A5069078682- AI in cancer detection
- Digital Imaging for Blood Diseases
- Image Retrieval and Classification Techniques
- Radiomics and Machine Learning in Medical Imaging
- Oral Health Pathology and Treatment
- Cell Image Analysis Techniques
- Oral and Maxillofacial Pathology
- Machine Learning and Data Classification
- Gene expression and cancer classification
- COVID-19 diagnosis using AI
- Anomaly Detection Techniques and Applications
- Numerical Methods and Algorithms
- Neural Networks and Applications
- Medical Image Segmentation Techniques
- Mycobacterium research and diagnosis
- Brain Tumor Detection and Classification
- Image and Signal Denoising Methods
- SARS-CoV-2 detection and testing
- Matrix Theory and Algorithms
- Image Processing Techniques and Applications
- Software Engineering Research
- Head and Neck Cancer Studies
- Sports Performance and Training
- Colorectal Cancer Screening and Detection
- Sports Analytics and Performance
Instituto Federal de Educação, Ciência e Tecnologia do Triângulo Mineiro
2012-2024
Federal Institute of São Paulo
2024
Universidade Federal de Uberlândia
2013
Early diagnosis of potentially malignant disorders, such as oral epithelial dysplasia, is the most reliable way to prevent cancer. Computational algorithms have been used an auxiliary tool aid specialists in this process. Usually, experiments are performed on private data, making it difficult reproduce results. There several public datasets histological images, but studies focused dysplasia images use inaccessible datasets. This prevents improvement aimed at lesion. study introduces...
Covid-19 is a severe illness caused by the Sars-CoV-2 virus, initially identified in China late 2019 and swiftly spreading globally. Since virus primarily impacts lungs, analyzing chest X-rays stands as reliable widely accessible means of diagnosing infection. In computer vision, deep learning models such CNNs have been main adopted approach for detection X-ray images. However, we believe that handcrafted features can also provide relevant results, shown previously similar image...
In this work, a method is proposed to analyze the influence of color normalization in classification lymphoma images. The approach combines multidimensional fractal techniques, curvelet transforms and Haralick features. considered feature selection technique different approaches evaluate combinations, such as decision tree, random forest, support vector machine, naive bayes k-star. classifications were analyzed considering three common classes: mantle cell lymphoma, follicular chronic...
Oral epithelial dysplasia is a potentially malignant lesion that presents challenges for diagnosis. The use of digital systems in histological analysis can aid specialists to obtain data allows robust and fast grading process, but there are few methods the literature proposing system this lesion. This study method oral histopathological images combining deep features polynomial classifier. ResNet50 AlexNet models were trained with information was extracted from convolutional layers,...
Breast cancer is one of the most common diseases in women world. There are various imaging techniques employed diagnosis. The histological image analysis supported by computational systems has proved to be quite effective diagnosing disease. In this paper, we present an approach quantify and classify tissue samples breast based on features extracted from intensity histogram, co-occurrence matrix Shannon, Renyi, Tsallis Kapoor entropies. attribute set was obtain feature vectors which were...
Histological image analysis through systems to aid diagnosis plays an important role in medicine with supplementary reading for the specialist's diagnosis. This work proposes a method based on association of extracted features by fractal techniques, regularization and polynomial classifier. The feature vectors were classified applying cross-validation technique 10 folds. evaluation results occurred metrics such as accuracy (ACC) imbalance metric (IAM). proposed approach achieved significant...