CarveMix: A simple data augmentation method for brain lesion segmentation. 2023

Xinru Zhang, and Chenghao Liu, and Ni Ou, and Xiangzhu Zeng, and Zhizheng Zhuo, and Yunyun Duan, and Xiaoliang Xiong, and Yizhou Yu, and Zhiwen Liu, and Yaou Liu, and Chuyang Ye
School of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing, China.

Brain lesion segmentation provides a valuable tool for clinical diagnosis and research, and convolutional neural networks (CNNs) have achieved unprecedented success in the segmentation task. Data augmentation is a widely used strategy to improve the training of CNNs. In particular, data augmentation approaches that mix pairs of annotated training images have been developed. These methods are easy to implement and have achieved promising results in various image processing tasks. However, existing data augmentation approaches based on image mixing are not designed for brain lesions and may not perform well for brain lesion segmentation. Thus, the design of this type of simple data augmentation method for brain lesion segmentation is still an open problem. In this work, we propose a simple yet effective data augmentation approach, dubbed as CarveMix, for CNN-based brain lesion segmentation. Like other mixing-based methods, CarveMix stochastically combines two existing annotated images (annotated for brain lesions only) to obtain new labeled samples. To make our method more suitable for brain lesion segmentation, CarveMix is lesion-aware, where the image combination is performed with a focus on the lesions and preserves the lesion information. Specifically, from one annotated image we carve a region of interest (ROI) according to the lesion location and geometry with a variable ROI size. The carved ROI then replaces the corresponding voxels in a second annotated image to synthesize new labeled images for network training, and additional harmonization steps are applied for heterogeneous data where the two annotated images can originate from different sources. Besides, we further propose to model the mass effect that is unique to whole brain tumor segmentation during image mixing. To evaluate the proposed method, experiments were performed on multiple publicly available or private datasets, and the results show that our method improves the accuracy of brain lesion segmentation. The code of the proposed method is available at https://github.com/ZhangxinruBIT/CarveMix.git.

UI MeSH Term Description Entries
D007091 Image Processing, Computer-Assisted A technique of inputting two-dimensional or three-dimensional images into a computer and then enhancing or analyzing the imagery into a form that is more useful to the human observer. Biomedical Image Processing,Computer-Assisted Image Processing,Digital Image Processing,Image Analysis, Computer-Assisted,Image Reconstruction,Medical Image Processing,Analysis, Computer-Assisted Image,Computer-Assisted Image Analysis,Computer Assisted Image Analysis,Computer Assisted Image Processing,Computer-Assisted Image Analyses,Image Analyses, Computer-Assisted,Image Analysis, Computer Assisted,Image Processing, Biomedical,Image Processing, Computer Assisted,Image Processing, Digital,Image Processing, Medical,Image Processings, Medical,Image Reconstructions,Medical Image Processings,Processing, Biomedical Image,Processing, Digital Image,Processing, Medical Image,Processings, Digital Image,Processings, Medical Image,Reconstruction, Image,Reconstructions, Image
D008279 Magnetic Resonance Imaging Non-invasive method of demonstrating internal anatomy based on the principle that atomic nuclei in a strong magnetic field absorb pulses of radiofrequency energy and emit them as radiowaves which can be reconstructed into computerized images. The concept includes proton spin tomographic techniques. Chemical Shift Imaging,MR Tomography,MRI Scans,MRI, Functional,Magnetic Resonance Image,Magnetic Resonance Imaging, Functional,Magnetization Transfer Contrast Imaging,NMR Imaging,NMR Tomography,Tomography, NMR,Tomography, Proton Spin,fMRI,Functional Magnetic Resonance Imaging,Imaging, Chemical Shift,Proton Spin Tomography,Spin Echo Imaging,Steady-State Free Precession MRI,Tomography, MR,Zeugmatography,Chemical Shift Imagings,Echo Imaging, Spin,Echo Imagings, Spin,Functional MRI,Functional MRIs,Image, Magnetic Resonance,Imaging, Magnetic Resonance,Imaging, NMR,Imaging, Spin Echo,Imagings, Chemical Shift,Imagings, Spin Echo,MRI Scan,MRIs, Functional,Magnetic Resonance Images,Resonance Image, Magnetic,Scan, MRI,Scans, MRI,Shift Imaging, Chemical,Shift Imagings, Chemical,Spin Echo Imagings,Steady State Free Precession MRI
D001921 Brain The part of CENTRAL NERVOUS SYSTEM that is contained within the skull (CRANIUM). Arising from the NEURAL TUBE, the embryonic brain is comprised of three major parts including PROSENCEPHALON (the forebrain); MESENCEPHALON (the midbrain); and RHOMBENCEPHALON (the hindbrain). The developed brain consists of CEREBRUM; CEREBELLUM; and other structures in the BRAIN STEM. Encephalon
D001932 Brain Neoplasms Neoplasms of the intracranial components of the central nervous system, including the cerebral hemispheres, basal ganglia, hypothalamus, thalamus, brain stem, and cerebellum. Brain neoplasms are subdivided into primary (originating from brain tissue) and secondary (i.e., metastatic) forms. Primary neoplasms are subdivided into benign and malignant forms. In general, brain tumors may also be classified by age of onset, histologic type, or presenting location in the brain. Brain Cancer,Brain Metastases,Brain Tumors,Cancer of Brain,Malignant Primary Brain Tumors,Neoplasms, Intracranial,Benign Neoplasms, Brain,Brain Neoplasm, Primary,Brain Neoplasms, Benign,Brain Neoplasms, Malignant,Brain Neoplasms, Malignant, Primary,Brain Neoplasms, Primary Malignant,Brain Tumor, Primary,Brain Tumor, Recurrent,Cancer of the Brain,Intracranial Neoplasms,Malignant Neoplasms, Brain,Malignant Primary Brain Neoplasms,Neoplasms, Brain,Neoplasms, Brain, Benign,Neoplasms, Brain, Malignant,Neoplasms, Brain, Primary,Primary Brain Neoplasms,Primary Malignant Brain Neoplasms,Primary Malignant Brain Tumors,Benign Brain Neoplasm,Benign Brain Neoplasms,Benign Neoplasm, Brain,Brain Benign Neoplasm,Brain Benign Neoplasms,Brain Cancers,Brain Malignant Neoplasm,Brain Malignant Neoplasms,Brain Metastase,Brain Neoplasm,Brain Neoplasm, Benign,Brain Neoplasm, Malignant,Brain Neoplasms, Primary,Brain Tumor,Brain Tumors, Recurrent,Cancer, Brain,Intracranial Neoplasm,Malignant Brain Neoplasm,Malignant Brain Neoplasms,Malignant Neoplasm, Brain,Neoplasm, Brain,Neoplasm, Intracranial,Primary Brain Neoplasm,Primary Brain Tumor,Primary Brain Tumors,Recurrent Brain Tumor,Recurrent Brain Tumors,Tumor, Brain
D006801 Humans Members of the species Homo sapiens. Homo sapiens,Man (Taxonomy),Human,Man, Modern,Modern Man
D016571 Neural Networks, Computer A computer architecture, implementable in either hardware or software, modeled after biological neural networks. Like the biological system in which the processing capability is a result of the interconnection strengths between arrays of nonlinear processing nodes, computerized neural networks, often called perceptrons or multilayer connectionist models, consist of neuron-like units. A homogeneous group of units makes up a layer. These networks are good at pattern recognition. They are adaptive, performing tasks by example, and thus are better for decision-making than are linear learning machines or cluster analysis. They do not require explicit programming. Computational Neural Networks,Connectionist Models,Models, Neural Network,Neural Network Models,Neural Networks (Computer),Perceptrons,Computational Neural Network,Computer Neural Network,Computer Neural Networks,Connectionist Model,Model, Connectionist,Model, Neural Network,Models, Connectionist,Network Model, Neural,Network Models, Neural,Network, Computational Neural,Network, Computer Neural,Network, Neural (Computer),Networks, Computational Neural,Networks, Computer Neural,Networks, Neural (Computer),Neural Network (Computer),Neural Network Model,Neural Network, Computational,Neural Network, Computer,Neural Networks, Computational,Perceptron

Related Publications

Xinru Zhang, and Chenghao Liu, and Ni Ou, and Xiangzhu Zeng, and Zhizheng Zhuo, and Yunyun Duan, and Xiaoliang Xiong, and Yizhou Yu, and Zhiwen Liu, and Yaou Liu, and Chuyang Ye
October 2022, Computers in biology and medicine,
Xinru Zhang, and Chenghao Liu, and Ni Ou, and Xiangzhu Zeng, and Zhizheng Zhuo, and Yunyun Duan, and Xiaoliang Xiong, and Yizhou Yu, and Zhiwen Liu, and Yaou Liu, and Chuyang Ye
January 2019, Frontiers in computational neuroscience,
Xinru Zhang, and Chenghao Liu, and Ni Ou, and Xiangzhu Zeng, and Zhizheng Zhuo, and Yunyun Duan, and Xiaoliang Xiong, and Yizhou Yu, and Zhiwen Liu, and Yaou Liu, and Chuyang Ye
January 2022, Frontiers in neuroscience,
Xinru Zhang, and Chenghao Liu, and Ni Ou, and Xiangzhu Zeng, and Zhizheng Zhuo, and Yunyun Duan, and Xiaoliang Xiong, and Yizhou Yu, and Zhiwen Liu, and Yaou Liu, and Chuyang Ye
January 2022, Frontiers in oncology,
Xinru Zhang, and Chenghao Liu, and Ni Ou, and Xiangzhu Zeng, and Zhizheng Zhuo, and Yunyun Duan, and Xiaoliang Xiong, and Yizhou Yu, and Zhiwen Liu, and Yaou Liu, and Chuyang Ye
February 2024, Journal of imaging informatics in medicine,
Xinru Zhang, and Chenghao Liu, and Ni Ou, and Xiangzhu Zeng, and Zhizheng Zhuo, and Yunyun Duan, and Xiaoliang Xiong, and Yizhou Yu, and Zhiwen Liu, and Yaou Liu, and Chuyang Ye
July 2020, Sensors (Basel, Switzerland),
Xinru Zhang, and Chenghao Liu, and Ni Ou, and Xiangzhu Zeng, and Zhizheng Zhuo, and Yunyun Duan, and Xiaoliang Xiong, and Yizhou Yu, and Zhiwen Liu, and Yaou Liu, and Chuyang Ye
January 2020, PloS one,
Xinru Zhang, and Chenghao Liu, and Ni Ou, and Xiangzhu Zeng, and Zhizheng Zhuo, and Yunyun Duan, and Xiaoliang Xiong, and Yizhou Yu, and Zhiwen Liu, and Yaou Liu, and Chuyang Ye
April 2021, Medical physics,
Xinru Zhang, and Chenghao Liu, and Ni Ou, and Xiangzhu Zeng, and Zhizheng Zhuo, and Yunyun Duan, and Xiaoliang Xiong, and Yizhou Yu, and Zhiwen Liu, and Yaou Liu, and Chuyang Ye
January 2024, Sensors (Basel, Switzerland),
Xinru Zhang, and Chenghao Liu, and Ni Ou, and Xiangzhu Zeng, and Zhizheng Zhuo, and Yunyun Duan, and Xiaoliang Xiong, and Yizhou Yu, and Zhiwen Liu, and Yaou Liu, and Chuyang Ye
May 2024, Physics in medicine and biology,
Copied contents to your clipboard!