Intelligent Diagnostic System for Nuclei Structure Classification of Thyroid Cancerous and Non-Cancerous Tissues
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2017, Vol 8, Issue 7
Abstract
Recently, image mining has opened new bottlenecks in the field of biomedical discoveries and machine leaning techniques have brought significant revolution in medical diagnosis. Especially, classification problem of human cancerous tissues would assume to be one of the really challenging problems since it requires very high optimized algorithms to select the appropriate features from histopathological images of well-differentiated thyroid cancers. For instance prediction of initial changes in neoplasm such as hidden patterns of nuclei overlapping sequences, variations in nuclei structures, distortion in chromatin distributions and identification of other micro- architectural behaviors would provide more meticulous assistance to doctors in early diagnosis of cancer. In-order to mitigate all above stated problems this paper proposes a novel methodology so called “Intelligent Diagnostic System for Nuclei Structural Classification of Thyroid Cancerous and Non-Cancerous Tissues” which classifies nuclei structures and cancerous behaviors from medical images by using proposed algorithm Auto_Tissue_Analysis. Overall methodology of approach is comprised of four layers. In first layer noise reduction techniques are used. In second layer feature selection techniques are used. In third layer decision model is constructed by using random forest (tree based) algorithm. Finally result visualization and performance evaluation is done by using confusion matrix, precision and recall measures. The overall classification accuracy is measured about 74% with 10-k fold cross validation.
Authors and Affiliations
Jamil Ahmed Chandio, M. Abdul Rehman Soomrani
Keywords
Related Articles
- EP ID EP260405
- DOI 10.14569/IJACSA.2017.080746
- Views 54
- Downloads 0
A Compact Modified Square Printed Planar Antenna for UWB Microwave Imaging Applications
In this paper, both frequency and time domain performances of a new compact planar antenna for the ultra-wideband (UWB) applications are fully investigated. The proposed antenna has the size of 12x18 mm² providing a frac...
Analysis of Guess and Determined Attack on Non Linear Modified SNOW 2.0 Using One LFSR
stream ciphers encrypt the data bit by bit. In this research a new model of stream cipher SNOW 2.0 has been proposed i.e. Non linear modified SNOW 2.0 using one Linear Feedback Shift Register (LFSR) with the embedding of...
Regression-Based Feature Selection on Large Scale Human Activity Recognition
In this paper, we present an approach for regression-based feature selection in human activity recognition. Due to high dimensional features in human activity recognition, the model may have over-fitting and can’t learn...
A New Approach for Enhancing the Quality of Medical Computerized Tomography Images
Computerized tomography (CT) images contribute immensely to medical research and diagnosis. However, due to degradative factors such as noise, low contrast, and blurring, CT images tend to be a degraded representation of...
High-Speed FPGA-based of the Particle Swarm Optimization using HLS Tool
The Particle Swarm Optimization (PSO) is a heuristic search method inspired by different biological populations on their swarming or collaborative behavior. This novel work has implemented PSO for the Travelling Salesman...