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.

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.