Deep neural network for semi-automatic classification of term and preterm uterine recordings

作者：

Highlights：

• To develop a new and improved method for the semi-automatic prediction of preterm birth.

• To characterize the uterine records of TPEHGT DS database in terms sample entropy and Wavelet entropy.

• To demonstrate high -level features extraction based on SSAE network is effective.

• To evaluate the classification performance of the new method using the newly TPEHGT DS database.

摘要

•To develop a new and improved method for the semi-automatic prediction of preterm birth.•To characterize the uterine records of TPEHGT DS database in terms sample entropy and Wavelet entropy.•To demonstrate high -level features extraction based on SSAE network is effective.•To evaluate the classification performance of the new method using the newly TPEHGT DS database.

论文关键词：EHG and TOCO signals,sample entropy,wavelet entropy,stacked sparse autoencoder,softmax

论文评审过程：Received 9 April 2019, Revised 25 February 2020, Accepted 14 April 2020, Available online 19 April 2020, Version of Record 30 April 2020.

论文官网地址：https://doi.org/10.1016/j.artmed.2020.101861