A reliable nuclei segmentation is still an open-ended problem, especially in the breast cancer histology images. For the same, this paper proposes an intelligent gravitational search algorithm based superpixel clustering method for automatic nuclei segmentation. In the proposed method, a novel variant of gravitational search algorithm, intelligent gravitational search algorithm, is employed to obtain the optimal cluster centroids. The experimental and statistical results evince that the proposed variant surpasses existing meta-heuristic algorithms on 47 benchmark functions belonging to different problem categories i.e., unimodal, multimodal, and real-parameter single objective optimization problems of CEC, 2013. Further, the segmentation accuracy of the proposed method is examined on H&E stained estrogen receptor positive (ER+) breast cancer images. Experiments affirm that the proposed method is comparatively an efficacious and accurate method for segmenting the nuclei within breast cancer histology images.

An automatic nuclei segmentation method using intelligent gravitational search algorithm based superpixel clustering

Colorectal cancer is one of the most common types of cancer according to worldwide incidences statistics. The correct diagnosis of this lesion leads to the indication of the most adequate treatments for cancer-affected patients. The diagnosis is made through the visual analysis of tissue samples by pathologists. However, this analysis is susceptible to intra- and inter-pathologists variability in addition to being a complex and time-consuming task. To deal with these challenges, image processing methods are developed for application on histological images obtained through the digitization of the tissue samples. To do so, feature extraction and classification techniques are investigated to aid pathologists and make it possible a faster and more objective diagnosis definition. Therefore, in this work, we propose a method that associates multidimensional fractal techniques, curvelet transforms and Haralick descriptors for the study and pattern recognition of colorectal cancer, which not yet explored in the Literature. The proposed method considered a feature selection approach and different classification techniques for evaluating associations, such as decision tree, random forest, support vector machine, naive Bayes, k*, and a polynomial method. This strategy allowed for more precise interpretations regarding the best associations for the separation of groups concerning histological images of colorectal cancer. The proposal was tested on colorectal images from two distinct datasets commonly investigated in the Literature. The best result was reached with features based mainly on lacunarity and percolation obtained from curvelet sub-images, using a polynomial classifier. The tests were evaluated by applying the 10-fold cross-validation method and the result was 0.994 of AUC, which is a relevant contribution to the Literature of pattern recognition of colorectal cancer. The obtained performance with a detailed analysis involving different types of features and classifiers are important contributions for pathologists, specialists interested in the study of this cancer and histological image processing researchers, which aim to develop the clinically applicable computational techniques.

Classification of colorectal cancer based on the association of multidimensional and multiresolution features

While it is well established that cortical morphology differs in relation to a variety of inter-individual factors, it is often characterized using estimates of volume, thickness, surface area, or gyrification. Here we developed a computational approach for estimating sulcal width and depth that relies on cortical surface reconstructions output by FreeSurfer. While other approaches for estimating sulcal morphology exist, studies often require the use of multiple brain morphology programs that have been shown to differ in their approaches to localize sulcal landmarks, yielding morphological estimates based on inconsistent boundaries. To demonstrate the approach, sulcal morphology was estimated in three large sample of adults across the lifespan, in relation to aging. A fourth sample is additionally used to estimate test–retest reliability of the approach. This toolbox is now made freely available as supplemental to this paper: https://cmadan.github.io/calcSulc/
 .

/pdf/robust-estimation-of-sulcal-morphology-2xgyy4s5r7.pdf

Robust estimation of sulcal morphology

PURPOSE To achieve automatic classification of viable and necrotic tumor regions in osteosarcoma, most of the existing deep learning methods can only design a simple model to prevent overfitting on small datasets, which leads to the weak ability of extracting image features and low accuracy of the models. In order to solve the above problem, a deep model with Siamese network (DS-Net) was designed in this paper. METHODS The DS-Net constructed on the basis of full convolutional networks is composed of an auxiliary supervision network (ASN) and a classification network. The construction of the ASN based on the Siamese network aims to solve the problem of a small training set (the main bottleneck of deep learning in medical images). It uses paired data as the input and updates the network through combined labels. The classification network uses the features extracted by the ASN to perform accurate classification. RESULTS Pathological diagnosis is the most accurate method to identify osteosarcoma. However, due to intraclass variation and interclass similarity, it is challenging for pathologists to accurately identify osteosarcoma. Through the experiments on hematoxylin and eosin (H&E)-stained osteosarcoma histology slides, the DS-Net we constructed can achieve an average accuracy of 95.1%. Compared with existing methods, the DS-Net performs best in the test dataset. CONCLUSIONS The DS-Net we constructed can not only effectively realize the histological classification of osteosarcoma, but also be applicable to many other medical image classification tasks affected by small datasets.

Deep model with Siamese network for viable and necrotic tumor regions assessment in osteosarcoma.

Extraction of sulcal medial surface and classification of Alzheimer's disease using sulcal features

Currently, diagnosis of colon cancer is based on manual examination of histopathological images by a pathologist. This can be time consuming and interpretation of the images is subject to inter- and intra-observer variability. This may be improved by introducing a computer-aided diagnosis (CAD) system for automatic detection of cancer tissue within whole slide hematoxylin and eosin (H&E) stains. Cancer disrupts the normal control mechanisms of cell proliferation and differentiation, affecting the structure and appearance of the cells. Therefore, extracting features from segmented cell nuclei structures may provide useful information to detect cancer tissue. A framework for automatic classification of regions of interest (ROI) containing either benign or cancerous colon tissue extracted from whole slide H&E stained images using cell nuclei features was proposed. A total of 1,596 ROI's were extracted from 87 whole slide H&E stains (44 benign and 43 cancer). A cell nuclei segmentation algorithm consisting of color deconvolution, k-means clustering, local adaptive thresholding, and cell separation was performed within the ROI's to extract cell nuclei features. From the segmented cell nuclei structures a total of 750 texture and intensity-based features were extracted for classification of the ROI's. The nine most discriminative cell nuclei features were used in a random forest classifier to determine if the ROI's contained benign or cancer tissue. The ROI classification obtained an area under the curve (AUC) of 0.96, sensitivity of 0.88, specificity of 0.92, and accuracy of 0.91 using an optimized threshold. The developed framework showed promising results in using cell nuclei features to classify ROIs into containing benign or cancer tissue in H&E stained tissue samples. © 2017 International Society for Advancement of Cytometry.

https://onlinelibrary.wiley.com/doi/pdf/10.1002/cyto.a.23175

Using cell nuclei features to detect colon cancer tissue in hematoxylin and eosin stained slides.

Alzheimer’s disease (AD), an age-related progressive neurodegenerative disorder, is the most common cause of dementia. It is characterised by abnormal neuroanatomical changes in the brain, some of which can be difficult to distinguish from the alterations caused by normal aging. Sulcal morphology is affected by AD atrophy, indicates significant differences between cognitively normal (CN) and AD subjects, and proves to be a potential AD biomarker. 210 subjects (100 CN, 110 AD) were acquired from the ADNI database. 120 sulci were extracted per subject using BrainVISA sulcal identification pipeline. Mean curvature, surface area and volume were calculated for each sulcus, parameterized by a 3D mesh, and used as AD/CN classification features. 184 subjects were correctly classified (AD=98, CN=86), producing an accuracy of 88%, sensitivity of 89%, specificity of 86%, based on 33 features. Results indicate that sulcal morphology, when based on specific features, could be a valuable AD biomarker.

https://link.springer.com/content/pdf/10.1007%2F978-3-319-19665-7_9.pdf

Anders Munk Rasmussen

Papers

Using cell nuclei features to detect colon cancer tissue in hematoxylin and eosin stained slides.

Classification of Alzheimer’s Disease from MRI Using Sulcal Morphology