A dual meta-learning framework based on idle data for enhancing segmentation of pancreatic cancer

被引:18
作者
Li, Jun [1 ]
Qi, Liang [2 ]
Chen, Qingzhong [1 ]
Zhang, Yu-Dong [2 ]
Qian, Xiaohua [1 ]
机构
[1] Shanghai Jiao Tong Univ, Sch Biomed Engn, Shanghai 200030, Peoples R China
[2] Nanjing Med Univ, Affiliated Hosp 1, Dept Radiol, Nanjing 210009, Peoples R China
基金
中国国家自然科学基金; 上海市自然科学基金;
关键词
Pancreatic cancer segmentation; Idle data; Dual meta-learning; Random style transfer; ADAPTATION; IMAGE; CT;
D O I
10.1016/j.media.2021.102342
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Automated segmentation of pancreatic cancer is vital for clinical diagnosis and treatment. However, the small size and inconspicuous boundaries limit the segmentation performance, which is further exacerbated for deep learning techniques with the few training samples due to the high threshold of image acquisition and annotation. To alleviate this issue caused by the small-scale dataset, we collect idle multi-parametric MRIs of pancreatic cancer from different studies to construct a relatively large dataset for enhancing the CT pancreatic cancer segmentation. Therefore, we propose a deep learning segmentation model with the dual meta-learning framework for pancreatic cancer. It can integrate the common knowledge of tumors obtained from idle MRIs and salient knowledge from CT images, making high-level features more discriminative. Specifically, the random intermediate modalities between MRIs and CT are first generated to smoothly fill in the gaps in visual appearance and provide rich intermediate representations for ensuing meta-learning scheme. Subsequently, we employ intermediate modalities-based model-agnostic meta-learning to capture and transfer commonalities. At last, a meta-optimizer is utilized to adaptively learn the salient features within CT data, thus alleviating the interference due to internal differences. Com prehensive experimental results demonstrated our method achieved the promising segmentation performance, with a max Dice score of 64.94% on our private dataset, and outperformed state-of-the-art methods on a public pancreatic cancer CT dataset. The proposed method is an effective pancreatic cancer segmentation framework, which can be easily integrated into other segmentation networks and thus promises to be a potential paradigm for alleviating data scarcity challenges using idle data.(c) 2022 Elsevier B.V. All rights reserved.
引用
收藏
页数:12
相关论文
共 44 条
[11]  
Finn C, 2017, PR MACH LEARN RES, V70
[12]   Image Style Transfer Using Convolutional Neural Networks [J].
Gatys, Leon A. ;
Ecker, Alexander S. ;
Bethge, Matthias .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :2414-2423
[13]   DLOW: Domain Flow for Adaptation and Generalization [J].
Gong, Rui ;
Li, Wen ;
Chen, Yuhua ;
Van Gool, Luc .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :2472-2481
[14]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[15]   Densely Connected Convolutional Networks [J].
Huang, Gao ;
Liu, Zhuang ;
van der Maaten, Laurens ;
Weinberger, Kilian Q. .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :2261-2269
[16]   SynSeg-Net: Synthetic Segmentation Without Target Modality Ground Truth [J].
Huo, Yuankai ;
Xu, Zhoubing ;
Moon, Hyeonsoo ;
Bao, Shunxing ;
Assad, Albert ;
Moyo, Tamara K. ;
Savona, Michael R. ;
Abramson, Richard G. ;
Landman, Bennett A. .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2019, 38 (04) :1016-1025
[17]   nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation [J].
Isensee, Fabian ;
Jaeger, Paul F. ;
Kohl, Simon A. A. ;
Petersen, Jens ;
Maier-Hein, Klaus H. .
NATURE METHODS, 2021, 18 (02) :203-+
[18]  
Jiang Y., 2020, IEEEACM T COMPUTATIO, V18, P40
[19]   Domain Generalizer: A Few-Shot Meta Learning Framework for Domain Generalization in Medical Imaging [J].
Khandelwal, Pulkit ;
Yushkevich, Paul .
DOMAIN ADAPTATION AND REPRESENTATION TRANSFER, AND DISTRIBUTED AND COLLABORATIVE LEARNING, DART 2020, DCL 2020, 2020, 12444 :73-84
[20]  
Li Z., 2017, ARXIV PREPRINT ARXIV, DOI [10.2514/6.2017-4530, DOI 10.2514/6.2017-4530]