RESUMO
Purpose: Standard automated perimetry is the gold standard to monitor visual field (VF) loss in glaucoma management, but it is prone to intrasubject variability. We trained and validated a customized deep learning (DL) regression model with Xception backbone that estimates pointwise and overall VF sensitivity from unsegmented optical coherence tomography (OCT) scans. Methods: DL regression models have been trained with four imaging modalities (circumpapillary OCT at 3.5 mm, 4.1 mm, and 4.7 mm diameter) and scanning laser ophthalmoscopy en face images to estimate mean deviation (MD) and 52 threshold values. This retrospective study used data from patients who underwent a complete glaucoma examination, including a reliable Humphrey Field Analyzer (HFA) 24-2 SITA Standard (SS) VF exam and a SPECTRALIS OCT. Results: For MD estimation, weighted prediction averaging of all four individuals yielded a mean absolute error (MAE) of 2.89 dB (2.50-3.30) on 186 test images, reducing the baseline by 54% (MAEdecr%). For 52 VF threshold values' estimation, the weighted ensemble model resulted in an MAE of 4.82 dB (4.45-5.22), representing an MAEdecr% of 38% from baseline when predicting the pointwise mean value. DL managed to explain 75% and 58% of the variance (R2) in MD and pointwise sensitivity estimation, respectively. Conclusions: Deep learning can estimate global and pointwise VF sensitivities that fall almost entirely within the 90% test-retest confidence intervals of the 24-2 SS test. Translational Relevance: Fast and consistent VF prediction from unsegmented OCT scans could become a solution for visual function estimation in patients unable to perform reliable VF exams.
Assuntos
Aprendizado Profundo , Glaucoma , Glaucoma/diagnóstico por imagem , Humanos , Estudos Retrospectivos , Tomografia de Coerência Óptica , Transtornos da Visão/diagnóstico , Campos VisuaisRESUMO
We made the decision in our hospital to radically eliminate the paper archive by bulk scanning over a million medical records. This reorganization goes together with installation of new workflows for injecting information that is still captured on paper as automatically as feasible into the electronic medical record. In this article we describe our organizational and technical approach and we highlight principles which our experience suggests to be useful.
Assuntos
Arquivos , Documentação/métodos , Administração Hospitalar , Sistemas Computadorizados de Registros Médicos/organização & administração , Sistemas de Gerenciamento de Base de Dados/organização & administração , Humanos , Interface Usuário-ComputadorRESUMO
OBJECTIVES: Clinical imaging data are essential for developing research software for computer-aided diagnosis, treatment planning and image-guided surgery, yet existing systems are poorly suited for data sharing between healthcare and academia: research systems rarely provide an integrated approach for data exchange with clinicians; hospital systems are focused towards clinical patient care with limited access for external researchers; and safe haven environments are not well suited to algorithm development. We have established GIFT-Cloud, a data and medical image sharing platform, to meet the needs of GIFT-Surg, an international research collaboration that is developing novel imaging methods for fetal surgery. GIFT-Cloud also has general applicability to other areas of imaging research. METHODS: GIFT-Cloud builds upon well-established cross-platform technologies. The Server provides secure anonymised data storage, direct web-based data access and a REST API for integrating external software. The Uploader provides automated on-site anonymisation, encryption and data upload. Gateways provide a seamless process for uploading medical data from clinical systems to the research server. RESULTS: GIFT-Cloud has been implemented in a multi-centre study for fetal medicine research. We present a case study of placental segmentation for pre-operative surgical planning, showing how GIFT-Cloud underpins the research and integrates with the clinical workflow. CONCLUSIONS: GIFT-Cloud simplifies the transfer of imaging data from clinical to research institutions, facilitating the development and validation of medical research software and the sharing of results back to the clinical partners. GIFT-Cloud supports collaboration between multiple healthcare and research institutions while satisfying the demands of patient confidentiality, data security and data ownership.
Assuntos
Computação em Nuvem , Comportamento Cooperativo , Diagnóstico por Imagem , Disseminação de Informação , Segurança Computacional , Administração Hospitalar , Universidades/organização & administraçãoRESUMO
Radiological Picture Archiving and Communication Systems (PACS) have only relatively recently become abundant. Many hospitals have made the transition to PACS about a decade ago. During that decade requirements and available technology have changed considerably. In this paper we look at factors that influence the design of tomorrow's systems, especially those in larger multidisciplinary hospitals. We discuss their impact on PACS architecture (a technological perspective) as well as their impact on radiology (a management perspective). We emphasize that many of these influencing factors originate outside radiology and that radiology has little impact on these factors. That makes it the more important for managers in radiology to be aware of architectural aspects and it may change cooperation of radiology with, among others, the hospital's central IT department.
Assuntos
Armazenamento e Recuperação da Informação/tendências , Serviço Hospitalar de Radiologia/organização & administração , Sistemas de Informação em Radiologia/tendências , Tomada de Decisões Assistida por Computador , Difusão de Inovações , Eficiência Organizacional , Humanos , Integração de Sistemas , Tecnologia Radiológica/tendênciasRESUMO
PURPOSE: Sensation is an essential aspect of fecal continence. We aimed to correlate manovolumetric and radiologic changes at successive levels of rectal filling sensation. METHODS: Combined anorectal manometry and proctography were performed in nine volunteers. Images, volumes, and pressures were analyzed at the start of the test, at 20 seconds before first sensation, and at first, constant, urge, and maximum tolerable sensation. RESULTS: Consecutive levels of rectal filling sensation were associated with progressive opening and dilation of the upper anal canal (up to 44 mm) and sliding down of the rectal contents (14 mm), which had already started before the first sensation. This coincided initially with a pressure decrease in the proximal anal canal (from 94 to 42 mmHg). With constant sensation and particularly with urge sensation, rectal pressure increase appeared to be responsible for further proximal anal dilation. This was accompanied by a significant increase of proximal anal pressure (up to 133 mmHg) and sharpening of the angle between the anal axis and the horizontal reference line. CONCLUSION: The proximal anal canal or its surrounding structures play an important role in the desire-to-defecate sensation. They can be activated by a progressive buildup of rectal reservoir pressure in the presence of a competent distal anal sphincter barrier.