Vários desenvolvimentos tecnológicos estão convergindo de forma a aumentar a influência da área de imagens nas pesquisas biomédicas e na medicina clínica. Muitos pesquisadores têm trabalhado no desenvolvimento de sistemas computadorizados para detecção automatizada e quantificação de anormalidades em imagens radiológicas. Estes sistemas são dedicados ao diagnóstico auxiliado por computador. Este artigo discute os conceitos básicos relacionados ao diagnóstico auxiliado por computador e apresenta uma revisão bibliográfica sobre o assunto. Unitermos: Diagnóstico auxiliado por computador. Radiografia digital. Processamento de imagem. Visão computacional. Inteligência artificial.Computer-aided diagnosis in radiology. ResumoAbstract do computador como referência. A resposta do computador pode ser útil, uma vez que o diagnóstico do radiologista é baseado em avaliação subjetiva, estando sujeito a variações intra e interpessoais, bem como perda de informação devido à natureza sutil do achado radiológico, baixa qualidade da imagem, sobreposição de estruturas, fadiga visual ou distração. Além disso, foi demonstrado que uma dupla leitura (por dois radiologistas) pode aumentar a sensibilidade do diagnós-tico (3) . A proposta do CAD é funcionar como um segundo especialista.Basicamente, existem dois tipos de aplicações de sistemas CAD. Um é o auxílio à detecção de lesões, a partir da localização de padrões anormais através da varredura da imagem pelo computador (por exemplo, agrupamentos de microcalcificações em imagens mamográ-ficas ou nódulos pulmonares em imagens de tórax). O outro é o auxílio ao diagnós-tico, através da quantificação de características da imagem e sua classificação como correspondendo a padrões normais ou anormais (por exemplo, a associação da quantidade e forma das microcalcificações presentes em um agrupamento com a malignidade ou não do tumor, ou a associação da textura dos pulmões com lesões intersticiais em imagens de tórax). Em geral, os sistemas CAD utilizam-se de técnicas provenientes de duas áreas do conhecimento: visão computacional, que envolve o processamento de imagem para realce, segmentação e extração de atributos, e inteligência artificial, que inclui métodos para seleção de atributos e reconhecimento de padrões (4) . Por ter base conceitual genérica e ampla, a idéia do CAD pode ser aplicada a todas as modalidades de obtenção de imagem, incluindo radiografia convencional, tomografia computadorizada, ressonância magnética, ultra-sonografia e medicina nuclear. Pode-se, também, desenvolver esquemas de CAD para todos os tipos de exame de todas as partes do corpo, como crânio, tórax, abdome, osso e sistema vascular, entre outros. Porém, os principais objetos de pesquisa para o desenvolvimento de sistemas CAD têm sido as áreas de mamografia, para a detecção precoce do câncer de mama; tórax, para a detecção de nódulos pulmonares, lesões intersticiais e pneumotórax; e angiografia, para a análise quantitativa de estenoses e de fluxo sanguíneo(1) . VISÃO COMPUTACIONAL E INTELIGÊNCIA ARTIFICIALVisão ...
Background. The image-based identification of distinct tissues within dermatological wounds enhances patients' care since it requires no intrusive evaluations. This manuscript presents an approach, we named QTDU , that combines deep learning models with superpixel-driven segmentation methods for assessing the quality of tissues from dermatological ulcers. Method. QTDU consists of a three-stage pipeline for the obtaining of ulcer segmentation, tissues' labeling, and wounded area quantification. We set up our approach by using a real and annotated set of dermatological ulcers for training several deep learning models to the identification of ulcered superpixels. Results. Empirical evaluations on 179,572 superpixels divided into four classes showed QTDU accurately spot wounded tissues (AUC = 0.986, sensitivity = 0.97, and specificity = 0.974) and outperformed machinelearning approaches in up to 8.2% regarding F1-Score through fine-tuning of a ResNet-based model. Last, but not least, experimental evaluations also showed QTDU correctly quantified wounded tissue areas within a 0.089 Mean Absolute Error ratio. Conclusions. Results indicate QTDU effectiveness for both tissue segmentation and wounded area quantification tasks. When compared to existing machine-learning approaches, the combination of superpixels and deep learning models outperformed the competitors within strong significant levels. can be automatically evaluated by Computer-Aided Diagnosis (CAD) tools, or even used for the searching of massive databases through content-only queries, as in Content-Based Image Retrieval (CBIR) applications. In both CAD and CBIR cases, the detection of abnormalities requires the extraction of patterns from images, while a decision-making strategy is necessary for juxtaposing new images to those in the database [4,5].Since dermatological lesions are routinely diagnosed by biopsies and surrounding skin aspects, ulcers can be computationally characterized by particular types of tissues (and their areas) within the wounded region [6,7]. For instance, Mukherjee et al.[8] proposed a five-color classification model and applied a color-based low-level extractor further labeled by a Support-Vector Machine (SVM) strategy at an 87.61% hit ratio. Such idea of concatenating feature extraction and classification is found at the core of most wound segmentation strategies, as in the study of Kavitha et al.[9] that evaluated leg ulcerations by extracting patterns based on local spectral histograms to be labeled by a Multi-Layer Perceptron (MLP) classifier with 87.05% accuracy. Analogously, Pereyra et al.[10] discussed the use of color descriptors and an Instancebased Learning (IbL) classifier with a 61.7% hit ratio, whereas Veredas et al. [11] suggested the use of texture descriptors and an MLP classifier with 84.84% accuracy.Blanco et al.[4] and Chino et al.[12] followed a slightly different premise for finding proper similarity measures and comparison criteria for dermatological wounds. Their approaches are based on a divide-andconquer stra...
Background: Currently, magnetic resonance imaging (MRI) is used to evaluate active inflammatory sacroiliitis related to axial spondyloarthritis (axSpA). The qualitative and semiquantitative diagnosis performed by expert radiologists and rheumatologists remains subject to significant intrapersonal and interpersonal variation. This encouraged us to use machine-learning methods for this task. Methods: In this retrospective study including 56 sacroiliac joint MRI exams, 24 patients had positive and 32 had negative findings for inflammatory sacroiliitis according to the ASAS group criteria. The dataset was randomly split with~80% (46 samples, 20 positive and 26 negative) as training and~20% as external test (10 samples, 4 positive and 6 negative). After manual segmentation of the images by a musculoskeletal radiologist, multiple features were extracted. The classifiers used were the Support Vector Machine, the Multilayer Perceptron (MLP), and the Instance-Based Algorithm, combined with the Relief and Wrapper methods for feature selection. Results: Based on 10-fold cross-validation using the training dataset, the MLP classifier obtained the best performance with sensitivity = 100%, specificity = 95.6% and accuracy = 84.7%, using 6 features selected by the Wrapper method. Using the test dataset (external validation) the same MLP classifier obtained sensitivity = 100%, specificity = 66.7% and accuracy = 80%. Conclusions: Our results show the potential of machine learning methods to identify SIJ subchondral bone marrow edema in axSpA patients and are promising to aid in the detection of active inflammatory sacroiliitis on MRI STIR sequences. Multilayer Perceptron (MLP) achieved the best results.
This paper presents the metric histogram, a new and efficient technique to capture the brightness feature of images, allowing faster retrieval of images based on their content. Histograms provide a fast way to chop down large subsets of images, but are difficult to be indexed in existing data access methods. The proposed metric histograms reduce the dimensionality of the feature vectors leading to faster and more flexible indexing and retrieval processes. A new metric distance function DM( ) to measure the dissimilarity between images through their metric histograms is also presented. This paper shows the improvements obtained using the metric histograms over the traditional ones, through experiments for answering similarity queries over two databases containing respectively 500 and 4,247 magnetic resonance medical images. The experiments performed showed that metric histograms are more than 10 times faster than the traditional approach of using histograms and keep the same recovering capacity.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.