Objective: To evaluate the diagnostic performance of susceptibility map-weighted imaging (SMwI) taken in different acquisition planes for discriminating patients with neurodegenerative parkinsonism from those without. Materials and Methods: This retrospective, observational, single-institution study enrolled consecutive patients who visited movement disorder clinics and underwent brain MRI and 18F-FP-CIT PET between September 2021 and December 2021. SMwI images were acquired in both the oblique (perpendicular to the midbrain) and the anterior commissure-posterior commissure (AC-PC) planes. Hyperintensity in the substantia nigra was determined by two neuroradiologists. 18F-FP-CIT PET was used as the reference standard. Inter-rater agreement was assessed using Cohen’s kappa coefficient. The diagnostic performance of SMwI in the two planes was analyzed separately for the right and left substantia nigra. Multivariable logistic regression analysis with generalized estimating equations was applied to compare the diagnostic performance of the two planes. Results: In total, 194 patients were included, of whom 105 and 103 had positive results on 18F-FP-CIT PET in the left and right substantia nigra, respectively. Good inter-rater agreement in the oblique (κ = 0.772/0.658 for left/right) and AC-PC planes (0.730/0.741 for left/right) was confirmed. The pooled sensitivities for two readers were 86.4% (178/206, left) and 83.3% (175/210, right) in the oblique plane and 87.4% (180/206, left) and 87.6% (184/210, right) in the AC-PC plane. The pooled specificities for two readers were 83.5% (152/182, left) and 82.0% (146/178, right) in the oblique plane, and 83.5% (152/182, left) and 86.0% (153/178, right) in the AC-PC plane. There were no significant differences in the diagnostic performance between the two planes (P > 0.05). Conclusion There are no significant difference in the diagnostic performance of SMwI performed in the oblique and AC-PC plane in discriminating patients with parkinsonism from those without. This finding affirms that each institution may choose the imaging plane for SMwI according to their clinical settings.

Purpose: This study aimed to evaluate the quality of artificial intelligence (AI)/machine learning (ML) studies on hemorrhagic stroke using the Minimum Information for Medical AI Reporting (MINIMAR) and Minimum Information About Clinical Artificial Intelligence Modeling (MI-CLAIM) frameworks to promote clinical application. Materials and Methods: PubMed, MEDLINE, and Embase were searched for AI/ML studies on hemorrhagic stroke. Out of the 531 articles found, 29 relevant original research articles were included. MINIMAR and MI-CLAIM scores were assigned by two experienced radiologists to assess the quality of the studies. Results: We analyzed 29 investigations that utilized AI/ML in the field of hemorrhagic stroke, involving a median of 224.5 patients. The majority of studies focused on diagnostic outcomes using computed tomography scans (89.7%) and were published in computer science journals (48.3%). The overall adherence rates to reporting guidelines, as assessed through the MINIMAR and MI-CLAIM frameworks, were 47.6% and 46.0%, respectively. In MINIMAR, none of the studies reported the socioeconomic status of the patients or how missing values had been addressed. In MI-CLAIM, only two studies applied model-examination techniques to improve model interpretability. Transparency and reproducibility were limited, as only 10.3% of the studies had publicly shared their code. Cohen’s kappa between the two radiologists was 0.811 and 0.779 for MINIMAR and MI-CLAIM, respectively. Conclusion The overall reporting quality of published AI/ML studies on hemorrhagic stroke is suboptimal. It is necessary to incorporate model examination techniques for interpretability and promote code openness to enhance transparency and increase the clinical applicability of AI/ML studies.

Purpose: This study aimed to develop and validate a convolutional neural network (CNN) that automatically detects an aberrant right subclavian artery (ARSA) on preoperative computed tomography (CT) for thyroid cancer evaluation. Materials and Methods: A total of 556 CT with ARSA and 312 CT with normal aortic arch from one institution were used as the training set for model development. A deep learning model for the classification of patch images for ARSA was developed using two-dimension CNN from EfficientNet. The diagnostic performance of our model was evaluated using external test sets (112 and 126 CT) from two institutions. The performance of the model was compared with that of radiologists for detecting ARSA using an independent dataset of 1683 consecutive neck CT. Results: The performance of the model was achieved using two external datasets with an area under the curve of 0.97 and 0.99, and accuracy of 97% and 99%, respectively. In the temporal validation set, which included a total of 20 patients with ARSA and 1663 patients without ARSA, radiologists overlooked 13 ARSA cases. In contrast, the CNN model successfully detected all the 20 patients with ARSA. Conclusion We developed a CNN-based deep learning model that detects ARSA using CT. Our model showed high performance in the multicenter validation.

Background: and PurposeThe correlation between dopamine transporter (DAT) imaging and neuromelanin-sensitive magnetic resonance imaging (NM-MRI) in early-stage Parkinson’s disease (PD) has not yet been established. This study aimed to determine the correlation between NM-MRI and DAT positron-emission tomography (PET) in patients with early-stage PD. Methods: Fifty drug-naïve patients with early-stage PD who underwent both 0.8-mm isovoxel NM-MRI and DAT PET were enrolled retrospectively. Using four regions of interest (nigrosome 1 and nigrosome 2 [N1 and N2] regions) from a previous study, the contrast ratios (CRs) of 12 regions were measured: N1, N2, flipped N1, flipped N2, combined N1 and N2, and whole substantia nigra pars compacta [SNpc] (all on both sides). The clinically more affected side was separately assessed. The standardized uptake value ratios (SUVRs) were measured in the striatum using DAT PET. A partial correlation analysis was performed between the SUVR and CR measurements. Results: CR of the flipped left N1 region was significantly correlated with SUVR of the right posterior putamen (p=0.047), and CR values of the left N1 region, left N2 region, flipped right N1 region, and combined left N1 and N2 regions were significantly correlated with SUVR of the left posterior putamen (p=0.011, 0.038, 0.020, and 0.010, respectively). SUVR of the left anterior putamen was significantly correlated with CR of the left N2 region (p=0.027). On the clinically more affected side, the CR values of the N1 region, combined N1 and N2 regions, and the whole SNpc were significantly correlated with SUVR of the posterior putamen (p=0.001, 0.024, and 0.021, respectively). There were significant correlations between the SUVR of the anterior putamen and the CR values of the N1 region, combined N1 and N2 regions, and whole SNpc (p=0.027, 0.001, and 0.036, respectively). Conclusions This study found that there were significant correlations between CR values in the SNpc on NM-MRI and striatal SUVR values on DAT PET on both sides in early-stage PD.

Purpose: To understand the effects of datasets with various parameters on pretrained network performance, the generalization capacity of the artificial neural network for myelin water imaging (ANN-MWI) is explored by testing datasets with various scan protocols (i.e., resolution and refocusing RF pulse shape) and types of disorders (i.e., neuromyelitis optica and edema). Materials and Methods: ANN-MWI was trained to generate a T2 distribution, from which the myelin water fraction value was measured. The training and test datasets were acquired from healthy controls and multiple sclerosis patients using a multiecho gradient and spin-echo sequence with the same scan protocols. To test the generalization capacity of ANN-MWI, datasets with different settings were utilized.The datasets were acquired or generated with different resolutions, refocusing pulse shape, and types of disorders. For all datasets, the evaluation was performed in a white matter mask by calculating the normalized root-mean-squared error (NRMSE) between the results from the conventional method and ANN-MWI. Additionally, for the patient datasets, the NRMSE was calculated in each lesion mask. Results: The results of ANN-MWI showed high reliability in generating myelin water fraction maps from the datasets with different resolutions. However, the increased errors were reported for the datasets with different refocusing pulse shapes and disorder types. Specifically, the region of lesions in edema patients reported high NRMSEs. These increased errors indicate the dependency of ANN-MWI on refocusing pulse flip angles and T 2 characteristics. Conclusion This study proposes information about the generalization accuracy of a trained network when applying deep learning to processing myelin water imaging.

BACKGROUND: Pathologic diagnosis of central nervous system (CNS) neoplasms is made by comparing light microscopic, immunohistochemical, and molecular cytogenetic findings with clinicoradiologic observations. Intraoperative frozen cytology smears can improve the diagnostic accuracy for CNS neoplasms. Here, we evaluate the diagnostic value of cytology in frozen diagnoses of CNS neoplasms. METHODS: Cases were selected from patients undergoing both frozen cytology and frozen sections. Diagnostic accuracy was evaluated. RESULTS: Four hundred and fifty-four cases were included in this retrospective single-center review study covering a span of 10 years. Five discrepant cases (1.1%) were found after excluding 53 deferred cases (31 cases of tentative diagnosis, 22 cases of inadequate frozen sampling). A total of 346 cases of complete concordance and 50 cases of partial concordance were classified as not discordant cases in the present study. Diagnostic accuracy of intraoperative frozen diagnosis was 87.2%, and the accuracy was 98.8% after excluding deferred cases. Discrepancies between frozen and permanent diagnoses (n = 5, 1.1%) were found in cases of nonrepresentative sampling (n = 2) and misinterpretation (n = 3). High concordance was observed more frequently in meningeal tumors (97/98, 99%), metastatic brain tumors (51/52, 98.1%), pituitary adenomas (86/89, 96.6%), schwannomas (45/47, 95.8%), high-grade astrocytic tumors (47/58, 81%), low grade astrocytic tumors (10/13, 76.9%), non-neoplastic lesions (23/36, 63.9%), in decreasing frequency. CONCLUSIONS: Using intraoperative cytology and frozen sections of CNS tumors is a highly accurate diagnostic ancillary method, providing subtyping of CNS neoplasms, especially in frequently encountered entities.
Brain Neoplasms ; Central Nervous System Neoplasms ; Central Nervous System ; Cytogenetics ; Diagnosis ; Frozen Sections ; Humans ; Meningeal Neoplasms ; Methods ; Neurilemmoma ; Pituitary Neoplasms ; Retrospective Studies

PURPOSE: The objective of this study was to obtain improved susceptibility weighted images (SWI) of the cervical spinal cord using respiratory-induced artifact compensation. MATERIALS AND METHODS: The artifact from B0 fluctuations by respiration could be compensated using a double navigator echo approach. The two navigators were inserted in an SWI sequence before and after the image readouts. The B0 fluctuation was measured by each navigator echoes, and the inverse of the fluctuation was applied to eliminate the artifact from fluctuation. The degree of compensation was quantified using a quality index (QI) term for compensated imaging using each navigator. Also, the effect of compensation was analyzed according to the position of the spinal cord using QI values. RESULTS: Compensation using navigator echo gave the improved visualization of SWI in cervical spinal cord compared to non-compensated images. Before compensation, images were influenced by artificial noise from motion in both the superior (QI = 0.031) and inferior (QI = 0.043) regions. In most parts of the superior regions, the second navigator resulted in better quality (QI = 0.024, P < 0.01) compared to the first navigator, but in the inferior regions the first navigator showed better quality (QI = 0.033, P < 0.01) after correction. CONCLUSION: Motion compensation using a double navigator method can increase the improvement of the SWI in the cervical spinal cord. The proposed method makes SWI a useful tool for the diagnosis of spinal cord injury by reducing respiratory-induced artifact.
Artifacts ; Cervical Cord ; Compensation and Redress ; Diagnosis ; Methods ; Noise ; Qi ; Respiration ; Spinal Cord ; Spinal Cord Injuries

The prediction of successful recanalization following thrombolytic or endovascular treatment may be helpful to determine the strategy of recanalization treatment in acute stroke. Thrombus can be detected using noncontrast computed tomography (CT) as a hyperdense artery sign or blooming artifact on a T2*-weighted gradient-recalled image. The detection of thrombus using CT depends on slice thickness. Thrombus burden can be determined in terms of the length, volume, and clot burden score. The thrombus size can be quantitatively measured on thin-section CT or CT angiography/magnetic resonance angiography. The determination of thrombus size may be predictive of successful recanalization/non-recanalization after intravenous thrombolysis and endovascular treatment. However, cut-offs of thrombus size for predicting recanalization/non-recanalization are different among studies, due to different methods of measurements. Thus, a standardized method to measure the thrombus is necessary for thrombus imaging to be useful and reliable in clinical practice. Software-based measurements may provide a reliable and accurate assessment. The measurement should be easy and rapid to be more widely used in practice, which could be achieved by improvement of the user interface. In addition to prediction of recanalization, sequential measurements of thrombus volume before and after the treatment may also be useful to determine the efficacy of new thrombolytic drugs. This manuscript reviews the diagnosis of thrombus, prediction of recanalization using thrombus imaging, and practical considerations for the measurement of thrombus burden and density on CT.
Angiography ; Arteries ; Artifacts ; Diagnosis ; Endovascular Procedures ; Fibrinolytic Agents ; Methods ; Reperfusion* ; Stroke* ; Thrombolytic Therapy ; Thrombosis*

PURPOSE: Fluid-attenuated inversion recovery (FLAIR) imaging can be obtained faster with shorter repletion time (TR), but it gets noisier. We hypothesized that shorter-TR FLAIR obtained at 3 tesla (3T) with a 32-channel coil may be comparable to conventional FLAIR. The aim of this study was to compare the diagnostic value between conventional FLAIR (TR = 9000 ms, FLAIR9000) and shorter-TR FLAIR (TR = 6000 ms, FLAIR6000) at 3T in terms of diffusion-weighted imaging-FLAIR mismatch. MATERIALS AND METHODS: We recruited 184 patients with acute ischemic stroke (28 patients < 4.5 hours) who had undergone 5-mm diffusion-weighted imaging (DWI) and two successive 5-mm FLAIR images (no gap; in-plane resolution, 0.9 × 0.9 mm) at 3T with a 32-channel coil. The acquisition times for FLAIR9000 and FLAIR6000 were 108 seconds (generalized autocalibrating partially parallel acquisitions [GRAPPA] = 2) and 60 seconds (GRAPPA = 3), respectively. Two radiologists independently assessed the paired imaging sets (DWI-FLAIR9000 and DWI-FLAIR6000) for the presence of matched hyperintense lesions on each FLAIR imaging. The signal intensity ratios (area of DWI lesion to contralateral normal-appearing region) on both FLAIR imaging sets were compared. RESULTS: DWI-FLAIR9000 mismatch was present in 39 of 184 (21.2%) patients, which was perfectly the same on FLAIR6000. Three of 145 patients (2%) with DWI-matched lesions on FLAIR9000 had discrepancy on FLAIR6000, showing no significant difference (P > 0.05). Interobserver agreement was excellent for both DWI-FLAIR9000 and DWI-FLAIR6000 (k = 0.904 and 0.883, respectively). Between the two FLAIR imaging sets, there was no significant difference of signal intensity ratio (mean, standard deviation; 1.25 ± 0.20; 1.24 ± 0.20, respectively) (P > 0.05). CONCLUSION: For the determination of mismatch or match between DWI and FLAIR imaging, there is no significant difference between FLAIR9000 and FLAIR6000 at 3T with a 32-channel coil.
Humans ; Magnetic Resonance Imaging ; Stroke

BACKGROUND AND PURPOSE: The benefit of statins in acute stroke remains uncertain. Statins may prevent stroke recurrence during the acute stage of stroke via pleiotropic effects. However, statins may increase the risk of intracerebral hemorrhage. We investigated the effect and safety of rosuvastatin in acute stroke patients. METHODS: This randomized, double-blind, multi-center trial compared rosuvastatin 20 mg and placebo in statin-naive stroke patients who underwent diffusion-weighted imaging (DWI) within 48 hours after symptom onset. The primary outcome was occurrence of new ischemic lesions on DWI at 5 or 14 days. RESULTS: This trial was stopped early after randomization of 316 patients due to slow enrollment. Among 289 patients with at least one follow-up imaging, the frequency of new ischemic lesions on DWI was not different between groups (rosuvastatin: 27/137, 19.7% vs. placebo: 36/152, 23.6%) (relative risk 0.83, 95% confidence interval 0.53-1.30). Infarct volume growth at 5 days (log-transformed volume change, rosuvastatin: 0.2+/-1.0 mm3 vs. placebo: 0.3+/-1.3 mm3; P=0.784) was not different, either. However, hemorrhagic infarction or parenchymal/subarachnoid hemorrhage on gradient-recalled echo magnetic resonance imaging occurred less frequently in the rosuvastatin group (6/137, 4.4%) than the placebo group (22/152, 14.5%, P=0.007). Among 314 patients with at least one dose of study medication, progression or clinical recurrence of stroke tended to occur less frequently in the rosuvastatin group (1/155, 0.6% vs. 7/159, 4.4%, P=0.067). Adverse events did not differ between groups. CONCLUSIONS: The efficacy of rosuvastatin in reducing recurrence in acute stroke was inconclusive. However, statin use was safe and reduced hemorrhagic transformation.
Cerebral Hemorrhage ; Follow-Up Studies ; Hemorrhage ; Humans ; Hydroxymethylglutaryl-CoA Reductase Inhibitors ; Infarction ; Magnetic Resonance Imaging ; Random Allocation ; Recurrence ; Stroke* ; Rosuvastatin Calcium