Identification of endometrial tuberculosis in infertility using Non-Subsampled Contourlet based convolution neural network
作者：
Highlights：
• Endometrial Tuberculosis (ETB) is a cause of rising female infertility.
• An integrative Non-Subsampled Contourlet based CNN proposed to identify ETB.
• The proposed model obtained a F1-score of 0.869 on real TVUS images of females.
• A 16.01% reduction in trainable parameters and 41.08 % in training time attained.
• A two tailed t-test confirms the 95% confidence level on the model performance.
摘要
•Endometrial Tuberculosis (ETB) is a cause of rising female infertility.•An integrative Non-Subsampled Contourlet based CNN proposed to identify ETB.•The proposed model obtained a F1-score of 0.869 on real TVUS images of females.•A 16.01% reduction in trainable parameters and 41.08 % in training time attained.•A two tailed t-test confirms the 95% confidence level on the model performance.
论文关键词：Female genital tuberculosis,Transvaginal ultrasound image analysis,Convolution neural networks,Endometrial tuberculosis,Non-Subsampled Contourlet transform
论文评审过程：Received 22 April 2020, Revised 25 March 2022, Accepted 21 April 2022, Available online 26 April 2022, Version of Record 29 April 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.117282
