Intelligent Bone Age Assessment: An Automated System to Detect a Bone Growth Problem Using Convolutional Neural Networks with Attention Mechanism

Abstract

Skeletal bone age assessment using X-ray images is a standard clinical procedure to detect any anomaly in bone growth among kids and babies. The assessed bone age indicates the actual level of growth, whereby a large discrepancy between the assessed and chronological age might point to a growth disorder. Hence, skeletal bone age assessment is used to screen the possibility of growth abnormalities, genetic problems, and endocrine disorders. Usually, the manual screening is assessed through X-ray images of the non-dominant hand using the Greulich–Pyle (GP) or Tanner–Whitehouse (TW) approach. The GP uses a standard hand atlas, which will be the reference point to predict the bone age of a patient, while the TW uses a scoring mechanism to assess the bone age using several regions of interest information. However, both approaches are heavily dependent on individual domain knowledge and expertise, which is prone to high bias in inter and intra-observer results. Hence, an automated bone age assessment system, which is referred to as Attention-Xception Network (AXNet) is proposed to automatically predict the bone age accurately. The proposed AXNet consists of two parts, which are image normalization and bone age regression modules. The image normalization module will transform each X-ray image into a standardized form so that the regressor network can be trained using better input images. This module will first extract the hand region from the background, which is then rotated to an upright position using the angle calculated from the four key-points of interest. Then, the masked and rotated hand image will be aligned such that it will be positioned in the middle of the image. Both of the masked and rotated images will be obtained through existing state-of-the-art deep learning methods. The last module will then predict the bone age through the Attention-Xception network that incorporates multiple layers of spatial-attention mechanism to emphasize the important features for more accurate bone age prediction. From the experimental results, the proposed AXNet achieves the lowest mean absolute error and mean squared error of 7.699 months and 108.869 months2, respectively. Therefore, the proposed AXNet has demonstrated its potential for practical clinical use with an error of less than one year to assist the experts or radiologists in evaluating the bone age objectively.

Design of an Incremental Music Teaching and Assisted Therapy System Based on Artificial Intelligence Attention Mechanism

“…With the rapid development of artificial intelligence technology represented by deep neural networks, it is possible to achieve automatic and accurate segmentation of MS lesions based on MRI [ 2 ]. The realization of automatic and fast accurate MS lesion segmentation can not only reduce the burden of manual segmentation of MS lesions by experts, save the time and energy of experts in analyzing patients' conditions, and reduce the incorrect diagnosis due to subjective factors of experts, but also, because MS lesions show diffuse and multiplicity in imaging, it is difficult for inexperienced doctors to identify them accurately, and the realization of automatic and accurate MS lesion identification can to a certain extent, the automatic and accurate identification of MS lesions can assist in the diagnosis of MS by inexperienced physicians, which is conducive to the promotion and use in medically underdeveloped areas [ 3 ].…”

Optimized Deep Learning for Human age Estimation

“…The BWLO_DRN proposed in this work for estimating bone age using the hand X-ray images is investigated for its effectiveness by comparing it with techniques, such as DL [1], MLP [3], Global_local feature_CNN [4], and Attention-guided approach [6] by considering the images obtained from RSNA Bone Age Detection and a real-time dataset.…”

Deforestation detection using deep learning-based semantic segmentation techniques: a systematic review

“…As a deep learning architecture achieves exceptional performance on training data through a substantial dataset and strategic multiscale unit placement, it may excel during training, but it may experience significant performance degradation during test phase. This is a pervasive issue in deep learning, referred to as overfitting, whereby a model becomes exceptionally proficient during training phase yet struggles to generalize effectively to new unseen data (Zulkifley et al, 2021). The overfit model inadvertently captures the noise and fluctuations present in the training data rather than the fundamental underlying patterns, representative of the intended problem.…”

“…One approach to tackle overfitting challenge is by incorporating an attention mechanism into the deep learning architecture. In this context, the work in Zulkifley et al (2021) introduced the Attention-Xception Network (AXNet), which strategically guides the network to allocate more weight to specific image regions by integrating it with the Xception architecture. The results underscore that implementing the attention mechanism enhances network capabilities by emphasizing weights on selected regions of interest, as evidenced by the attention maps.…”