Deep Learning Based Software to Identify Large Vessel Occlusion on Noncontrast Computed Tomography.

BACKGROUND AND PURPOSE: Reliable recognition of large vessel occlusion (LVO) on noncontrast computed tomography (NCCT) may accelerate identification of endovascular treatment candidates. We aim to validate a machine learning algorithm (MethinksLVO) to identify LVO on NCCT. METHODS: Patients with suspected acute stroke who underwent NCCT and computed tomography angiography (CTA) were included. Software detection of LVO (MethinksLVO) on NCCT was tested against the CTA readings of 2 experienced radiologists (NR-CTA). We used a deep learning algorithm to identify clot signs on NCCT. The software image output trained a binary classifier to determine LVO on NCCT. We studied software accuracy when adding National Institutes of Health Stroke Scale and time from onset to the model (MethinksLVO+). RESULTS: From 1453 patients, 823 (57%) had LVO by NR-CTA. The area under the curve for the identification of LVO with MethinksLVO was 0.87 (sensitivity: 83%, specificity: 71%, positive predictive value: 79%, negative predictive value: 76%) and improved to 0.91 with MethinksLVO+ (sensitivity: 83%, specificity: 85%, positive predictive value: 88%, negative predictive value: 79%). CONCLUSIONS: In patients with suspected acute stroke, MethinksLVO software can rapidly and reliably predict LVO. MethinksLVO could reduce the need to perform CTA, generate alarms, and increase the efficiency of patient transfers in stroke networks.

CT Assessment of Otic Capsule Bone Density in Paget's Disease of the Temporal Bone and Its Relationship With Hearing Loss.

OBJECTIVES: To study computed tomography findings in Paget's disease of temporal bone (PDTB) and analyze the relations between otic capsule bone mineral density values measured in Hounsfield Units (HU) and hearing loss (HL). STUDY DESIGN: Observational case-control study. SETTING: Tertiary referral center. PATIENTS: Radiographically confirmed PDTB cases and control group. INTERVENTION: Diagnostic. MAIN OUTCOME MEASURES: Hearing thresholds and computed tomography bone density values. RESULTS: Twenty-three ears in the case group (PDTB) and 27 control ears were included. In the PDTB group, HL was found in 87% of the ears (43% mixed) and an air-conduction threshold of 50.7 dB (SD = 19.8). In the control group, 48% of the ears showed HL (7% mixed) and an air-conduction threshold of 34.5 dB (SD = 20.6) was found; the difference was statistically significant (p < 0.05). Measurements of bone density (HU) in the otic capsule (regions of interest [ROI] 1 and 2) and in the petrous bone (ROI 3) were significantly lower (p < 0.05) in the PDTB group than in controls.The PDTB group presented a significant association between otic capsule bone density in ROI 1 and mean otic capsule density with air and bone-conduction thresholds (p < 0.05). In controls, no association was observed between any density value and audiometric thresholds. CONCLUSION: PDTB patients showed more frequent HL, lower thresholds, and a higher proportion of mixed HL than controls. Bone density (HU) was decreased in all ROIs in PDTB patients in comparison with controls. Bone density in the otic capsule was associated with HL in PDTB patients, but no association was observed between bone density and HL in controls.

Cerebrospinal Fluid Output as a Risk Factor of Chronic Hydrocephalus After Aneurysmal Subarachnoid Hemorrhage.

BACKGROUND: Chronic shunt-dependent hydrocephalus is a well-known complication of subarachnoid hemorrhage. Although the risk factors have been extensively investigated, most fail to predict permanent shunt dependency. It is unknown whether the volume of cerebrospinal fluid (CSF) from external ventricular drainage and the daily volume of drainage during the acute hydrocephalus phase (first 72 hours) can predict shunt dependency. We aimed to determine whether CSF output during the acute hydrocephalus phase is a risk factor for shunt dependency. METHODS: Patients with aneurysmal subarachnoid hemorrhage and hydrocephalus treated with external ventricular drainage were prospectively registered in our database between January 2017 and March 2020. Factors evaluated for predicting shunt dependency included age; sex; Hunt and Hess grade; World Federation of Neurological Surgeons grade; acute hydrocephalus; modified Fisher grade; aneurysm treatment modality; hospital length of stay; modified Rankin score; average daily overall CSF production; average CSF output for the first 24, 48, and 72 hours; external ventricular drainage days; the number of wean/clamp failures; and ventriculoperitoneal shunting. RESULTS: Univariate analysis identified Hunt and Hess grade; acute hydrocephalus at onset; external ventricular drainage; overall CSF output; average CSF output for the first 24, 48, and 72 hours; and CSF output until the first clamp as significant risk factors for shunt dependency (P < 0.001). In a multivariate logistic regression analysis, overall CSF output and average CSF output for the first 72 hours were significant risk factors for shunt dependency. CONCLUSIONS: Overall CSF output, especially during the acute hydrocephalus phase (first 72 hours), predicts the development of chronic hydrocephalus.

Painless bilateral visual loss in a 33-year-old woman with severe arterial hypotension.

A 32-year-old woman experienced dizziness and headache for 5 months. She also complained of painless, progressive bilateral visual loss for several weeks. Before developing the initial symptoms, she had an uncomplicated pregnancy except for dizziness and systemic hypotension during the first term. Fundus examination disclosed prominent retinal arteries as well diffuse microaneurysms, widespread intraretinal hemorrhages, and hyperemic optic disks. Brain magnetic resonance imaging revealed multiple supratentorial white-matter lesions suggestive of ischemic strokes. Initially, she had severe systemic hypotension (41/17 mm Hg). When reassessed, blood pressure was normal in the lower limbs, but there was severe hypotension in the upper limbs. An angio-computed tomography of the supraortic trunks showed occlusion of both primitive carotid arteries, both subclavian arteries and the right axillary and humeral arteries. Based on these findings, the diagnosis of Takayasu type-I arteritis with ischemic retinopathy and cerebrovascular disease was established. Bilateral retinal panphotocoagulation and aorta to right carotid bypass were performed because of the severity of the ischemic lesions.

Radiologic Predictors for Extent of Resection in Pituitary Adenoma Surgery. A Single-Center Study.

BACKGROUND: Preoperative radiologic evaluation of pituitary adenomas is essential. Despite the efforts made to determine the achieved resection grade after pituitary adenoma surgery, there is a high level of disagreement among all the available classifications and measurement methods used. Our study aimed to determine pituitary adenoma imaging features, easily obtained from preoperative magnetic resonance, which could be used as resection predictor variables. Second, we analyzed the usefulness of the ellipsoid method in pituitary adenoma volume determination. METHODS: Two-hundred and ninety-four pituitary adenomas, which were surgically treated in our department, were retrospectively analyzed. Age, gender, surgical approach, hormonal status, greater tumor diameter, volume, cavernous sinus invasion, and extent of resection were evaluated. RESULTS: One-hundred and forty-eight surgical procedures were conducted with a microsurgical transsphenoidal approach whereas 146 were conducted with an endoscopic endonasal approach. Gross total resection was achieved in 54.08% of cases. There were no significant differences in the extent of resection regarding the approach used, age, gender, or hormonal production by the tumor. Only Knosp grade (P < 0.001) and tumor volume (P < 0.05) had a statistically and independent significant relationship with the extent of resection. Furthermore, we found a high correlation between the calculated volume, using the ellipsoid method, and the volume measurement obtained with complex planimetry methods. CONCLUSIONS: Pituitary adenoma volume and cavernous sinus invasion, graded with the Knosp scale, are 2 pituitary tumor features that, when used in combination, predict the complexity of the surgery and the difficulty of achieving gross total resection in pituitary adenoma surgery.

Value of bone SPECT-CT to predict chronic pain relief after percutaneous vertebroplasty in vertebral fractures.

BACKGROUND CONTEXT: Longer life span has resulted in increased risk of vertebral osteoporotic fractures. Among minimally invasive procedures, percutaneous vertebroplasty (PV) has shown excellent results in the treatment of chronic vertebral pain. The role of preintervention bone single photon emission computed tomography-computed tomography (SPECT-CT) has not been clearly established for the management of these patients. PURPOSE: To determine the value of bone SPECT-CT in patient selection, treatment planning, and prediction of response to PV. A comparison with magnetic resonance imaging (MRI) was also aimed. STUDY DESIGN: Prospective consecutive series. PATIENT SAMPLE: We studied the performance of bone SPECT-CT on 33 consecutive patients with chronic pain because of vertebral fracture intended for PV. OUTCOME MEASURES: Improvement of clinical status was based on comparison of preprocedure and postprocedure outcome measurements of pain, mobility, and analgesic use. METHODS: Bone SPECT was done using a dual-detector variable-angle gamma camera coupled with a two-slice CT scanner (Symbia T2 System; Siemens, Munich, Germany). Magnetic resonance imaging was done using a magnet of 1.5 T (Giroscan System ACS NT Intera; Philips, Amsterdam, The Netherlands). RESULTS: Of the 33 patients, 24 finally underwent PV. Positive SPECT-CT images predicted clinical improvement in 91% (21 of 23) of them. Agreement between SPECT-CT and MRI was 80% (20 of 25). Single photon emission computed tomography-computed tomography images showed an alternative cause of pain in some cases, such as new fractures or multiple coexisting fractures, persisting bone remodeling in a previous cemented vertebra, and facet or discal degenerative disease. Single photon emission computed tomography-computed tomography was mandatory in eight patients that could no receive MRI, all of whom improved after PV. CONCLUSIONS: Positive bone SPECT-CT seems a good predictor of postprocedural response. It also adds valuable information as to the cause of back pain and facilitates complete patient evaluation in patients that can not receive MRI.

Validation of the new Graded Prognostic Assessment scale for brain metastases: a multicenter prospective study.

BACKGROUND: Prognostic indexes are useful to guide tailored treatment strategies for cancer patients with brain metastasis (BM). We evaluated the new Graded Prognostic Assessment (GPA) scale in a prospective validation study to compare it with two published prognostic indexes. METHODS: A total of 285 newly diagnosed BM (n = 85 with synchronous BM) patients, accrued prospectively between 2000 and 2009, were included in this analysis. Mean age was 62 ± 12.0 years. The median KPS and number of BM was 70 (range, 20-100) and 3 (range, 1-50), respectively. The majority of primary tumours were lung (53%), or breast (17%) cancers. Treatment was administered to 255 (89.5%) patients. Only a minority of patients could be classified prospectively in a favourable prognostic class: GPA 3.5-4: 3.9%; recursive partitioning analysis (RPA) 1, 8.4% and Basic Score for BM (BSBM) 3, 9.1%. Mean follow-up (FU) time was 5.2 ± 4.7 months. RESULTS: During the period of FU, 225 (78.9%) patients died. The 6 months- and 1 year-OS was 36.9% and 17.6%, respectively. On multivariate analysis, performance status (P < 0.001), BSBM (P < 0.001), Center (P = 0.007), RPA (P = 0.02) and GPA (P = 0.03) were statistically significant for OS. The survival prediction performances' of all indexes were identical. Noteworthy, the significant OS difference observed within 3 months of diagnosis between the BSBM, RPA and GPA classes/groups was not observed after this cut-off time point. Harrell's concordance indexes C were 0.58, 0.61 and 0.58 for the GPA, BSBM and RPA, respectively. CONCLUSIONS: Our data suggest that the new GPA index is a valid prognostic index. In this prospective study, the prediction performance was as good as the BSBM or RPA systems. These published indexes may however have limited long term prognostication capability.