Cardiovascular diseases represent the number one cause of death in the world, including the most common disorders in the heart's health, namely coronary artery disease (CAD). CAD is mainly caused by fat accumulated in the arteries' internal walls, creating an atherosclerotic plaque that impacts the blood flow functional behavior. Anatomical plaque characteristics are essential but not sufficient for a complete functional assessment of CAD. In fact, plaque analysis and visual inspection alone have proven insufficient to determine the lesion severity and hemodynamic repercussion. Furthermore, the fractional flow reserve (FFR) exam, which is considered the gold standard for stenosis functional impair determination, is invasive and contains several limitations. Such a panorama evidences the need for new techniques applied to image exams to improve CAD functional assessment. In this article, we perform a systematic literature review on emerging methods determining CAD significance, thus delivering a unique base for comparing these methods, qualitatively and quantitatively. Our goal is to guide further studies with evidence from the most promising methods, highlighting the benefits from both areas. We summarize benchmarks,
Objectives: Artificial intelligence has generated a significant impact in the health field. The aim of this study was to perform the training and validation of a convolutional neural network (CNN)-based model to automatically classify six clinical representation categories of oral lesion images. Method: The CNN model was developed with the objective of automatically classifying the images into six categories of elementary lesions: (1) papule/nodule; (2) macule/spot; (3) vesicle/bullous; (4) erosion; (5) ulcer and (6) plaque. We selected four architectures and using our dataset we decided to test the following architectures: ResNet-50, VGG16, InceptionV3 and Xception. We used the confusion matrix as the main metric for the CNN evaluation and discussion. Results: A total of 5069 images of oral mucosa lesions were used. The oral elementary lesions classification reached the best result using an architecture based on InceptionV3. After hyperparameter optimization, we reached more than 71% correct predictions in all six lesion classes. The classification achieved an average accuracy of 95.09% in our dataset. Conclusions: We reported the development of an artificial intelligence model for the automated classification of elementary lesions from oral clinical images, achieving satisfactory performance. Future directions include the study of including trained layers to establish patterns of characteristics that determine benign, potentially malignant and malignant lesions.
Atherosclerosis represents the restriction of blood flow in the heart muscle and is one of the main causes of death in the world. The assessment of atherosclerosis is challenging and is currently evaluated by the Fractional Flow Reserve (FFR) and the Quantitative Flow Ratio (QFR). Both exams are based on angiography, which is the gold standard for geometrical assessment. This study presents a pipeline to automatically determine the presence of narrowing in the right coronary artery (RCA) angiography exams, segmenting the artery silhouette, selecting regions of interest (ROIs) followed by a classification model. Initial results suggest a valid sequence of steps to classify the lesion, but require some improvements in the network architecture for better classification accuracy.
Doenças cardiovasculares representam a causa número um de óbitos no mundo, e inclui a doença mais comum na saúde cardíaca, chamada de doença arterial coronariana (DAC). DAC é causada principalmente pelo acúmulo de gordura no interior das paredes arteriais, criando uma placa aterosclerótica que impacta o comportamento funcional no fluxo sanguíneo. As características anatômicas das placas são essenciais para a correta avaliação funcional das DACs. De fato, não há métodoúnico para avaliar todos os segmentos da artéria coronária com alta acurácia. O panorama apresentado, evidencia a necessidade de novas técnicas aplicadas em exames de imagem para melhorar a avaliação funcional de doenças arteriais coronarianas, substituindo etapas manuais com detecção automática de lesões. Esse estudo apresenta uma arquitetura de rede neural para detecção de objetos, chamada DeepCADD para determinar a posição da lesão em exames de angiografias em artérias coronárias esquerdas. Usando uma rede neural convolucional baseada em regiões (Mask R-CNN), nós buscamos atingir precisão comparável ao padrão-ouro, automatizando uma etapa manual no protocolo atual. Nós substituímos o backbone da Mask R-CNN com uma rede ResNet-50 treinada com segmentos de artérias coronárias para melhorar a detecção de pequenos objetos em imagens de angiografia. Nós também treinamos o DeepCADD com angiografias coletadas em uma instituição de saúde local. DeepCADD apresentou melhores resultados de sensibilidade em comparação com os estudos relacionados e correlação significante com os especialistas durante a validação, o que sugere seu uso no protocolo atual da angiografia. DeepCADD aumentou a correlação entre os especialistas e proveu sugestões de DAC, especialmente em lesões com vários segmentos afetados, diferenciando a arquitetura proposta da atual literatura. DeepCADD detecta um grande número de candidatos verdadeiros positivos para a posterior quantificação das lesões. Com isso, esperamos expandir o uso do DeepCADD para as demais artérias e para a avaliação dinâmica de lesões em estudos posteriores.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.