A fully-automated deep learning pipeline for cervical cancer classification

作者：

Highlights：

• Deep learning models for detection and classification of cervical cancer.

• Faster detection of cervix region with higher intersection of union scores.

• Faster classification of cervical cancer with higher accuracy scores.

• Lightweight deep learning architectures for mobile device deployment.

• Evaluation of proposed pipeline using standard cervigram image datasets.

摘要

•Deep learning models for detection and classification of cervical cancer.•Faster detection of cervix region with higher intersection of union scores.•Faster classification of cervical cancer with higher accuracy scores.•Lightweight deep learning architectures for mobile device deployment.•Evaluation of proposed pipeline using standard cervigram image datasets.

论文关键词：Cervical cancer,Deep learning,Cervix detection,Cervical region-of-interest,Convolutional neural networks,Guanacaste and Intel&mobileodt cervigram datasets

论文评审过程：Received 25 March 2019, Revised 28 July 2019, Accepted 12 September 2019, Available online 19 September 2019, Version of Record 27 September 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.112951