Feasibility of the fat-suppression image-subtraction method using deep learning for abnormality detection on knee MRI.

Purpose: To evaluate the feasibility of using a deep learning (DL) model to generate fat-suppression images and detect abnormalities on knee magnetic resonance imaging (MRI) through the fat-suppression image-subtraction method. Material and methods: A total of 45 knee MRI studies in patients with knee disorders and 12 knee MRI studies in healthy volunteers were enrolled. The DL model was developed using 2-dimensional convolutional neural networks for generating fat-suppression images and subtracting generated fat-suppression images without any abnormal findings from those with normal/abnormal findings and detecting/classifying abnormalities on knee MRI. The image qualities of the generated fat-suppression images and subtraction-images were assessed. The accuracy, average precision, average recall, F-measure, sensitivity, and area under the receiver operator characteristic curve (AUROC) of DL for each abnormality were calculated. Results: A total of 2472 image datasets, each consisting of one slice of original T1WI, original intermediate-weighted images, generated fat-suppression (FS)-intermediate-weighted images without any abnormal findings, generated FS-intermediate-weighted images with normal/abnormal findings, and subtraction images between the generated FS-intermediate-weighted images at the same cross-section, were created. The generated fat-suppression images were of adequate image quality. Of the 2472 subtraction-images, 2203 (89.1%) were judged to be of adequate image quality. The accuracies for overall abnormalities, anterior cruciate ligament, bone marrow, cartilage, meniscus, and others were 89.5-95.1%. The average precision, average recall, and F-measure were 73.4-90.6%, 77.5-89.4%, and 78.4-89.4%, respectively. The sensitivity was 57.4-90.5%. The AUROCs were 0.910-0.979. Conclusions: The DL model was able to generate fat-suppression images of sufficient quality to detect abnormalities on knee MRI through the fat-suppression image-subtraction method.

Diagnostic Value of Advanced Metal Artifact Reduction Magnetic Resonance Imaging for Periprosthetic Joint Infection.

MATERIALS AND METHODS: Magnetic resonance imaging around metal joint prostheses including multiacquisition variable-resonance image combination selective at 1.5 T (from April 2014 to August 2020) was retrospectively evaluated by 2 radiologists for detection of abnormal findings (joint effusion, capsular thickening, pericapsular edema, soft-tissue fluid collection, soft-tissue edema, bone marrow edema pattern around the implant [BME pattern], lymphadenopathy, and others) and overall image impression for PJI. Regarding the soft-tissue fluid collection, presence of communication to the joint or capsular-like structure was evaluated. Clinical assessments were recorded. Positive predictive values (PPVs), negative predictive values (NPVs), and odds ratios (ORs) for PJI were calculated for the abnormal findings. Overall image impression for PJI was evaluated. χ2, Fisher exact, t, and Mann-Whitney U tests and receiver operating characteristic analysis were used. Interobserver agreement was assessed with κ statistics. RESULTS: Forty-three joints in 36 patients (mean ± SD age, 75.4 ± 8.8 years; 30 women; hip [n = 29], knee [n = 12], and elbow [n = 2]) were evaluated. Eighteen joints (42%) were clinically diagnosed as PJI. The findings suggesting PJI were capsular thickening (PPV, 70%; NPV, 90%; OR, 20.6), soft-tissue fluid collection (PPV, 81%; NPV, 81%; OR, 19.1), soft-tissue edema (PPV, 67%; NPV, 89%; OR, 17), pericapsular edema (PPV, 76%; NPV, 81%; OR, 13.7), and joint effusion (PPV, 55%; NPV, 100%; OR, 12). Soft-tissue fluid collection without capsular-like structure (PPV, 83%; NPV, 74%; OR, 14.4) or with communication to the joint (PPV, 75%; NPV, 71%; OR, 7.3) suggested PJI. The combinations of joint effusion, capsular thickening, pericapsular edema, soft-tissue fluid collection, and soft-tissue edema highly suggested PJI. Regarding the BME pattern, the combination with soft-tissue edema raised the possibility of PJI (PPV, 73%; NPV, 69%; OR, 5.9). Regarding the interobserver agreements for each abnormal finding, κ values were 0.60 to 0.77. Regarding the overall image impression, weighted κ value was 0.97 and areas under the receiver operating characteristic curve were 0.949 (95% confidence interval, 0.893-1.005) and 0.926 (95% confidence interval, 0.860-0.991) with no significant difference (P = 0.534). CONCLUSIONS: The findings suggesting PJI were capsular thickening, soft-tissue fluid collection, soft-tissue edema, pericapsular edema, and joint effusion. The combinations of them highly suggested PJI. Regarding the BME pattern, the combination with soft-tissue edema raised the possibility of PJI.

Transient Ischemic Attack: Which Determines Diffusion-Weighted Image Positivity?

AIM OF THE STUDY: Diffusion-weighted image (DWI) of magnetic resonance imaging (MRI) can reveal high signal lesion in up to 50% of transient ischemic attack (TIA) patients. However, it is not well-known which factors determine developing DWI positivity. In order to answer this question, we analyzed factors relevant to DWI positivity in TIA patients. METHODS: We had 257 stroke patients at a university emergency/neurology wards. They were 140 men, 117 women, mean age 72 (45-88) years. Among them, 24 (9.3%) had TIA (14 men, 10 women, mean age 71 [58-82] years). All patients underwent a 1.5T MRI. In 24 TIA patients, we investigated the following parameters in relation with stroke maturation: ABCD2 score, smoking habits, blood profile, HbA1C, dyslipidemia, coagulation factors, carotid echography, electrocardiography, cardiac echography, chest X-ray, neurological symptom/signs, imaging, and recurrence of neurological symptom on follow-up. RESULTS: In 24 TIA patients, 13 (54%) were DWI positive and 11 (46%) were DWI negative. After an extensive analysis, all parameters were not relevant to DWI positivity except for plasma osmolarity, i.e., plasma osmolarity in DWI positive cases (305.3 mOsm/l) is significantly higher than that in DWI negative cases (301.3 mOsm/l) (P = .0064). As for recurrence, 4 of 24 TIA patients recurred. They were 1 (9.0%) of 11 DWI negative cases and 3 (23.1%) of 13 DWI positive cases. Therefore, DWI positive cases recurred more frequently than DWI negative cases did, although it did not reach statistical significance. CONCLUSIONS: TIA with DWI positivity in our institute was 54%, closely associated with initial dehydration and might predict stroke recurrence.

Diagnostic imaging of dementia with Lewy bodies by susceptibility-weighted imaging of nigrosomes versus striatal dopamine transporter single-photon emission computed tomography: a retrospective observational study.

INTRODUCTION: The characteristics of dementia with Lewy bodies (DLB), Alzheimer's disease (AD) and amnestic mild cognitive impairment (a-MCI) overlap but require different treatments; therefore, it is important to differentiate these pathologies. Assessment of dopamine uptake in the striatum using dopamine transporter (DaT) single-photon emission computed tomography (SPECT) is the gold standard for diagnosing DLB; however, this modality is expensive, time consuming and involves radiation exposure. Degeneration of the substantia nigra nigrosome-1, which occurs in DLB, but not in AD/a-MCI, can be identified by 3T susceptibility-weighted imaging (SWI). Therefore, the aim of this retrospective observational study was to compare SWI with DaT-SPECT for differentiation of DLB from AD/a-MCI. METHODS: SWI data were acquired for patients with clinically diagnosed DLB (n = 29), AD (n = 18), a-MCI (n = 13) and healthy controls (n = 26). Images were analysed for nigrosome-1 degeneration. Diagnostic accuracy was evaluated for DLB, AD and a-MCI compared with striatal dopamine uptake using DaT-SPECT. RESULTS: SWI achieved 90% diagnostic accuracy (93% sensitivity, 87% specificity) for the detection of nigrosome-1 degeneration in DLB and not in AD/a-MCI as compared with 88.3% accuracy (93% sensitivity, 84% specificity) using DaT-SPECT. CONCLUSIONS: SWI nigrosome-1 evaluation was useful in differentiating DLB from AD/a-MCI, with high accuracy. This less invasive and less expensive method is a potential alternative to DaT-SPECT for the diagnosis of DLB.

Evaluating Hip Periprosthetic Joint Infection with Metal-artifact-reduction MR Imaging.

PURPOSE: To evaluate the significant findings of hip periprosthetic joint infection (PJI) using metal-artifact-reduction (MAR) MRI and to compare the MRI results to other clinical markers. METHODS: The results of MRI, including two-dimensional fast-spin echo sequences with increased bandwidth and multi-acquisition variable-resonance image combination selective for hips with orthopedic implants at 1.5T (from April 2014 to November 2021), were retrospectively assessed for imaging findings and diagnostic impressions by two radiologists. Clinical data and courses were also investigated. Univariate and multivariate analyses were performed to identify the significant MRI findings in patients with hip PJI and those who underwent surgical intervention. The MRI impressions were compared with other clinical markers in diagnosing hip PJI. RESULTS: Thirty-seven hip joints in 24 Asian patients (age = 73.9 ± 10.8 years; 18 females) were included. Twelve hip joints (32%) had PJI; seven underwent a surgical intervention. The significant findings for hip PJI included periosteal edema of the acetabulum, intermuscular edema, intramuscular fluid collection, and lymphadenopathy (P < 0.05). In the cases with surgical intervention, the significant findings included capsular distension, capsular thickening, an osteolysis-like pattern of the femur, subcutaneous fluid collection, and lymphadenopathy (P < 0.05). The MRI impressions had high diagnostic significance for both hip PJI cases and those with surgical intervention (P < 0.001). The MRI impression was more significant for hip PJI than the other clinical markers (P < 0.05), while the other clinical markers were more significant in the cases with surgical intervention (P < 0.05). CONCLUSION: The significant findings in the hip PJI cases included acetabular periosteal edema, intermuscular edema, intramuscular fluid collection, and lymphadenopathy. The significant findings in the cases with surgical intervention included capsular distention, capsular thickening, a femoral osteolysis-like pattern, subcutaneous fluid collection, and lymphadenopathy. The utilization of MAR MRI demonstrated great diagnostic significance for hip PJI.

Discrimination of dementia with Lewy bodies from Alzheimer's disease using voxel-based morphometry of white matter by statistical parametric mapping 8 plus diffeomorphic anatomic registration through exponentiated Lie algebra.

INTRODUCTION: The purpose of this study was to identify brain atrophy specific for dementia with Lewy bodies (DLB) and to evaluate the discriminatory performance of this specific atrophy between DLB and Alzheimer's disease (AD). METHODS: We retrospectively reviewed 60 DLB and 30 AD patients who had undergone 3D T1-weighted MRI. We randomly divided the DLB patients into two equal groups (A and B). First, we obtained a target volume of interest (VOI) for DLB-specific atrophy using correlation analysis of the percentage rate of significant whole white matter (WM) atrophy calculated using the Voxel-based Specific Regional Analysis System for Alzheimer's Disease (VSRAD) based on statistical parametric mapping 8 (SPM8) plus diffeomorphic anatomic registration through exponentiated Lie algebra, with segmented WM images in group A. We then evaluated the usefulness of this target VOI for discriminating the remaining 30 DLB patients in group B from the 30 AD patients. Z score values in this target VOI obtained from VSRAD were used as the determinant in receiver operating characteristic (ROC) analysis. RESULTS: Specific target VOIs for DLB were determined in the right-side dominant dorsal midbrain, right-side dominant dorsal pons, and bilateral cerebellum. ROC analysis revealed that the target VOI limited to the midbrain exhibited the highest area under the ROC curves of 0.75. CONCLUSIONS: DLB patients showed specific atrophy in the midbrain, pons, and cerebellum. Midbrain atrophy demonstrated the highest power for discriminating DLB and AD. This approach may be useful for determining the contributions of DLB and AD pathologies to the dementia syndrome.

Unexpected discovery of a diffuse astrocytoma of the conus medullaris in an elderly NF1 patient.

Neurofibromatosis type 1 (NF1) is one of the most common genetic neurocutaneous disorders, and it is well known to be associated with peripheral or central nervous system malignancies. The most common malignant tumors are malignant peripheral nerve sheath tumors (MPNSTs); MPNSTs are the most common cause of death in patients with NF1. Central nervous system malignancies rarely occur. So far, the occurrence of spinal cord malignancies is exceedingly rare. Herein, we report a rare case of a 69-year-old male with NF1 following tumor resection twice for cutaneous MPNSTs developing intramedullary diffuse astrocytoma in the conus medullaris, which initially presented with traumatic spinal cord injury associated with a compression fracture from fall. Contrast-enhanced magnetic resonance imaging and biopsy of the spinal cord were required to establish the final diagnosis.

MIBG Myocardial Scintigraphy Identifies Premotor PD/DLB During a Negative DAT Scan Period: Second Report.

OBJECTIVES: Neuroimaging markers for Parkinson's disease (PD)/dementia with Lewy bodies (DLB) include dopamine transporter (DAT) scanning and metaiodobenzylguanidine (MIBG) myocardial scintigraphy. It is unknown which marker is useful to identify the premotor phase PD/DLB. We reported four patients who, during a negative DAT scan period, had a positive MIBG result that suggested premotor PD/DLB. Here we report 18 additional patients. METHODS: This study was a prospective cohort study. The recruiting period was five years; prospective follow-up period, 5.5 ± 3.0 years; and a once a year (minimum) follow-up visit. We recruited 745 referred subjects. The inclusion criteria were having at least one of the following known PD nonmotor features: (1) autonomic: postural hypotension (pure autonomic failure [PAF]), constipation, bladder dysfunction; (2) sleep: REM sleep behavior disorder (RBD); and (3) cognitive: mild cognitive impairment or psychiatric symptoms. Also, the patient had to have undergone both DAT and MIBG tests. RESULTS: Only 18 patients fulfilled these criteria. Their characteristics were: elderly (mean age 75.5 years), with long histories (onset 61.0 years; duration 14.5 years), and predominately male (14 men, four women). The patients' neurologic diagnoses were constipation/RBD in 10, constipation/RBD/PAF in six, and constipation/PAF in two. During the follow-up period, seven patients developed PD or DLB. An abnormal MIBG result was noted in 94%, and an abnormal DAT result was noted in 56%. CONCLUSIONS: MIBG has the potential to be a useful marker during the DAT scan negative period to identify premotor PD/DLB, but further studies are needed.

Differentiation Between Dementia With Lewy Bodies And Alzheimer's Disease Using Voxel-Based Morphometry Of Structural MRI: A Multicenter Study.

BACKGROUND: The differential diagnosis of dementia with Lewy bodies (DLB) and Alzheimer's disease (AD) is particularly important because DLB patients respond better to cholinesterase inhibitors but sometimes exhibit sensitivity to neuroleptics, which may cause worsening of clinical status. Antemortem voxel-based morphometry (VBM) using structural MRI has previously revealed that patients with DLB have normal hippocampal volume, but atrophy in the dorsal mesopontine area. OBJECTIVES: The aim of this multicenter study was to determine whether VBM of the brain stem in addition to that of medial temporal lobe structures improves the differential diagnosis of AD and DLB. METHODS: We retrospectively chose 624 patients who were clinically diagnosed with either DLB (239 patients) or AD (385 patients) from 10 institutes using different MR scanners with different magnetic field strengths. In all cases, VBM was performed on 3D T1-weighted images. The degree of local atrophy was calculated using Z-score by comparison with a database of normal volumes of interest (VOIs) in medial temporal lobe (MTL) and the dorsal brain stem (DBS). The discrimination of DLB and AD was evaluated using Z-score values in these two VOIs. MRI data from 414 patients were used as the training data set to determine the classification criteria, with the MRI data from the remaining 210 patients used as the test data set. RESULTS: The DLB and AD patients did not differ with respect to mean age or Mini-Mental State Examination scores. Z-index scores showed that there was significantly more atrophy in MTL of AD patients, compared to DLB patients and in DBS of DLB patients, compared to AD patients. The discrimination accuracies of VBM were 63.3% in the test data set and 73.4% in the training data set. CONCLUSION: VBM of DBS in addition to that of MTL improves the differentiation of DLB and AD.

Young-Onset Dementia with Lewy Bodies.

Young-onset (< 65 years) dementia is a challenging clinical problem. A 61-year-old man visited our clinic because of a 2-year history of mild cognitive impairment of the executive disorder type. He was initially suspected of having young-onset Alzheimer's disease due to the lack of motor signs or hippocampal atrophy by conventional brain MRI. However, he proved to have anosmia, erectile dysfunction, hypersexuality, constipation, REM sleep behavior disorder, and emotional lability; imaging findings included positive brain perfusion SPECT, nigrosome MRI, DAT scan, and MIBG myocardial scintigraphy. All these clinical imaging features led to the correct diagnosis of young-onset dementia with Lewy bodies (YOD-DLB). It is hoped that this case report will help facilitate a future prospective study to diagnose and follow YOD-DLB patients with the aim of determining appropriate management and care.

Atypical Distribution of Late Gadolinium Enhancement of the Left Ventricle on Cardiac Magnetic Resonance in Classical Anderson-Fabry Disease.

Anderson-Fabry disease (AFD) is an X-linked lysosomal storage disorder caused by a deficiency of alpha-galactosidase A. Approximately 50% of patients with AFD may have cardiac involvement. Gadolinium-enhanced cardiac magnetic resonance (CMR) is useful for the diagnosis of cardiac involvement of AFD by recognizing typical late gadolinium enhancement (LGE) patterns. We report a 48-year-old man with cardiac involvement in classical AFD, showing atypical distribution of the LGE at the mid-lateral wall of left ventricle, predominantly apical segments without basal involvement on gadolinium-enhanced CMR.

Imaging spectrum of sporadic cerebral amyloid angiopathy: multifaceted features of a single pathological condition.

OBJECTIVES: Sporadic cerebral amyloid angiopathy (CAA) is common cause of cerebrovascular disorders that predominantly affect elderly patients. When symptomatic, cortical-subcortical intracerebral haemorrhage (ICH) in the elderly is the most well-known manifestation of CAA. Furthermore, the clinical presentation varies from a sudden neurological deficit to seizures, transient symptoms and acute progressive cognitive decline. Despite its clinical importance, this multifaceted nature poses a diagnostic challenge for radiologists. The aims of this study were to expound the characteristics of neuroimaging modalities, which cover a wide spectrum of CAA-related imaging findings, and to review the various abnormal findings for which CAA could be responsible. CONCLUSIONS: Radiologically, in addition to typical ICH, CAA leads to various types of abnormal findings, including microbleed, subarachnoid haemorrhage, superficial siderosis, microinfarction, reversible oedema, and irreversible leukoaraiosis. Taking into consideration the clinical importance of CAA-related disorders such as haemorrhagic risks and treatable oedema, it is necessary for radiologists to understand the wide spectrum of CAA-related imaging findings. TEACHING POINTS: • To describe the characteristics of imaging modalities and findings of CAA-related disorders. • MRI, especially gradient echo sequences, provides the useful information of CAA-related haemosiderin depositions. • To understand the wide spectrum of CAA-related neuroimaging and clinical features is important.

IgG4-related inflammatory pseudotumors mimicking multiple meningiomas.

IgG4-related disease is an emerging clinicopathologic entity. Hypophysitis, diffuse thickening of dura, and enlargement of the trigeminal nerve are well-known intracranial involvements of IgG4-related disease. This report of a case of systemic IgG4-related disease is the first to present neuroimaging of apparent supratentorial meningioma-like lesions and thickening and contrast enhancement of the walls of the intracranial internal carotid arteries. It is important to recognize IgG4-related intracranial pseudotumors so that patients do not undergo unnecessary surgical procedures.

Clinical value of routine use of thin-section 3D MRI using 3D FSE sequences with a variable flip angle technique for internal derangements of the knee joint at 3T.

PURPOSE: To determine the clinical value of routine use of thin-section 3D MRI using 3D FSE sequences with a variable flip angle technique for internal derangements of the knee joint at 3T. METHOD AND MATERIALS: Thirty-four knees in 34 patients suspected of having internal derangements of the knee joint were included. Following standard 2D MRI protocol including sagittal PDWI, T1WI and T2*WI, coronal fat-suppressed PDWI, and axial fat-suppressed PDWI with 3-4mm thicknesses, fat-suppressed and water-excitation PDWI using 3D FSE sequences with a variable flip angle technique with 0.6mm thickness were obtained in coronal plane and the three major planes with 1mm thickness (3D MRI) was reformatted. The standard 2D MRI protocol and reformatted 3D MRI protocol (three sagittal 2D sequence images plus 3D MRI) were independently analyzed by two radiologists concerning presence or absence of lesions in the menisci, cartilage, and ligament. Interobserver agreements in both the MRI protocols were assessed by weighted-kappa coefficients. Regarding diagnostic accuracy, areas under the receiver operating characteristic curves (Az values) of both the MRI protocols were compared. RESULTS: Thirty-eight meniscal lesions, 39 cartilage lesions, and 20 ligamentous lesions were surgically detected. Excellent interobserver agreements (kappa=0.91-0.98) were seen in both the MRI protocols, with a slightly better tendency in the reformatted 3D MRI protocol. Average Az values in detection of the meniscal, cartilage, and ligamentous lesions were significantly higher in the reformatted 3D MRI protocol than in the standard 2D MRI protocol (p<0.01 or p<0.001). CONCLUSION: Routine use of reformatted thin-section 3D MRI using 3D FSE sequences with a variable flip angle technique may improve diagnostic accuracy and confidence in detection of internal derangements of the knee joint.