Title: Gestational age determination of ultrasound foetal images using artificial neural network
Authors: Jujjavarapu Sunitha Kumari; Usha Rani Nelakuditi
Addresses: Department of Electronics and Communication Engineering, Vignan's Foundation for Science, Technology & Research (Deemed to be University), Vadlamudi, Guntur – 522213, Andhra Pradesh, India ' Department of Electronics and Communication Engineering, Vignan's Foundation for Science, Technology & Research (Deemed to be University), Vadlamudi, Guntur – 522213, Andhra Pradesh, India
Abstract: Gestation age estimation is an important task in assessing high risks existing during pregnancy. Ultrasound foetal images provide valuable information for better understanding of developmental stages. To accomplish this, suitable biometric parameters are monitored manually and the accuracy of this determination relies on skilled sonographer or image qualities. The main aim of the proposed approach is to evaluate the biometric parameters automatically for determining gestational age based foetal growth using ultrasound images. Foetal images undergo adaptive histogram equalisation for characteristics enhancement followed by normal shrink homomorphic filtering and canny edge detection-based segmentation to extract the significant features. The desired parameters are recognised by probability boosting tree (PBT) classification that are further provided to adaptive artificial neural network (ANN) for evaluating the foetal status in terms of gestational age. This integrated neural network accurately measures the growth of foetus with minimised error, shorter time and no significant difference exists between the estimated and the actual values.
Keywords: ultrasound foetal images; image enhancement; edge detection; normal shrink homomorphic technique; PBT classification; ANN; artificial neural network.
International Journal of Bioinformatics Research and Applications, 2022 Vol.18 No.1/2, pp.113 - 129
Received: 28 Jun 2019
Accepted: 16 Apr 2020
Published online: 07 Apr 2022 *