International Journal of Electrical and Computer Engineering (IJECE) Vol. 13, No. 2, April 2023, pp. 2078~2085 ISSN: 2088-8708, DOI: 10.11591/ijece.v13i2.pp2078-2085  2078 Journal homepage: http://ijece.iaescore.com Bone age assessment based on deep learning architecture Alaa Jamal Jabbar, Ashwan A. Abdulmunem Department of Computer Science, Computer Science and Information Technology, University of Kerbala, Kerbala, Iraq Article Info ABSTRACT Article history: Received May 26, 2022 Revised Sep 22, 2022 Accepted Oct 16, 2022 The fast advancement of technology has prompted the creation of automated systems in a variety of sectors, including medicine. One application is an automated bone age evaluation from left-hand X-ray pictures, which assists radiologists and pediatricians in making decisions about the growth status of youngsters. However, one of the most difficult aspects of establishing an automated system is selecting the best approach for producing effective and dependable predictions, especially when working with large amounts of data. As part of this work, we investigate the use of the convolutional neural networks (CNNs) model to classify the age of the bone. The work’s dataset is based on the radiological society of North America (RSNA) dataset. To address this issue, we developed and tested deep learning architecture for autonomous bone assessment, we design a new deep convolution network (DCNN) model. The assessment measures that use in this work are accuracy, recall, precision, and F-score. The proposed model achieves 97% test accuracy for bone age classification. Keywords: Bone age assessment Classification Convolutional neuron network Deep learning X-ray images This is an open access article under the CC BY-SA license. Corresponding Author: Alaa Jamal Jabbar Department of Computer Science, College of Computer Science and Information Technology, University of Kerbala Kerbala, Iraq Email: alaa.jamal@s.uokerbala.edu.iq 1. INTRODUCTION The identification of bone aging is an important problem in the medical industry. Determining bone age is a standardized process in which doctors scan a child's hands to determine a child's skeletal maturity [1]. Due to the nature of bone growth, the test is only accurate between the ages of 0 and 19 years old [2], [3]. It is often used as an indicator of developmental problems in children compared to chronological age. It can also be used to determine the age when a birth certificate cannot be obtained [4]. Due to the discriminatory stage of ossification in the non-dominant hand, it is normally done by a radiological examination of the left hand., Following that, a comparison with chronological age is made: a disparity between the two figures is found to indicate abnormality [5], [6]. Left-hand radiograph analysis is widely used to assess bone maturity because of its ease of use, low radiation exposure, and availability of different ossification centers [7]. Due to the task's similarities to deep learning's normal object recognition and classification problems, bone age assessments have grown to be a prominent focus of the machine learning community [8]. Bone age assessment (BAA) can be performed according to Greulich and Pyle (GP) or according to Tanner-Whitehouse (TW2) [9]. Advances in machine learning, image processing, statistical learning, and many other domains have given rise to breakthrough technologies with new and novel solutions [10]. The machine learning community has paid close attention to medical imaging in particular, resulting in new approaches to old problems [11]. The emergence and spread of convolutional neural networks (CNNs), a deep learning technology, has recently occurred and has attracted interest in medical imaging analysis. Many of these restrictions are addressed by deep-learning techniques, which enable an algorithm to autonomously