Medical Image Fusion & Processing — 60+ IEEE Project Topics
Medical image fusion combines complementary information from multiple modalities (CT, MRI, PET, SPECT, ultrasound) of the same patient to improve diagnosis and treatment planning. Related processing tasks — segmentation, registration, enhancement and CAD — form the backbone of modern medical imaging research and final-year projects.
Below are 60+ carefully selected IEEE-style topics organised by domain, with recommended tools (MATLAB, Python, MONAI, PyTorch, TensorFlow, 3D Slicer).
Tools Used for Medical Image Processing
MATLAB
Image Processing Toolbox, Wavelet Toolbox, Deep Learning Toolbox — classic fusion, metrics and teaching pipelines.
Python + OpenCV / scikit-image
Fast prototyping, classical algorithms and custom pipelines.
MONAI + PyTorch
State-of-the-art medical deep learning (segmentation, registration, fusion networks).
TensorFlow / Keras
U-Net variants, GANs and classification models for medical images.
SimpleITK / ITK
Robust registration, filtering and multi-dimensional image handling.
3D Slicer
Interactive visualisation, segmentation and extension development.
Nibabel / pydicom
DICOM and NIfTI I/O for clinical datasets.
MeVisLab / Fiji
Rapid visual prototyping and classical image analysis.
Multimodal & Classical Image Fusion (1–18)
CT-MRI · PET-MRI · SPECT-CT · Wavelet · NSCT · PCA · Fuzzy · Sparse
| # | IEEE 2026 Medical Image Processing Topic | Domain | Tools Used |
|---|---|---|---|
| 01 | CT-MRI Multimodal Fusion using Discrete Wavelet Transform for Brain Tumour VisualisationFusion | Image Fusion | MATLAB |
| 02 | PET-MRI Fusion with Non-Subsampled Contourlet Transform (NSCT) for OncologyFusion | Image Fusion | MATLAB |
| 03 | SPECT-CT Fusion using PCA and Weighted Averaging for Bone Metastasis DetectionFusion | Image Fusion | MATLAB / Python |
| 04 | Ultrasound-MRI Fusion for Prostate Biopsy GuidanceFusion | Image Fusion | MATLAB / 3D Slicer |
| 05 | Multi-Focus Medical Image Fusion using Sparse RepresentationFusion | Image Fusion | MATLAB |
| 06 | Fuzzy Logic based Multimodal Medical Image Fusion with Edge PreservationFusion | Image Fusion | MATLAB |
| 07 | Pulse-Coupled Neural Network (PCNN) based Medical Image FusionFusion | Image Fusion | MATLAB |
| 08 | Guided Filter based Fusion of CT and MRI for Soft-Tissue and Bone DetailFusion | Image Fusion | MATLAB / Python |
| 09 | Laplacian Pyramid and Morphological Processing for Medical Image FusionFusion | Image Fusion | MATLAB |
| 10 | Curvelet Transform based Fusion for Retinal and Fundus Image EnhancementFusion | Image Fusion | MATLAB |
| 11 | Shearlet Transform Multimodal Fusion for Brain PathologyFusion | Image Fusion | MATLAB |
| 12 | Intensity-Hue-Saturation (IHS) and Wavelet Hybrid Fusion for PET-CTFusion | Image Fusion | MATLAB |
| 13 | Region-based Medical Image Fusion using Graph-Cut Segmentation PriorFusion | Image Fusion | MATLAB / Python |
| 14 | Multi-Scale Decomposition Fusion with Structural Similarity OptimisationFusion | Image Fusion | MATLAB |
| 15 | Anisotropic Diffusion and Wavelet Fusion for Noisy Medical ImagesFusion | Image Fusion | MATLAB |
| 16 | Quaternion Wavelet Transform based Colour Medical Image FusionFusion | Image Fusion | MATLAB |
| 17 | Parameter-Adaptive PCNN with NSCT for Multimodal Medical FusionFusion | Image Fusion | MATLAB |
| 18 | Comparative Study of Spatial vs Transform Domain Medical Image Fusion MetricsFusion | Image Fusion | MATLAB / Python |
Deep Learning based Medical Image Fusion (19–30)
CNN · GAN · Attention · Transformer · U-Net Fusion · MONAI
| # | IEEE 2026 Medical Image Processing Topic | Domain | Tools Used |
|---|---|---|---|
| 19 | CNN based End-to-End Multimodal Medical Image Fusion NetworkDL Fusion | Deep Learning | PyTorch / TensorFlow |
| 20 | GAN-based Medical Image Fusion with Adversarial Detail PreservationDL Fusion | Deep Learning | PyTorch |
| 21 | Attention-Guided Multimodal Fusion Network for CT-MRI Brain ImagesDL Fusion | Deep Learning | PyTorch / MONAI |
| 22 | Transformer-based Medical Image Fusion with Swin or ViT BackboneDL Fusion | Deep Learning | PyTorch |
| 23 | U-Net Architecture Adapted for Multimodal Feature Fusion and ReconstructionDL Fusion | Deep Learning | PyTorch / Keras |
| 24 | Unsupervised Medical Image Fusion using CycleGAN and Perceptual LossDL Fusion | Deep Learning | PyTorch |
| 25 | Multi-Scale Dense Network for PET-MRI Fusion in Neuro-OncologyDL Fusion | Deep Learning | PyTorch / MONAI |
| 26 | Explainable AI (Grad-CAM) for Interpretable Medical Image Fusion DecisionsDL Fusion | Deep Learning | PyTorch |
| 27 | Self-Supervised Pretraining for Medical Image Fusion with Limited LabelsDL Fusion | Deep Learning | PyTorch / MONAI |
| 28 | Lightweight Mobile-Friendly CNN for Real-Time Ultrasound-MRI FusionDL Fusion | Deep Learning | TensorFlow Lite / PyTorch |
| 29 | Cross-Modal Attention Fusion for Multi-Parametric MRI SequencesDL Fusion | Deep Learning | PyTorch |
| 30 | Comparative Evaluation of Classical vs Deep Learning Medical Image FusionDL Fusion | Deep Learning | MATLAB + PyTorch |
Medical Image Segmentation (31–42)
U-Net · nnU-Net · Brain · Lung · Cardiac · Tumour · Organ
| # | IEEE 2026 Medical Image Processing Topic | Domain | Tools Used |
|---|---|---|---|
| 31 | Brain Tumour Segmentation on BraTS Dataset using U-Net and Attention U-NetSegmentation | Segmentation | PyTorch / MONAI |
| 32 | Lung Nodule Segmentation from CT using 3D CNN and nnU-NetSegmentation | Segmentation | MONAI / PyTorch |
| 33 | Cardiac MRI Left Ventricle and Myocardium SegmentationSegmentation | Segmentation | PyTorch / MATLAB |
| 34 | Liver and Tumour Segmentation from Abdominal CT (LiTS Dataset)Segmentation | Segmentation | MONAI |
| 35 | Retinal Vessel Segmentation using U-Net and FR-UNet VariantsSegmentation | Segmentation | PyTorch / TensorFlow |
| 36 | Multi-Organ Segmentation from CT using Transformer-based ModelsSegmentation | Segmentation | PyTorch / MONAI |
| 37 | Skin Lesion Segmentation for Melanoma Detection (ISIC Dataset)Segmentation | Segmentation | PyTorch / Keras |
| 38 | Prostate Segmentation from MRI using Hybrid CNN-TransformerSegmentation | Segmentation | MONAI |
| 39 | COVID-19 Lung Infection Segmentation from Chest CTSegmentation | Segmentation | PyTorch / MATLAB |
| 40 | Kidney and Tumour Segmentation (KiTS Dataset) with Cascaded NetworksSegmentation | Segmentation | MONAI |
| 41 | Semi-Supervised Medical Image Segmentation with Limited AnnotationsSegmentation | Segmentation | PyTorch |
| 42 | Interactive Segmentation with Deep Learning and User ScribblesSegmentation | Segmentation | PyTorch / 3D Slicer |
Medical Image Registration (43–48)
Rigid · Non-rigid · Multi-modal · Deep Registration
| # | IEEE 2026 Medical Image Processing Topic | Domain | Tools Used |
|---|---|---|---|
| 43 | Multi-Modal CT-MRI Rigid and Affine Registration using Mutual InformationRegistration | Registration | SimpleITK / MATLAB |
| 44 | Non-Rigid Deformable Registration of Lung CT for Follow-up StudiesRegistration | Registration | SimpleITK / ANTs concepts |
| 45 | Deep Learning based End-to-End Medical Image Registration (VoxelMorph style)Registration | Registration | PyTorch / MONAI |
| 46 | Ultrasound to MRI Registration for Image-Guided InterventionsRegistration | Registration | 3D Slicer / MATLAB |
| 47 | Group-wise Registration of Longitudinal Brain MRI for Atrophy AnalysisRegistration | Registration | SimpleITK / Python |
| 48 | Landmark-Free Deep Registration for Multi-Parametric Prostate MRIRegistration | Registration | PyTorch |
Image Enhancement & Denoising (49–54)
Denoising · Super-resolution · Contrast · Artefact Removal
| # | IEEE 2026 Medical Image Processing Topic | Domain | Tools Used |
|---|---|---|---|
| 49 | Deep Learning Denoising of Low-Dose CT using Residual NetworksEnhancement | Enhancement | PyTorch / TensorFlow |
| 50 | MRI Super-Resolution with Generative Adversarial NetworksEnhancement | Enhancement | PyTorch |
| 51 | CLAHE and Adaptive Histogram Equalisation for Ultrasound Contrast EnhancementEnhancement | Enhancement | MATLAB / OpenCV |
| 52 | Metal Artefact Reduction in CT using Deep Learning InpaintingEnhancement | Enhancement | PyTorch |
| 53 | Speckle Noise Reduction in Ultrasound with BM3D and Deep NetworksEnhancement | Enhancement | MATLAB / Python |
| 54 | Motion Artefact Correction in MRI using Self-Supervised LearningEnhancement | Enhancement | PyTorch |
CAD & Classification (55–60)
Disease Detection · Classification · Prognosis · Explainable CAD
| # | IEEE 2026 Medical Image Processing Topic | Domain | Tools Used |
|---|---|---|---|
| 55 | Deep Learning based Pneumonia Detection from Chest X-RayCAD | CAD | PyTorch / TensorFlow |
| 56 | Breast Cancer Classification from Mammography using Transfer LearningCAD | CAD | Keras / PyTorch |
| 57 | Diabetic Retinopathy Grading from Fundus Images with Explainable AICAD | CAD | PyTorch |
| 58 | Multi-Class Brain Tumour Classification from MRI using Ensemble CNNsCAD | CAD | PyTorch / MATLAB |
| 59 | COVID-19 Detection and Severity Scoring from Chest CTCAD | CAD | PyTorch / MONAI |
| 60 | Skin Cancer Classification (Melanoma vs Benign) with MobileNet and Grad-CAMCAD | CAD | TensorFlow / PyTorch |
3D Reconstruction & Additional Topics (61–65)
Volume Rendering · Surface Reconstruction · Multi-view
| # | IEEE 2026 Medical Image Processing Topic | Domain | Tools Used |
|---|---|---|---|
| 61 | 3D Surface Reconstruction of Organs from CT/MRI Segmentation Masks3D | 3D Reconstruction | 3D Slicer / Python |
| 62 | Volume Rendering and Virtual Endoscopy from CT Colonography3D | 3D Reconstruction | 3D Slicer / VTK |
| 63 | Multi-View Fusion of X-Ray Projections for Limited-Angle Tomography3D | 3D Reconstruction | PyTorch / MATLAB |
| 64 | Federated Learning for Multi-Institution Medical Image SegmentationDL | Deep Learning | PyTorch / MONAI |
| 65 | Privacy-Preserving Medical Image Analysis with Differential Privacy and Federated LearningDL | Deep Learning | PyTorch |
Additional topics available on request: histopathology image analysis, multi-modal transformer fusion, domain adaptation for cross-scanner robustness, and real-time fusion for surgical navigation. Contact us with your preferred modality and tool.
Need a Personalised Medical Image Fusion / Processing Project?
Share your preferred domain (fusion, segmentation, registration, CAD…), tool (MATLAB / Python / MONAI) and deadline. We deliver complete source code, datasets or links, metrics, IEEE base paper, report, PPT and viva support.
Frequently Asked Questions — Medical Image Fusion
What are the best medical image fusion project topics for 2026?
Top topics include deep learning multimodal CT-MRI and PET-MRI fusion, attention-guided and transformer fusion networks, GAN-based fusion, classical wavelet/NSCT fusion, and explainable fusion for clinical use. Segmentation, registration and CAD topics are also in high demand.
Which tools are used for medical image processing final year projects?
MATLAB (Image Processing & Deep Learning Toolboxes), Python with OpenCV, scikit-image, SimpleITK, MONAI, PyTorch, TensorFlow/Keras, and 3D Slicer for visualisation and interactive work.
Do you provide complete medical image fusion project packages?
Yes. Packages include source code, model weights where applicable, sample data or dataset links, quantitative metrics (SSIM, PSNR, MI, QAB/F), IEEE 2026 base paper, report, PPT and viva Q&A.
What is the difference between medical image fusion and general image fusion?
Medical image fusion specifically combines complementary modalities (CT, MRI, PET, SPECT, ultrasound) of the same patient to aid diagnosis while preserving clinically relevant anatomical and functional information. Evaluation prioritises diagnostic quality and standard radiology metrics.