Your browser doesn't support javascript.
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 19.621
Filtrar
2.
Br J Radiol ; 93(1106): 20190855, 2020 Feb 01.
Artigo em Inglês | MEDLINE | ID: mdl-31965813

RESUMO

Advances in computing hardware and software platforms have led to the recent resurgence in artificial intelligence (AI) touching almost every aspect of our daily lives by its capability for automating complex tasks or providing superior predictive analytics. AI applications are currently spanning many diverse fields from economics to entertainment, to manufacturing, as well as medicine. Since modern AI's inception decades ago, practitioners in radiological sciences have been pioneering its development and implementation in medicine, particularly in areas related to diagnostic imaging and therapy. In this anniversary article, we embark on a journey to reflect on the learned lessons from past AI's chequered history. We further summarize the current status of AI in radiological sciences, highlighting, with examples, its impressive achievements and effect on re-shaping the practice of medical imaging and radiotherapy in the areas of computer-aided detection, diagnosis, prognosis, and decision support. Moving beyond the commercial hype of AI into reality, we discuss the current challenges to overcome, for AI to achieve its promised hope of providing better precision healthcare for each patient while reducing cost burden on their families and the society at large.


Assuntos
Inteligência Artificial/tendências , Radiologia/tendências , Algoritmos , Técnicas de Apoio para a Decisão , Previsões , Humanos , Interpretação de Imagem Assistida por Computador , Neoplasias/radioterapia , Radioterapia/tendências
6.
Radiologe ; 60(1): 6-14, 2020 Jan.
Artigo em Alemão | MEDLINE | ID: mdl-31915840

RESUMO

METHODICAL ISSUE: Machine learning (ML) algorithms have an increasingly relevant role in radiology tackling tasks such as the automatic detection and segmentation of diagnosis-relevant markers, the quantification of progression and response, and their prediction in individual patients. STANDARD RADIOLOGICAL METHODS: ML algorithms are relevant for all image acquisition techniques from computed tomography (CT) and magnetic resonance imaging (MRI) to ultrasound. However, different modalities result in different challenges with respect to standardization and variability. METHODICAL INNOVATIONS: ML algorithms are increasingly able to analyze longitudinal data for the training of prediction models. This is relevant since it enables the use of comprehensive information for predicting individual progression and response, and the associated support of treatment decisions by ML models. PERFORMANCE: The quality of detection and segmentation algorithms of lesions has reached an acceptable level in several areas. The accuracy of prediction models is still increasing, but is dependent on the availability of representative training data. ACHIEVEMENTS: The development of ML algorithms in radiology is progressing although many solutions are still at a validation stage. It is accompanied by a parallel and increasingly interlinked development of basic methods and techniques which will gradually be put into practice in radiology. PRACTICAL CONSIDERATIONS: Two factors will impact the relevance of ML in radiological practice: the thorough validation of algorithms and solutions, and the creation of representative diverse data for the training and validation in a realistic context.


Assuntos
Aprendizado de Máquina , Radiologia , Algoritmos , Humanos , Terminologia como Assunto
8.
World Neurosurg ; 133: e874-e892, 2020 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-31541754

RESUMO

OBJECTIVE: The increasing challenges facing the training of future neurosurgeons have led to continued development of simulation-based training, particularly for neurosurgical subspecialties. The simulators must be scientifically validated to fully assess their benefit and determine their educational effects. In this second part, we aim to identify the available simulators for spine, pediatric neurosurgery, interventional neuroradiology, and nontechnical skills, assess their validity, and determine their effectiveness. METHODS: Both Medline and Embase were searched for English language articles that validate simulation models for neurosurgery. Each study was screened according to the Messick validity framework, and rated in each domain. The McGaghie model of translational outcomes was then used to determine a level of effectiveness for each simulator or training course. RESULTS: Overall, 114 articles for 108 simulation-based training models or courses were identified. These articles included 24 for spine simulators, 3 for nontechnical skills, 10 for 9 pediatric neurosurgery simulators, and 12 for 11 interventional neuroradiology simulators. Achieving the highest rating for each validity domain were 3 models for content validity; 16 for response processes; 1 for internal structure; 2 for relations to other variables; and only 1 for consequences. For translational outcomes, 2 training courses achieved a level of effectiveness of >2, showing skills transfer beyond the simulator environment. CONCLUSIONS: With increasing simulators, there is a need for more validity studies and attempts to investigate translational outcomes to the operating theater when using these simulators. Nontechnical skills training is notably lacking, despite demand within the field.


Assuntos
Competência Clínica , Procedimentos Neurocirúrgicos/educação , Treinamento por Simulação/métodos , Medula Espinal/cirurgia , Coluna Vertebral/cirurgia , Criança , Humanos , Radiologia/educação
11.
Dentomaxillofac Radiol ; 49(1): 20190107, 2020 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-31386555

RESUMO

OBJECTIVES: To investigate the current clinical applications and diagnostic performance of artificial intelligence (AI) in dental and maxillofacial radiology (DMFR). METHODS: Studies using applications related to DMFR to develop or implement AI models were sought by searching five electronic databases and four selected core journals in the field of DMFR. The customized assessment criteria based on QUADAS-2 were adapted for quality analysis of the studies included. RESULTS: The initial electronic search yielded 1862 titles, and 50 studies were eventually included. Most studies focused on AI applications for an automated localization of cephalometric landmarks, diagnosis of osteoporosis, classification/segmentation of maxillofacial cysts and/or tumors, and identification of periodontitis/periapical disease. The performance of AI models varies among different algorithms. CONCLUSION: The AI models proposed in the studies included exhibited wide clinical applications in DMFR. Nevertheless, it is still necessary to further verify the reliability and applicability of the AI models prior to transferring these models into clinical practice.


Assuntos
Inteligência Artificial , Radiografia Dentária , Radiologia , Algoritmos , Inteligência Artificial/normas , Inteligência Artificial/tendências , Humanos , Radiografia Dentária/métodos , Radiografia Dentária/tendências , Reprodutibilidade dos Testes
12.
Harefuah ; 158(12): 807-811, 2019 Dec.
Artigo em Hebraico | MEDLINE | ID: mdl-31823536

RESUMO

INTRODUCTION: Lumbar disc herniation is a medical condition in which obscurity exists in the relation between the clinical and the radiological definition. The following paper was written by both surgeons and a radiologist, who are engaged in the field of spine surgery. The aim is to provide clear definitions as to the different pathologies involving disc herniation. The secondary goal of this article is to differentiate between the radiological picture and the clinical syndrome which are not necessarily connected. We hope this review will illuminate these issues and simplify the definitions and make it easier for all to use, primary care practitioners, general orthopedics and trauma care providers.


Assuntos
Deslocamento do Disco Intervertebral , Vértebras Lombares , Humanos , Degeneração do Disco Intervertebral , Radiografia , Radiologia
13.
Nihon Hoshasen Gijutsu Gakkai Zasshi ; 75(11): 1260-1269, 2019.
Artigo em Japonês | MEDLINE | ID: mdl-31748451

RESUMO

We analyzed 197 fall incidents in the questionnaire survey about the incident that occurred in Department of Radiology. In the past paper about the patient safety, there is no report that evaluated incident data directly. The purpose of this paper is to analyze the factor of the medical incidents using statistical technique scientifically. In this paper, we do not suggest concrete precaution. At first, we found the number of patients (each gender, modality, generation) in the five facilities of the coworker of one week. We found an incident rate from this patient total number, and we normalized data. As a result, we were able to do each risk evaluation because a risk ratio and relative risk degree was found. And, we were able to identify modality and the generation with the significant difference using the testing for differences in population rate. By our analyses, we revealed the chapter which must strengthen safety management.


Assuntos
Acidentes por Quedas , Segurança do Paciente , Radiologia , Humanos , Gestão de Riscos , Gestão da Segurança
14.
Radiologe ; 59(11): 951, 2019 Nov.
Artigo em Alemão | MEDLINE | ID: mdl-31667566
15.
Can Assoc Radiol J ; 70(4): 327-328, 2019 11.
Artigo em Inglês | MEDLINE | ID: mdl-31685097
16.
Pathologe ; 40(Suppl 3): 271-276, 2019 Dec.
Artigo em Alemão | MEDLINE | ID: mdl-31745604

RESUMO

Radiomics deals with the statistical analysis of radiologic image data. In this article, radiomics is introduced and some of its applications are presented. In particular, an example is used to demonstrate that pathology and radiology can work together for better diagnoses. There is no denying that artificial intelligence will find its place in radiology (and pathology). Deep learning in particular will increasingly find applications. However, the impact on clinical routine is more long term and probably gradual, so AI will initially only be used in the form of specialized tools to support everyday clinical practice until methods and programs improve to the extent that AI can also take on more general diagnoses. However, this will not replace pathologists and radiologists in the long term, but rather turn them into "information specialists" who interpret the results obtained and integrate them into clinical contours.


Assuntos
Inteligência Artificial , Interpretação de Imagem Radiográfica Assistida por Computador , Radiologia , Tecnologia Radiológica , Aprendizado Profundo , Humanos , Interpretação de Imagem Radiográfica Assistida por Computador/métodos , Radiografia
17.
J Pediatr Orthop ; 39(10): 505-509, 2019.
Artigo em Inglês | MEDLINE | ID: mdl-31599859

RESUMO

BACKGROUND: Variation exists in the Pavlik harness (PH) treatment regimen for infantile developmental dysplasia of the hip (DDH). The purpose of this study was to determine if the daily PH wear duration (23 vs. 24 h) and frequency of follow-up visits affect the clinical and radiographic outcomes of infants with dislocated but reducible (Ortolani+) hips. METHODS: This study reviewed prospectively enrolled patients with DDH in a single center who presented at age <6 months with Ortolani+ hips and were treated with PH. Recommended daily PH wear duration (23 vs. 24 h) and the frequency of clinic visits in first 4 weeks after the initiation of PH treatment were analyzed. The clinical success (stable hip that did not require closed or open reduction or the use of an abduction orthosis) and radiographic success based on the acetabular index at 2-year follow-up were compared between different PH regimen groups. RESULTS: Sixty-two patients (74 hips, 53 females) with Ortolani+ hips had a mean age of presentation of 23±28 days (range, 4 to 128 d) and mean follow-up of 33.2±18.4 months (range, 8 to 85 mo). Overall clinical success rate of PH for Ortolani+ hips was 93% (69/74 hips) and radiographic success rate at 2 years was 84% (48/57 hips). There was no difference in clinical or radiographic success rate between the 23- and 24-hour wear groups (P>0.99, 0.73) or between hips assessed almost weekly compared with once or twice during the first 4 weeks of PH treatment (P>0.99 for both). CONCLUSIONS: The 23- versus 24-hour PH regimen and frequency of clinic visits in the first 4 weeks of PH treatment did not affect the clinical or radiographic success rate of Ortolani+ hips in infantile DDH. A strict weekly clinic visit and 24-hour PH regimen may not be necessary to obtain stable reduced hips in infants presenting <6 months of age with Ortolani+ hips. LEVEL OF EVIDENCE: Level III-therapeutic.


Assuntos
Braquetes , Luxação Congênita de Quadril/terapia , Visita a Consultório Médico , Criança , Pré-Escolar , Protocolos Clínicos , Feminino , Seguimentos , Luxação Congênita de Quadril/diagnóstico por imagem , Humanos , Lactente , Recém-Nascido , Masculino , Radiologia , Estudos Retrospectivos , Fatores de Tempo , Resultado do Tratamento
18.
Can Assoc Radiol J ; 70(4): 329-334, 2019 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-31585825

RESUMO

This is a condensed summary of an international multisociety statement on ethics of artificial intelligence (AI) in radiology produced by the ACR, European Society of Radiology, RSNA, Society for Imaging Informatics in Medicine, European Society of Medical Imaging Informatics, Canadian Association of Radiologists, and American Association of Physicists in Medicine. AI has great potential to increase efficiency and accuracy throughout radiology, but it also carries inherent pitfalls and biases. Widespread use of AI-based intelligent and autonomous systems in radiology can increase the risk of systemic errors with high consequence and highlights complex ethical and societal issues. Currently, there is little experience using AI for patient care in diverse clinical settings. Extensive research is needed to understand how to best deploy AI in clinical practice. This statement highlights our consensus that ethical use of AI in radiology should promote well-being, minimize harm, and ensure that the benefits and harms are distributed among stakeholders in a just manner. We believe AI should respect human rights and freedoms, including dignity and privacy. It should be designed for maximum transparency and dependability. Ultimate responsibility and accountability for AI remains with its human designers and operators for the foreseeable future. The radiology community should start now to develop codes of ethics and practice for AI that promote any use that helps patients and the common good and should block use of radiology data and algorithms for financial gain without those two attributes.


Assuntos
Inteligência Artificial/ética , Radiologia/ética , Canadá , Consenso , Europa (Continente) , Humanos , Radiologistas/ética , Sociedades Médicas , Estados Unidos
19.
Eur J Radiol ; 120: 108661, 2019 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-31610322

RESUMO

Radiologists often encounter imaging requisitions that lack important information needed for accurate diagnostic studies. Reason for exam Imaging Reporting and Data System (RI-RADS) is proposed as a grading system for evaluation of the quality of clinically pertinent information provided in imaging requisitions. Three categories of information are suggested as key indicators of quality: impression, clinical findings, and the diagnostic question. This scheme is intended to improve the quality of imaging requisitions and overall patient care.


Assuntos
Radiografia/normas , Sistemas de Informação em Radiologia/normas , Sistemas de Dados , Erros de Diagnóstico/prevenção & controle , Humanos , Registros Médicos/normas , Melhoria de Qualidade , Radiologia/normas , Projetos de Pesquisa
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA