ABSTRACT
Bone age assessment is used to diagnose paediatric growth because some types of bone diseases occur in childhood. To overcome these issues, AlexNet-Based Deep Convolutional Neural Network Optimized with the Group Teaching Optimization Algorithm is proposed. First, input images are gathered via RSNA paediatric bone age dataset. These images are preprocessed using Wavelet Packet Transform Cochlear Filter Bank. Then input hand X-ray images’ ROI is segmented using Bayesian fuzzy clustering. Then segmented ROI region is fed to ADCNN that accurately predicts BAA. In general, ADCNN does not divulge any optimization techniques adopted for determining the optimal parameters and ensuring accurate classification. Therefore, the GTOA is used to optimize the ADCNN weight parameters. The proposed approach is done in MATLAB and various performance metrics such as accuracy, F-score, sensitivity, precision, specificity, CCC and CC. The BAA-ADCNN-GTOA method provides higher accuracy 23.75%, 17.97%, 31.65% compared with existing methods, like BAA-CNN-RRNN, BAA-RNN-AF-SFO, BAA-U-Net-CTO- WOA, respectively.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Additional information
Notes on contributors
E. P. Hemand
E. P. Hemand received B.Tech degree in CSE from Government College of Engineering- Kannur, Kannur, affiliated to Kannur University, Kerala in 2008. M.Tech Degree in Computer Network Engineering from RV College of Engineering, Bangalore Karnataka, affiliated to VTU, Belgaum, Karnataka in 2012. He has been working at KMCT College of Engineering, Kozhikode, Kerala as Assistant professor in the Computer science and Engineering department since 2012. He is currently working toward a Ph.D. degree at the Department of Computer science and Engineering, NIT Calicut, Kozhikode, Kerala, India. His research interests include machine learning, image processing, and cyber security.
Mohandass G.
Mohandass G. received B.E. degree in EIE from Dr. Pauls Engineering College, Villupuram Dt Vanur Taluk, 605109 affiliated to Madras University, Chennai, Tamil Nadu in 2005. M.Tech Degree in Biomedical Signal Processing and Instrumentation Engineering from Sastra University Thanjavur, Tamil Nadu in 2005. He completed Ph.D. degree at the Faculty of Electronics Engineering, Sathyabama University, Chennai, India. His research interests include soft computing application in medical image analysis.
Francis H. Shajin
Francis H. Shajin graduated from Anna University, India. He has more than 10 years of experience in research and development field. He has published more than 35 papers in international journals. His current research interests include very-large-scale integration, soft computing, image processing, machine learning and networking.
D. Kirubakaran
D. Kirubakaran has obtained his Ph.D from Anna University in 2010 and M.E. degree from Bharathidasan University in 2000. His area of interest is AC-AC converters for induction heating & renewable energy systems. He had guided 10 Ph.D research scholars. He has published more than 60 papers on referred international journals. He is a life member of ISTE. He is having 22 years of teaching experience. He is working as Professor & Heading EEE department at St. Joseph's Institute of technology, Chennai since 2011.