Imaging of the extracranial internal carotid artery in acute ischemic stroke: assessment of stenosis, plaques, and image quality using relaxation-enhanced angiography without contrast and triggering (REACT).

Background: In stroke magnetic resonance imaging (MRI), contrast-enhanced magnetic resonance angiography (CE-MRA) is the clinical standard to depict extracranial arteries but native MRA techniques are of increased interest to facilitate clinical practice. The purpose of this study was to assess the detection of extracranial internal carotid artery (ICA) stenosis and plaques as well as the image quality of cervical carotid arteries between a novel flow-independent relaxation-enhanced angiography without contrast and triggering (REACT) sequence and CE-MRA in acute ischemic stroke (AIS). Methods: In this retrospective, single-center study, 105 consecutive patients (65.27±18.74 years, 63 males) were included, who received a standard stroke protocol at 3T in clinical routine including Compressed SENSE (CS) accelerated (factor 4) 3D isotropic REACT (fixed scan time: 02:46 min) and CS accelerated (factor 6) 3D isotropic CE-MRA. Three radiologists independently assessed scans for the presence of extracranial ICA stenosis and plaques (including hyper-/hypointense signal) with concomitant diagnostic confidence using 3-point scales (3= excellent). Vessel quality, artifacts, and image noise of extracranial carotid arteries were subjectively scored on 5-point scales (5= excellent/none). Wilcoxon tests were used for statistical comparison. Results: Considering CE-MRA as the standard of reference, REACT provided a sensitivity of 89.8% and specificity of 95.2% for any and of 93.5% and 95.8% for clinically relevant (≥50%) extracranial ICA stenosis and yielded a to CE-MRA comparable diagnostic confidence [mean ± standard deviation (SD), median (interquartile range): 2.8±0.5, 3 (3-3) vs. 2.7±0.5, 3 (2-3), P=0.03]. Using REACT, readers detected more plaques overall (n=57.3 vs. 47.7, P<0.001) and plaques of hyperintense signal (n=12.3 vs. 5.7, P=0.02) with higher diagnostic confidence [2.8±0.5, 3 (3-3) vs. 2.6±0.7, 3 (2-3), P<0.001] than CE-MRA. After analyzing a total of 1,260 segments, the vessel quality of all segments combined [4.61±0.66 vs. 4.58±0.68, 5 (4-5) vs. 5 (4-5), P=0.0299] and artifacts [4.51±0.70 vs. 4.44±0.73, 5 (4-5) vs. 5 (4-5), P>0.05] were comparable between the sequences with REACT showing a lower image noise [4.43±0.67 vs. 4.25±0.71, 5 (4-5) vs. 4 (4-5), P<0.001]. Conclusions: Without the use of gadolinium-based contrast agents or triggering, REACT provides a high sensitivity and specificity for extracranial ICA stenosis and a potential improved depiction of adjacent plaques while yielding to CE-MRA comparable vessel quality in a large patient cohort with AIS.

Fully Automated MR Detection and Segmentation of Brain Metastases in Non-small Cell Lung Cancer Using Deep Learning.

BACKGROUND: Non-small cell lung cancer (NSCLC) is the most common tumor entity spreading to the brain and up to 50% of patients develop brain metastases (BMs). Detection of BMs on MRI is challenging with an inherent risk of missed diagnosis. PURPOSE: To train and evaluate a deep learning model (DLM) for fully automated detection and 3D segmentation of BMs in NSCLC on clinical routine MRI. STUDY TYPE: Retrospective. POPULATION: Ninety-eight NSCLC patients with 315 BMs on pretreatment MRI, divided into training (66 patients, 248 BMs) and independent test (17 patients, 67 BMs) and control (15 patients, 0 BMs) cohorts. FIELD STRENGTH/SEQUENCE: T1 -/T2 -weighted, T1 -weighted contrast-enhanced (T1 CE; gradient-echo and spin-echo sequences), and FLAIR at 1.0, 1.5, and 3.0 T from various vendors and study centers. ASSESSMENT: A 3D convolutional neural network (DeepMedic) was trained on the training cohort using 5-fold cross-validation and evaluated on the independent test and control sets. Three-dimensional voxel-wise manual segmentations of BMs by a neurosurgeon and a radiologist on T1 CE served as the reference standard. STATISTICAL TESTS: Sensitivity (recall) and false positive (FP) findings per scan, dice similarity coefficient (DSC) to compare the spatial overlap between manual and automated segmentations, Pearson's correlation coefficient (r) to evaluate the relationship between quantitative volumetric measurements of segmentations, and Wilcoxon rank-sum test to compare the volumes of BMs. A P value <0.05 was considered statistically significant. RESULTS: In the test set, the DLM detected 57 of the 67 BMs (mean volume: 0.99 ± 4.24 cm3 ), resulting in a sensitivity of 85.1%, while FP findings of 1.5 per scan were observed. Missed BMs had a significantly smaller volume (0.05 ± 0.04 cm3 ) than detected BMs (0.96 ± 2.4 cm3 ). Compared with the reference standard, automated segmentations achieved a median DSC of 0.72 and a good volumetric correlation (r = 0.95). In the control set, 1.8 FPs/scan were observed. DATA CONCLUSION: Deep learning provided a high detection sensitivity and good segmentation performance for BMs in NSCLC on heterogeneous scanner data while yielding a low number of FP findings. Level of Evidence 3 Technical Efficacy Stage 2.

Deep learning assistance increases the detection sensitivity of radiologists for secondary intracranial aneurysms in subarachnoid hemorrhage.

PURPOSE: To evaluate whether a deep learning model (DLM) could increase the detection sensitivity of radiologists for intracranial aneurysms on CT angiography (CTA) in aneurysmal subarachnoid hemorrhage (aSAH). METHODS: Three different DLMs were trained on CTA datasets of 68 aSAH patients with 79 aneurysms with their outputs being combined applying ensemble learning (DLM-Ens). The DLM-Ens was evaluated on an independent test set of 104 aSAH patients with 126 aneuryms (mean volume 129.2 ± 185.4 mm3, 13.0% at the posterior circulation), which were determined by two radiologists and one neurosurgeon in consensus using CTA and digital subtraction angiography scans. CTA scans of the test set were then presented to three blinded radiologists (reader 1: 13, reader 2: 4, and reader 3: 3 years of experience in diagnostic neuroradiology), who assessed them individually for aneurysms. Detection sensitivities for aneurysms of the readers with and without the assistance of the DLM were compared. RESULTS: In the test set, the detection sensitivity of the DLM-Ens (85.7%) was comparable to the radiologists (reader 1: 91.2%, reader 2: 86.5%, and reader 3: 86.5%; Fleiss κ of 0.502). DLM-assistance significantly increased the detection sensitivity (reader 1: 97.6%, reader 2: 97.6%,and reader 3: 96.0%; overall P=.024; Fleiss κ of 0.878), especially for secondary aneurysms (88.2% of the additional aneurysms provided by the DLM). CONCLUSION: Deep learning significantly improved the detection sensitivity of radiologists for aneurysms in aSAH, especially for secondary aneurysms. It therefore represents a valuable adjunct for physicians to establish an accurate diagnosis in order to optimize patient treatment.

The Woven EndoBridge (WEB) Versus Conventional Coiling for Treatment of Patients with Aneurysmal Subarachnoid Hemorrhage: Propensity Score-Matched Analysis of Clinical and Angiographic Outcome Data.

OBJECTIVE: Conventional coiling is standard for treatment of ruptured intracranial aneurysms. We compared clinical and angiographic outcomes between intrasaccular flow disruption with the Woven EndoBridge (WEB) and conventional coiling in patients with aneurysmal subarachnoid hemorrhage (aSAH) using a propensity score-matched analysis. METHODS: This is a retrospective study of consecutive patients with aSAH treated with the WEB or conventional coiling between 2010 and 2019. Baseline characteristics, procedural complications, angiographic results, and functional outcome were compared between both groups. RESULTS: Fifty-two patients treated with the WEB and 236 patients treated by coiling were included. The WEB group was characterized by a higher patient age (P = 0.024), a wider aneurysm neck (P < 0.001), and more frequent location at the posterior circulation (P = 0.004). Procedural complications were comparable between WEB (19.2%) and coiling (22.7%, P = 0.447). In-hospital mortality rates were higher in the coiling group (WEB: 5.8%, coiling: 17.8%; P = 0.0034). Favorable outcome (modified Rankin scale ≤2) was obtained in 51.3% after WEB embolization and in 55.0% after coiling (P = 0.653). Retreatment was performed in 26.4% of patients after WEB and in 25.8% after coiling (P = 0.935). Propensity score analysis confirmed these results and revealed higher adequate occlusion rates at midterm follow-up for WEB-treated aneurysms (WEB: 93.9%, coiling: 76.2%, P = 0.058). CONCLUSIONS: Compared with conventional coiling, aSAH patients treated with the WEB have a similar clinical and potentially improved angiographic outcome at midterm follow-up. The WEB might be considered as an alternative to conventional coiling for the treatment of RIAs, in particular for those with wide-necked and thus challenging anatomy.

Relaxation-Enhanced Angiography Without Contrast and Triggering (REACT) for Fast Imaging of Extracranial Arteries in Acute Ischemic Stroke at 3 T.

PURPOSE: To evaluate a novel flow-independent 3D isotropic REACT sequence compared with CE-MRA for the imaging of extracranial arteries in acute ischemic stroke (AIS). METHODS: This was a retrospective study of 35 patients who underwent a stroke protocol at 3 T including REACT (fixed scan time: 2:46 min) and CE-MRA of the extracranial arteries. Three radiologists evaluated scans regarding vessel delineation, signal, and contrast and assessed overall image noise and artifacts using 5-point scales (5: excellent delineation/no artifacts). Apparent signal- and contrast-to-noise ratios (aSNR/aCNR) were measured for the common carotid artery (CCA), internal carotid artery (ICA, C1 segment), and vertebral artery (V2 segment). Two radiologists graded the degree of proximal ICA stenosis. RESULTS: Compared to REACT, CE-MRA showed better delineation for the CCA and ICA (C1 and C2 segments) (median 5, range 2-5 vs. 4, range 3-5; P < 0.05). For the ICA (C1 and C2 segments), REACT provided a higher signal (5, range 3-5; P < 0.05/4.5, range 3-5; P > 0.05 vs. 4, range 2-5) and contrast (5, range 3-5 vs. 4, range 2-5; P > 0.05) than CE-MRA. The remaining segments of the blood-supplying vessels showed equal medians. There was no significant difference regarding artifacts, whereas REACT provided significantly lower image noise (4, range 3-5 vs. 4 range 2-5; P < 0.05) with a higher aSNR (P < 0.05) and aCNR (P < 0.05) for all vessels combined. For clinically relevant (≥50%) ICA stenosis, REACT achieved a detection sensitivity of 93.75% and a specificity of 100%. CONCLUSION: Given its fast acquisition, comparable image quality to CE-MRA and high sensitivity and specificity for the detection of ICA stenosis, REACT was proven to be a clinically applicable method to assess extracranial arteries in AIS.

Primary Central Nervous System Lymphoma: Clinical Evaluation of Automated Segmentation on Multiparametric MRI Using Deep Learning.

BACKGROUND: Precise volumetric assessment of brain tumors is relevant for treatment planning and monitoring. However, manual segmentations are time-consuming and impeded by intra- and interrater variabilities. PURPOSE: To investigate the performance of a deep-learning model (DLM) to automatically detect and segment primary central nervous system lymphoma (PCNSL) on clinical MRI. STUDY TYPE: Retrospective. POPULATION: Sixty-nine scans (at initial and/or follow-up imaging) from 43 patients with PCNSL referred for clinical MRI tumor assessment. FIELD STRENGTH/SEQUENCE: T1 -/T2 -weighted, T1 -weighted contrast-enhanced (T1 CE), and FLAIR at 1.0, 1.5, and 3.0T from different vendors and study centers. ASSESSMENT: Fully automated voxelwise segmentation of tumor components was performed using a 3D convolutional neural network (DeepMedic) trained on gliomas (n = 220). DLM segmentations were compared to manual segmentations performed in a 3D voxelwise manner by two readers (radiologist and neurosurgeon; consensus reading) from T1 CE and FLAIR, which served as the reference standard. STATISTICAL TESTS: Dice similarity coefficient (DSC) for comparison of spatial overlap with the reference standard, Pearson's correlation coefficient (r) to assess the relationship between volumetric measurements of segmentations, and Wilcoxon rank-sum test for comparison of DSCs obtained in initial and follow-up imaging. RESULTS: The DLM detected 66 of 69 PCNSL, representing a sensitivity of 95.7%. Compared to the reference standard, DLM achieved good spatial overlap for total tumor volume (TTV, union of tumor volume in T1 CE and FLAIR; average size 77.16 ± 62.4 cm3 , median DSC: 0.76) and tumor core (contrast enhancing tumor in T1 CE; average size: 11.67 ± 13.88 cm3 , median DSC: 0.73). High volumetric correlation between automated and manual segmentations was observed (TTV: r = 0.88, P < 0.0001; core: r = 0.86, P < 0.0001). Performance of automated segmentations was comparable between pretreatment and follow-up scans without significant differences (TTV: P = 0.242, core: P = 0.177). DATA CONCLUSION: In clinical MRI scans, a DLM initially trained on gliomas provides segmentation of PCNSL comparable to manual segmentation, despite its complex and multifaceted appearance. Segmentation performance was high in both initial and follow-up scans, suggesting its potential for application in longitudinal tumor imaging. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 2.

MRI Follow-up of Astrocytoma: Automated Coregistration and Color-Coding of FLAIR Sequences Improves Diagnostic Accuracy With Comparable Reading Time.

BACKGROUND: MRI follow-up is widely used for longitudinal assessment of astrocytoma, yet reading can be tedious and error-prone, in particular when changes are subtle. PURPOSE/HYPOTHESIS: To determine the effect of automated, color-coded coregistration (AC) of fluid attenuated inversion recovery (FLAIR) sequences on diagnostic accuracy, certainty, and reading time compared to conventional follow-up MRI assessment of astrocytoma patients. STUDY TYPE: Retrospective. POPULATION: In all, 41 patients with neuropathologically confirmed astrocytoma. FIELD STRENGTH/SEQUENCE: 1.0-3.0T/FLAIR ASSESSMENT: The presence or absence of tumor progression was determined based on FLAIR sequences, contrast-enhanced T1 sequences, and clinical data. Three radiologists assessed 47 MRI study pairs in a conventional reading (CR) and in a second reading supported by AC after 6 weeks. Readers determined the presence/absence of tumor progression and indicated diagnostic certainty on a 5-point Likert scale. Reading time was recorded by an independent assessor. STATISTICAL TESTS: The Wilcoxon test was used to assess reading time and diagnostic certainty. Differences in diagnostic accuracy, sensitivity, and specificity were analyzed with the McNemar mid-p test. RESULTS: Readers attained significantly higher overall sensitivity (0.86 vs. 0.75; P < 0.05) and diagnostic accuracy (0.84 vs. 0.73; P < 0.05) for detection of progressive nonenhancing tumor burden when using AC compared to CR. There was a strong trend towards higher specificity within the AC-augmented reading, yet without statistical significance (0.83 vs. 0.71; P = 0.08). Sensitivity for unequivocal disease progression was similarly high in both approaches (AC: 0.94, CR: 0.92), while for marginal disease progressions, it was significantly higher in AC (AC: 0.78, CR: 0.58; P < 0.05). Reading time including application loading time was comparable (AC: 38.1 ± 16.8 sec, CR: 36.0 ± 18.9 s; P = 0.25). DATA CONCLUSION: Compared to CR, AC improves comparison of FLAIR signal hyperintensity at MRI follow-up of astrocytoma patients, allowing for a significantly higher diagnostic accuracy, particularly for subtle disease progression at a comparable reading time. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY STAGE: 6 J. Magn. Reson. Imaging 2020;52:1197-1206.