Friday 29th of March 2024
 

Proposed Seed Pixel Region Growing Segmentation and Artificial Neural Network Classifier for Detecting the Renal Calculi in Ultrasound Images for Urologist Decisions


Sujata Navratnam, Siti Fazilah Shamsudin, Valliappan Raman and Sundresan Perumal

The most common problem in the daily lives of men and woman is the occurrence of kidney stone, which is named as renal calculi, due to living nature of the people. These calculi can be occurred in kidney, urethra or in the urinary bladder. Most of the existing study in the diagnosis of ultrasound image of the kidney stone identifies the presence or absence of stone in the kidney. The main objective of the paper is to propose a computer aided diagnosis prototype for early detection of kidney stones which helps to change the diet condition and prevention of stone formation in future. The proposed work is based image acquisition, image enhancement, segmentation, feature extraction and classification, whereas in initial stage, ultrasound of kidney image is diagnosed for the presence of renal calculi stone and its level of growth measured in sizes. Seed pixel based region growing segmentation is applied in our work to localize the intensity threshold variation, based on the different threshold variation, it is categorized into a class of images as normal, stone and stone at early stages. The proposed segmentation is based on identifying the homogeneous regions which depends on the granularity features, therefore interested structure with different dimensions are compared with speckle size and extracted. The shape and different size of the grown regions are depending on the entries in lookup table. After completing the stage of region growing, region merging is used to suppress the high frequency artifacts in the ultrasound image. Once the segmented portion of stone is extracted and statistical features are calculated, which can be feed as feature selection by principle component analysis method. The extracted features are in input for artificial neural network classifier for achieving the improved accuracy compared to previous works. The expected output findings are based on texture feature values, threshold variations, size of the stone from the ultrasound kidney image samples with the support of clinical research center. The findings in our study and observation are based on correct estimate size of the stones, position of the stones in location of kidney; these findings are not performed in previous work. The enhanced seed pixel region growing segmentation and ANN classification helps to diagnose the presence or absence of renal calculi kidney stones, which leads to an early detection stone formation in the kidney and improve the accuracy rate of classification.

Keywords: Kidney Stone, Segmentation, Feature Extraction and Classification

Download Full-Text


ABOUT THE AUTHORS

Sujata Navratnam
Sujata Navratnam is a lecturer in KDU University College, Malaysia. Her research interests are in image processing, ICT in education and software engineering

Siti Fazilah Shamsudin
Siti Fazilah Shamsudin is a lecturer in KDU University College, Malaysia. Her research interests are in software engineering, computer network and security.

Valliappan Raman
Dr. Valliappan Raman is a Lecturer at Swinburne University of Technology Sarawak. He have worked as team to acquire many external research grants and published papers in impact factor journals. His research interests are in medical imaging, data mining and health informatics

Sundresan Perumal
Dr.Sundresan Perumal is a senior lecturer in Universiti Sains Islamic Malaysia. He acquired various external research grants and published papers in impact factor journals. His research interests are in cyber security, medical imaging, data mining and network forensics


IJCSI Published Papers Indexed By:

 

 

 

 
+++
About IJCSI

IJCSI is a refereed open access international journal for scientific papers dealing in all areas of computer science research...

Learn more »
Join Us
FAQs

Read the most frequently asked questions about IJCSI.

Frequently Asked Questions (FAQs) »
Get in touch

Phone: +230 911 5482
Email: info@ijcsi.org

More contact details »