Medical image fusion based on transfer learning techniques and coupled neural P systems

Dinh, Phu-Hung; Giang, Nguyen Long

doi:10.1007/s00521-023-09294-2

Cited by 4 publications

(3 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the existing ones, two-scale image decomposition (TSID) methods (Fig. 2) are widely used in many research works for medical image fusion such as two-scale using Discrete wavelet transform (DWT) [11,12], Fast fourier transform (FFT) [9,10], or Gaussian Blur filter (GBF) [18]. In this section, we present the use of a Gaussian blur filter to perform the TSID of an input image (I) into two parts, called the base layer (I b ) and the detail layer (I d ).…”

Section: Gaussian-blur Filter Two-scale Image Decomposition (Gbf-tsid)mentioning

confidence: 99%

“…The base layer demonstrates the large-scale deviation or general features of the image while the detail layer contains small-scale variations or detailed information of the image. We chose GBF for TSID since it is efficiently used in other research works in medical image fusion [18].…”

Section: Gaussian-blur Filter Two-scale Image Decomposition (Gbf-tsid)mentioning

confidence: 99%

“…For example, in [9,10,16,17], the authors employ meta-heuristic optimization algorithms and maximum local energy functions to create fusion rules for detail and base features. Besides, in [18,19], the authors utilize deep learning-based transfer learning techniques for medical image fusion. Those methods significantly improve the fusion quality of medical images.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A New Method for Medical Image Fusion Based on Gaussian Blur Filter and Robinson Compass Operator

Kieu,

Huynh,

Nghiem

et al. 2024

JCC

View full text Add to dashboard Cite

Medical image fusion is a process of extracting features from multi-modal medical images and combining them into a composite image. It brings huge support in medical imaging and clinical diagnosis. However, the extraction of both structural and functional information from input MRI and PET images using multi-scale transform fusion methods poses a challenge of providing high-quality decomposition layers since during the decomposition process, images can still lose information such as blur or noise at the edges of the image. To address this limitation, we present a new method to improve the visual information fidelity of medical image fusion. Firstly, the YCbCr color space is utilized to prevent distortion when merging color and grey images. The second algorithm uses the CLAHE model, which allows the input images to have good contrast. Then, a Gaussian blur filter is employed to decompose the images into base and detail layers. The use of Gaussian blur ensures a smoothing filter of the edges. After that, the Robinson compass operator is applied to create the fusion rule of detail components. Finally, the fused base and detail layers are concatenated together to form the final composite image. The experimental results show that the proposed approach outperforms the latest methods in bringing visual information fidelity of the input images to the fused image, which is helpful in supporting doctors and radiologists in visual analysis of the medical images.

show abstract

Section: Gaussian-blur Filter Two-scale Image Decomposition (Gbf-tsid)mentioning

confidence: 99%

Section: Gaussian-blur Filter Two-scale Image Decomposition (Gbf-tsid)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A New Method for Medical Image Fusion Based on Gaussian Blur Filter and Robinson Compass Operator

Kieu,

Huynh,

Nghiem

et al. 2024

JCC

View full text Add to dashboard Cite

show abstract

MIF-BTF-MRN: Medical image fusion based on the bilateral texture filter and transfer learning with the ResNet-101 network

Dinh

2025

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

A dual-branch infrared and visible image fusion network using progressive image-wise feature transfer

Xu,

Zhou,

Xiao

et al. 2024

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

Medical image fusion based on transfer learning techniques and coupled neural P systems

Cited by 4 publications

References 73 publications

A New Method for Medical Image Fusion Based on Gaussian Blur Filter and Robinson Compass Operator

A New Method for Medical Image Fusion Based on Gaussian Blur Filter and Robinson Compass Operator

MIF-BTF-MRN: Medical image fusion based on the bilateral texture filter and transfer learning with the ResNet-101 network

A dual-branch infrared and visible image fusion network using progressive image-wise feature transfer

Contact Info

Product

Resources

About