Machine Learning Based Classification of Colorectal Cancer Tumour Tissue in Whole-Slide Images

Abstract

The recent introduction of whole-slide scanning systems enabled accumulation of highquality pathology images into large collections, thus opening new perspectives in cancer research, as well as new analysis challenges. Automated identification of tumour tissue in the whole-slide image enables further use of developed grading systems that classify tumour cell abnormalities and predict tumour developments. In this article, we describe several possibilities to achieve epithelium-stroma classification of tumour tissues in digital pathology images by employing annotated superpixels to train machine learning algorithms. We emphasize that annotating superpixels rather than manually outlining tissue classes in raw images is less time consuming, and more effective way of producing ground truth for computational pathology pipelines. In our approach feature space for supervised learning is created from tissue class assigned superpixels by extracting colour and texture parameters, and applying dimensionality reduction methods. Alternatively, to train convolutional neural network, labelled superpixels are used to generate square image patches by moving fixed size window around each superpixel centroid. The proposed method simplifies the process of ground truth data collection and should minimize the time spent by a skilled expert to perform manual annotation of whole-slide images. We evaluate our method on a private data set of colorectal cancer images. Obtained results confirm that a method produces accurate reference data suitable for the use of different machine learning based classification algorithms.

A Comprehensive Review of Computer-aided Whole-slide Image Analysis: from Datasets to Feature Extraction, Segmentation, Classification, and Detection Approaches

“…[87] extracts the first-order statistics of 14 color channels, and the color histogram of each RGB channel is 8×38 bin histogram. In [88], for each 2D superpixel (for example, grayscale superpixel), two statistics are calculated of mean and standard deviation of the pixel value. For 3D superpixels (such as RGB superpixels), eight statistics are calculated the mean and standard deviation of the pixel value for each color channel and each RGB superpixel, then this as a color function.…”

Research on Machine Translation of Deep Neural Network Learning Model Based on Ontology

“…The machine translation Web server specification is a logical relationship, which is added to the J2EE platform, mainly including the port components and SOAP transmission provided by the Web container and the EJB container. J2EE Web services must be mapped to existing J2EE platform roles through a single port [36][37][38]. For example, J2EE Web service product provider roles are mapped to J2EE product provider roles.…”

Attribute Reduction Algorithm Based Early Warning Model of Sports Injury

“…Attribute reduction based on mutual information is to express the basic concept and operation of rough sugar set from the perspective of information theory. The basic information of mutual information has been introduced in the previous [22,23]. The basic idea is to select the most important attribute set to add to the core based on the core of the condition attribute relative to the decision attribute in the decision table, and finally take the mutual information equality as the end condition of reduction.…”