Hand Wrist X-Ray Images in Bone Age Assessment Using Particle Swarm and Convolutional Neural Network Algorithm
Akanksha Sharma1, Prabhjeet Kaur2
1Akanksha Sharma, Dept. of CSE, Sachdeva Engineering College for Girls, Gharuan, Mohali, India.
2Prabhjeet Kaur, Dept. of CSE, Sachdeva Engineering College for Girls, Gharuan, Mohali, India.
Manuscript received on 02 June 2019 | Revised Manuscript received on 10 June 2019 | Manuscript published on 30 June 2019 | PP: 3091-3097 | Volume-8 Issue-8, June 2019 | Retrieval Number: H7251068819/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Bone age assessment is method of analyzing the maturity of bones of an individual using x-ray images. Generally, left hand wrist is used for imaging for the reason that calcium deposit in the ossification area of the bones recognizes the organic growth of the bones. Bone age assessment (BAA) is method of checking ossification maturity level in left hand wrist using x ray images for bone age assessment using graphical approach. In early stage, two main techniques used for bone age assessment are Greulich-Pyle (GP) and Tanner Whitehouse (TW2) technique. The radiograph bone of the patient is matched with standard radiographs using graphics and results are determined in Greulich-Pyle method, whereas in Tanner Whitehouse method scoring approach is used for assessment of bone age. In last developed method, maturity level of bone age of ulna and radius was analyzed utilizing convolutional neural network. Medical technologists determine the age of person through radiograph technology of hand wrist of the person and that process of recognizing age is known as bone as assessment. In this research, two algorithms are congregated for prediction of particle using convolutional neural network. The main research section defined that to search the BAA (Bone Age Assessment) from the UCI machine learning repository site and reviewed the various BAA techniques. To develop a filtration and optimized feature vector extraction and selection method to smooth the hand wrist X-ray images. To implement deep learning approach using CNN to classify the assessment rate based on the X-ray Bone Images. After that evaluation of the performance metrics such as error rate, PSNR (Peak Signal to Noise Ratio) and Accuracy Rate and compared with the various methods
Keyword: Bone age assessment, Convolutional neural network, Radiograph technology, Tanner Whitehouse method.
Scope of the Article: Adaptive Networking Applications.