Detecting Large Vessel Occlusion at Multiphase CT Angiography by Using a Deep Convolutional Neural Network.

Background Large vessel occlusion (LVO) stroke is one of the most time-sensitive diagnoses in medicine and requires emergent endovascular therapy to reduce morbidity and mortality. Leveraging recent advances in deep learning may facilitate rapid detection and reduce time to treatment. Purpose To develop a convolutional neural network to detect LVOs at multiphase CT angiography. Materials and Methods This multicenter retrospective study evaluated 540 adults with CT angiography examinations for suspected acute ischemic stroke from February 2017 to June 2018. Examinations positive for LVO (n = 270) were confirmed by catheter angiography and LVO-negative examinations (n = 270) were confirmed through review of clinical and radiology reports. Preprocessing of the CT angiography examinations included vasculature segmentation and the creation of maximum intensity projection images to emphasize the contrast agent-enhanced vasculature. Seven experiments were performed by using combinations of the three phases (arterial, phase 1; peak venous, phase 2; and late venous, phase 3) of the CT angiography. Model performance was evaluated on the held-out test set. Metrics included area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. Results The test set included 62 patients (mean age, 69.5 years; 48% women). Single-phase CT angiography achieved an AUC of 0.74 (95% confidence interval [CI]: 0.63, 0.85) with sensitivity of 77% (24 of 31; 95% CI: 59%, 89%) and specificity of 71% (22 of 31; 95% CI: 53%, 84%). Phases 1, 2, and 3 together achieved an AUC of 0.89 (95% CI: 0.81, 0.96), sensitivity of 100% (31 of 31; 95% CI: 99%, 100%), and specificity of 77% (24 of 31; 95% CI: 59%, 89%), a statistically significant improvement relative to single-phase CT angiography (P = .01). Likewise, phases 1 and 3 and phases 2 and 3 also demonstrated improved fit relative to single phase (P = .03). Conclusion This deep learning model was able to detect the presence of large vessel occlusion and its diagnostic performance was enhanced by using delayed phases at multiphase CT angiography examinations. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Ospel and Goyal in this issue.

Metabolic pathways in context: mTOR signalling in the retina and optic nerve - A review.

The mechanistic target of rapamycin (mTOR) signalling network plays a key role in growth and development, autophagy, metabolism, inflammation as well as ageing, and it is therefore important in ocular health and disease. mTOR dysregulation has been identified in a range of conditions, including age-related macular degeneration, diabetic retinopathy, retinitis pigmentosa, traumatic optic neuropathy and glaucoma. Experimental modulation of the pathway has contributed to the understanding of these diseases and offers the potential for new avenues of therapy. This review discusses the mTOR pathway and its role in health and in diseases of the retina and optic nerve.

Deep Learning in Neuroradiology: A Systematic Review of Current Algorithms and Approaches for the New Wave of Imaging Technology.

PURPOSE: To systematically review and synthesize the current literature and to develop a compendium of technical characteristics of existing deep learning applications in neuroradiology. MATERIALS AND METHODS: A Preferred Reporting Items for Systematic Reviews and Meta-Analyses systematic review was conducted through September 1, 2019, using PubMed, Cochrane, and Web of Science databases. A total of 155 articles discussing deep learning applications in neuroimaging were identified, divided by imaging modality, and characterized by imaging task, data source, algorithm type, and outcome metrics. RESULTS: A total of 155 studies were identified and divided into: MRI (n = 115), functional MRI (n = 19), CT (n = 9), PET (n = 18), and US (n = 1). Seven were multimodal. MRI applications were described in 74%, and 76 (49%) were tasked with image segmentation. Of the 155 articles identified in this study, 65 (42%) were tested on institutional data; only 16 were validated against publicly available data. In addition, 53 studies (34%) used a combined dataset of less than 100, and 124 (80%) used a combined dataset of less than 1000. CONCLUSION: Although deep learning has demonstrated potential for each of these modalities, this review highlights several needs in the field of deep learning research including use of internal datasets without external validation, unavailability of implementation methods, inconsistent assessment metrics, and lack of clinical validation. However, the rapid growth of deep learning in neuroradiology holds promise and, as strides are made to improve standardization, generalizability, and reproducibility, it may soon play a role in clinical diagnosis and treatment of neurologic disorders.Supplemental material is available for this article.© RSNA, 2020.

Delivery Characteristics of the Preloaded POB-MA 877PA Intraocular Lens System: Comparison of 2 Incision Sizes.

PURPOSE: To obtain real-world data regarding the delivery characteristics of a preloaded delivery system, the Bi-Flex POB-MA 877PA, and to compare them in 2 main port incision sizes: 2.4 mm and 2.75 mm. DESIGN: Prospective multicenter observational cohort study. METHODS: Consecutive elective phacoemulsification and intraocular lens surgeries using the POB-MA 877PA implant were performed by a single experienced surgeon between December 2017 and April 2018. Patients were divided into 2 groups with group 1 and 2 underwent phacoemulsification through a main port size of 2.4 mm and 2.75 mm, respectively. Delivery characteristics were recorded, with a main outcome defined as lens delivery entirely into the capsular bag using the preloaded injector without additional manipulation. Other variances were classified as minor or major issues depending on lens or anatomical damage or requirement to replace device. RESULTS: A total of 110 total cases were included, with 59 cases in group 1 (2.4 mm) and 51 cases in group 2 (2.75 mm). Group 2 had a significantly lower proportion of cases that required secondary manipulation of the lens than group 1 [8 (15.7%) cases vs 24 (40.7%) cases; P < 0.05]. In groups 1 and 2, 3 (5.1%) and 3 (5.9%) cases had major issues, respectively. CONCLUSIONS: The delivery characteristics of the POB-MA 877PA intraocular lens systems are different in the 2.4-mm and 2.75-mm main port incisions, with a lower proportion of cases requiring secondary manipulation in the 2.75-mm incision size. Despite its preloaded nature however, there are still delivery issues with these intraocular lens systems.

Orbital tuberculosis: perspectives from Victoria, Australia.

PURPOSE: Orbital tuberculosis (TB) is a rare extra-pulmonary manifestation of tuberculosis and its clinical diagnosis poses unique challenges, with potential for destructive complications as well as social and public health implications. The aim of this study is to report our experience of patients presenting with orbital TB and to identify common aspects. METHODS: A systematic search for mandatory notifications of orbital tuberculosis between January 01, 1994 and December 12, 2016 was undertaken in the Victorian Tuberculosis database. In addition, members of the Australian and New Zealand Society of Ophthalmic Plastic Surgeons (ANZSOPS) were surveyed to identify cases of orbital tuberculosis diagnosed on biopsy in the past 20 years. Medical case notes of identified cases were reviewed retrospectively. RESULTS: Three cases were identified as having occurred in Victoria, aged 44-59 years old. All cases had emigrated from endemic countries with higher tuberculosis burden. Diagnosis of tuberculosis was often difficult due to few or non-viable acid fast bacilli and low yield of positive culture in paucicellular orbital specimens. CONCLUSIONS: Orbital TB is rare but remains an important differential diagnosis of orbital mass lesions. The diagnosis of orbital TB requires a high index of clinical suspicion and targeted investigations in patients originating from endemic areas. Diagnosis and treatment rely on effective collaboration between ophthalmologists, infectious disease physicians, and pathologists.

Bilateral facial nerve palsies secondary to chronic inflammatory demyelinating polyneuropathy following adalimumab treatment.

PURPOSE: Chronic Inflammatory Demyelinating Polyneuropathy (CIDP) presents uncommonly with cranial nerve involvement with ophthalmological implications. METHODS: We report the case of a 37year-old man who developed CIDP which manifested as progressive and relapsing bilateral facial nerve palsy with lagophthalmos and exposure keratopathy, in the setting of treatment of Crohn's disease with the anti-TNF-alpha agent adalimumab. RESULTS: Symptoms gradually improved over the course of several months following withdrawal of adalimumab and treatment with intravenous immunoglobulin (IVIg) and oral prednisolone. CONCLUSION: Bilateral facial nerve involvement occurs uncommonly as a feature of CIDP in its classic form. The prognosis is good for recovery of facial nerve function with discontinuation of anti-TNF-alpha therapy and concurrent use of steroid and intravenous immunoglobulin in this case.

Breast cancer screening with digital breast tomosynthesis - 4 year experience and comparison with national data.

BACKGROUND: To determine if mammography combined with digital breast tomosynthesis (DBT), leads to superior performance in screening for breast cancer compared to digital mammography (DM) alone. METHODS: We retrospectively collected data from A) the results of population-based mammography-screening provided by the National Cancer Registry in Taiwan, and B) the results from all screening mammography performed with DBT from 2012 through 2015 at Kaohsiung Veterans General Hospital (VGHKS) since the institution of DBT at the end of 2011. This was compared data from 3 years with DM performed prior to DBT implementation. We calculated the results of medical audit of VGHKS and compared this with national data. Fisher's exact test is applied. RESULTS: VGHKS data demonstrated a higher cancer detection rate (CDR) and positive predictive value 1 (PPV 1) than the national average. Most prominently in the year 2014, our CDR was 120% better than that of the national average. CDR ranged from 6.3 to 8.1‰ prior to the introduction of DBT, and following DBT implementation this improved to 8.5-11.4‰, reflecting a mean increase of 32.2%. Early cancer detection was 50% higher and node negative rate was 25% higher than the national average of latest year. A 17.8% reduction in recall rate (RR) was achieved due to a decrease in unnecessary recall. CONCLUSION: There was a 32.2% increase in CDR and a 17.8% decrease in RR when DBT was used as an adjunct to DM, as compared to DM alone. CDRs were approximately twofold better than national average data. DBT was more effective at detecting cancer in ductal carcinoma in situ and stage 1.

Using Routine Hemoglobin A1c Testing to Determine the Glycemic Status in Psychiatric Inpatients.

AIM: Using routine hemoglobin A1c (HbA1c) testing to describe the prevalence, characteristics, and length of stay (LOS) of psychiatry inpatients with type 2 diabetes compared to those with pre-diabetes and those without diabetes. METHODS: In this prospective observational study, all inpatients aged greater than 30 years admitted to the Austin Health Psychiatry Unit, a major tertiary hospital, affiliated with the University of Melbourne, between February 2014 and April 2015 had routine HbA1c testing as part of the Diabetes Discovery Initiative. Patients were divided into three groups: diabetes (HbA1c ≥ 6.5%, 48 mmol/mol), pre-diabetes (HbA1c 5.7-6.4%, 39-46 mmol/mol), or no diabetes (HbA1c ≤ 5.6%, 38 mmol/mol). Baseline characteristics, co-morbidities, psychiatric illnesses, and treatment were recorded. RESULTS: There were a total of 335 psychiatry inpatients (median age 41 years). The most prevalent diagnoses were schizophrenia, depression, and substance abuse. Of the 335 psychiatric inpatients, 14% (n = 46) had diabetes and 19% (n = 63) had pre-diabetes, a prevalence threefold greater than in the aged matched general population. Compared to inpatients with pre-diabetes and no diabetes, those with diabetes were older and were at least twice as likely to have hypertension, obesity, and hyperlipidemia (all p ≤ 0.002). In multivariable analyses, diabetes was associated with increasing age (p = 0.02), substance abuse (p = 0.04), dyslipidaemia (p = 0.03), and aripiprazole use (p = 0.01). Patients with diabetes also had a 70% longer expected LOS (95% CI: 20-130%; p = 0.001), compared to those with pre-diabetes and no diabetes. CONCLUSION: Despite relative youth, one-third of all psychiatric inpatients above the age of 30 have diabetes or pre-diabetes. Presence of diabetes in psychiatric inpatients is associated with older age, substance abuse, and longer LOS. Routine inpatient HbA1c testing provides an opportunity for early detection and optimization of diabetes care.

Factors contributing to frequent attendance to the emergency department of a remote Northern Territory hospital.

OBJECTIVES: To determine the clinical and environmental variables associated with frequent presentations by adult patients to a remote Australian hospital emergency department (ED) for reasons other than chronic health conditions. DESIGN: Unmatched case-control study of all adult patients attending Katherine Hospital ED between 1 January and 31 December 2012. PARTICIPANTS: Cases were defined as frequent attenders (FAs) without a chronic health condition who presented to the ED six or more times during the 12-month period. A single presentation was randomly selected for data collection. Controls were patients who presented on only one occasion. OUTCOME MEASURES: Basic demographic data were collected, including clinical outcomes, Indigenous status, living arrangements, and whether alcohol and violence contributed to the presentation. Environmental variables were extracted from the Bureau of Meteorology database and mapped to each presentation. RESULTS: FAs were much more likely to be homeless (odds ratio [OR], 16.4; P < 0.001) and to be Aboriginal (OR, 2.16; P < 0.001); alcohol as a contributing factor was also more likely (OR, 2.77; P = 0.001). FAs were more likely to present in hotter, wetter weather, although the association was statistically weak. Clinical presentations by cases and controls were similar; the annual death rates for both groups were high (3.6% and 1.5%, respectively). CONCLUSIONS: There was a strong association between FA and Aboriginal status, homelessness and the involvement of alcohol, but alcohol was more likely to contribute to presentation by non-Aboriginal FAs who had stable living conditions. FAs and non-FAs had similar needs for emergency medical care, with strikingly higher death rates than the national average in both groups. As a result of this study, Katherine Hospital has initiated a Frequent Attender Pathway that automatically triggers a dedicated ED service for those at greatest clinical risk. Homelessness is a serious problem in the Northern Territory, and is associated with poor health outcomes.