Thaina Aparecida Azevedo Tosta

Computational method for unsupervised segmentation of lymphoma histological images based on fuzzy 3-partition entropy and genetic algorithm

A segmentation method of lymphoma histological images is proposed.A public image dataset was used for the method evaluation.The proposed method is based on genetic algorithm and fuzzy 3-partition entropy.Neoplastic cells of different lymphomas were successfully identified.In comparison with other methods, this has reached the best results. Non-Hodgkin lymphoma is the most common cancer of the lymphatic system and should be considered as a group of several closely related cancers, which can show differences in their growth patterns, their impact on the body and how they are treated. The diagnosis of the different types of neoplasia is made by a specialist through the analysis of histological images. However, these analyses are complex and the same case can lead to different understandings among pathologists, due to the exhaustive analysis of decisions, the time required and the presence of complex histological features. In this context, computational algorithms can be applied as tools to aid specialists through the application of segmentation methods to identify regions of interest that are essential for lymphomas diagnosis. In this paper, an unsupervised method for segmentation of nuclear components of neoplastic cells is proposed to analyze histological images of lymphoma stained with hematoxylin-eosin. The proposed method is based on the association among histogram equalization, Gaussian filter, fuzzy 3-partition entropy, genetic algorithm, morphological techniques and the valley-emphasis method in order to analyze neoplastic nuclear components, improve the contrast and illumination conditions, remove noise, split overlapping cells and refine contours. The results were evaluated through comparisons with those provided by a specialist and techniques available in the literature considering the metrics of accuracy, sensitivity, specificity and variation of information. The mean value of accuracy for the proposed method was 81.48%. Although the method obtained sensitivity rates between 41% and 51%, the accuracy values showed relevance when compared to those provided by other studies. Therefore, the novelties presented here may already encourage new studies with a more comprehensive overview of lymphoma segmentation.

Features based on the percolation theory for quantification of non-Hodgkin lymphomas

Non-Hodgkin lymphomas are a health problem that affects over 70,000 people per year in the United States alone. The early diagnosis and the identification of this lymphoma are essential for an effective treatment. The classification of non-Hodgkin lymphomas is a task that continues to rank as one of the main challenges faced by hematologists, pathologists, as well as in the producing of computer vision methods due to its inherent complexity. In this paper, we present a new method to quantify and classify tissue samples of non-Hodgkin lymphomas based on the percolation theory. The method consists of associating multiscale and multidimensional approaches in order to divide the image into smaller regions and then verifying color similarity between pixels. A cluster labeling algorithm was applied to each region of interest to obtain the values for the number of clusters, occurrence of percolation and coverage ratio of the largest cluster. The method was tested on different classifiers aiming to differentiate three different groups of non-Hodgkin lymphomas. The obtained results (AUC rates between 0.940 and 0.993) were compared to those provided by methods consolidated in the Literature, which indicates that the percolation theory is a suitable approach for identifying these three classes of non-Hodgkin lymphomas, those being: mantle cell lymphoma, follicular lymphoma and chronic lymphocytic leukemia.

Multiscale Tetrahedral Meshes for FEM Simulations of Esophageal Injury

The radiofrequency cardiac ablation is a minimal invasive surgical procedure used for treating tachycardia, atrial fibrillation and atrial flutter. A possible complication is esophageal injury: the union of tissues from left atrium and esophagus, through necrosis. While this operation is being made, it is necessary to monitor the tissues temperatures accurately. The tests needed are complex and imply in death risks of the patient. Researchers are directed to simulate, with the finite element method, the behavior of the tissues under the influence of different levels of temperature: the objective is improving the cardiac ablation. Computational strategies were described in this work in order to obtain integrated meshes from thoracic and abdominal structures which are relevant to the study of this procedure. The methodology was based on strategies to represent structures in different scale and integrate software packages to generate meshes. The results were integrated, multiscale, and highly refined tetrahedral meshes from thoracic structures. The models were evaluated from dihedral angles histograms, indicating values between 5 and 170 degrees.

Unsupervised Segmentation of Leukocytes Images Using Thresholding Neighborhood Valley-Emphasis

Blood smear image analysis is essential to correlate the amount of leukocytes in these images with malignancies such as the leukemias. Techniques of digital image processing can be used to aid pathologists in this analysis, leading to appropriate treatments for the patient. This paper presents an unsupervised segmentation method for the nuclear structures in leukocytes. Deconvolution was used to split the Giemsa stain components and the regions of interest were selected using a thresholding algorithm called Neighborhood Valley-emphasis. A postprocessing approach based on morphological operators was applied in these detected structures. The proposed algorithm was tested on 367 images containing leukocytes and other blood structures. A performance analysis was conducted through the Jaccard and accuracy metrics featuring results of 89.89% and 99.57%, respectively. Such results were compared to other published articles and this was considered the most promising method.

Fitness Functions Evaluation for Segmentation of Lymphoma Histological Images Using Genetic Algorithm

For disease monitoring, grade definition and treatments orientation, specialists analyze tissue samples to identify structures of different types of cancer. However, manual analysis is a complex task due to its subjectivity. To help specialists in the identification of regions of interest, segmentation methods are used on histological images obtained by the digitization of tissue samples. Besides, features extracted from these specific regions allow for more objective diagnoses by using classification techniques. In this paper, fitness functions are analyzed for unsupervised segmentation and classification of chronic lymphocytic leukemia and follicular lymphoma images by the identification of their neoplastic cellular nuclei through the genetic algorithm. Qualitative and quantitative analyses allowed the definition of the Renyi entropy as the most adequate for this application. Images classification has reached results of 98.14% through accuracy metric by using this fitness function.

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.

Using wavelet sub-band and fuzzy 2-partition entropy to segment chronic lymphocytic leukemia images

Abstract Histological images analysis is an important procedure to diagnose different types of cancer. One of them is the chronic lymphocytic leukemia (CLL), which can be identified by applying image segmentation techniques. This study presents an unsupervised method to segment neoplastic nuclei in CLL images. Firstly, deconvolution, histogram equalization and mean filter were applied to enhance nuclear regions. Then, a segmentation technique based on a combination of wavelet transform, fuzzy 2-partition entropy and genetic algorithm was used, followed by removal of false positive regions, and application of valley-emphasis and morphological operations. In order to evaluate the proposed algorithm H&E-stained histological images were used. In the accuracy metric, the proposed method attained more than 80%, which can surpass similar methods. This proposal presents spatial distribution that has a good consistency with a manual segmentation and lower overlapping rate than other techniques in the literature.

Application of Evolutionary Algorithms on Unsupervised Segmentation of Lymphoma Histological Images

Histological images analysis is widely used to carry out diagnoses of different types of cancer. Digital image processing methods can be used for this purpose, leading to more objective diagnoses. Segmentation techniques are applied to identify cellular structures indicative of diseases. In addition, the extracted features from these specific regions can aid pathologists in diagnoses decision using classification techniques. In this paper, we present an evaluation of evolutionary algorithms applied to lymphoma images for segmentation of their neoplastic cellular nuclei. In a second stage, we investigated the performance of the segmented images in the classification step. Initially, the R channel from RGB color model was processed with histogram equalization and Gaussian filter. In the segmentation step, optimization methods were analyzed in combination with the fuzzy 3-partition technique. Then, we also applied the valley-emphasis method and morphological operations to remove false positive regions in the post-processing step. Intensity and texture features were extracted and classified by the support vector machine method for diagnoses of 62 and 99 images of follicular lymphoma and mantle cell lymphoma, respectively. The results were evaluated through qualitative and quantitative analyses and the differential evolution method has reached the best results in the segmentation step. This technique allowed a relevant performance on the classification task with a mean value of accuracy of 99.38%.