Machine learning approach for segmenting glands in colon histology images using local intensity and texture features

  title={Machine learning approach for segmenting glands in colon histology images using local intensity and texture features},
  author={Rupali Khatun and Soumick Chatterjee},
  journal={2018 IEEE 8th International Advance Computing Conference (IACC)},
  • Rupali KhatunS. Chatterjee
  • Published 1 December 2018
  • Computer Science
  • 2018 IEEE 8th International Advance Computing Conference (IACC)
Colon Cancer is one of the most common types of cancer. The treatment is planned to depend on the grade or stage of cancer. One of the preconditions for grading of colon cancer is to segment the glandular structures of tissues. Manual segmentation method is very time-consuming, and it leads to life risk for the patients. The principal objective of this project is to assist the pathologist to accurate detection of colon cancer. In this paper, the authors have proposed an algorithm for an… 

Figures and Tables from this paper

Colon Cancer Diagnosis Based on Machine Learning and Deep Learning: Modalities and Analysis Techniques

A comprehensive review of the current studies on colon cancer, classified into deep-learning (DL) and machine- learning (ML) techniques, and their main strengths and limitations are identified.

Using an ontology of the human cardiovascular system to improve the classification of histological images

This work used a Histological Ontology to correct, and therefore improve the classification of histological images, and was capable of recognising the epithelial tissue, previously not detected by any of the computer vision methods used, including a CNN proposal called HistoResNet evaluated in the experiments.

Lung Function Decline Predicting Using Improved EfficientNet

  • Yuxuan Tian
  • Medicine
    2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)
  • 2022
The result can be seen that the improved EfficienNet model owns the best performance with -6.89 Laplace Log Likelihood, which is higher than Resnet34, Resnet50 and EfficientNet respectively.



Gland segmentation from histology images using informative morphological scale space

This work proposes an automated solution for gland segmentation from hematoxylin & eosin (H&E) stained histology images based on a novel informative morphological scale space that uses the entropy of the connected components in a novel manner to prevent over segmentation of objects.

Gland segmentation in colon histology images: The glas challenge contest

A Nonlinear Mapping Approach to Stain Normalization in Digital Histopathology Images Using Image-Specific Color Deconvolution

The experimental results suggest that the paradigm of color normalization, as a preprocessing step, can significantly help histological image analysis algorithms to demonstrate stable performance which is insensitive to imaging conditions in general and scanner variations in particular.

A Stochastic Polygons Model for Glandular Structures in Colon Histology Images

The proposed Random Polygons Model (RPM) treats each glandular structure in an image as a polygon made of a random number of vertices, where the vertices represent approximate locations of epithelial nuclei.

Machine Learning in Medical Imaging

This special issue focuses on major trends and challenges in this area, and it presents work aimed at identifying new cutting-edge techniques and their use in medical imaging, as well as a series of medical imaging applications of machine-learning techniques.

Predicting credit card customer churn in banks using data mining

An ensemble system incorporating majority voting and involving Multilayer Perceptron, Logistic Regression, decision trees, Random Forest, Radial Basis Function, and Support Vector Machine as the constituents is developed to solve the customer credit card churn prediction via data mining.

Feature Selection for Knowledge Discovery and Data Mining

Colon Cancer Treatment (PDQ®)

    machinelearning This tertiary sourcereuses information from other sources but does not name them