A 3D deep learning approach to epicardial fat segmentation in non-contrast and post-contrast cardiac CT images

被引:8
作者
Siriapisith, Thanongchai [1 ]
Kusakunniran, Worapan [2 ]
Haddawy, Peter [2 ,3 ]
机构
[1] Mahidol Univ, Fac Med, Dept Radiol, Siriraj Hosp, Bangkok, Thailand
[2] Mahidol Univ, Fac Informat & Commun Technol, Salaya, Nakhon Pathom, Thailand
[3] Univ Bremen, Bremen Spatial Cognit Ctr, Bremen, Germany
关键词
Epicardial fat; Computed tomography; 3D segmentation; Deep learning; 3D U-Net; Attention gate; Deep supervision;
D O I
10.7717/peerj-cs.806
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Epicardial fat (ECF) is localized fat surrounding the heart muscle or myocardium and enclosed by the thin-layer pericardium membrane. Segmenting the ECF is one of the most difficult medical image segmentation tasks. Since the epicardial fat is infiltrated into the groove between cardiac chambers and is contiguous with cardiac muscle, segmentation requires location and voxel intensity. Recently, deep learning methods have been effectively used to solve medical image segmentation problems in several domains with state-of-the-art performance. This paper presents a novel approach to 3D segmentation of ECF by integrating attention gates and deep supervision into the 3D U-Net deep learning architecture. The proposed method shows significant improvement of the segmentation performance, when compared with standard 3D U-Net. The experiments show excellent performance on non-contrast CT datasets with average Dice scores of 90.06%. Transfer learning from a pre-trained model of a non-contrast CT to contrast-enhanced CT dataset was also performed. The segmentation accuracy on the contrast-enhanced CT dataset achieved a Dice score of 88.16%.
引用
收藏
页数:18
相关论文
共 42 条
[1]   Fine-Tuning U-Net for Ultrasound Image Segmentation: Different Layers, Different Outcomes [J].
Amiri, Mina ;
Brooks, Rupert ;
Rivaz, Hassan .
IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL, 2020, 67 (12) :2510-2518
[2]  
Anderson P., 2017, ABS170707998 CORR
[3]   Epicardial Fat: Definition, Measurements and Systematic Review of Main Outcomes [J].
Bertaso, Angela Gallina ;
Bertol, Daniela ;
Duncan, Bruce Bartholow ;
Foppa, Murilo .
ARQUIVOS BRASILEIROS DE CARDIOLOGIA, 2013, 101 (01) :E18-E28
[4]   Deep Learning for Quantification of Epicardial and Thoracic Adipose Tissue From Non-Contrast CT [J].
Commandeur, Frederic ;
Goeller, Markus ;
Betancur, Julian ;
Cadet, Sebastien ;
Doris, Mhairi ;
Chen, Xi ;
Berman, Daniel S. ;
Slomka, Piotr J. ;
Tamarappoo, Balaji K. ;
Dey, Damini .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2018, 37 (08) :1835-1846
[5]   3D Slicer as an image computing platform for the Quantitative Imaging Network [J].
Fedorov, Andriy ;
Beichel, Reinhard ;
Kalpathy-Cramer, Jayashree ;
Finet, Julien ;
Fillion-Robin, Jean-Christophe ;
Pujol, Sonia ;
Bauer, Christian ;
Jennings, Dominique ;
Fennessy, Fiona ;
Sonka, Milan ;
Buatti, John ;
Aylward, Stephen ;
Miller, James V. ;
Pieper, Steve ;
Kikinis, Ron .
MAGNETIC RESONANCE IMAGING, 2012, 30 (09) :1323-1341
[6]   Optimizing Attention for Sequence Modeling via Reinforcement Learning [J].
Fei, Hao ;
Zhang, Yue ;
Ren, Yafeng ;
Ji, Donghong .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (08) :3612-3621
[7]   Automatic segmentation of prostate MRI using convolutional neural networks: Investigating the impact of network architecture on the accuracy of volume measurement and MRI-ultrasound registration [J].
Ghavami, Nooshin ;
Hu, Yipeng ;
Gibson, Eli ;
Bonmati, Ester ;
Emberton, Mark ;
Moore, Caroline M. ;
Barratt, Dean C. .
MEDICAL IMAGE ANALYSIS, 2019, 58
[8]   Liver segmentation with 2.5D perpendicular UNets [J].
Han, Lin ;
Chen, Yuanhao ;
Li, Jiaming ;
Zhong, Bowei ;
Lei, Yuzhu ;
Sun, Minghui .
COMPUTERS & ELECTRICAL ENGINEERING, 2021, 91
[9]   Boundary Loss-Based 2.5D Fully Convolutional Neural Networks Approach for Segmentation: A Case Study of the Liver and Tumor on Computed Tomography [J].
Han, Yuexing ;
Li, Xiaolong ;
Wang, Bing ;
Wang, Lu .
ALGORITHMS, 2021, 14 (05)
[10]   Automatic segmentation and quantification of epicardial adipose tissue from coronary computed tomography angiography [J].
He, Xiuxiu ;
Guo, Bang Jun ;
Lei, Yang ;
Wang, Tonghe ;
Fu, Yabo ;
Curran, Walter J. ;
Zhang, Long Jiang ;
Liu, Tian ;
Yang, Xiaofeng .
PHYSICS IN MEDICINE AND BIOLOGY, 2020, 65 (09)