.png){kind=icon}
.png){kind=icon}
Return
Multi-objective segmentation approach for bone age assessment using parameter tuning-based U-net architecture
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-021-11793-0.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Bone age assessment investigates the ossification improvement for estimating the skeletal age of the pediatrics for analyzing their skeletal growth and forecast their future adult height. The main intent of this paper is to contribute a novel deep learning-based bone segmentation for bone age assessment. Here, the datasets are gathered from both the manual as well as the RSNA database. The segmentation of 5 regions Distal Phalanx of thumb, middle phalanx, third metacarpal, radius, and ulna is performed by the optimized U-Net model. As an improvement in the existing U-Net architecture, tuning of the activation function is adopted by the hybridization of two meta-heuristic algorithms such as Class Topper Optimization (CTO) and Whale Optimization Algorithm (WOA) termed as Whale-based Class Topper Optimization (W-CTO). This improved model is developed with the intention of solving the multi-objective segmentation that concerns the parameters like entropy and variance. Moreover, the effect of the proposed segmentation is analyzed by estimating the bone age with the deep Convolutional Neural Network (Deep CNN). From the analysis, the overall MASE of W-CTO-U-Net+CNN is 14.66%, 22.06%, and 5.53% higher than RNN, CNN, and NN, respectively, and RMSE of W-CTO-U-Net+CNN is 53.28%, 22.02%, and 32.87% better than RNN, CNN, and NN, respectively.. The performance comparison of the proposed segmentation model over the conventional approaches confirms its effective performance with relatively high accuracy.
Keywords:
Bone age assessment
Multi-objective segmentation
Optimized U-net architecture
Whale-based class topper optimization
Deep convolutional neural network
Journal
IF:
3
Papers:
1.9W
Citations:
3.2W