Cell nuclei segmentation in histopathological images is essential for diagnosing oral epithelial dysplasia, a condition associated with an increased risk of oral cancer. Deep learning models have demonstrated significant potential in this task, but challenges persist due to variations in staining, tissue morphology, and artifacts. This study investigates segmentation models and proposes ensemble approaches to improve instance segmentation in OED histological images. The ensemble integrates diverse segmentation models using different voting rules, with the$D_{C^{-}}$weighted averaging achieving the best results. The proposed method obtained an accuracy of$\mathbf{9 4. 0 9 \%}$and a Dice coefficient of 0.9461, surpassing individual models and demonstrating significant improvement. Comparative analysis with the literature shows that the ensemble achieved competitive performance across multiple datasets. These results reinforce the potential of ensemble learning to enhance segmentation accuracy, contributing to the development of robust computer-aided diagnosis systems.

Cancer remains a major global health threat due to its high mortality rate and the challenges associated with its treatment, especially in the later stages. It is very important that the patient identify the cancer as soon as possible to increase recovery chances, and for this, histological images are often used. These images are often looked at by a professional, who analyzes it and categorizes the tissue in labels, but it is often a difficult process for these professionals to analyze a great number of images, and that is why it is used computer vision and neural networks to aid in the identification steps of the disease. A very important network structure that can be used in computer vision is a model called U-Net, named after the U shape made by the decoding and encoding blocks, this network model extracts information while changing the size of the image, being able to get the finest to the more general features of the image. This network can also use an attention system to further improve the feature extraction phase and aid in even better segmentation, with multiple attention models for different purposes. Therefore, this study shows how these attention channels can be tweaked to improve the model results, allowing different types of attention to improve in areas of weakness of the model.

Covid-19 is a severe illness caused by the Sars-CoV-2 virus, initially identified in China in late 2019 and swiftly spreading globally. Since the virus primarily impacts the lungs, analyzing chest X-rays stands as a reliable and widely accessible means of diagnosing the infection. In computer vision, deep learning models such as CNNs have been the main adopted approach for detection of Covid-19 in chest X-ray images. However, we believe that handcrafted features can also provide relevant results, as shown previously in similar image classification challenges. In this study, we propose a method for identifying Covid-19 in chest X-ray images by extracting and classifying local and global percolation-based features. This technique was tested on three datasets: one comprising 2,002 segmented samples categorized into two groups (Covid-19 and Healthy); another with 1,125 non-segmented samples categorized into three groups (Covid-19, Healthy, and Pneumonia); and a third one composed of 4,809 non-segmented images representing three classes (Covid-19, Healthy, and Pneumonia). Then, 48 percolation features were extracted and give as input into six distinct classifiers. Subsequently, the AUC and accuracy metrics were assessed. We used the 10-fold cross-validation approach and evaluated lesion sub-types via binary and multiclass classification using the Hermite polynomial classifier, a novel approach in this domain. The Hermite polynomial classifier exhibited the most promising outcomes compared to five other machine learning algorithms, wherein the best obtained values for accuracy and AUC were 98.72% and 0.9917, respectively. We also evaluated the influence of noise in the features and in the classification accuracy. These results, based in the integration of percolation features with the Hermite polynomial, hold the potential for enhancing lesion detection and supporting clinicians in their diagnostic endeavors.

Early diagnosis of potentially malignant disorders, such as oral epithelial dysplasia (OED), is the most reliable way to prevent oral cancer. Computational algorithms have been used as a tool to aid specialists in this process. In recent years, CNN-based methods have gained more attention due to their improved results in nuclei segmentation tasks. Despite these relevant results, achieving high segmentation accuracy remains a challenging task. In this paper, we propose an ensemble of segmentation models to improve the performance of nuclei segmentation in OED histopathology images. The proposed ensemble consists of four CNN segmentation models, which were combined using three ensemble strategies: simple averaging, weighted averaging and majority voting, achieved accuracy of 90.69%, 90.70% and 88.49%, respectively, when applied to OED images. The model's performance was also evaluated on three publicly available datasets and achieved comparable performance to state-of-the-art segmentation methods. These values indicate that the proposed ensemble methods can be used in medical image analysis applications.

Liver cancer is one of the most common types of cancer according to World Health Statistics. Computer-aided diagnosis (CAD) systems are used in medical imaging for liver tumor identification and classification. Texture is a type of feature that can provide measurements of properties such as smoothness and regularity of the image. Handcraft techniques based on fractal geometry allow quantifying self-similarity properties present in images. However, new studies have shown that using information obtained from deep-learned feature maps can maximize the results of classical classifiers. This work presents an approach that investigates descriptors obtained by handcrafted and deep learning features, feature selection methods and the Hermite polynomial (HP) algorithm to classifier liver histological images. The results were evaluated using metrics such as accuracy (ACC) and the imbalance accuracy metric (IAM). The association with fractal features, Lasso regularization and the HP algorithm achieved 0.98 of IAM and 99.53% ACC, which was relevant when evaluated with other studies in the literature.

Oral epithelial dysplasia is a common type of pre-cancerous lesion that can be categorized as mild, moderate and severe. The manual diagnosis of this type of lesion is a time consuming and complex task. The use of digital systems applied to microscopic image analysis can aid the decision making of specialists. In recent years, deep learning-based methods are getting more attention due to its improved results in nuclei segmentation tasks. In this paper, we propose a methodology for nuclei segmentation on images of dysplastic tissues using neural networks. Several optimization algorithms and color normalization methods were evaluated. The methodology was performed on a dataset of mice tongue images. The experimental evaluations showed that the Nadam optimizer in combination with images without the use of color normalization obtained the best results. The method was able to segment the images with an average accuracy of 0.887, the sensitivity of 0.762 and specificity of 0.942. The algorithm was compared to other segmentation methods and showed relevant results. These values indicate that the proposed method can be used as a tool to aid specialists in the nuclei analysis of histological images of the buccal cavity.

Fracta1 techniques are widely explored to quantity and recognize texture patterns in digital images. Among the different types of fractal techniques, one that stands out is the Higuchi fractal dimension. The Higuchi fractal dimension allows determining how much space is filled in a two-dimensional image through the projection of the image in 1D signals. This property provides the possibility to calculate the Higuchi fractal dimension of specific regions of an image. The main drawback of this technique is that it does not allow the analysis of color images. In this work, a new Higuchi fractal dimension model is presented with the inclusion of multidimensional and multiscale strategies to expand the traditional Higuchi dimension for texture analysis in color images. The multidimensional approach was applied considering each pixel of the color image as an n-dimensional vector. The multiscale strategy was defined using different scales of observation. The proposed model was applied to a set of 151 colorectal histological images to test its ability to quantity and separate the benign and malignant groups from colorectal cancer. The performance of the proposed model was compared with that provided by consolidated fractal dimension techniques. The results obtained are promising and indicate that the proposal contributes significantly to the literature focused on the quantification and recognition of texture patterns with fractal techniques.