An automatic method for segmentation of liver lesions in computed tomography images using deep neural networks

作者：

Highlights：

• A computational method for liver lesions segmentation in CT images is presented.

• Our method uses two deep neural networks and image processing techniques.

• This method uses a dataset of CT images from LiTS.

• The method achieved a Dice of 82.99%.

摘要

•A computational method for liver lesions segmentation in CT images is presented.•Our method uses two deep neural networks and image processing techniques.•This method uses a dataset of CT images from LiTS.•The method achieved a Dice of 82.99%.

论文关键词：Liver cancer,Liver lesion segmentation,Convolutional neural networks,Computed tomography

论文评审过程：Received 24 November 2020, Revised 15 March 2021, Accepted 16 April 2021, Available online 23 April 2021, Version of Record 10 May 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115064