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 91
- Downloads 0
Sorting Pairs of Points Based on Their Distances
Sorting data is one of the main problems in computer science which studied vastly and used in several places. In several geometric problems, like problems on point sets or lines in the plane or Euclidean space with highe...
Binary PSOGSA for Load Balancing Task Scheduling in Cloud Environment
In cloud environments, load balancing task scheduling is an important issue that directly affects resource utilization. Unquestionably, load balancing scheduling is a serious aspect that must be considered in the cloud r...
Word Sense Disambiguation Approach for Arabic Text
Word Sense Disambiguation (WSD) consists of identifying the correct sense of an ambiguous word occurring in a given context. Most of Arabic WSD systems are based generally on the information extracted from the local cont...
Robust Fuzzy-Second Order Sliding Mode based Direct Power Control for Voltage Source Converter
This paper focuses on a second order sliding mode based direct power controller (SOSM-DPC) of a three-phase grid-connected voltage source converter (VSC). The proposed control scheme combined with fuzzy logic aims at reg...
Implementation of Efficient Speech Recognition System on Mobile Device for Hindi and English Language
Speech recognition or speech to text conversion has rapidly gained a lot of interest by large organizations in order to ease the process of human to machine communication. Optimization of the speech recognition process i...