Deep neural network to locate and segment brain tumors outperformed the expert technicians who created the training data.

Purpose: Deep learning (DL) algorithms have shown promising results for brain tumor segmentation in MRI. However, validation is required prior to routine clinical use. We report the first randomized and blinded comparison of DL and trained technician segmentations. Approach: We compiled a multi-institutional database of 741 pretreatment MRI exams. Each contained a postcontrast T1-weighted exam, a T2-weighted fluid-attenuated inversion recovery exam, and at least one technician-derived tumor segmentation. The database included 729 unique patients (470 males and 259 females). Of these exams, 641 were used for training the DL system, and 100 were reserved for testing. We developed a platform to enable qualitative, blinded, controlled assessment of lesion segmentations made by technicians and the DL method. On this platform, 20 neuroradiologists performed 400 side-by-side comparisons of segmentations on 100 test cases. They scored each segmentation between 0 (poor) and 10 (perfect). Agreement between segmentations from technicians and the DL method was also evaluated quantitatively using the Dice coefficient, which produces values between 0 (no overlap) and 1 (perfect overlap). Results: The neuroradiologists gave technician and DL segmentations mean scores of 6.97 and 7.31, respectively ( p < 0.00007 ). The DL method achieved a mean Dice coefficient of 0.87 on the test cases. Conclusions: This was the first objective comparison of automated and human segmentation using a blinded controlled assessment study. Our DL system learned to outperform its "human teachers" and produced output that was better, on average, than its training data.

Multiple reader comparison of 2D TOF, 3D TOF, and CEMRA in screening of the carotid bifurcations: Time to reconsider routine contrast use?

BACKGROUND AND PURPOSE: MR contrast-enhanced techniques are undergoing increased scrutiny since the FDA applied a warning for gadolinium-based MR contrast agents due to gadolinium deposition within multiple organ systems. While CE-MRA provides excellent image quality, is it required in a screening carotid study? This study compares 2D TOF and 3D TOF MRA vs. CE-MRA in defining carotid stenosis in a large clinical patient population, and with multiple readers with varying experience. MATERIALS AND METHODS: 200 consecutive patients had their carotid bifurcations evaluated with 2D TOF, 3D TOF and CE-MRA sequences by 6 board-certified neuroradiologists. Stenosis and quality of examinations were defined for each study. Inter-rater reliability was assessed using two-way random effects intraclass correlation coefficients. Intra-reader reliability was computed via weighted Cohen's κ. Weighted Cohen's κ were also computed to assess agreement in stenosis ratings between enhanced images and unenhanced images. RESULTS: Agreement between unenhanced and enhanced ratings was substantial with a pooled weighted κ of 0.733 (0.628-0.811). For 5 of the 6 readers, the combination of unenhanced 2D TOF and 3D TOF showed better agreement with contrast-enhanced than either 2D TOF or 3D TOF alone. Intra-reader reliability was substantial. CONCLUSIONS: The combination of 2D TOF and 3D TOF MRA showed substantial agreement with CE-MRA regarding degree of carotid stenosis in this large outpatient population across multiple readers of varying experience. Given the scrutiny that GBCA are undergoing due to concerns regarding CNS and soft tissue deposition, it seems prudent to reserve CE-MRA for cases which are not satisfactorily answered by the nonenhanced study or other noninvasive examinations.

Normal Variant Occipital Pneumatization.

OBJECTIVE: Evaluate prevalence and pattern of occipital pneumatization (OP). PATIENTS: Individuals with imaging evidence of OP on computed tomography (CT). INTERVENTION(S): High resolution CT scans of the temporal bone. MAIN OUTCOME MEASURE: The prevalence and pattern of OP on 1000 CT scans performed at a large academic healthcare system. RESULTS: OP had a prevalence of 11.8% (n = 118) while occipital condyle pneumatization occurred in only 0.3%. Occipital air cells were right-sided in 27.1% (n = 32), left-sided in 51.7% (n = 61), and bilateral in 21.2% (n = 25), and OP was contiguous with the occipitomastoid suture. In cases of unilateral OP, the contralateral jugular foramen demonstrated relative enlargement (p = 0.006), but a direct association could not be established. CONCLUSIONS: The occipital bone is an accessory site of skull base pneumatization in 11.8% of the population undergoing temporal bone CT, while air cell extension into the occipital condyle occurs more rarely. These occipital air cells have a left-sided predilection and are always in direct proximity to the occipitomastoid suture, suggesting developmental egress from the mastoid. OP is a normal variant and lacks features of craniocervical pneumatization, which is a rare disorder.

Pantopaque contrast mimicking intracanalicular vestibular schwannoma.

Pantopaque (iophendylate) is an oily contrast medium historically used during spine imaging. Due to its persistence in the subarachnoid space and the potential to lead to severe arachnoiditis, it is no longer used today. We present a 40-year-old male with new-onset headaches, imbalance, and vertigo. Brain magnetic resonance imaging revealed a 2-mm T1 -hyperintense intracanalicular lesion. Numerous hyperdense foci were scattered throughout the subarachnoid space on computed tomography. Further history revealed the patient received Pantopaque 30 years prior, after sustaining spinal trauma. Remnant Pantopaque contrast is an important differential when evaluating a patient with a suspected intracranial tumor in order to avoid unwarranted surgical intervention. Laryngoscope, 127:1916-1919, 2017.

Magnetic Resonance Imaging Assessment of Vascular Contact of the Facial Nerve in the Asymptomatic Patient.

Objective The objective of this study was to determine the prevalence of facial nerve vascular contact on magnetic resonance imaging (MRI) in patients without hemifacial spasm (HFS). Study Design Our radiology database was queried to identify consecutive adult patients without a history of HFS, intracranial tumor, brain radiation therapy, intracranial surgery, traumatic brain injury, or trigeminal nerve vascular compression. One hundred high-resolution MRIs of the posterior fossa were independently reviewed by two neuroradiologists for facial nerve vascular contact (200 sides). Main Outcome Measures The prevalence of vascular nerve contact in the non-HFS patient, the location of contact along the facial nerve, the culprit vessel, and severity of compression was recorded. Results The presence of vascular contact in the non-HFS patient may be as high as 53%. It is typically mild to moderate in severity, most commonly involves the cisternal portion, and usually caused by the anterior inferior cerebellar artery. Conclusion Vascular contact of the facial nerve is frequently identified in asymptomatic individuals but tends to be more peripheral and mild compared with previous descriptions of neurovascular contact in HFS patients. These results should be considered in assessing the candidacy of HFS patients for microvascular decompression.

CT interpretation in a telestroke network: agreement among a spoke radiologist, hub vascular neurologist, and hub neuroradiologist.

BACKGROUND AND PURPOSE: The American Stroke Association guidelines emphasized the need for further high-quality studies that assess agreement by radiologists and nonradiologists engaged in emergency telestroke assessments and decision-making. Therefore, the objective of this study was to determine the level of agreement of baseline brain CT scan interpretations of patients with acute stroke presenting to telestroke spoke hospitals between central reading committee neuroradiologists and each of 2 groups, spoke hospital radiologists and hub hospital vascular neurologists (telestrokologists). METHODS: The Stroke Team Remote Evaluation Using a Digital Observation Camera Arizona trial was a prospective, urban single-hub, rural 2-spoke, randomized, blinded, controlled trial of a 2-way, site-independent, audiovisual telemedicine and teleradiology system designed for remote evaluation of adult patients with acute stroke versus telephone consultation to assess eligibility for treatment with intravenous thrombolysis. In the telemedicine arm, the subjects' CT scans were interpreted by the hub telestrokologist and in the telephone arm by the spoke radiologist. All subjects' CT scans were subsequently interpreted centrally, independently, and blindly by 2 hub neuroradiologists. The primary CT outcome was determination of a CT-based contraindication to thrombolytic treatment. Kappa statistics and exact agreement rates were used to analyze interobserver agreement. RESULTS: Fifty-four subjects underwent random assignment. The overall agreement for the presence of radiological contraindications to thrombolysis was excellent (0.91) and did not differ substantially between the hub telestrokologist to neuroradiologist and spoke radiologist to neuroradiologist (0.92 and 0.89, respectively). CONCLUSIONS: In the context of a telestroke network designed to assess patients with acute stroke syndromes, agreement over the presence or absence of radiological contraindications to thrombolysis was excellent whether the comparisons were between a telestrokologist and neuroradiologist or between spoke radiologist and neuroradiologist. CLINICAL TRIAL REGISTRATION: URL: http://www.clinicaltrials.gov. Unique identifier: NCT00623350.

Accuracy of dementia diagnosis: a direct comparison between radiologists and a computerized method.

There has been recent interest in the application of machine learning techniques to neuroimaging-based diagnosis. These methods promise fully automated, standard PC-based clinical decisions, unbiased by variable radiological expertise. We recently used support vector machines (SVMs) to separate sporadic Alzheimer's disease from normal ageing and from fronto-temporal lobar degeneration (FTLD). In this study, we compare the results to those obtained by radiologists. A binary diagnostic classification was made by six radiologists with different levels of experience on the same scans and information that had been previously analysed with SVM. SVMs correctly classified 95% (sensitivity/specificity: 95/95) of sporadic Alzheimer's disease and controls into their respective groups. Radiologists correctly classified 65-95% (median 89%; sensitivity/specificity: 88/90) of scans. SVM correctly classified another set of sporadic Alzheimer's disease in 93% (sensitivity/specificity: 100/86) of cases, whereas radiologists ranged between 80% and 90% (median 83%; sensitivity/specificity: 80/85). SVMs were better at separating patients with sporadic Alzheimer's disease from those with FTLD (SVM 89%; sensitivity/specificity: 83/95; compared to radiological range from 63% to 83%; median 71%; sensitivity/specificity: 64/76). Radiologists were always accurate when they reported a high degree of diagnostic confidence. The results show that well-trained neuroradiologists classify typical Alzheimer's disease-associated scans comparable to SVMs. However, SVMs require no expert knowledge and trained SVMs can readily be exchanged between centres for use in diagnostic classification. These results are encouraging and indicate a role for computerized diagnostic methods in clinical practice.

PET/CT imaging of conus medullaris metastasis from lung cancer.

An intradural extramedullary metastasis is usually detected at an advanced stage of the disease or during workup for manifestations of spinal cord compression. Early diagnosis of such a lesion is rare and mostly fortuitous. The authors present a case of treated nonsmall cell lung carcinoma with an asymptomatic conus medullaris metastasis, which was demonstrated by PET/CT imaging during restaging evaluation.