Automated Detection of Cerebral Aneurysms on TOF-MRA Using a Deep Learning Approach: An External Validation Study.

BACKGROUND AND PURPOSE: Cerebral aneurysms yield the risk of rupture, severe disability and death. Thus, early detection of cerebral aneurysms is crucial to ensure timely treatment, if necessary. AI-based software tools are expected to enhance radiologists' performance in detecting pathologies like cerebral aneurysms in the future. Our aim was to evaluate the diagnostic performance of an artificial intelligence-based software designed to detect intracranial aneurysms on TOF-MRA. MATERIALS AND METHODS: One hundred ninety-one MR imaging data sets were analyzed using the software mdbrain for the presence of intracranial aneurysms on TOF-MRA obtained using two 3T MR imaging scanners or a 1.5T MR imaging scanner according to our clinical standard protocol. The results were compared with the reading of an experienced radiologist as a criterion standard to measure the sensitivity, specificity, positive and negative predictive values, and accuracy of the software. Additionally, detection rates depending on size, morphology, and location of the aneurysms were evaluated. RESULTS: Fifty-four aneurysms were detected by the expert reader. The overall sensitivity of the software for the detection of cerebral aneurysms was 72.6%, the specificity was 87.2%, and the accuracy was 82.6%. The positive predictive value was 67.9%, and the negative predictive value was 88.5%. We observed a sensitivity of 100% for saccular aneurysms of >5 mm without signs of thrombosis and low detection rates for fusiform or thrombosed aneurysms of 33.3% and 16.7%, respectively. Of 8 aneurysms that were not included in the initial written reports but were detected by the expert reader, retrospectively, 4 were detected by the software. CONCLUSIONS: Our data suggest that the software can assist radiologists in reporting TOF-MRA. The software was highly reliable in detecting saccular aneurysms, while for fusiform or thrombosed aneurysms, further improvements are needed. Further studies are necessary to investigate the impact of the software on detection rates, interrater reliability, and reading times.

Anticompensatory quick eye movements after head impulses: A peripheral vestibular sign in spontaneous nystagmus.

BACKGROUND: Differentiating central from peripheral origins of spontaneous nystagmus (SN) is challenging. Looking for a simple sign of peripheral disease with the video Head Impulsive Test we noticed anti-compensatory eye movements (AQEM) in patients with peripheral etiologies of spontaneous nystagmus (SN). Here we assess the diagnostic accuracy of AQEM in differentiating peripheral from central vestibular disorders. METHODS: We recorded the eye movements in response to horizontal head impulses in a group of 43 consecutive patients with acute vestibular syndrome (12 with central, 31 with peripheral disorders), 5 patients after acute vestibular neurectomy (positive controls) and 39 healthy subjects (negative controls). AQEM were defined as quick eye movements (peak velocity above 50°/s) in the direction of the head movement. RESULTS: All patients with peripheral disorders and positive controls had AQEM (latency 231 ± 53 ms, amplitude 3.4 ± 1.4°, velocity 166 ± 55°/s) when their head was moved to the opposite side of the lesion. Central patients did not have AQEM. AQEM occurrence rate was higher in peripheral patients with contralesional (74 ± 4%, mean ± SD) in comparison to ipsilesional (1 ± 4%) impulses (p< 0.001). Overall diagnostic accuracy for differentiating central from peripheral patients was 96% (95% CI for AUC ROC curve: 0.90 to 1.0) for VOR gain and 100% (95% CI: 1.0 to 1.0) for AQEM occurrence rate. CONCLUSIONS: These results suggest that AQEM are a sign of vestibular imbalance in a peripheral deficit. In addition to VOR gain they should be added to the evaluation of the head impulse test.

Gaze stabilization in chronic vestibular-loss and in cerebellar ataxia: interactions of feedforward and sensory feedback mechanisms.

During gaze shifts, humans can use visual, vestibular, and proprioceptive feedback, as well as feedforward mechanisms, for stabilization against active and passive head movements. The contributions of feedforward and sensory feedback control, and the role of the cerebellum, are still under debate. To quantify these contributions, we increased the head moment of inertia in three groups (ten healthy, five chronic vestibular-loss and nine cerebellar-ataxia patients) while they performed large gaze shifts to flashed targets in darkness. This induces undesired head oscillations. Consequently, both active (desired) and passive (undesired) head movements had to be compensated for to stabilize gaze. All groups compensated for active and passive head movements, vestibular-loss patients less than the other groups (P < 0.001, passive/active compensatory gains: vestibular-loss 0.23 ± 0.09/0.43 ± 0.12, healthy 0.80 ± 0.17/0.83 ± 0.15, cerebellar-ataxia 0.68 ± 0.17/0.77 ± 0.30, mean ± SD). The compensation gain ratio against passive and active movements was smaller than one in vestibular-loss patients (0.54 ± 0.10, P=0.001). Healthy and cerebellar-ataxia patients did not differ in active and passive compensation. In summary, vestibular-loss patients can better stabilize gaze against active than against passive head movements. Therefore, feedforward mechanisms substantially contribute to gaze stabilization. Proprioception alone is not sufficient (gain 0.2). Stabilization against active and passive head movements was not impaired in our cerebellar ataxia patients.

[Vertigo in children and adolescents. Part 1: Epidemiology and diagnosis of peripheral vestibular disorders]. / Schwindel bei Kindern und Jugendlichen. Teil 1: Epidemiologie und Diagnostik peripher-vestibulärer Schwindelsyndrome.

Migraine equivalents are the most common cause of vertigo in children and adolescents. Vertigo and balance disorders occur frequently in children during the course of otitis media, middle ear effusion and viral infections. If otitis media is associated with reduced hearing and vertigo, labyrinthitis must be considered. Craniocerebral injury is another important cause of vertigo in children. In contrast, spontaneous benign paroxysmal positional vertigo is rare among children. The isolated cases of endolymphatic hydrops that occur in children are usually secondary. Perilymph fistula can have congenital, infectious or trauma-related causes. The following characteristics are useful for differentiating between different vertiginous syndromes: type and duration of vertigo, triggering/aggravating/alleviating factors and accompanying symptoms. A neuro-ophthalmologic examination is essential to rule out central vestibular disorders.