Final published version
Licence: Unspecified
Final published version
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - Learning Active Contour Models for Medical Image Segmentation
AU - Chen, Xu
AU - Williams, Bryan
AU - Vallabhanehi, Srini
AU - Czanner, Gabriela
AU - Williams, Rachel
AU - Zheng, Yalin
PY - 2020/1/9
Y1 - 2020/1/9
N2 - Image segmentation is an important step in medical image processing and has been widely studied and developed for refinement of clinical analysis and applications. New models based on deep learning have improved results but are restricted to pixel-wise fitting of the segmentation map. Our aim was to tackle this limitation by developing a new model based on deep learning which takes into account the area inside as well as outside the region of interest as well as the size of boundaries during learning. Specifically, we propose a new loss function which incorporates area and size information and integrates this into a dense deep learning model. We evaluated our approach on a dataset of more than 2,000 cardiac MRI scans. Our results show that the proposed loss function outperforms other mainstream loss function Cross-entropy on two common segmentation networks. Our loss function is robust while using different hyperparameter lambda.
AB - Image segmentation is an important step in medical image processing and has been widely studied and developed for refinement of clinical analysis and applications. New models based on deep learning have improved results but are restricted to pixel-wise fitting of the segmentation map. Our aim was to tackle this limitation by developing a new model based on deep learning which takes into account the area inside as well as outside the region of interest as well as the size of boundaries during learning. Specifically, we propose a new loss function which incorporates area and size information and integrates this into a dense deep learning model. We evaluated our approach on a dataset of more than 2,000 cardiac MRI scans. Our results show that the proposed loss function outperforms other mainstream loss function Cross-entropy on two common segmentation networks. Our loss function is robust while using different hyperparameter lambda.
U2 - 10.1109/CVPR.2019.01190
DO - 10.1109/CVPR.2019.01190
M3 - Conference contribution/Paper
SN - 9781728132945
SP - 11632
EP - 11640
BT - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PB - IEEE
T2 - IEEE Conference on Computer Vision and Pattern Recognition 2019
Y2 - 16 June 2019 through 20 June 2019
ER -