Your browser doesn't support javascript.
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 22.608
Filtrar
1.
Adv Exp Med Biol ; 1213: 3-21, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32030660

RESUMO

Deep learning is the state-of-the-art machine learning approach. The success of deep learning in many pattern recognition applications has brought excitement and high expectations that deep learning, or artificial intelligence (AI), can bring revolutionary changes in health care. Early studies of deep learning applied to lesion detection or classification have reported superior performance compared to those by conventional techniques or even better than radiologists in some tasks. The potential of applying deep-learning-based medical image analysis to computer-aided diagnosis (CAD), thus providing decision support to clinicians and improving the accuracy and efficiency of various diagnostic and treatment processes, has spurred new research and development efforts in CAD. Despite the optimism in this new era of machine learning, the development and implementation of CAD or AI tools in clinical practice face many challenges. In this chapter, we will discuss some of these issues and efforts needed to develop robust deep-learning-based CAD tools and integrate these tools into the clinical workflow, thereby advancing towards the goal of providing reliable intelligent aids for patient care.


Assuntos
Aprendizado Profundo , Diagnóstico por Computador , Diagnóstico por Imagem , Interpretação de Imagem Assistida por Computador , Humanos
2.
Adv Exp Med Biol ; 1213: 47-58, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32030662

RESUMO

Image-based computer-aided diagnosis (CAD) algorithms by the use of convolutional neural network (CNN) which do not require the image-feature extractor are powerful compared with conventional feature-based CAD algorithms which require the image-feature extractor for classification of lung abnormalities. Moreover, computer-aided detection and segmentation algorithms by the use of CNN are useful for analysis of lung abnormalities. Deep learning will improve the performance of CAD systems dramatically. Therefore, they will change the roles of radiologists in the near future. In this article, we introduce development and evaluation of such image-based CAD algorithms for various kinds of lung abnormalities such as lung nodules and diffuse lung diseases.


Assuntos
Aprendizado Profundo , Diagnóstico por Computador , Interpretação de Imagem Assistida por Computador , Pneumopatias/diagnóstico por imagem , Pulmão/diagnóstico por imagem , Humanos
3.
Adv Exp Med Biol ; 1213: 59-72, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32030663

RESUMO

For computer-aided diagnosis (CAD), detection, segmentation, and classification from medical imagery are three key components to efficiently assist physicians for accurate diagnosis. In this chapter, a completely integrated CAD system based on deep learning is presented to diagnose breast lesions from digital X-ray mammograms involving detection, segmentation, and classification. To automatically detect breast lesions from mammograms, a regional deep learning approach called You-Only-Look-Once (YOLO) is used. To segment breast lesions, full resolution convolutional network (FrCN), a novel segmentation model of deep network, is implemented and used. Finally, three conventional deep learning models including regular feedforward CNN, ResNet-50, and InceptionResNet-V2 are separately adopted and used to classify or recognize the detected and segmented breast lesion as either benign or malignant. To evaluate the integrated CAD system for detection, segmentation, and classification, the publicly available and annotated INbreast database is used over fivefold cross-validation tests. The evaluation results of the YOLO-based detection achieved detection accuracy of 97.27%, Matthews's correlation coefficient (MCC) of 93.93%, and F1-score of 98.02%. Moreover, the results of the breast lesion segmentation via FrCN achieved an overall accuracy of 92.97%, MCC of 85.93%, Dice (F1-score) of 92.69%, and Jaccard similarity coefficient of 86.37%. The detected and segmented breast lesions are classified via CNN, ResNet-50, and InceptionResNet-V2 achieving an average overall accuracies of 88.74%, 92.56%, and 95.32%, respectively. The performance evaluation results through all stages of detection, segmentation, and classification show that the integrated CAD system outperforms the latest conventional deep learning methodologies. We conclude that our CAD system could be used to assist radiologists over all stages of detection, segmentation, and classification for diagnosis of breast lesions.


Assuntos
Neoplasias da Mama/diagnóstico por imagem , Aprendizado Profundo , Diagnóstico por Computador , Interpretação de Imagem Assistida por Computador , Mamografia/métodos , Humanos
4.
Zhonghua Wei Chang Wai Ke Za Zhi ; 23(1): 33-37, 2020 Jan 25.
Artigo em Chinês | MEDLINE | ID: mdl-31958928

RESUMO

The rapid development of computer technologies brings us great changes in daily life and work. Artificial intelligence is a branch of computer science, which is to allow computers to exercise activities that are normally confined to intelligent life. The broad sense of artificial intelligence includes machine learning and robots. This article mainly focuses on machine learning and related medical fields, and deep learning is an artificial neural network in machine learning. Convolutional neural network (CNN) is a type of deep neural network, that is developed on the basis of deep neural network, further imitating the structure of the visual cortex of the brain and the principle of visual activity. The current machine learning method used in medical big data analysis is mainly CNN. In the next few years, it is the developing trend that artificial intelligence as a conventional tool will enter the relevant departments of medical image interpretation. In addition, this article also shares the progress of the integration of artificial intelligence and biomedicine combined with actual cases, and mainly introduces the current status of CNN application research in pathological diagnosis, imaging diagnosis and endoscopic diagnosis for gastrointestinal diseases.


Assuntos
Inteligência Artificial , Gastroenteropatias/diagnóstico , Gastroenteropatias/terapia , Diagnóstico por Computador , Humanos , Aprendizado de Máquina , Terapia Assistida por Computador
6.
Gastroenterology ; 158(1): 76-94.e2, 2020 01.
Artigo em Inglês | MEDLINE | ID: mdl-31593701

RESUMO

Since 2010, substantial progress has been made in artificial intelligence (AI) and its application to medicine. AI is explored in gastroenterology for endoscopic analysis of lesions, in detection of cancer, and to facilitate the analysis of inflammatory lesions or gastrointestinal bleeding during wireless capsule endoscopy. AI is also tested to assess liver fibrosis and to differentiate patients with pancreatic cancer from those with pancreatitis. AI might also be used to establish prognoses of patients or predict their response to treatments, based on multiple factors. We review the ways in which AI may help physicians make a diagnosis or establish a prognosis and discuss its limitations, knowing that further randomized controlled studies will be required before the approval of AI techniques by the health authorities.


Assuntos
Inteligência Artificial , Diagnóstico por Computador/métodos , Gastroenterologia/métodos , Gastroenteropatias/diagnóstico , Hepatopatias/diagnóstico , Tomada de Decisão Clínica/métodos , Sistemas de Apoio a Decisões Clínicas , Árvores de Decisões , Gastroenteropatias/mortalidade , Gastroenteropatias/terapia , Humanos , Hepatopatias/mortalidade , Hepatopatias/terapia , Prognóstico , Resultado do Tratamento
7.
Khirurgiia (Mosk) ; (12): 91-99, 2019.
Artigo em Russo | MEDLINE | ID: mdl-31825348

RESUMO

Recently, more and more attention has been paid to the utility of artificial intelligence in medicine. Radiology differs from other medical specialties with its high digitalization, so most software developers operationalize this area of medicine. The primary condition for machine learning is met because medical diagnostic images have high reproducibility. Today, the most common anatomic area for computed tomography is the thorax, particularly with the widespread lung cancer screening programs using low-dose computed tomography. In this regard, the amount of information that needs to be processed by a radiologist is snowballing. Thus, automatic image analysis will allow more studies to be interpreted. This review is aimed at highlighting the possibilities of machine learning in the chest computed tomography.


Assuntos
Diagnóstico por Computador/tendências , Detecção Precoce de Câncer , Neoplasias Pulmonares/diagnóstico por imagem , Aprendizado de Máquina/tendências , Tórax/diagnóstico por imagem , Tomografia Computadorizada por Raios X/tendências , Detecção Precoce de Câncer/instrumentação , Detecção Precoce de Câncer/métodos , Previsões , Humanos , Reprodutibilidade dos Testes
9.
Zhonghua Wai Ke Za Zhi ; 57(12): 934-938, 2019 Dec 01.
Artigo em Chinês | MEDLINE | ID: mdl-31826599

RESUMO

Objective: To examine the value and clinical application of convolutional neural network in pathological diagnosis of metastatic lymph nodes of gastric cancer. Methods: Totally 124 patients with advanced gastric cancer who underwent radical gastrectomy plus D2 lymphadenectomy at Affiliated Hospital of Qingdao University from July 2016 to December 2018 were selected in the study. According to the chronological order, the first 80 cases were served as learning group. The remaining 44 cases were served as verification group. There were 45 males and 35 females in the study group, with average age of 57.6 years. There were 29 males and 15 females in the validation group, with average age of 9.2 years. The pre-training convolutional neural network architecture Resnet50 was trained and fine-tuned by 21 352 patches with cancer areas and 14 997 patches without cancer areas in the training group. A total of 78 whole-slide image served as a test dataset including positive (n=38) and negative (n=40) lymph nodes. The convolutional neural network computer-aided detection (CNN-CAD) system was used to analyze the ability of convolutional neural network system to screen metastatic lymph nodes at the level of slice by setting threshold, and evaluate the system's classification accuracy by calculating its sensitivity, specificity, positive predictive value, negative predictive value and area under the receiver operating characteristic curve (AUC). Results: The classification accuracy of CNN-CAD system at slice level was 100%.The AUC for the CNN-CAD system was 0.89. The sensitivity was 0.778, specificity was 0.995, overall accuracy was 0.989. Positive and negative predictive values were 0.822 and 0.994, respectively. The CNN-CAD system achieved the same classification results as pathologists. Conclusions: The CNN-CAD system has been constructed to distinguished benign and malignant lymph node slides with high accuracy and specificity. It could achieve the similar classification results as pathologists.


Assuntos
Linfonodos/patologia , Neoplasias Gástricas/diagnóstico por imagem , Neoplasias Gástricas/patologia , Criança , Conjuntos de Dados como Assunto , Diagnóstico por Computador , Feminino , Gastrectomia/métodos , Humanos , Processamento de Imagem Assistida por Computador , Excisão de Linfonodo , Linfonodos/cirurgia , Metástase Linfática , Masculino , Pessoa de Meia-Idade , Neoplasias Gástricas/cirurgia
10.
Medicine (Baltimore) ; 98(50): e18324, 2019 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-31852123

RESUMO

BACKGROUND: Although many machine learning algorithms have been developed to detect anterior cruciate ligament (ACL) injury based on magnetic resonance imaging (MRI), the performance of different algorithms required further investigation. The objectives of this current systematic review are to evaluate the diagnostic accuracy of machine-learning-assisted detection for ACL injury based on MRI and find the current best algorithm. METHOD: We will conduct a comprehensive database search for clinical diagnostic tests in PubMed, EMBASE, Cochrane Library, and Web of science without restrictions on publication status and language. The reference lists of the included articles will also be checked to identify additional studies for potential inclusion. Two reviewers will independently review all literature for inclusion and assess their methodological quality using Quality Assessment of Diagnostic Accuracy Studies version 2. Clinical diagnostic tests exploring the efficacy of machine-learning-assisted system for detecting ACL injury based on MRI will be considered for inclusion. Another 2 reviewers will independently extract data from eligible studies based on a pre-designed standardized form. Any disagreements will be resolved by consensus. RevMan 5.3 and Stata SE 12.0 software will be used for data synthesis. If appropriate, we will calculate the summary sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratio of machine-learning-assisted diagnosis system for ACL injury detection. A hierarchical summary receiver operating characteristic (HSROC) curve will also be plotted, and the area under the ROC curve (AUC) is going to calculated using the bivariate model. If the pooling of results is considered inappropriate, we will present and describe our findings in diagrams and tables and describe them narratively. RESULT: This is the first systematic assessment of machine learning system for the detection of ACL injury based on MRI. We predict it will provide highquality synthesis of existing evidence for the diagnostic accuracy of machine-learning-assisted detection for ACL injury and a relatively comprehensive reference for clinical practice and development of interdisciplinary field of artificial intelligence and medicine. CONCLUSION: This protocol outlined the significance and methodologically details of a systematic review of machine-learning-assisted detection for ACL injury based on MRI. The ongoing systematic review will provide high-quality synthesis of current evidence of machine learning system for detecting ACL injury. REGISTRATION: The meta-analysis has been prospectively registered in PROSPERO (CRD42019136581).


Assuntos
Lesões do Ligamento Cruzado Anterior/diagnóstico por imagem , Diagnóstico por Computador/estatística & dados numéricos , Aprendizado de Máquina , Imagem por Ressonância Magnética/estatística & dados numéricos , Diagnóstico por Computador/métodos , Humanos , Imagem por Ressonância Magnética/métodos , Metanálise como Assunto , Curva ROC , Projetos de Pesquisa , Sensibilidade e Especificidade , Revisão Sistemática como Assunto
12.
Zhonghua Lao Dong Wei Sheng Zhi Ye Bing Za Zhi ; 37(10): 768-772, 2019 Oct 20.
Artigo em Chinês | MEDLINE | ID: mdl-31726509

RESUMO

Objective: To investigate the visual application of the CiteSpace software in the field of work-related musculoskeletal disorders (WMSDs) . Methods: The literature on WMSDs research, published from 1991 to 2017, was retrieved in Web of Science database. The CiteSpace 5.2 was used to make visualization analysis on the hotspots and tendency of the keywords, authors, countries (regions) and research institutes in relevant literature. Results: A total of 3224 literatures were included in the analysis. The amount of the literatures published was increasing annually. The key word co-occurrence network showed that the research hotspots mainly focused on the study of epidemiology, risk factors, symptoms, and other aspects of WMSDs. The cooperation network and time network of counties and regions showed that America and Europe were at the leading position in the field of WMSD, and the top three were America, Canada and Sweden. The developing countries, like Brazil and China, had also begun to make relative research since 2000. In research cooperation, the collaboration among countries, research institutions was relatively close, and multiple leading core authors and teams were formed in the international arena. Conclusion: The CiteSpace software can directly demonstrate the hotspots and tendency in the area of WMSDs.


Assuntos
Diagnóstico por Computador , Doenças Musculoesqueléticas/diagnóstico , Doenças Profissionais/diagnóstico , Software , Humanos
13.
Rev Med Suisse ; 15(671): 2092-2097, 2019 Nov 13.
Artigo em Francês | MEDLINE | ID: mdl-31742940

RESUMO

Lung cancer remains the most common cause of cancer deaths in the world, but its mortality can be significantly reduced by diagnosis and early detection. Computerized resources were developed to assist radiologists in their management of the large volume of thoracic images to be analyzed. Their objective is the detection of pulmonary nodules with high sensitivity and a low rate of false-positives and the ability to differentiate benign and malignant nodules. The volume of a pulmonary nodule and its volume doubling time are essential to nodule management. Computer aided detection or diagnosis (CAD) software are not currently used in clinically settings on a routine basis . Significant advances are expected due to the implementation of the artificial intelligence systems who will probably be integrated into the multidisciplinary management of any pulmonary nodule.


Assuntos
Inteligência Artificial , Diagnóstico por Computador , Neoplasias Pulmonares/diagnóstico , Neoplasias Pulmonares/terapia , Humanos , Neoplasias Pulmonares/patologia , Nódulos Pulmonares Múltiplos/diagnóstico , Nódulos Pulmonares Múltiplos/patologia , Nódulos Pulmonares Múltiplos/terapia , Sensibilidade e Especificidade
14.
Medicine (Baltimore) ; 98(42): e17596, 2019 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-31626135

RESUMO

To date, consumer health tools available over the web suffer from serious limitations that lead to low quality health- related information. While health data in our world are abundant, access to it is limited because of liability and privacy constraints.The objective of the present study was to develop and evaluate an algorithm-based tool which aims at providing the public with reliable, data-driven information based and personalized information regarding their symptoms, to help them and their physicians to make better informed decisions, based on statistics describing "people like you", who have experienced similar symptoms.We studied anonymized medical records of Maccabi Health Care. The data were analyzed by employing machine learning methodology and Natural Language Processing (NLP) tools. The NLP tools were developed to extract information from unstructured free-text written by Maccabi's physicians.Using machine learning and NLP on over 670 million notes of patients' visits with Maccabi physicians accrued since 1993, we developed predictors for medical conditions based on patterns of symptoms and personal characteristics.The algorithm was launched for Maccabi insured members on January 7, 2018 and for members of Integrity Family Care program in Alabama on May 1, 2018.The App. invites the user to describe her/ his main symptom or several symptoms, and this prompts a series of questions along the path developed by the algorithm, based on the analysis of 70 million patients' visits to their physicians.Users started dialogues with 225 different types of symptoms, answering on average 22 questions before seeing how people similar to them were diagnosed. Users usually described between 3 and 4 symptoms (mean 3.2) in the health dialogue.In response to the question "conditions verified by your doctor", 82.4% of responders (895/1085) in Maccabi reported that the diagnoses suggested by K's health dialogues were in agreement with their doctor's final diagnosis. In Integrity Health Services, 85.4% of responders (111/130) were in agreement with the physicians' diagnosis.While the program achieves very high approval rates by its users, its primary achievement is the 85% accuracy in identifying the most likely diagnosis, with the gold standard being the final diagnosis made by the personal physician in each individual case. Moreover, the machine learning algorithm continues to update itself with the feedback given by users.


Assuntos
Algoritmos , Apendicite/diagnóstico , Tomada de Decisões , Diagnóstico por Computador/métodos , Aprendizado de Máquina , Complicações na Gravidez/diagnóstico , Adulto , Apendicectomia , Apendicite/cirurgia , Feminino , Humanos , Gravidez , Smartphone
15.
Zhongguo Yi Liao Qi Xie Za Zhi ; 43(5): 359-361, 2019 Sep 30.
Artigo em Chinês | MEDLINE | ID: mdl-31625336

RESUMO

Based on the developing situation of Computer Aided Diagnosis/Detection (CAD) software, considering the domestic and international regulation of CAD software, according to current Medical Device Classification Catalog and related laws of China Food and Drug Administration (CFDA), this paper investigated and analyzed the classification of CAD software, and provided technical suggestion on classifying principle of CAD software applying Artificial Intelligence (AI) or other advanced technology from medical device regulation scope, for the reference of regulatory and technical departments.


Assuntos
Diagnóstico por Computador , Interpretação de Imagem Radiográfica Assistida por Computador , Software , Inteligência Artificial , China
17.
Phys Med ; 64: 1-9, 2019 Aug.
Artigo em Inglês | MEDLINE | ID: mdl-31515007

RESUMO

BACKGROUND: Microcalcification clusters in mammograms can be considered as early signs of breast cancer. However, their detection is a very challenging task because of different factors: large variety of breast composition, highly textured breast anatomy, impalpable size of microcalcifications in some cases, as well as inherent low contrast of mammograms. Thus, the need to support the clinicians' work with an automatic tool. METHODS: In this work a three-phases approach for clustered microcalcification detection is presented. Specifically, it is made up of a pre-processing step, aimed at highlighting potentially interesting breast structures, followed by a single microcalcification detection step, based on Hough transform, that is able to grasp the innate characteristic shape of the structures of interest. Finally, a cluster identification step to group microcalcifications is carried out by means of a clustering algorithm able to codify expert domain rules. RESULTS: The detection performance of the proposed method has been evaluated on 364 mammograms of 182 patients obtaining a true positive ratio of 91.78% with 2.87 false positives per image. CONCLUSIONS: Experimental results demonstrated that the proposed method is able to detect microcalcification clusters in digital mammograms showing performance comparable to different methodologies exploited in the state-of-art approaches, with the advantage that it does not require any training phase and a large set of data. The performance of the proposed approach remains high even for more difficult clinical cases of mammograms of young women having high-density breast tissue thus resulting in a reduced contrast between microcalcifications and surrounding dense tissues.


Assuntos
Calcinose/diagnóstico por imagem , Diagnóstico por Computador/métodos , Mamografia/métodos , Adulto , Idoso , Algoritmos , Automação , Neoplasias da Mama/complicações , Neoplasias da Mama/diagnóstico por imagem , Calcinose/complicações , Reações Falso-Positivas , Feminino , Humanos , Processamento de Imagem Assistida por Computador , Pessoa de Meia-Idade
20.
Bone Joint J ; 101-B(9): 1042-1049, 2019 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-31474147

RESUMO

AIMS: Several radiological methods of measuring anteversion of the acetabular component after total hip arthroplasty (THA) have been described. These are limited by low reproducibility, are less accurate than CT 3D reconstruction, and are cumbersome to use. These methods also partly rely on the identification of obscured radiological borders of the component. We propose two novel methods, the Area and Orthogonal methods, which have been designed to maximize use of readily identifiable points while maintaining the same trigonometric principles. PATIENTS AND METHODS: A retrospective study of plain radiographs was conducted on 160 hips of 141 patients who had undergone primary THA. We compared the reliability and accuracy of the Area and Orthogonal methods with two of the current leading methods: those of Widmer and Lewinnek, respectively. RESULTS: The 160 anteroposterior pelvis films revealed that the proposed Area method was statistically different from those described by Widmer and Lewinnek (p < 0.001 and p = 0.004, respectively). They gave the highest inter- and intraobserver reliability (0.992 and 0.998, respectively), and took less time (27.50 seconds (sd 3.19); p < 0.001) to complete. In addition, 21 available CT 3D reconstructions revealed the Area method achieved the highest Pearson's correlation coefficient (r = 0.956; p < 0.001) and least statistical difference (p = 0.704) from CT with a mean within 1° of CT-3D reconstruction between ranges of 1° to 30° of measured radiological anteversion. CONCLUSION: Our results support the proposed Area method to be the most reliable, accurate, and speedy. They did not support any statistical superiority of the proposed Orthogonal method to that of the Widmer or Lewinnek method. Cite this article: Bone Joint J 2019;101-B:1042-1049.


Assuntos
Acetábulo/diagnóstico por imagem , Artroplastia de Quadril/efeitos adversos , Anteversão Óssea/diagnóstico por imagem , Cabeça do Fêmur/diagnóstico por imagem , Prótese de Quadril/efeitos adversos , Acetábulo/cirurgia , Anteversão Óssea/etiologia , Diagnóstico por Computador , Cabeça do Fêmur/cirurgia , Humanos , Radiografia , Reprodutibilidade dos Testes , Estudos Retrospectivos , Tomografia Computadorizada por Raios X
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA