Development and validation of an automatic classification algorithm for the diagnosis of Alzheimer's disease using a high-performance interpretable deep learning network.

OBJECTIVES: To develop and validate an automatic classification algorithm for diagnosing Alzheimer's disease (AD) or mild cognitive impairment (MCI). METHODS AND MATERIALS: This study evaluated a high-performance interpretable network algorithm (TabNet) and compared its performance with that of XGBoost, a widely used classifier. Brain segmentation was performed using a commercially approved software. TabNet and XGBoost were trained on the volumes or radiomics features of 102 segmented regions for classifying subjects into AD, MCI, or cognitively normal (CN) groups. The diagnostic performances of the two algorithms were compared using areas under the curves (AUCs). Additionally, 20 deep learning-based AD signature areas were investigated. RESULTS: Between December 2014 and March 2017, 161 AD, 153 MCI, and 306 CN cases were enrolled. Another 120 AD, 90 MCI, and 141 CN cases were included for the internal validation. Public datasets were used for external validation. TabNet with volume features had an AUC of 0.951 (95% confidence interval [CI], 0.947-0.955) for AD vs CN, which was similar to that of XGBoost (0.953 [95% CI, 0.951-0.955], p = 0.41). External validation revealed the similar performances of two classifiers using volume features (0.871 vs. 0.871, p = 0.86). Likewise, two algorithms showed similar performances with one another in classifying MCI. The addition of radiomics data did not improve the performance of TabNet. TabNet and XGBoost focused on the same 13/20 regions of interest, including the hippocampus, inferior lateral ventricle, and entorhinal cortex. CONCLUSIONS: TabNet shows high performance in AD classification and detailed interpretation of the selected regions. CLINICAL RELEVANCE STATEMENT: Using a high-performance interpretable deep learning network, the automatic classification algorithm assisted in accurate Alzheimer's disease detection using 3D T1-weighted brain MRI and detailed interpretation of the selected regions. KEY POINTS: • MR volumetry data revealed that TabNet had a high diagnostic performance in differentiating Alzheimer's disease (AD) from cognitive normal cases, which was comparable with that of XGBoost. • The addition of radiomics data to the volume data did not improve the diagnostic performance of TabNet. • Both TabNet and XGBoost selected the clinically meaningful regions of interest in AD, including the hippocampus, inferior lateral ventricle, and entorhinal cortex.

Added Value of Deep Learning-based Detection System for Multiple Major Findings on Chest Radiographs: A Randomized Crossover Study.

Background Previous studies assessing the effects of computer-aided detection on observer performance in the reading of chest radiographs used a sequential reading design that may have biased the results because of reading order or recall bias. Purpose To compare observer performance in detecting and localizing major abnormal findings including nodules, consolidation, interstitial opacity, pleural effusion, and pneumothorax on chest radiographs without versus with deep learning-based detection (DLD) system assistance in a randomized crossover design. Materials and Methods This study included retrospectively collected normal and abnormal chest radiographs between January 2016 and December 2017 (https://cris.nih.go.kr/; registration no. KCT0004147). The radiographs were randomized into two groups, and six observers, including thoracic radiologists, interpreted each radiograph without and with use of a commercially available DLD system by using a crossover design with a washout period. Jackknife alternative free-response receiver operating characteristic (JAFROC) figure of merit (FOM), area under the receiver operating characteristic curve (AUC), sensitivity, specificity, false-positive findings per image, and reading times of observers with and without the DLD system were compared by using McNemar and paired t tests. Results A total of 114 normal (mean patient age ± standard deviation, 51 years ± 11; 58 men) and 114 abnormal (mean patient age, 60 years ± 15; 75 men) chest radiographs were evaluated. The radiographs were randomized to two groups: group A (n = 114) and group B (n = 114). Use of the DLD system improved the observers' JAFROC FOM (from 0.90 to 0.95, P = .002), AUC (from 0.93 to 0.98, P = .002), per-lesion sensitivity (from 83% [822 of 990 lesions] to 89.1% [882 of 990 lesions], P = .009), per-image sensitivity (from 80% [548 of 684 radiographs] to 89% [608 of 684 radiographs], P = .009), and specificity (from 89.3% [611 of 684 radiographs] to 96.6% [661 of 684 radiographs], P = .01) and reduced the reading time (from 10-65 seconds to 6-27 seconds, P < .001). The DLD system alone outperformed the pooled observers (JAFROC FOM: 0.96 vs 0.90, respectively, P = .007; AUC: 0.98 vs 0.93, P = .003). Conclusion Observers including thoracic radiologists showed improved performance in the detection and localization of major abnormal findings on chest radiographs and reduced reading time with use of a deep learning-based detection system. © RSNA, 2021 Online supplemental material is available for this article.

Assessment of rapidly advancing bone age during puberty on elbow radiographs using a deep neural network model.

OBJECTIVES: Bone age is considered an indicator for the diagnosis of precocious or delayed puberty and a predictor of adult height. We aimed to evaluate the performance of a deep neural network model in assessing rapidly advancing bone age during puberty using elbow radiographs. METHODS: In all, 4437 anteroposterior and lateral pairs of elbow radiographs were obtained from pubertal individuals from two institutions to implement and validate a deep neural network model. The reference standard bone age was established by five trained researchers using the Sauvegrain method, a scoring system based on the shapes of the lateral condyle, trochlea, olecranon apophysis, and proximal radial epiphysis. A test set (n = 141) was obtained from an external institution. The differences between the assessment of the model and that of reviewers were compared. RESULTS: The mean absolute difference (MAD) in bone age estimation between the model and reviewers was 0.15 years on internal validation. In the test set, the MAD between the model and the five experts ranged from 0.19 to 0.30 years. Compared with the reference standard, the MAD was 0.22 years. Interobserver agreement was excellent among reviewers (ICC: 0.99) and between the model and the reviewers (ICC: 0.98). In the subpart analysis, the olecranon apophysis exhibited the highest accuracy (74.5%), followed by the trochlea (73.7%), lateral condyle (73.7%), and radial epiphysis (63.1%). CONCLUSIONS: Assessment of rapidly advancing bone age during puberty on elbow radiographs using our deep neural network model was similar to that of experts. KEY POINTS: • Bone age during puberty is particularly important for patients with scoliosis or limb-length discrepancy to determine the phase of the disease, which influences the timing and method of surgery. • The commonly used hand radiographs-based methods have limitations in assessing bone age during puberty due to the less prominent morphological changes of the hand and wrist bones in this period. • A deep neural network model trained with elbow radiographs exhibited similar performance to human experts on estimating rapidly advancing bone age during puberty.

Linear sign in cystic brain lesions ≥5 mm: A suggestive feature of perivascular space.

OBJECTIVE: To determine the prevalence of a linear sign within enlarged perivascular space (EPVS) and chronic lacunar infarction (CLI) ≥ 5 mm on T2-weighted imaging (T2WI) and time-of-flight (TOF) magnetic resonance angiography (MRA), and to evaluate the diagnostic value of the linear signs for EPVS over CLI. METHODS: This study included 101 patients with cystic lesions ≥ 5 mm on brain MRI including TOF MRA. After classification of cystic lesions into EPVS or CLI, two readers assessed linear signs on T2WI and TOF MRA. We compared the prevalence and the diagnostic performance of linear signs. RESULTS: Among 46 EPVS and 51 CLI, 84 lesions (86.6%) were in basal ganglia. The prevalence of T2 and TOF linear signs was significantly higher in the EPVS than in the CLI (P < .001). For the diagnosis of EPVS, T2 and TOF linear signs showed high sensitivity (> 80%). TOF linear sign showed significantly higher specificity (100%) and accuracy (92.8% and 90.7%) than T2 linear sign (P < .001). CONCLUSIONS: T2 and TOF linear signs were more frequently observed in EPVS than CLI. They showed high sensitivity in differentiation of them, especially for basal ganglia. TOF sign showed higher specificity and accuracy than T2 sign. KEY POINTS: • Linear sign is a suggestive feature of EPVS. • Time-of-flight magnetic resonance angiography can reveal the lenticulostriate artery within perivascular spaces. • Linear sign helps differentiation of EPVS and CLI, especially in basal ganglia.

Fatty rind of intramuscular soft-tissue tumors of the extremity: is it different from the split fat sign?

OBJECTIVE: To analyze intramuscular soft-tissue tumors with fatty rind, and to evaluate the difference between fatty rind and split fat sign on magnetic resonance imaging (MRI). MATERIALS AND METHODS: We retrospectively analyzed 50 pathologically confirmed intramuscular masses on MRI. We evaluated the distribution and shape of fatty rind and muscle atrophy. RESULTS: Fatty rind was found more frequently in benign lesions (80% [36 out of 45]) compared with malignant lesions (25% [1 out of 5]; P = 0.013). Thirty-six benign lesions were peripheral nerve sheath tumors (PNSTs; n = 19), hemangiomas (n = 11), myxomas (n = 2), ganglion cysts (n = 2), giant cell tumor (n = 1), and leiomyoma (n = 1). One malignant lesion was a low-grade fibromyxoid sarcoma. In all masses with fatty rind, fat was confined to the proximal and the distal ends. In 12 cases, complete or partial circumferential fatty rind was also noted. Fatty rinds at both ends showed crescent, triangular, or combined shape. The prevalence of crescent-shaped fatty rind was significantly higher in benign PNST (17 out of 38) compared with the other tumors (1 out of 32; P < 0.001). Complete circumferential fat was noted only in hemangioma (n = 5). Triangular fatty rind was related to peripheral location of the mass or muscle atrophy. CONCLUSION: Most intramuscular tumors with fatty rinds were benign, and PNST was the most common tumor type. Fatty rind could be caused by displaced neurovascular bundle fat, fatty atrophy of the muscle involved, or intermuscular or perimysial fat. Crescent-shaped fatty rind was noted more frequently in benign PNSTs.

Intravascular papillary endothelial hyperplasia: magnetic resonance imaging of finger lesions.

OBJECTIVE: To describe magnetic resonance imaging (MRI) features of intravascular papillary endothelial hyperplasia (IPEH), to identify findings differentiating IPEH of the finger from that of other locations, and to correlate these with pathology. MATERIALS AND METHODS: Nineteen patients with 20 I.E. masses of the finger (n = 13) and other locations (n = 7) were evaluated. All patients underwent MRI, and the results were correlated with pathology. RESULTS: Seventeen IPEHs, including all IPEHs of the finger, were located in the subcutis, the three other lesions in the muscle layer. On T1WI, all masses were isointense or slightly hyperintense. IPEHs of the finger (n = 13) revealed focal hyperintense nodules (n = 2) or central hypointensity (n = 2) on T1WI, hypointensity with a hyperintense rim (n = 7), hyperintensity with hypointense nodules (n = 5), or isointensity with a hypointense rim (n = 1) on T2WI, and rim enhancement (n = 5), heterogeneous enhancement with nodular nonenhanced areas (n = 6), peripheral nodular enhancement (n = 1), or no enhancement (n = 1) on gadolinium-enhanced T1WI. IPEHs of other locations (n = 7) demonstrated focal hyperintense nodules (n = 5) on T1WI, hyperintensity with hypointense nodules (n = 5) or heterogeneous signal intensity (n = 2) on T2WI, and rim or rim and septal enhancement (n = 6) or peripheral nodular enhancement (n = 1). Microscopically, IPEHs were composed of thrombi that were hypointense on T2WI and papillary endothelial proliferations that showed T2 hyperintensity and enhancement. CONCLUSION: MRI of finger IPEH reveals well-demarcated subcutaneous masses with hypointensity or hypointense nodules with peripheral hyperintensity on T2WI, as well as peripheral enhancement. T1 hyperintense nodules, internal heterogeneity on T2WI, and septal enhancement are more common in IPEH of other locations.

Non-stenotic intracranial arteries have atherosclerotic changes in acute ischemic stroke patients: a 3T MRI study.

INTRODUCTION: The aim of this study is to evaluate the degree of atherosclerotic changes in intracranial arteries by assessing arterial wall thickness using T1-weighted 3D-turbo spin echo (3D-TSE) and time-of-flight MR angiography (TOF-MRA) in patients with acute ischemic stroke as compared with unaffected controls. METHODS: Thirty-three patients with acute ischemic stroke and 36 control patients were analyzed. Acute ischemic stroke patients were divided according to TOAST classification. At both distal internal carotid arteries and basilar artery without stenosis, TOF-MRA was used to select non-stenotic portion of assessed arteries. 3D-TSE was used to measure the area including the lumen and wall (AreaOuter) and luminal area (AreaInner). The area of the vessel wall (AreaVW) of assessed intracranial arteries and the ratio index (RI) of each patient were determined. RESULTS: AreaInner, AreaOuter, AreaVW, and RI showed good inter-observer reliability and excellent intra-observer reliability. AreaInner did not significantly differ between stroke patients and controls (P = 0.619). However, AreaOuter, AreaVW, and RI were significantly larger in stroke patients (P < 0.001). The correlation coefficient between AreaInner and AreaOuter was higher in the controls (r = 0.918) than in large vessel disease patients (r = 0.778). RI of large vessel disease patients was significantly higher than that of normal control, small vessel disease, and cardioembolic groups. CONCLUSION: In patients with acute ischemic stroke, wall thickening and positive remodeling are evident in non-stenotic intracranial arteries. This change is more definite in stroke subtype that is related to atherosclerosis than that in other subtypes which are not.

A Case-Control Clinical Trial on a Deep Learning-Based Classification System for Diagnosis of Amyloid-Positive Alzheimer's Disease.

OBJECTIVE: A deep learning-based classification system (DLCS) which uses structural brain magnetic resonance imaging (MRI) to diagnose Alzheimer's disease (AD) was developed in a previous recent study. Here, we evaluate its performance by conducting a single-center, case-control clinical trial. METHODS: We retrospectively collected T1-weighted brain MRI scans of subjects who had an accompanying measure of amyloid-beta (Aß) positivity based on a 18F-florbetaben positron emission tomography scan. The dataset included 188 Aß-positive patients with mild cognitive impairment or dementia due to AD, and 162 Aß-negative controls with normal cognition. We calculated the sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC) of the DLCS in the classification of Aß-positive AD patients from Aß-negative controls. RESULTS: The DLCS showed excellent performance, with sensitivity, specificity, positive predictive value, negative predictive value, and AUC of 85.6% (95% confidence interval [CI], 79.8-90.0), 90.1% (95% CI, 84.5-94.2), 91.0% (95% CI, 86.3-94.1), 84.4% (95% CI, 79.2-88.5), and 0.937 (95% CI, 0.911-0.963), respectively. CONCLUSION: The DLCS shows promise in clinical settings where it could be routinely applied to MRI scans regardless of original scan purpose to improve the early detection of AD.

Bone Age Assessment Using Artificial Intelligence in Korean Pediatric Population: A Comparison of Deep-Learning Models Trained With Healthy Chronological and Greulich-Pyle Ages as Labels.

OBJECTIVE: To develop a deep-learning-based bone age prediction model optimized for Korean children and adolescents and evaluate its feasibility by comparing it with a Greulich-Pyle-based deep-learning model. MATERIALS AND METHODS: A convolutional neural network was trained to predict age according to the bone development shown on a hand radiograph (bone age) using 21036 hand radiographs of Korean children and adolescents without known bone development-affecting diseases/conditions obtained between 1998 and 2019 (median age [interquartile range {IQR}], 9 [7-12] years; male:female, 11794:9242) and their chronological ages as labels (Korean model). We constructed 2 separate external datasets consisting of Korean children and adolescents with healthy bone development (Institution 1: n = 343; median age [IQR], 10 [4-15] years; male: female, 183:160; Institution 2: n = 321; median age [IQR], 9 [5-14] years; male: female, 164:157) to test the model performance. The mean absolute error (MAE), root mean square error (RMSE), and proportions of bone age predictions within 6, 12, 18, and 24 months of the reference age (chronological age) were compared between the Korean model and a commercial model (VUNO Med-BoneAge version 1.1; VUNO) trained with Greulich-Pyle-based age as the label (GP-based model). RESULTS: Compared with the GP-based model, the Korean model showed a lower RMSE (11.2 vs. 13.8 months; P = 0.004) and MAE (8.2 vs. 10.5 months; P = 0.002), a higher proportion of bone age predictions within 18 months of chronological age (88.3% vs. 82.2%; P = 0.031) for Institution 1, and a lower MAE (9.5 vs. 11.0 months; P = 0.022) and higher proportion of bone age predictions within 6 months (44.5% vs. 36.4%; P = 0.044) for Institution 2. CONCLUSION: The Korean model trained using the chronological ages of Korean children and adolescents without known bone development-affecting diseases/conditions as labels performed better in bone age assessment than the GP-based model in the Korean pediatric population. Further validation is required to confirm its accuracy.

Re-Assessment of Applicability of Greulich and Pyle-Based Bone Age to Korean Children Using Manual and Deep Learning-Based Automated Method.

PURPOSE: To evaluate the applicability of Greulich-Pyle (GP) standards to bone age (BA) assessment in healthy Korean children using manual and deep learning-based methods. MATERIALS AND METHODS: We collected 485 hand radiographs of healthy children aged 2-17 years (262 boys) between 2008 and 2017. Based on GP method, BA was assessed manually by two radiologists and automatically by two deep learning-based BA assessment (DLBAA), which estimated GP-assigned (original model) and optimal (modified model) BAs. Estimated BA was compared to chronological age (CA) using intraclass correlation (ICC), Bland-Altman analysis, linear regression, mean absolute error, and root mean square error. The proportion of children showing a difference >12 months between the estimated BA and CA was calculated. RESULTS: CA and all estimated BA showed excellent agreement (ICC ≥0.978, p<0.001) and significant positive linear correlations (R²≥0.935, p<0.001). The estimated BA of all methods showed systematic bias and tended to be lower than CA in younger patients, and higher than CA in older patients (regression slopes ≤-0.11, p<0.001). The mean absolute error of radiologist 1, radiologist 2, original, and modified DLBAA models were 13.09, 13.12, 11.52, and 11.31 months, respectively. The difference between estimated BA and CA was >12 months in 44.3%, 44.5%, 39.2%, and 36.1% for radiologist 1, radiologist 2, original, and modified DLBAA models, respectively. CONCLUSION: Contemporary healthy Korean children showed different rates of skeletal development than GP standard-BA, and systemic bias should be considered when determining children's skeletal maturation.

Diagnostic performance of deep learning-based automatic white matter hyperintensity segmentation for classification of the Fazekas scale and differentiation of subcortical vascular dementia.

PURPOSE: To validate the diagnostic performance of commercially available, deep learning-based automatic white matter hyperintensity (WMH) segmentation algorithm for classifying the grades of the Fazekas scale and differentiating subcortical vascular dementia. METHODS: This retrospective, observational, single-institution study investigated the diagnostic performance of a deep learning-based automatic WMH volume segmentation to classify the grades of the Fazekas scale and differentiate subcortical vascular dementia. The VUNO Med-DeepBrain was used for the WMH segmentation system. The system for segmentation of WMH was designed with convolutional neural networks, in which the input image was comprised of a pre-processed axial FLAIR image, and the output was a segmented WMH mask and its volume. Patients presented with memory complaint between March 2017 and June 2018 were included and were split into training (March 2017-March 2018, n = 596) and internal validation test set (April 2018-June 2018, n = 204). RESULTS: Optimal cut-off values to categorize WMH volume as normal vs. mild/moderate/severe, normal/mild vs. moderate/severe, and normal/mild/moderate vs. severe were 3.4 mL, 9.6 mL, and 17.1 mL, respectively, and the AUC were 0.921, 0.956 and 0.960, respectively. When differentiating normal/mild vs. moderate/severe using WMH volume in the test set, sensitivity, specificity, and accuracy were 96.4%, 89.9%, and 91.7%, respectively. For distinguishing subcortical vascular dementia from others using WMH volume, sensitivity, specificity, and accuracy were 83.3%, 84.3%, and 84.3%, respectively. CONCLUSION: Deep learning-based automatic WMH segmentation may be an accurate and promising method for classifying the grades of the Fazekas scale and differentiating subcortical vascular dementia.

Origin of Satellite Ganglion Cysts with Effusion in the Flexor Hallucis Longus Tendon Sheath around the Hallux.

BACKGROUND: To describe the clinical and magnetic resonance imaging findings of ganglion cysts with effusion in the flexor hallucis longus tendon sheath around the hallux to evaluate their origin. METHODS: Patients with recurrent or painful ganglion cysts around the hallux with effusion in the flexor hallucis longus tendon sheath who underwent surgical treatment at St. Vincent's Hospital from February 2007 to August 2016 were investigated. Surgical indication was a painful or recurrent mass caused by the cystic lesions. Those without effusion of the flexor hallucis longus tendon sheath were excluded. We assessed the clinical and magnetic resonance imaging findings. RESULTS: Magnetic resonance imaging findings in all patients showed several ganglion cysts around the hallux and large fluid accumulations within the flexor hallucis longus tendon sheath. Regarding the location, six ganglion cysts were on the dorsomedial aspect, one on the plantar medial aspect, seven on the plantar lateral aspect, and one in the toe pulp. Ten patients showed joint effusions in both the metatarsophalangeal and interphalangeal joints, two in the metatarsophalangeal joints, and three in the interphalangeal joints. There were communication stalks with a tail shape or abutment between ganglion cysts with surrounding joint effusions. Intraoperatively, connections between ganglion cysts, the synovial cyst of the flexor hallucis longus tendon sheath, and surrounding joints were seen. CONCLUSIONS: Synovial fluid accumulation in the metatarsophalangeal or interphalangeal joint supplies the synovial cyst of the flexor hallucis longus tendon sheath and subsequently ganglion cysts in the hallux. In clinical practice, the surgeon should carefully check surrounding joints with tendon sheaths to prevent recurrence of the ganglion cysts around the hallux.

Differentiation of multiple myeloma and metastases: Use of axial diffusion-weighted MR imaging in addition to standard MR imaging at 3T.

BACKGROUND: Metastasis and multiple myeloma are common malignant bone marrow lesions which may be difficult to distinguish because of similar imaging findings. The purpose of this study was to determine the value of adding diffusion-weighted imaging (DWI) to standard MR imaging to differentiate multiple myeloma from metastasis. METHODS: 25 patients with metastasis and 18 patients with multiple myeloma underwent 3T MR imaging with DWI (b = 0, 800 s/mm2) were enrolled. They all had pathologically confirmed bone lesions and were in a treatment naïve state. Two readers who were blind of final diagnosis measured the average ADC (ADCav) and minimum ADC (ADCmin) on the DWI. They then estimated the diagnosis, based on the standard MR imaging and measured ADC values. Another reader performed histogram analysis on the whole tumor volume and obtained mean ADC (ADCvol), standard deviation (SDvol), skewness, and kurtosis. Comparison of the obtained values from DWI was performed by the t-test or Mann-Whitney U test. The receiver operating characteristic (ROC) curve with areas under the curve (AUC) was used to obtain the cut off values and to evaluate the diagnostic performance of the two readers. RESULTS: ADCav, ADCmin, and ADCvol of multiple myeloma were significantly lower than those of metastasis: ADCav, 752 µm2/sec versus 1081 µm2/sec; ADCmin, 704 µm2/sec vs 835 µm2/sec; ADCvol 761 µm2/sec vs 1184 µm2/sec (p < .001). In histogram analysis, ADC values of multiple myeloma showed narrow distribution than metastasis: SDvol, 144 vs 257 (p < .001). Areas under the receiver operating characteristic curve was significantly higher with additive DWI than standard MR alone: 0.762 vs 0.953; 0.706 vs 0.950 (p < .05) for two readers. CONCLUSIONS: This study suggested that the addition of axial DWI to standard MR imaging can be helpful to diagnose multiple myeloma from metastasis at 3T.

Diagnosis of Nerve Root Compromise of the Lumbar Spine: Evaluation of the Performance of Three-dimensional Isotropic T2-weighted Turbo Spin-Echo SPACE Sequence at 3T.

OBJECTIVE: To explore the performance of three-dimensional (3D) isotropic T2-weighted turbo spin-echo (TSE) sampling perfection with application optimized contrasts using different flip angle evolution (SPACE) sequence on a 3T system, for the evaluation of nerve root compromise by disc herniation or stenosis from central to extraforaminal location of the lumbar spine, when used alone or in combination with conventional two-dimensional (2D) TSE sequence. MATERIALS AND METHODS: Thirty-seven patients who had undergone 3T spine MRI including 2D and 3D sequences, and had subsequent spine surgery for nerve root compromise at a total of 39 nerve levels, were analyzed. A total of 78 nerve roots (48 symptomatic and 30 asymptomatic sites) were graded (0 to 3) using different MRI sets of 2D, 3D (axial plus sagittal), 3D (all planes), and combination of 2D and 3D sequences, with respect to the nerve root compromise caused by posterior disc herniations, lateral recess stenoses, neural foraminal stenoses, or extraforaminal disc herniations; grading was done independently by two readers. Diagnostic performance was compared between different imaging sets using the receiver operating characteristics (ROC) curve analysis. RESULTS: There were no statistically significant differences (p = 0.203 to > 0.999) in the ROC curve area between the imaging sets for both readers 1 and 2, except for combined 2D and 3D (0.843) vs. 2D (0.802) for reader 1 (p = 0.035), and combined 2D and 3D (0.820) vs. 3D including all planes (0.765) for reader 2 (p = 0.049). CONCLUSION: The performance of 3D isotropic T2-weighted TSE sequence of the lumbar spine, whether axial plus sagittal images, or all planes of images, was not significantly different from that of 2D TSE sequences, for the evaluation of nerve root compromise of the lumbar spine. Combining 2D and 3D might possibly improve the diagnostic accuracy compared with either one.

Subtraction MR Venography Acquired from Time-Resolved Contrast-Enhanced MR Angiography: Comparison with Phase-Contrast MR Venography and Single-Phase Contrast-Enhanced MR Venography.

OBJECTIVE: To evaluate the image characteristics of subtraction magnetic resonance venography (SMRV) from time-resolved contrast-enhanced MR angiography (TRMRA) compared with phase-contrast MR venography (PCMRV) and single-phase contrast-enhanced MR venography (CEMRV). MATERIALS AND METHODS: Twenty-one patients who underwent brain MR venography (MRV) using standard protocols (PCMRV, CEMRV, and TRMRA) were included. SMRV was made by subtracting the arterial phase data from the venous phase data in TRMRA. Co-registration and subtraction of the two volume data was done using commercially available software. Image quality and the degree of arterial contamination of the three MRVs were compared. In the three MRVs, 19 pre-defined venous structures (14 dural sinuses and 5 cerebral veins) were evaluated. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of the three MRVs were also compared. RESULTS: Single-phase contrast-enhanced MR venography showed better image quality (median score 4 in both reviewers) than did the other two MRVs (p < 0.001), whereas SMRV (median score 3 in both reviewers) and PCMRV (median score 3 in both reviewers) had similar image quality (p ≥ 0.951). SMRV (median score 0 in both reviewers) suppressed arterial signal better than did the other MRVs (median score 1 in CEMRV, median score 2 in PCMRV, both reviewers) (p < 0.001). The dural sinus score of SMRV (median and interquartile range [IQR] 48, 43-50 for reviewer 1, 47, 43-49 for reviewer 2) was significantly higher than for PCMRV (median and IQR 31, 25-34 for reviewer 1, 30, 23-32 for reviewer 2) (p < 0.01) and did not differ from that of CEMRV (median and IQR 50, 47-52 for reviewer 1, 49, 45-51 for reviewer 2) (p = 0.146 in reviewer 1 and 0.123 in reviewer 2). The SNR and CNR of SMRV (median and IQR 104.5, 83.1-121.2 and 104.1, 74.9-120.5, respectively) were between those of CEMRV (median and IQR 150.3, 111-182.6 and 148.4, 108-178.2) and PCMRV (median and IQR 59.4, 49.2-74.9 and 53.6, 43.8-69.2). CONCLUSION: Subtraction magnetic resonance venography is a promising MRV method, with acceptable image quality and good arterial suppression.