A new approach to medical image fusion based on the improved Extended difference-of-Gaussians combined with the Coati optimization algorithm

Biomedical Signal Processing and Control, Год журнала: 2024, Номер 93, С. 106175 - 106175

Опубликована: Март 11, 2024

Язык: Английский

---

An effective medical image fusion method utilizing moth-flame optimization and coupled neural P systems

Neural Computing and Applications, Год журнала: 2025, Номер unknown

Опубликована: Март 11, 2025

Язык: Английский

---

FFSWOAFuse: Multi-modal medical image fusion via fermatean fuzzy set and whale optimization algorithm

Computers in Biology and Medicine, Год журнала: 2025, Номер 189, С. 109889 - 109889

Опубликована: Март 6, 2025

Язык: Английский

---

Deep Multi-Modal Skin-Imaging-Based Information-Switching Network for Skin Lesion Recognition

Bioengineering, Год журнала: 2025, Номер 12(3), С. 282 - 282

Опубликована: Март 12, 2025

The rising prevalence of skin lesions places a heavy burden on global health resources and necessitates an early precise diagnosis for successful treatment. diagnostic potential recent multi-modal lesion detection algorithms is limited because they ignore dynamic interactions information sharing across modalities at various feature scales. To address this, we propose deep learning framework, Multi-Modal Skin-Imaging-based Information-Switching Network (MDSIS-Net), end-to-end recognition. MDSIS-Net extracts intra-modality features using transfer in multi-scale fully shared convolutional neural network introduces innovative information-switching module. A cross-attention mechanism dynamically calibrates integrates to improve inter-modality associations representation this tested clinical disfiguring dermatosis data the public Derm7pt melanoma dataset. Visually Intelligent System Image Analysis (VISIA) captures five modalities: spots, red marks, ultraviolet (UV) porphyrins, brown spots dermatosis. model performs better than existing approaches with mAP 0.967, accuracy 0.960, precision 0.935, recall f1-score 0.947. Using dermoscopic pictures from dataset, outperforms current benchmarks melanoma, 0.877, 0.907, 0.911, 0.815, 0.851. model’s interpretability proven by Grad-CAM heatmaps correlating focus areas. In conclusion, our enhances identification capturing relationship fine-grained details images, improving both interpretability. This work advances decision making lays foundation future developments

Язык: Английский

---

FS-Diff: Semantic guidance and clarity-aware simultaneous multimodal image fusion and super-resolution

Information Fusion, Год журнала: 2025, Номер 121, С. 103146 - 103146

Опубликована: Апрель 7, 2025

Язык: Английский

---

Advancing multimodal medical image fusion: an adaptive image decomposition approach based on multilevel Guided filtering

Royal Society Open Science, Год журнала: 2024, Номер 11(4)

Опубликована: Апрель 1, 2024

With the rapid development of medical imaging methods, multimodal image fusion techniques have caught interest researchers. The aim is to preserve information from diverse sensors using various models generate a single informative image. main challenge derive trade-off between spatial and spectral qualities resulting fused computing efficiency. This article proposes fast reliable method for depending on multilevel Guided edge-preserving filtering (MLGEPF) decomposition rule. First, each was divided into three sublayer categories an MLGEPF scheme: small-scale component, large-scale component background component. Secondly, two strategies—pulse-coupled neural network based structure tensor maximum based—are applied combine types layers, layers' properties. different sublayers are combined create at end. A total 40 pairs brain images four separate conditions were tested in experiments. pair includes case studies including magnetic resonance (MRI) , TITc, single-photon emission computed tomography (SPECT) positron (PET). We included qualitative analysis demonstrate that visual contrast surrounding tissue increased our proposed method. To further enhance comparison, we asked group observers compare method’s outputs with other methods score them. Overall, scheme received positive subjective review. Moreover, objective assessment indicators category also included. Our achieves high evaluation outcome feature mutual (FMI), sum correlation differences (SCD), Qabf Qy indexes. implies algorithm has better performance preservation efficient structural transferring.

Язык: Английский

---

Multi-modal remote sensing image fusion method guided by local extremum maps-guided image filter

Signal Image and Video Processing, Год журнала: 2024, Номер 18(5), С. 4375 - 4383

Опубликована: Март 22, 2024

Язык: Английский

---

FusionDiff: A unified image fusion network based on diffusion probabilistic models

Computer Vision and Image Understanding, Год журнала: 2024, Номер 244, С. 104011 - 104011

Опубликована: Апрель 10, 2024

Язык: Английский

---

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

Biomedical Signal Processing and Control, Год журнала: 2024, Номер 100, С. 106976 - 106976

Опубликована: Окт. 10, 2024

Язык: Английский

---

Dual-channel Rybak neural network based medical image fusion

Optics & Laser Technology, Год журнала: 2024, Номер 181, С. 112018 - 112018

Опубликована: Ноя. 1, 2024

Язык: Английский

---