An automatic approach for heart segmentation in CT scans through image processing techniques and Concat-U-Net
作者：
Highlights：
• This work investigates a method for heart segmentation in planning CT.
• It composed of atlas, CNN and image processing techniques.
• The method was applied in 36 CT scans with an average of 200 slices.
• We proposed a deep convolutional neural network with concatenation blocks.
• The method achieved 95.25% of the Dice and 87.95% of Jaccard.
摘要
•This work investigates a method for heart segmentation in planning CT.•It composed of atlas, CNN and image processing techniques.•The method was applied in 36 CT scans with an average of 200 slices.•We proposed a deep convolutional neural network with concatenation blocks.•The method achieved 95.25% of the Dice and 87.95% of Jaccard.
论文关键词：Computed tomography,Deep learning,Heart segmentation,Organs at risk,Radiotherapy
论文评审过程：Received 17 April 2021, Revised 17 December 2021, Accepted 31 January 2022, Available online 12 February 2022, Version of Record 16 February 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.116632
