patients who underwent head/neck DWI. The DWI in 25 patients demonstrated an untreated lesion. We performed qualitative and quantitative assessments in the DWI analyses with both deep learning (DL)- and conventional parallel imaging (PI)-based reconstructions. For the qualitative assessment, we visually evaluated the overall image quality, soft tissue conspicuity, degree of artifact(s), and lesion conspicuity based on a five-point system. In the quantitative assessment, we measured the signal-to-noise ratio (SNR) of the bilateral parotid glands, submandibular gland, the posterior muscle, and the lesion. We then calculated the contrast-to-noise ratio (CNR) between the lesion and the adjacent muscle. RESULTS: Significant differences were observed in the qualitative analysis between the DWI with PI-based and DL-based reconstructions for all of the evaluation items (p < 0.001). In the quantitative analysis, significant differences in the SNR and CNR between the DWI with PI-based and DL-based reconstructions were observed for all of the evaluation items (p = 0.002 ~ p < 0.001). DISCUSSION: DL-based image reconstruction with the model-based technique effectively provided sufficient image quality in head/neck DWI.

Deep Learning of Phase-Contrast Images of Cancer Stem Cells Using a Selected Dataset of High Accuracy Value Using Conditional Generative Adversarial Networks.

Artificial intelligence (AI) technology for image recognition has the potential to identify cancer stem cells (CSCs) in cultures and tissues. CSCs play an important role in the development and relapse of tumors. Although the characteristics of CSCs have been extensively studied, their morphological features remain elusive. The attempt to obtain an AI model identifying CSCs in culture showed the importance of images from spatially and temporally grown cultures of CSCs for deep learning to improve accuracy, but was insufficient. This study aimed to identify a process that is significantly efficient in increasing the accuracy values of the AI model output for predicting CSCs from phase-contrast images. An AI model of conditional generative adversarial network (CGAN) image translation for CSC identification predicted CSCs with various accuracy levels, and convolutional neural network classification of CSC phase-contrast images showed variation in the images. The accuracy of the AI model of CGAN image translation was increased by the AI model built by deep learning of selected CSC images with high accuracy previously calculated by another AI model. The workflow of building an AI model based on CGAN image translation could be useful for the AI prediction of CSCs.

Phase I Randomized Trial of 17 O-Labeled Water: Safety and Feasibility Study of Indirect Proton MRI for the Evaluation of Cerebral Water Dynamics.

BACKGROUND: 17 O-labeled water (PSO17) is a contrast agent developed to measure brain water dynamics and cerebral blood flow. PURPOSE: To evaluate the safety and feasibility of PSO17. STUDY TYPE: Prospective study. SUBJECTS: A total of 12 male healthy volunteers (23.1 ± 1.9 years) were assigned to three groups of four subjects: placebo (normal saline), PSO17 10%, and PSO17 20%. FIELD STRENGTH/SEQUENCE: Dynamic 3D fluid attenuated inversion recovery (FLAIR, fast spin echo with variable refocusing flip angle) scans of the brain were performed with 3-T MRI. ASSESSMENT: Contrast agents were injected 5 minutes after the start of a 10-minute scan. Any symptoms, vital signs, and blood and urine tests were evaluated at five timepoints from preinjection to 4 days after. Blood samples for pharmacokinetic analysis, including half-life (T1/2), maximum fraction (Cmax ), time-to-maximum fraction (Tmax ), and area under the curve (AUC), were collected at 13 timepoints from preinjection to 168 hours after. Regions of interest were set in the cerebral cortex (CC), basal ganglia/thalamus (BG/TM), and white matter (WM), and 17 O concentrations were calculated from signal changes and evaluated using Cmax . STATISTICAL TESTS: All items were compared among the three groups using Tukey-Kramer's honestly significant difference test. Statistical significance was defined as P < 0.5. RESULTS: No safety issues were noted with the intravenous administration of PSO17. The T1/2 was approximately 160 hours, and the AUCs were 1.77 ± 0.10 and 3.75 ± 0.36 in the PSO17 10% and 20% groups, respectively. 17 O fractions calculated from MRI signals were higher in the PSO17 20% group than in the 10% and placebo groups. Significant differences were noted between all pairs of groups in the CC and BG/TM, and between PSO17 20% and both placebo and 10% groups in the WM. DATA CONCLUSION: PSO17 might be considered safe as a contrast medium. Dynamic 3D-FLAIR might detect dose-dependent signal changes and estimate 17 O. EVIDENCE LEVEL: 1 TECHNICAL EFFICACY: Stage 1.

Variations and natural history of primary intraparenchymal lesions associated with neurofibromatosis type 2.

The study aimed to investigate the clinical implications and natural history of primary intraparenchymal lesions in patients with neurofibromatosis type 2. Radiological findings of 15 neurofibromatosis type 2 cases were retrospectively collected. Twenty-seven primary intraparenchymal lesions were observed in 7 out of 15 patients (47%). Cortical/subcortical T2 hyperintense lesions and enlarged Virchow-Robin spaces were the most common findings in five and four patients, respectively. During the follow-up period (median 84 months), one new primary intraparenchymal lesion was identified and increased lesions were observed in two cases on contrast-enhanced MRI. Surgical resection was performed in one case pathologically diagnosed with atypical meningioma. Twenty-five other lesions without contrast enhancement presented no apparent growth during follow-up. Although most primary intraparenchymal lesions are benign, a subset of cases would present newly developed or increased lesions on contrast-enhanced MRI. Careful monitoring is necessary for such cases, and pathological confirmation should be considered.

Detection of impaired cerebrovascular reactivity in patients with chronic cerebral ischemia using whole-brain 7T MRA.

BACKGROUND: Cerebrovascular reactivity (CVR) to acetazolamide (ACZ) on single-photon emission computed tomography (SPECT) can be used to assess the severity of chronic cerebral ischemia; however, this is an invasive method. We examined whether whole-brain magnetic resonance angiography (MRA) at 7T could non-invasively detect impaired CVR in patients with chronic cerebral ischemia by demonstrating the leptomeningeal collaterals (LMCs). METHODS: Fifty-seven patients with symptomatic unilateral cervical stenosis underwent whole-brain time-of-flight MRA at 7T and cerebral perfusion SPECT before/after the ACZ challenge. MRA images were visually assessed based on 6-point grading systems to evaluate the development of LMCs toward the middle cerebral artery (MCA) and antegrade flow of MCA. CVR of the affected side was calculated from the SPECT data. Subsequently, we compared the LMC grades on MRA with CVR on SPECT. RESULTS: CVR was significantly lower in grades ≥ 2 of LMCs than in grades 0-1 (P < 0.05) when applying LMCs from the anterior cerebral artery (ACA) and/or posterior cerebral artery (PCA). These differences were more evident than those in the grading of the antegrade MCA flow. The LMC grades from ACA/PCA readily detected reduced CVR (< 18.4%) with a sensitivity/specificity of 0.79/0.82. CONCLUSION: The development of LMCs on whole-brain MRA at 7T can non-invasively detect reduced CVR with a high sensitivity/specificity in patients with unilateral cervical stenosis.

Computational Fluid Dynamics Analysis of Lateral Striate Arteries in Acute Ischemic Stroke Using 7T High-resolution Magnetic Resonance Angiography.

BACKGROUND: Infarcts in the lateral striate artery (LSA) territory can be caused by several pathological changes, including lipohyalinosis and microatheroma. However, fluid dynamic effects on these changes remain unknown. Thus, we investigated whether the fluid dynamic metrics of the LSAs were altered in patients with acute ischemic stroke using computational fluid dynamics (CFD) analysis. METHODS: Fifty-one patients with acute ischemic stroke confined in the basal ganglia and/or corona radiata underwent high-resolution magnetic resonance angiography (HR-MRA) at 7T. We performed CFD analyses to obtain indices including the wall shear stress (WSS), WSS gradient (WSSG), and flow velocity (FV) and compared these values between the ipsilesional and contralesional sides in the patients with infarcts in the LSA or non-LSA territories. RESULTS: In patients with LSA-territory infarcts, the WSS, WSSG, and FV values were significantly lower in the ipsilesional LSAs than in the contralesional LSAs (P = .01-.03), while these values in the proximal middle cerebral arteries showed no significant lateralities. In contrast, in patients with non-LSA-territory infarcts, there were no significant lateralities in the metrics between the ipsilesional and contralesional sides. CONCLUSIONS: The CFD analyses using HR-MRA revealed significantly low WSS and WSSG values of the ipsilesional LSAs compared with that of the contralesional side in patients with LSA-territory infarcts, suggesting that fluid dynamic factors of LSAs can be one of the risk factors for LSA-territory infarctions.

Improvement of the repeatability of parallel transmission at 7T using interleaved acquisition in the calibration scan.

BACKGROUND: Respiration-induced phase shift affects B0 /B1+ mapping repeatability in parallel transmission (pTx) calibration for 7T brain MRI, but is improved by breath-holding (BH). However, BH cannot be applied during long scans. PURPOSE: To examine whether interleaved acquisition during calibration scanning could improve pTx repeatability and image homogeneity. STUDY TYPE: Prospective. SUBJECTS: Nine healthy subjects. FIELD STRENGTH/SEQUENCE: 7T MRI with a two-channel RF transmission system was used. ASSESSMENT: Calibration scanning for B0 /B1+ mapping was performed under sequential acquisition/free-breathing (Seq-FB), Seq-BH, and interleaved acquisition/FB (Int-FB) conditions. The B0 map was calculated with two echo times, and the B1+ map was obtained using the Bloch-Siegert method. Actual flip-angle imaging (AFI) and gradient echo (GRE) imaging were performed using pTx and quadrature-Tx (qTx). All scans were acquired in five sessions. Repeatability was evaluated using intersession standard deviation (SD) or coefficient of variance (CV), and in-plane homogeneity was evaluated using in-plane CV. STATISTICAL TESTS: A paired t-test with Bonferroni correction for multiple comparisons was used. RESULTS: The intersession CV/SDs for the B0 /B1+ maps were significantly smaller in Int-FB than in Seq-FB (Bonferroni-corrected P < 0.05 for all). The intersession CVs for the AFI and GRE images were also significantly smaller in Int-FB, Seq-BH, and qTx than in Seq-FB (Bonferroni-corrected P < 0.05 for all). The in-plane CVs for the AFI and GRE images in Seq-FB, Int-FB, and Seq-BH were significantly smaller than in qTx (Bonferroni-corrected P < 0.01 for all). DATA CONCLUSION: Using interleaved acquisition during calibration scans of pTx for 7T brain MRI improved the repeatability of B0 /B1+ mapping, AFI, and GRE images, without BH. LEVEL OF EVIDENCE: 1 Technical Efficacy Stage 1 J. Magn. Reson. Imaging 2017.

Indirect MRI of 17 o-labeled water using steady-state sequences: Signal simulation and preclinical experiment.

BACKGROUND: Few studies have been reported for T2 -weighted indirect 17 O imaging. PURPOSE/HYPOTHESIS: To evaluate the feasibility of steady-state sequences for indirect 17 O brain imaging. STUDY TYPE: Signal simulation, phantom measurements, and prospective animal experiments were performed in accordance with the institutional guidelines for animal experiments. POPULATION/SUBJECTS/PHANTOM/SPECIMEN/ANIMAL MODEL: Signal simulations of balanced steady-state free precession (bSSFP) were performed for concentrations of 17 O ranging from 0.037-1.600%. Phantom measurements with concentrations of 17 O water ranging from 0.037-1.566% were also conducted. Six healthy beagle dogs were scanned with intravenous administration of 20% 17 O-labeled water (1 mL/kg). FIELD STRENGTH/SEQUENCE: Dynamic 3D-bSSFP scans were performed at 3T MRI. 17 O-labeled water was injected 60 seconds after the scan start, and the total scan duration was 5 minutes. ASSESSMENT: Based on the result of signal simulation and phantom measurement, signal changes in the beagle dogs were measured and converted into 17 O concentrations. STATISTICAL TESTS: The 17 O concentrations were averaged for every 15 seconds, and compared to the baseline (30-45 sec) with Dunnett's multiple comparison tests. RESULTS: Signal simulation revealed that the relationships between 17 O concentration and the natural logarithm of relative signals were linear. The intraclass correlation coefficient between relative signals in phantom measurement and signal simulations was 0.974. In the animal experiments, significant increases in 17 O concentration (P < 0.05) were observed 60 seconds after the injection of 17 O. At the end of scanning, mean respective 17 O concentrations of 0.084 ± 0.026%, 0.117 ± 0.038, 0.082 ± 0.037%, and 0.049 ± 0.004% were noted for the cerebral cortex, cerebellar cortex, cerebral white matter, and ventricle. DATA CONCLUSION: Dynamic steady-state sequences were feasible for indirect 17 O imaging, and absolute quantification was possible. This method can be applied for the measurement of permeability and blood flow in the brain, and for kinetic analysis of cerebrospinal fluid. LEVEL OF EVIDENCE: 2 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2018;47:1373-1379.

Computer-assisted cognitive remediation therapy increases hippocampal volume in patients with schizophrenia: a randomized controlled trial.

BACKGROUND: Cognitive remediation therapy (CRT) effectively reduces neurocognitive impairment in patients with schizophrenia, but few studies have used structural neuroimaging methods to assess its neuroanatomical effects. We investigated these effects, as well as the association between changes in cortical volume and neurocognitive performance. METHOD: Between August 2013 and September 2016, we performed a randomized controlled study comprising a CRT group (16 individuals) and a treatment-as-usual (TAU) group (15 individuals) of patients with schizophrenia. CRT participants engaged in twice-weekly computer-assisted CRT sessions and weekly group meetings for 12 weeks. T1-weighted magnetic resonance imaging was performed before and after the intervention period, and whole-brain voxel-based morphometric analysis was used to detect significant cortical gray matter volume changes. We also assessed the correlation between cortical volume changes and CRT-derived neurocognitive improvements. RESULTS: The CRT group exhibited significantly greater improvements than the TAU group in verbal fluency (P = 0.012) and global cognitive scores (P = 0.049). The CRT group also exhibited significantly greater increases in right hippocampal volume than the TAU group (P < 0.001). Changes in verbal fluency scores and right hippocampal volumes were positively correlated (r = 0.53, P = 0.001). CONCLUSION: We found that CRT significantly increased right hippocampal volumes and that these enhancements were positively correlated with changes in verbal fluency scores. Our results indicate that CRT induces cognitive improvement through hippocampal plasticity. TRIAL REGISTRATION: Registration number: UMIN000026146 , 2017/02/15, retrospectively registered.

Noninvasive Assessment of Oxygen Extraction Fraction in Chronic Ischemia Using Quantitative Susceptibility Mapping at 7 Tesla.

BACKGROUND AND PURPOSE: The oxygen extraction fraction (OEF) is an effective metric to evaluate metabolic reserve in chronic ischemia. However, OEF is considered to be accurately measured only when using positron emission tomography (PET). Thus, we investigated whether OEF maps generated by magnetic resonance quantitative susceptibility mapping (QSM) at 7 Tesla enabled detection of OEF changes when compared with those obtained with PET. METHODS: Forty-one patients with chronic stenosis/occlusion of the unilateral internal carotid artery or middle cerebral artery were examined using 7 Tesla-MRI and PET scanners. QSM images were obtained from 3-dimensional T2*-weighted images, using a multiple dipole-inversion algorithm. OEF maps were generated based on susceptibility differences between venous structures and brain tissues on QSM images. OEF ratios of the ipsilateral middle cerebral artery territory against the contralateral side were calculated on the QSM-OEF and PET-OEF images, using an anatomic template. RESULTS: The OEF ratio in the middle cerebral artery territory showed significant correlations between QSM-OEF and PET-OEF maps (r=0.69; P<0.001), especially in patients with a substantial increase in the PET-OEF ratio of 1.09 (r=0.79; P=0.004), although showing significant systematic biases for the agreements. An increased QSM-OEF ratio of >1.09, as determined by receiver operating characteristic analysis, showed a sensitivity and specificity of 0.82 and 0.86, respectively, for the substantial increase in the PET-OEF ratio. Absolute QSM-OEF values were significantly correlated with PET-OEF values in the patients with increased PET-OEF. CONCLUSIONS: OEF ratios on QSM-OEF images at 7 Tesla showed a good correlation with those on PET-OEF images in patients with unilateral steno-occlusive internal carotid artery/middle cerebral artery lesions, suggesting that noninvasive OEF measurement by MRI can be a substitute for PET.

Differential diagnosis of parkinsonism by a combined use of diffusion kurtosis imaging and quantitative susceptibility mapping.

PURPOSE: We investigated whether diffusion kurtosis imaging (DKI) and quantitative susceptibility mapping (QSM) could detect pathological changes that occur in Parkinson's disease (PD), multiple system atrophy with predominant parkinsonism (MSA-P) or predominant cerebellar ataxia (MSA-C), and progressive supranuclear palsy syndrome (PSPS) and thus be used for differential diagnosis that is often difficult. METHODS: Seventy patients (41 with PD, 6 with MSA-P, 7 with MSA-C, 16 with PSPS) and 20 healthy controls were examined using a 3.0 T MRI scanner. From DKI and QSM data, we automatically obtained mean kurtosis (MK), fractional anisotropy (FA), and mean diffusivity (MD) values of the midbrain tegmentum (MBT), pontine crossing tract (PCT), and superior/middle cerebellar peduncles (CPs), which were used to calculate diffusion MBT/PCT ratios (dMPRs) and diffusion superior/middle CP ratios (dCPRs), as well as MS (magnetic susceptibility) values of the anterior/posterior putamen (PUa and PUp) and globus pallidus (GP). RESULTS: dMPRs of MK were significantly decreased in PSPS and increased in MSA-C compared with the other groups, while dCPRs of MK showed significant differences only between MSA-C and PD, PSPS, or control. MS values were significantly increased in the PUp of MSA-P and in the PUa and GP of PSPS compared with those in PD. The combined use of MK-dMPR and MS-PUp showed sensitivities of 83-100% and specificities of 81-100% for discriminating among the disease groups, respectively. CONCLUSION: A quantitative assessment using DKI and QSM analyses, particularly MK-dMPR and MS-PUp values, can readily identify patients with parkinsonism.

Difference between tablet methods and paper questionnaire methods of conducting a survey with community-dwelling elderly.

[Purpose] This study aimed to develop a tablet app that emulates paper questionnaires used in clinical care, and to verify the difference between the utility of tablet survey methods and paper questionnaire methods with elderly people. [Subjects and Methods] A tablet app was developed in the Java language. A questionnaire was provided to 30 community-dwelling elderly people. The subjects were randomly allocated to the group responding on the tablet (tablet group) or that responding to a paper-based questionnaire (questionnaire group). Assessed items included response time to questions, whether or not they had queries regarding the survey, and data input time. For the tablet group, a questionnaire was conducted regarding the operability of the tablet. [Results] There was no difference in response time between the two groups. Significantly more people in the tablet group had queries regarding the survey. Data input time was 426 seconds for the tablet group and 1268 seconds for the questionnaire group. In the survey regarding tablet operability, there were no negative opinions about the visibility of the screen. [Conclusion] Tablets can be used with elderly people to shorten the data input time. The present findings suggested that tablet surveys could be effective for a large-scale investigation.

Detection of changes in the periaqueductal gray matter of patients with episodic migraine using quantitative diffusion kurtosis imaging: preliminary findings.

INTRODUCTION: The periaqueductal gray matter (PAG) is considered to play an important role in generating migraine, but findings from imaging studies remain unclear. Therefore, we investigated whether diffusion kurtosis imaging (DKI) can detect changes in the PAG of migraine patients. METHODS: We obtained source images for DKI from 20 patients with episodic migraine and 20 healthy controls using a 3 T magnetic resonance imaging scanner. Mean kurtosis (MK), fractional anisotropy (FA), and mean diffusivity (MD) maps were generated, and the values of the PAG and other deep gray and white matter structures were automatically measured using an atlas-based region-of-interest analysis. The metrics of these structures were compared between the patients and controls. RESULTS: The MK and MD values of the PAG were significantly increased in the migraine patients compared with the controls (p < 0.05). The FA values were not significantly different. There were no significant differences in the metrics of the other structures between the patients and controls. The MK values of the PAG were significantly positively correlated with both age and the untreated period in the patient group under univariate analysis (r = 0.53 and 0.56, respectively; p < 0.05) but not multivariate analysis. CONCLUSIONS: DKI detected significant increases in the MK and MD values of the PAG in patients with migraine, which suggests that structural changes in the PAG are associated with the pathophysiological mechanisms of migraine.

Deep Learning of Cancer Stem Cell Morphology.

Knowledge regarding cancer stem cell (CSC) morphology is limited, and more extensive studies are therefore required. Image recognition technologies using artificial intelligence (AI) require no previous expertise in image annotation. Herein, we describe the construction of AI models that recognize the CSC morphology in cultures and tumor tissues. The visualization of the AI deep learning process enables insight to be obtained regarding unrecognized structures in an image.

High Resolution TOF-MRA Using Compressed Sensing-based Deep Learning Image Reconstruction for the Visualization of Lenticulostriate Arteries: A Preliminary Study.

PURPOSE: To investigate the visibility of the lenticulostriate arteries (LSAs) in time-of-flight (TOF)-MR angiography (MRA) using compressed sensing (CS)-based deep learning (DL) image reconstruction by comparing its image quality with that obtained by the conventional CS algorithm. METHODS: Five healthy volunteers were included. High-resolution TOF-MRA images with the reduction (R)-factor of 1 were acquired as full-sampling data. Images with R-factors of 2, 4, and 6 were then reconstructed using CS-DL and conventional CS (the combination of CS and sensitivity conceding; CS-SENSE) reconstruction, respectively. In the quantitative assessment, the number of visible LSAs (identified by two radiologists), length of each depicted LSA (evaluated by one radiological technologist), and normalized mean squared error (NMSE) value were assessed. In the qualitative assessment, the overall image quality and the visibility of the peripheral LSA were visually evaluated by two radiologists. RESULTS: In the quantitative assessment of the DL-CS images, the number of visible LSAs was significantly higher than those obtained with CS-SENSE in the R-factors of 4 and 6 (Reader 1) and in the R-factor of 6 (Reader 2). The length of the depicted LSAs in the DL-CS images was significantly longer in the R-factor 6 compared to the CS-SENSE result. The NMSE value in CS-DL was significantly lower than in CS-SENSE for R-factors of 4 and 6. In the qualitative assessment of DL-CS images, the overall image quality was significantly higher than that obtained with CS-SENSE in the R-factors 4 and 6 (Reader 1) and in the R-factor 4 (Reader 2). The visibility of the peripheral LSA was significantly higher than that shown by CS-SENSE in all R-factors (Reader 1) and in the R-factors 2 and 4 (Reader 2). CONCLUSION: CS-DL reconstruction demonstrated preserved image quality for the depiction of LSAs compared to the conventional CS-SENSE when the R-factor is elevated.

Magnetic Resonance Water Tracer Imaging Using 17 O-Labeled Water.

ABSTRACT: Magnetic resonance imaging (MRI) is a crucial imaging technique for visualizing water in living organisms. Besides proton MRI, which is widely available and enables direct visualization of intrinsic water distribution and dynamics in various environments, MR-WTI (MR water tracer imaging) using 17 O-labeled water has been developed, benefiting from the many advancements in MRI software and hardware that have substantially improved the signal-to-noise ratio and made possible faster imaging. This cutting-edge technique allows the generation of novel and valuable images for clinical use. This review elucidates the studies related to MRI water tracer techniques centered around 17 O-labeled water, explaining the fundamental principles of imaging and providing clinical application examples. Anticipating continued progress in studies involving isotope-labeled water, this review is expected to contribute to elucidating the pathophysiology of various diseases related to water dynamics abnormalities and establishing novel imaging diagnostic methods for associated diseases.

Imaging of 17O-labeled Water Using Fast T2 Mapping with T2-preparation: A Phantom Study.

17O-labeled water is a T2-shortening contrast agent used in proton MRI and is a promising method for visualizing cerebrospinal fluid (CSF) dynamics because it provides long-term tracking of water molecules. However, various external factors reduce the accuracy of 17O-concentration measurements using conventional signal-intensity-based methods. In addition, T2 mapping, which is expected to provide a stable assessment, is generally limited to temporal-spatial resolution. We developed the T2-prepared based on T2 mapping used in cardiac imaging to adapt to long T2 values and tested whether it could accurately measure 17O-concentration in the CSF using a phantom. The results showed that 17O-concentration in a fluid mimicking CSF could be evaluated with an accuracy comparable to conventional T2-mapping (Carr-Purcell-Meiboom-Gill multi-echo spin-echo method). This method allows 17O-imaging with a high temporal resolution and stability in proton MRI. This imaging technique may be promising for visualizing CSF dynamics using 17O-labeled water.

Automated Detection of Cerebral Microbleeds on Two-dimensional Gradient-recalled Echo T2* Weighted Images Using a Morphology Filter Bank and Convolutional Neural Network.

PURPOSE: We present a novel algorithm for the automated detection of cerebral microbleeds (CMBs) on 2D gradient-recalled echo T2* weighted images (T2*WIs). This approach combines a morphology filter bank with a convolutional neural network (CNN) to improve the efficiency of CMB detection. A technical evaluation was performed to ascertain the algorithm's accuracy. METHODS: In this retrospective study, 60 patients with CMBs on T2*WIs were included. The gold standard was set by three neuroradiologists based on the Microbleed Anatomic Rating Scale guidelines. Images with CMBs were extracted from the training dataset comprising 30 cases using a morphology filter bank, and false positives (FPs) were removed based on the threshold of size and signal intensity. The extracted images were used to train the CNN (Vgg16). To determine the effectiveness of the morphology filter bank, the outcomes of the following two methods for detecting CMBs from the 30-case test dataset were compared: (a) employing the morphology filter bank and additional FP removal and (b) comprehensive detection without filters. The trained CNN processed both sets of initial CMB candidates, and the final CMB candidates were compared with the gold standard. The sensitivity and FPs per patient of both methods were compared. RESULTS: After CNN processing, the morphology-filter-bank-based method had a 95.0% sensitivity with 4.37 FPs per patient. In contrast, the comprehensive method had a 97.5% sensitivity with 25.87 FPs per patient. CONCLUSION: Through effective CMB candidate refinement with a morphology filter bank and FP removal with a CNN, we achieved a high CMB detection rate and low FP count. Combining a CNN and morphology filter bank may facilitate the accurate automated detection of CMBs on T2*WIs.

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.

Accelerating FLAIR imaging via deep learning reconstruction: potential for evaluating white matter hyperintensities.

PURPOSE: To evaluate deep learning-reconstructed (DLR)-fluid-attenuated inversion recovery (FLAIR) images generated from undersampled data, compare them with fully sampled and rapidly acquired FLAIR images, and assess their potential for white matter hyperintensity evaluation. MATERIALS AND METHODS: We examined 30 patients with white matter hyperintensities, obtaining fully sampled FLAIR images (standard FLAIR, std-FLAIR). We created accelerated FLAIR (acc-FLAIR) images using one-third of the fully sampled data and applied deep learning to generate DLR-FLAIR images. Three neuroradiologists assessed the quality (amount of noise and gray/white matter contrast) in all three image types. The reproducibility of hyperintensities was evaluated by comparing a subset of 100 hyperintensities in acc-FLAIR and DLR-FLAIR images with those in the std-FLAIR images. Quantitatively, similarities and errors of the entire image and the focused regions on white matter hyperintensities in acc-FLAIR and DLR-FLAIR images were measured against std-FLAIR images using structural similarity index measure (SSIM), regional SSIM, normalized root mean square error (NRMSE), and regional NRMSE values. RESULTS: All three neuroradiologists evaluated DLR-FLAIR as having significantly less noise and higher image quality scores compared with std-FLAIR and acc-FLAIR (p < 0.001). All three neuroradiologists assigned significantly higher frontal lobe gray/white matter visibility scores for DLR-FLAIR than for acc-FLAIR (p < 0.001); two neuroradiologists attributed significantly higher scores for DLR-FLAIR than for std-FLAIR (p < 0.05). Regarding white matter hyperintensities, all three neuroradiologists significantly preferred DLR-FLAIR (p < 0.0001). DLR-FLAIR exhibited higher similarity to std-FLAIR in terms of visibility of the hyperintensities, with 97% of the hyperintensities rated as nearly identical or equivalent. Quantitatively, DLR-FLAIR demonstrated significantly higher SSIM and regional SSIM values than acc-FLAIR, with significantly lower NRMSE and regional NRMSE values (p < 0.0001). CONCLUSIONS: DLR-FLAIR can reduce scan time and generate images of similar quality to std-FLAIR in patients with white matter hyperintensities. Therefore, DLR-FLAIR may serve as an effective method in traditional magnetic resonance imaging protocols.