Percolation Images: Fractal Geometry Features for Brain Tumor Classification.

Brain tumor detection is crucial for clinical diagnosis and efficient therapy. In this work, we propose a hybrid approach for brain tumor classification based on both fractal geometry features and deep learning. In our proposed framework, we adopt the concept of fractal geometry to generate a "percolation" image with the aim of highlighting important spatial properties in brain images. Then both the original and the percolation images are provided as input to a convolutional neural network to detect the tumor. Extensive experiments, carried out on a well-known benchmark dataset, indicate that using percolation images can help the system perform better.

OralEpitheliumDB: A Dataset for Oral Epithelial Dysplasia Image Segmentation and Classification.

Early diagnosis of potentially malignant disorders, such as oral epithelial dysplasia, is the most reliable way to prevent oral cancer. Computational algorithms have been used as an auxiliary tool to aid specialists in this process. Usually, experiments are performed on private data, making it difficult to reproduce the results. There are several public datasets of histological images, but studies focused on oral dysplasia images use inaccessible datasets. This prevents the improvement of algorithms aimed at this lesion. This study introduces an annotated public dataset of oral epithelial dysplasia tissue images. The dataset includes 456 images acquired from 30 mouse tongues. The images were categorized among the lesion grades, with nuclear structures manually marked by a trained specialist and validated by a pathologist. Also, experiments were carried out in order to illustrate the potential of the proposed dataset in classification and segmentation processes commonly explored in the literature. Convolutional neural network (CNN) models for semantic and instance segmentation were employed on the images, which were pre-processed with stain normalization methods. Then, the segmented and non-segmented images were classified with CNN architectures and machine learning algorithms. The data obtained through these processes is available in the dataset. The segmentation stage showed the F1-score value of 0.83, obtained with the U-Net model using the ResNet-50 as a backbone. At the classification stage, the most expressive result was achieved with the Random Forest method, with an accuracy value of 94.22%. The results show that the segmentation contributed to the classification results, but studies are needed for the improvement of these stages of automated diagnosis. The original, gold standard, normalized, and segmented images are publicly available and may be used for the improvement of clinical applications of CAD methods on oral epithelial dysplasia tissue images.

Unsupervised method for normalization of hematoxylin-eosin stain in histological images.

Histological images stained with hematoxylin-eosin are widely used by pathologists for cancer diagnosis. However, these images can have color variations that highly influence the histological image processing techniques. To deal with this potential limitation, normalization methods are useful for color correction. In this paper, a histological image color normalization is presented by considering the biological and hematoxylin-eosin properties. To this end, the stain representation of a reference image was applied in place of the original images representation, allowing the preservation of histological structures. This proposal was evaluated on histological images with great variations of contrast, and both visual and quantitative analyzes yielded promising results.

Color normalization of faded H&E-stained histological images using spectral matching.

Histological samples stained with hematoxylin-eosin (H&E) are commonly used by pathologists in cancer diagnoses. However, the preparation, digitization, and storage of tissue samples can lead to color variations that produce poor performance when using histological image processing techniques. Thus, normalization methods have been proposed to adjust the color of the image. This can be achieved through the use of a spectral matching technique, where it is first necessary to estimate the H&E representation and the stain concentration in the image pixels by means of the RGB model. This study presents an estimation method for H&E stain representation for the normalization of faded histological samples. This application has been explored only to a limited extent in the literature, but has the capacity to expand the use of faded samples. To achieve this, the normalized images must have a coherent color representation of the H&E stain with no introduction of noise, which was realized by applying the methodology described in this proposal. The estimation method presented here aims to normalize histological samples with different degrees of fading using a combination of fuzzy theory and the Cuckoo search algorithm, and dictionary learning with an initialization method for optimization. In visual and quantitative comparisons of estimates of H&E stain representation from the literature, our proposed method achieved very good results, with a high feature similarity between the original and normalized images.

Computational normalization of H&E-stained histological images: Progress, challenges and future potential.

Different types of cancer can be diagnosed with the analysis of histological samples stained with hematoxylin-eosin (H&E). Through this stain, it is possible to identify the architecture of tissue components and analyze cellular morphological aspects that are essential for cancer diagnosis. However, preparation and digitization of histological samples can lead to color variations that influence the performance of segmentation and classification algorithms in histological image analysis systems. Among the determinant factors of these color variations are different staining time, concentration and pH of the solutions, and the use of different digitization systems. This has motivated the development of normalization algorithms of histological images for their color adjustments. These methods are designed to guarantee that biological samples are not altered and artifacts are not introduced in the images, thus compromising the lesions diagnosis. In this context, normalization techniques are proposed to minimize color variations in histological images, and they are topics covered by important studies in the literature. In this proposal, it is presented a detailed study of the state of art of computational normalization of H&E-stained histological images, highlighting the main contributions and limitations of correlated works. Besides, the evaluation of normalization methods published in the literature are depicted and possible directions for new methods are described.

Multidimensional and fuzzy sample entropy (SampEnMF) for quantifying H&E histological images of colorectal cancer.

In this study, we propose to use a method based on the combination of sample entropy with multiscale and multidimensional approaches, along with a fuzzy function. The model was applied to quantify and classify H&E histological images of colorectal cancer. The multiscale approach was defined by analysing windows of different sizes and variations in tolerance for determining pattern similarity. The multidimensional strategy was performed by considering each pixel in the colour image as an n-dimensional vector, which was analysed from the Minkowski distance. The fuzzy strategy was a Gaussian function used to verify the pertinence of the distances between windows. The result was a method capable of computing similarities between pixels contained in windows of various sizes, as well as the information present in the colour channels. The power of quantification was tested in a public colorectal image dataset, which was composed of both benign and malignant classes. The results were given as inputs for classifiers of different categories and analysed by applying the k-fold cross-validation and holdout methods. The derived performances indicate that the proposed association was capable of distinguishing the benign and malignant groups, with values that surpassed those results obtained with important techniques available in the Literature. The best performance was an AUC value of 0.983, an important result, mainly when we consider the difficulties of clinical practice for the diagnosis of the colorectal cancer.

Lymphoma images analysis using morphological and non-morphological descriptors for classification.

Mantle cell lymphoma, follicular lymphoma and chronic lymphocytic leukemia are the principle subtypes of the non-Hodgkin lymphomas. The diversity of clinical presentations and the histopathological features have made diagnosis of such lymphomas a complex task for specialists. Computer aided diagnosis systems employ computational vision and image processing techniques, which contribute toward the detection, diagnosis and prognosis of digitised images of histological samples. Studies aimed at improving the understanding of morphological and non-morphological features for classification of lymphoma remain a challenge in this area. This work presents a new approach for the classification of information extracted from morphological and non-morphological features of nuclei of lymphoma images. We extracted data of the RGB model of the image and employed contrast limited adaptive histogram equalisation and 2D order-statistics filter methods to enhance the contrast and remove noise. The regions of interest were identified by the global thresholding method. The flood-fill and watershed techniques were used to remove the small false positive regions. The area, extent, perimeter, convex area, solidity, eccentricity, equivalent diameter, minor axis and major axis measurements were computed for the regions detected in the nuclei. In the feature selection stage, we applied the ANOVA, Ansari-Bradley and Wilcoxon rank sum methods. Finally, we employed the polynomial, support vector machine, random forest and decision tree classifiers in order to evaluate the performance of the proposed approach. The non-morphological features achieved higher AUC and AC values for all cases: the obtained rates were between 95% and 100%. These results are relevant, especially when we consider the difficulties of clinical practice in distinguishing the studied groups. The proposed approach is useful as an automated protocol for the diagnosis of lymphoma histological tissue.

An approach for COFFEE objective function to global DNA multiple sequence alignment.

Multiple sequence alignment (MSA) is one of the most important tasks in bioinformatics and it can be used to prediction of structures or functions of unknown proteins and to phylogenetic tree reconstruction. There are many heuristics to perform multiple sequence alignment, as Progressive Alignment, Ant Colony, Genetic Algorithms, among others. Along the years, some tools were proposed to perform MSA and MSA-GA is one of them. The MSA-GA is a tool based on Genetic Algorithm to perform multiple sequence alignment and its results are generally better than other well-known tools in bioinformatics, as Clustal W. The COFFEE objective function was implemented in the MSA-GA in order to allow it to produce better alignments to less similar sequence sets of proteins. Nonetheless, the COFFEE objective function is not suited do perform multiple sequence alignment of nucleotides. Thus, we have modified the COFFEE objective function, previously implemented in the MSA-GA, to allow it to obtain better results also to sequences of nucleotides. Our results have shown that our approach has achieved better results in all cases when compared with standard COFFEE and most of cases when compared with WSP for all test cases from BAliBase and BRAliBase. Moreover, our results are more reliable because their standard deviations have less variation.

Fractal dimension in quantifying the degree of myocardial cellular rejection after cardiac transplantation.

INTRODUCTION: The term "Fractal" is derived from the Latin fractus meaning "irregular" or "broken" considering the observed structure with a non-integer dimension. There are many studies which employed the Fractal Dimension (FD) as a diagnostic tool. One of the most common methods for its study is the "Box Counting Method". OBJECTIVE: The aim of the present study was to try to establish the contribution of FD in the quantification of myocardial cellular rejection after cardiac transplantation. METHODS: Microscopic digital images were captured at 800x600 resolution (magnification 100x). FD was calculated with the aid of "ImageJ software" with adaptations. The classification of the degrees of rejection was in agreement with the "International Society for Heart and Lung Transplantation" (ISHLT 2004). The final report of the degree of rejection was confirmed and redefined after an exhaustive review of the slides by an external experienced pathologist. 658 slides were evaluated with the following distribution among the degrees of rejection (R): 335 (0R); 214 (1R); 70 (2R); 39 (3R). The data were statistically analyzed with Kruskal-Wallis tests and ROC curves being considered significant values of P < 0.05. RESULTS: There was significant statistical difference between the various degrees of rejection with the exception of R3 versus R2. The same trend was observed in applying the ROC curve. CONCLUSION: FD may contribute to the assessment of myocardial cellular rejection. Higher values are directly associated with progressively higher degrees of rejection. This may help in decision making of doubtful cases and those which contemplate the intensification of immunosuppressive medication.

Dimensão fractal na quantificação do grau de rejeição celular miocárdica pós-transplante cardíaco / Fractal dimension in quantifying the degree of myocardial cellular rejection after cardiac transplantation

INTRODUÇÃO: O termo "fractal" é derivado do latim fractus, que significa "irregular" ou "quebrado", considerando a estrutura observada como tendo uma dimensão não-inteira. Há muitos estudos que empregaram a Dimensão Fractal (DF) como uma ferramenta de diagnóstico. Um dos métodos mais comuns para o seu estudo é a "Box-plot counting" (Método de contagem de caixas). OBJETIVO: O objetivo do estudo foi tentar estabelecer a contribuição da DF na quantificação da rejeição celular miocárdica após o transplante cardíaco. MÉTODOS: Imagens microscópicas digitalizadas foram capturadas na resolução 800x600 (aumento de 100x). A DF foi calculada com auxílio do "software ImageJ", com adaptações. A classificação dos graus de rejeição foi de acordo com a "Sociedade Internacional de Transplante Cardíaco e Pulmonar" (ISHLT 2004). O relatório final do grau de rejeição foi confirmado e redefinido após exaustiva revisão das lâminas por um patologista experiente externo. No total, 658 lâminas foram avaliadas, com a seguinte distribuição entre os graus de rejeição (R): 335 (0R), 214 (1R), 70 (2R), 39 (3R). Os dados foram analisados estatisticamente com os testes Kruskal-Wallis e curvas ROC sendo considerados significantes valores de P < 0,05. RESULTADOS: Houve diferença estatística significativa entre os diferentes graus de rejeição com exceção da 3R versus 2R. A mesma tendência foi observada na aplicação da curva ROC. CONCLUSÃO: ADF pode contribuir para a avaliação da rejeição celular do miocárdio. Os valores mais elevados estiveram diretamente associados com graus progressivamente maiores de rejeição. Isso pode ajudar na tomada de decisão em casos duvidosos e naqueles que possam necessitar de intensificação da medicação imunossupressora.

INTRODUCTION: The term "Fractal" is derived from the Latin fractus meaning "irregular" or "broken" considering the observed structure with a non-integer dimension. There are many studies which employed the Fractal Dimension (FD) as a diagnostic tool. One of the most common methods for its study is the "Box Counting Method". OBJECTIVE: The aim of the present study was to try to establish the contribution of FD in the quantification of myocardial cellular rejection after cardiac transplantation. METHODS: Microscopic digital images were captured at 800x600 resolution (magnification 100x). FD was calculated with the aid of "ImageJ software" with adaptations. The classification of the degrees of rejection was in agreement with the "International Society for Heart and Lung Transplantation" (ISHLT 2004). The final report of the degree of rejection was confirmed and redefined after an exhaustive review of the slides by an external experienced pathologist. 658 slides were evaluated with the following distribution among the degrees of rejection (R): 335 (0R); 214 (1R); 70 (2R); 39 (3R). The data were statistically analyzed with Kruskal-Wallis tests and ROC curves being considered significant values of P < 0.05. RESULTS: There was significant statistical difference between the various degrees of rejection with the exception of R3 versus R2. The same trend was observed in applying the ROC curve. CONCLUSION: FD may contribute to the assessment of myocardial cellular rejection. Higher values are directly associated with progressively higher degrees of rejection. This may help in decision making of doubtful cases and those which contemplate the intensification of immunosuppressive medication.