Jul 2026· 2026 7th International Conference on Smart Systems and Inventive Technology (ICSSIT)· pp. 1023-1028· 0 citations· 23 references
Abstract
Disease diagnosis and clinical treatment involve the combination of medical images, which is one of the major technologies in the medical field. As per literature analysis, the traditional methods have some limitations for generating the fused image, including low contrast, uncertainty, and distorted sides. To address these issues, we suggest a hybrid method of image fusion using NSCT (non-subsampled contourlet transform) and fuzzy sets. Firstly, the source images were fuzzified via a normalization process. After that, the fuzzy images are decomposed into approximation and detail layers at the various scales using multi-scale decomposition, i.e., NSCT. Secondly, the maximum and local variance-based rules are used to extract the significant structural and edge details from approximation and detail coefficients, respectively. Thirdly, the reconstruction process is carried out to achieve the final fused image, followed by the defuzzification process. This approach demonstrates the efficiency of the proposed fusion process with visual analysis, including different existing algorithms. Furthermore, the quantitative analysis proves the effectiveness of the proposed model using various quality metrics such as mean, standard deviation, and average gradient.
Medical image fusion (MIF) is the process of fusing two medical pictures from different modalities into one image. This technology tries to produce a fused output image from two source images that contain more effective and relevant information. This image is used in the healthcare industry, specifically for disease diagnosis. The main challenge is using a single image modality to diagnose diseases accurately. The fused image includes spectral and structural information for the source images to help doctors with disease diagnosis problems. Positron emission tomography (PET), magnetic resonance imaging (MRI), computed tomography (CT), and single photon emission computed tomography (SPECT) are some of the medical imaging modalities. Each modality has its benefits and drawbacks. Researchers have presented different MIF techniques that obtain high fusion results in the MIF field. This paper is a comprehensive survey of multiple state-of-the-art MIF techniques in the spatial and transform domains. It also discusses the main MIF evaluation metrics. Finally, quantitative and qualitative evaluations for some of these techniques are obtained.
A hybrid Fuzzy-CNN method is proposed: pixels or visual features are first «fuzzified» in a logical sense to account for uncertainties, and then fed into the neural network.
L. Kruglova, R. Samb, F. K. Sisej· ИНФОРМАЦИОННЫЕ СИСТЕМЫ И ТЕХ...· 0 citations
To address the issues of lesion scale differences, easy loss of fine-grained pigment information, and background interference in dermoscopic images, this paper constructs a multi-scale attention fusion classification network MSAF-EfficientNetV2 based on EfficientNetV2-S. The network extracts features in four stages. AMSF achieves dynamic fusion through channel mapping, spatial alignment, and sample-related scale weights. LAA strengthens the main body of the lesion and irregular boundaries with channel-spatial attention, and uses weighted cross-entropy to alleviate the long-tailed distribution of the seven classes. The experimental results used publicly available data to form two levels of evidence: In the MedMNIST+ 224×224 end-to-end benchmark, the accuracy of DenseNet121 was 84.74±0.51%, and the AUC of DINO ViT-B/16 was 96.50±0.51%; in the histopathologically confirmed true melanoma ISIC_0000013, the Otsu dark region accounted for 22.29%, and the darkest cluster in Lab-K-means accounted for 16.60%, with a Dice concordance of 85.38%. The publicly available ISIC 2017 segmentation experiment further showed that the Dice/Jaccard ratio of VGG16-U-Net was 91.5%/84.6%, and the Dice/Jaccard ratio in this case reached 96.2%/92.6%. The total number of network parameters is 20.069 M and the number of FLOPs is 5.775 G, indicating that the newly added fusion and attention structures maintain controllable computational overhead.
Yu-Chen Jiang, Xuewen Ding· Academic Journal of Science...· 0 citations
Multimodal medical image fusion integrates complementary information from CT, MRI, and PET to support clinical diagnosis and lesion localization. CNN-based methods are constrained by local receptive fields and fail to model long-range dependencies, while Transformer-based methods incur quadratic computational complexity; both paradigms suffer from inadequate inter-modal redundancy suppression, producing blurred edges and structural inconsistency. To address these limitations, Bi-CMFM is proposed, comprising the Bi-Path Residual Fusion module (BPRF), which employs parallel standard and dilated convolutions to preserve local texture while expanding the receptive field, and the Cross-Modal Fusion Module (CMFM), which applies a Cross-modal Feature Enhancement component (CFEM) and a selective scanning mechanism to model long-range dependencies at linear complexity. Experimental results demonstrate that Bi-CMFM achieves EN = 5.1281 and AG = 7.0127 on CT-MRI fusion, PSNR of 12.7624/19.6562 on PET-MRI/SPECT-MRI tasks, and top-ranked EN, SF, AG, SCD, and CC on KAIST, outperforming six representative baselines including DATFuse, DRCM, and FusionMamba.
Jingdong Yang· Poster Volume 0008 The 2026...· 0 citations
Medical image fusion (MIF) integrates complementary information from
multiple modalities to enhance diagnostic accuracy. However, existing approaches often struggle
to suppress noise while preserving critical anatomical details.
We propose ENCAF-NSST-AD, a fusion technique that combines the
Non-Subsampled Shearlet Transform (NSST) with anisotropic diffusion (AD) refinement. Lowfrequency
base layers (LFBL) are fused using an energy-based weighting strategy, while high-frequency
detail layers (HFDL) are integrated through a contrast-aware rule. The reconstructed image
is further enhanced using AD filtering with optimized parameters to improve clarity and preserve
structural information.
Experiments on standard medical image datasets demonstrate that ENCAF-NSST-AD consistently outperforms existing methods in both visual quality and quantitative metrics, including FMI, FF, entropy, and standard deviation.
Experiments on benchmark datasets demonstrate that ENCAF-NSST-AD achieves superior
fusion quality compared with existing state-of-the-art methods, exhibiting enhanced visual clarity
and higher values across standard quantitative metrics.
The proposed method effectively balances noise suppression with edge preservation,
addressing limitations of traditional MIF schemes. By combining adaptive fusion rules with edgepreserving
diffusion, ENCAF-NSST-AD preserves global contrast and fine anatomical boundaries,
resulting in fused images more suitable for clinical interpretation. Its energy- and contrast-
aware fusion with AD refinement represents a clinically relevant and patent-oriented advancement.
The integration of NSST with adaptive fusion rules and AD refinement produces robust
and diagnostically meaningful fusion outcomes. ENCAF-NSST-AD is an effective MIF approach
that can enhance clinical decision support in medical imaging.
Mohammed Rafiq, Prabhishek Singh, Ankur Maurya et al.· Recent Patents on Engineerin...· 0 citations
Advances in image acquisition and computational processing technologies have significantly transformed histological and hematological analysis. However, to maximize the clinical impact of these technologies, it is essential to develop automatic or semi-automatic segmentation techniques. The objective of this work is to develop an automatic multi-class segmentation technique that achieves competitive performance while minimizing computational costs. The proposed technique consists of an unsupervised algorithm that models a neutrosophic image by combining only two features: the luminance channel L* from the CIELUV color space and the HH sub-band of the discrete wavelet transform obtained from the grayscale image. The neutrosophic components are enhanced to promote robust clustering and segmentation, especially in regions of uncertainty. Finally, morphological operations are applied as a post-processing stage. Experimental results demonstrate strong performance in multiclass segmentation, with average standard index values above 90% and an overall correct classification rate of 97.07%. The developed algorithm has publicly available open-source code, operates directly on color images without requiring any training and achieves competitive results with a low-cost implementation.
F. Otero, André Fedérick Pontis, J. Pastore· Research on Biomedical Engin...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
