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

Abstract

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.

Fractal Neural Network: A new ensemble of fractal geometry and convolutional neural networks for the classification of histology images

“…There are few computer vision approaches that were able to perform well on different histological image categories [48,39,19,52]. Moreover, both handcrafted fractal features [46,48,49] and CNN models [31,6,3] were able to provide high accuracy rates in several CAD systems for histopathology tasks. Therefore, an ensemble method that addresses both fractal geometry and deep learning, which is the core of our proposal, could be able to improve these results when applied to different histology datasets.…”

“…Such media is said to be percolating if a fluid can flow through the whole system, from the top to the bottom. In computer vision, this concept can be applied to verify the image porosity, or some cluster properties regarding pixel neighborhoods [49]. The first steps to obtain percolation features from a colored image follow the same procedures described for obtaining FD and LAC features.…”

A Method For Multiclass Lymphoma Classification Based on Morphological and Non-Morphological Descriptors

“…All works presented in the table use more complex descriptors demanding more expensive image processing and hinder their model's interpretation by doctors, who are not familiar with this type of data. Furthermore, their methods are generally black-box, or at least, not trivial to be understood by non-specialists, such as SVM [6], [16], [25], neural networks [20] and polynomial classifiers [13], where the information is embedded in the model or requires an expensive training. In the other hand, our methodology uses simpler and easier to extract descriptors, and employs the GBDT algorithm, providing…”

Ensemble Learning-Based Solutions: An Approach for Evaluating Multiple Features in the Context of H&E Histological Images

“…For instance, Haralick and LBPs have been applied in several imaging contexts [32][33][34], exploring the identification of lung cancer subtypes [35], the presence of cancerous characteristics in breast tissue samples [18,36] and the classification of colorectal cancer [6]. In addition, techniques that involve fractals at multiple scales and/or dimensions have also been applied to quantify the pathological architectures of tumors [23,25,26], demonstrating relevant results in the pattern recognition of prostate cancer [37], lymphomas [38], intraepithelial neoplasia [39], breast tumors [40], colorectal cancer [13] and psoriatic lesions [41]. Moreover, fractal methods are important for texture analysis because they provide information about the complexity of textures and patterns that are similar at various levels of magnification [42].…”