基于NSST域像素相关分析的医学图像融合

doi:10.13229/j.cnki.jdxbgxb.20200365

摘要/Abstract

摘要：

针对像素级多模态医学图像融合信息丢失的问题，提出了一种基于非下采样剪切波变换（NSST）的像素相关性分析（PCAS）的图像融合方法。首先，对源图像进行NSST分解，获得高低频子带。然后，利用提出的中心像素方差计算邻域像素与中心像素的强度相关因子，构建邻域像素相关系数矩阵，并提出将相关性拉普拉斯能量和作为高频方向子带的融合规则。再次，计算低频子带中心像素能量以及邻域像素能量梯度信息，得到低频融合决策图。最后，通过逆变换得到融合结果图像。磁共振图像（MRI）和计算机断层扫描（CT）、单光子发射计算机断层成像（PET）、正电子发射断层成像（SPECT）的脑部图像融合实验结果表明，本文融合方法可以很好地保留源图像的显著信息和纹理细节。

关键词: 计算机应用, 图像处理, 图像融合, 非下采样剪切波变换, 像素相关性

Abstract:

To solve the problem of information loss in pixel-level multimodal medical image fusion, an image fusion method using pixel correlation analysis (PCA) in Non-subsampled Shearlet Transform (NSST) domain is proposed. First, NSST decomposition is performed on the source images to obtain high and low frequency sub-bands. The intensity correlation factor between neighborhood pixels and central pixel is calculated using the proposed center pixel variance, and the correlation coefficient matrix of neighborhood pixels is constructed. The proposed correlation-sum of modified laplacian (C-SML) is used as the fusion rule for high-frequency sub-bands. The energy of the central pixel and the energy gradient information of the neighboring pixels of the low-frequency sub-bands are calculated to obtain the fusion decision map for low-frequency sub-bands. Finally, the fused image is obtained by inverse NSST. The experimental results about magnetic resonance imaging (MRI) and computed tomography (CT), positron emission tomography (PET), single-photon emission computed tomography （SPECT） brain images indicate that the proposed fusion method can well retain the significant information and texture details of the source images.

Key words: computer application, image processing, image fusion, non-subsampled shearlet transform（NSST）, pixel correlation

中图分类号:

TP391

肖明尧,李雄飞,朱芮. 基于NSST域像素相关分析的医学图像融合[J]. 吉林大学学报(工学版), 2023, 53(9): 2640-2648.

Ming-yao XIAO,Xiong-fei LI,Rui ZHU. Medical image fusion based on pixel correlation analysis in NSST domain[J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(9): 2640-2648.

图/表 12

图1

图2

图3

图4

图5

图6

表1

表2

图7

图8

表3

表4

参考文献 16

1	Yang Y. Multimodal medical image fusion through a new DWT based technique[C]∥2010 4th International Conference on Bioinformatics and Biomedical Engineering, Chengdu, China, 2010: 1-4.
2	Srivastava R, Prakash O, Khare A. Local energy-based multimodal medical image fusion in curvelet domain[J]. IET Comput Vision, 2016, 10(6): 513-527.
3	Koley S, Galande A, Kelkar B, et al. Multispectral MRI image fusion for enhanced visualization of meningioma brain tumors and edema using contourlet transform and fuzzy statistics[J]. Journal of Medical and Biological Engineering, 2016, 36(4): 470-484.
4	Easley G, Labate D, Lim W Q. Sparse directional image representations using the discrete shearlet transform[J]. Applied and Computational Harmonic Analysis, 2008, 25(1): 25-46.
5	高印寒, 陈广秋, 刘妍妍. 基于图像质量评价参数的非下采样剪切波域自适应图像融合[J]. 吉林大学学报:工学版, 2014, 44(1): 225-234.
	Gao Yin-han, Chen Guang-qiu, Liu Yan-yan. Adaptive image fusion based on image quality assessment parameter in NSST system[J]. Journal of Jilin University(Engineering and Technology Edition), 2014, 44(1): 225-234.
6	Vishwakarma A, Bhuyan M K. Image fusion using adjustable non-subsampled shearlet transform[J]. IEEE Transactions on Instrumentation and Measurement, 2018, 68(9): 3367-3378.
7	Zhu Y L, Zhou X Y, Li X W, et al. Algorithm of medical image fusion based on Laplasse pyramid and PCA[C]∥IOP Conference Series: Materials Science and Engineering, Shanghai, China, 2019: 490(4): No.042030.
8	Devi M S, Balamurugan P. Local energy match based non-sub sampled contourlet Transform for multi modal medical image fusion[J]. International Journal of Engineering and Technology, 2018, 7(2): 165-169.
9	刘哲, 徐涛, 宋余庆,等. 基于NSCT变换和相似信息鲁棒主成分分析模型的图像融合技术[J]. 吉林大学学报:工学版, 2018,48(5): 1614-1620.
	Liu Zhe, Xu Tao, Song Yu-qing, et al. Image fusion technology based on NSCT transform and robust principal component analysis model of similarity information[J]. Journal of Jilin University (Engineering and Technology Edition), 2018,48(5):1614-1620.
10	Yin Ming, Liu Xiao-ning, Liu Yu, et al. Medical image fusion with parameter-adaptive pulse coupled neural network in nonsubsampled shearlet transform domain[J]. IEEE Transactions on Instrumentation and Measurement, 2018, 68(1): 49-64.
11	Kumar B K S. Image fusion based on pixel significance using cross bilateral filter[J]. Signal, Image and Video Processing, 2015, 9(5): 1193-1204.
12	Liu Y, Chen X, Ward R K, et al. Medical image fusion via convolutional sparsity based morphological component analysis[J]. IEEE Signal Processing Letters, 2019, 26(3): 485-489.
13	Nencini F, Garzelli A, Baronti S, et al. Remote sensing image fusion using the curvelet transform[J]. Information Fusion, 2007, 8(2): 143-156.
14	Li S, Kang X, Hu J. Image fusion with guided filtering[J]. IEEE Transactions on Image Processing, 2013, 22(7): 2864-2875.
15	Liu Yu, Liu Shu-ping, Wang Zeng-fu. A general framework for image fusion based on multi-scale transform and sparse representation[J]. Information Fusion, 2015, 24: 147-164.
16	Zhu Zhi-qin, Zheng Ming-yao, Qi Guan-qiu, et al. A phase congruency and local Laplacian energy based multi-modality medical image fusion method in NSCT domain[J]. IEEE Access, 2019, 7: 20811-20824.

相关文章 15

[1]	霍光,林大为,刘元宁,朱晓冬,袁梦,盖迪. 基于多尺度特征和注意力机制的轻量级虹膜分割模型[J]. 吉林大学学报(工学版), 2023, 53(9): 2591-2600.
[2]	何颖,王卓然,周旭,刘衍珩. 融合社交地理信息加权矩阵分解的兴趣点推荐算法[J]. 吉林大学学报(工学版), 2023, 53(9): 2632-2639.
[3]	张云佐,董旭,蔡昭权. 拟合下肢几何特征的多视角步态周期检测[J]. 吉林大学学报(工学版), 2023, 53(9): 2611-2619.
[4]	赵亚慧,李飞雨,崔荣一,金国哲,张振国,李德,金小峰. 基于跨语言预训练模型的朝汉翻译质量评估[J]. 吉林大学学报(工学版), 2023, 53(8): 2371-2379.
[5]	金小俊,孙艳霞,于佳琳,陈勇. 基于深度学习与图像处理的蔬菜苗期杂草识别方法[J]. 吉林大学学报(工学版), 2023, 53(8): 2421-2429.
[6]	车翔玖,徐欢,潘明阳,刘全乐. 生物医学命名实体识别的两阶段学习算法[J]. 吉林大学学报(工学版), 2023, 53(8): 2380-2387.
[7]	王连明,吴鑫. 基于姿态估计的物体3D运动参数测量方法[J]. 吉林大学学报(工学版), 2023, 53(7): 2099-2108.
[8]	张则强,梁巍,谢梦柯,郑红斌. 混流双边拆卸线平衡问题的精英差分进化算法[J]. 吉林大学学报(工学版), 2023, 53(5): 1297-1304.
[9]	刘培勇,董洁,谢罗峰,朱杨洋,殷国富. 基于多支路卷积神经网络的磁瓦表面缺陷检测算法[J]. 吉林大学学报(工学版), 2023, 53(5): 1449-1457.
[10]	张振海,季坤,党建武. 基于桥梁裂缝识别模型的桥梁裂缝病害识别方法[J]. 吉林大学学报(工学版), 2023, 53(5): 1418-1426.
[11]	姜宇,潘家铮,陈何淮,符凌智,齐红. 基于分割方法的繁体中文报纸文本检测[J]. 吉林大学学报(工学版), 2023, 53(4): 1146-1154.
[12]	于鹏,朴燕. 基于多尺度特征的行人重识别属性提取新方法[J]. 吉林大学学报(工学版), 2023, 53(4): 1155-1162.
[13]	潘弘洋,刘昭,杨波,孙庚,刘衍珩. 基于新一代通信技术的无人机系统群体智能方法综述[J]. 吉林大学学报(工学版), 2023, 53(3): 629-642.
[14]	何颖,樊俊松,王巍,孙庚,刘衍珩. 无人机空地安全通信与航迹规划的多目标联合优化方法[J]. 吉林大学学报(工学版), 2023, 53(3): 913-922.
[15]	吴振宇,刘小飞,王义普. 基于DKRRT^*-APF算法的无人系统轨迹规划[J]. 吉林大学学报(工学版), 2023, 53(3): 781-791.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

方法	EN	Q₀	Q_E	Q_W	SSIM	VIFF
CBF	4.5089	0.3739	0.6888	0.5437	0.4434	0.2796
CSMCA	4.5977	0.4172	0.7705	0.7435	0.5885	0.4263
CVT	4.4325	0.2485	0.4074	0.4301	0.2746	0.3645
DWT	4.3306	0.2717	0.4735	0.4610	0.2928	0.3606
GFF	4.6525	0.3750	0.7072	0.5603	0.5600	0.2483
MSTSR	4.5321	0.4138	0.7479	0.7003	0.5851	0.3650
NSCT	4.3689	0.2549	0.4460	0.4423	0.2859	0.3676
NSCT_LLE	4.8174	0.4257	0.7316	0.7687	0.6702	0.4455
NSST_PCNN	4.8998	0.3932	0.5647	0.5853	0.6384	0.3884
本文	4.8315	0.4279	0.7895	0.7951	0.6978	0.4457

方法	EN	Q₀	Q_E	Q_W	SSIM	VIFF
CBF	4.1089	0.3192	0.7428	0.5706	0.4962	0.3733
CSMCA	3.9229	0.3566	0.8441	0.7757	0.7012	0.5107
CVT	4.1180	0.2560	0.4491	0.4645	0.3740	0.4271
DWT	4.0214	0.2726	0.5275	0.4955	0.3894	0.4253
GFF	4.2733	0.3261	0.8399	0.7611	0.7214	0.4718
MSTSR	4.0168	0.3422	0.8465	0.7778	0.7507	0.5187
NSCT	4.0416	0.2593	0.4951	0.4763	0.3825	0.4309
NSCT_LLE	4.3168	0.3859	0.7553	0.7931	0.8548	0.5657
NSST_PCNN	4.7590	0.3510	0.5395	0.5631	0.7958	0.4584
本文	4.3983	0.3893	0.8572	0.8204	0.9035	0.5711

方法	EN	Q₀	Q_E	Q_W	SSIM	VIFF
CBF	4.4407	0.4400	0.7580	0.7218	0.7459	0.4807
CSMCA	4.1450	0.3864	0.7400	0.7085	0.7205	0.4939
CVT	4.2760	0.2668	0.4771	0.5136	0.4504	0.3620
DWT	4.1654	0.3003	0.5321	0.5352	0.4667	0.3735
GFF	4.5299	0.4519	0.7882	0.7203	0.7175	0.4832
MSTSR	4.4779	0.3791	0.7374	0.7317	0.7884	0.5112
NSCT	4.2083	0.2794	0.5116	0.5240	0.4598	0.3710
NSCT_LLE	4.5889	0.4576	0.7758	0.7622	0.8072	0.5402
NSST_PCNN	4.5503	0.4497	0.7660	0.7445	0.7938	0.5424
本文	4.6213	0.4580	0.7795	0.7624	0.8137	0.5442

方法	EN	Q₀	Q_E	Q_W	SSIM	VIFF
CBF	2.9244	0.2479	0.8378	0.7696	0.8727	0.5064
CSMCA	2.8241	0.2400	0.8296	0.7685	0.8394	0.5060
CVT	3.2507	0.2382	0.8182	0.7597	0.8173	0.5197
DWT	2.9895	0.2192	0.5864	0.5914	0.4378	0.4527
GFF	3.1406	0.2411	0.8684	0.7642	0.7207	0.4551
MSTSR	3.1921	0.2485	0.8315	0.7748	0.7267	0.5396
NSCT	3.0286	0.2096	0.5682	0.5775	0.4279	0.4577
NSCT_LLE	3.2026	0.2556	0.8355	0.7891	0.9110	0.5600
NSST_PCNN	3.2543	0.2512	0.8375	0.7983	0.9163	0.5595
本文	3.2674	0.2613	0.8346	0.7811	0.9176	0.5601