Multimodal medical image fusion algorithm based on pulse coupled neural networks and nonsubsampled contourlet transform

Ibrahim, Sa. I.; Makhlouf, Mohamed; El-Tawel, Gh. S.

doi:10.1007/s11517-022-02697-8

Cited by 19 publications

(4 citation statements)

References 31 publications

(59 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using the ADE20K dataset, a model is trained with Deeplab-v3 network as the backbone for the semantic segmentation of street view images [40,41]. The segmentation results are shown in Figure 3.…”

Section: Street View Imagementioning

confidence: 99%

Research on Traffic Accident Risk Prediction Method Based on Spatial and Visual Semantics

Li,

Luo

2023

IJGI

View full text Add to dashboard Cite

Predicting traffic accidents involves analyzing historical data, determining the relevant factors affecting the occurrence of traffic accidents, and predicting the likelihood of future traffic accidents. Most of the previous studies used statistical methods or single deep learning network model prediction methods while ignoring the visual effects of the city landscape on the drivers and the zero-inflation problem, resulting in poor prediction performance. Therefore, this paper constructs a city traffic accident risk prediction model that incorporates spatial and visual effects on drivers. The improved STGCN model is used in the model, a CNN and GRU replace the origin space–time convolution layer, two layers of a GCN are added to extract the city landscape similarity of different regions, and a BN layer is added to solve the gradient explosion problem. Finally, the features extracted from the time–space correlation module, the city landscape similarity module and the spatial correlation module are fused. The model is trained with the self-made Chicago dataset and compared with the existing network model. The comparison experiment proves that the prediction effect of the model in both the full time period and the high-frequency time period is better than that of the existing model. The ablation experiment proves that the city landscape similarity module added in this paper performs well in the high-frequency area.

show abstract

Section: Street View Imagementioning

confidence: 99%

Research on Traffic Accident Risk Prediction Method Based on Spatial and Visual Semantics

Li,

Luo

2023

IJGI

View full text Add to dashboard Cite

show abstract

“…Totally there are six objective quality criteria used to evaluate the performance of the proposed image fusion approach including entropy (EN), average gradient (AG), spatial frequency (SF), mutual information (MI) [31] , feature mutual information (FMI) [32] and visual information fidelity (VIF) [33] . EN, AG and SF measure the information content and texture details embedded within an image, i.e.…”

Section: Quality Assessment Of Image Fusionmentioning

confidence: 99%

A novel image fusion approach for improving vessel visibility in surgical filler injections

Sun,

Liu,

et al. 2023

Preprint

View full text Add to dashboard Cite

The occurrence of adverse events caused by intravascular injection or vascular compression of filler material remains a persistent concern for surgical filler injection. In order to enhance the visibility of facial vessels and make the injection procedure safe, this paper reports a simple yet effective image fusion approach that combines simultaneously captured visible and near-infrared images to produce vessel-highlighted effects. The visibility enhancement of vessel details involves applying a customized sharpening filter to the NIR image prior to merging it with the color facial. The validation of the fused images is conducted by employing quantitative objective metrics of image quality and clinical efficiency in the identification of vessels. The experimental results demonstrate the proposed approach can efficiently generate discernible impression of vessels with color and texture realistically persevered, and therefore contributes to augment the safety and precision of surgical planning or guidance in filler injections.

show abstract

“…Over the past few decades, a vast array of fusion algorithms has been suggested by researchers, such as: Laplacian pyramid (LP) [7][8][9], non-subsampled contourlet transform (NSCT) [10][11][12][13], non-subsampled Shearlet transform (NSST) [3,[14][15][16], and wavelet transform [17,18]. Barba-J, Vargas-Quintero, and Calderón-Agudelo [19] proposed a transform-based method for the fusion of CT and SPECT images, which used discrete Hermite transform to decompose the source images, and then fused them.…”

Section: Introductionmentioning

confidence: 99%

“…FIGURE13 | Source images and their fusion results of the proposed method with different loss functions.…”

mentioning

confidence: 99%

CFIFusion: Dual‐Branch Complementary Feature Injection Network for Medical Image Fusion

Xie,

Yu,

Ding

2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

The goal of fusing medical images is to integrate the diverse information that multimodal medical images hold. However, the challenges lie in the limitations of imaging sensors and the issue of incomplete modal information retention, which make it difficult to produce images encompassing both functional and anatomical information. To overcome these obstacles, several medical image fusion techniques based on CNN or transformer architectures have been presented. Nevertheless, CNN technique struggles to establish extensive dependencies between the fused and source images, and transformer architecture often overlooks shallow complementary features. To augment both the feature extraction capacity and the stability of the model, we introduce a framework, called dual‐branch complementary feature injection fusion (CFIFusion) technique, a for multimodal medical image fusion framework that combines unsupervised models of CNN model and transformer techniques. Specifically, in our framework, the entire source image and segmented source image are input into an adaptive backbone network to learn global and local features, respectively. To further retain the source images' complementary information, we design a multi‐scale complementary feature extraction framework as an auxiliary module, focusing on calculating feature differences at each level to capture the shallow complementary information. Then, we design a shallow information preservation module tailored for sliced image characteristics. Experimental results on the Harvard whole brain atlas dataset demonstrate that CFIFusion shows greater benefits than recent state‐of‐the‐art algorithms in terms of both subjective and objective evaluations.

show abstract

Multimodal medical image fusion algorithm based on pulse coupled neural networks and nonsubsampled contourlet transform

Cited by 19 publications

References 31 publications

Research on Traffic Accident Risk Prediction Method Based on Spatial and Visual Semantics

Research on Traffic Accident Risk Prediction Method Based on Spatial and Visual Semantics

A novel image fusion approach for improving vessel visibility in surgical filler injections

CFIFusion: Dual‐Branch Complementary Feature Injection Network for Medical Image Fusion

Contact Info

Product

Resources

About