5 papers
Beyond Fixed Luminance: Towards Panchromatic and Orthochromatic Image Colorization
Swarnim Maheshwari, Syed Imam Ali, Vineeth N. Balasubramanian
Most image colorization systems operate in space by predicting chroma () while preserving an input-derived luminance channel (). While effective on standard benchmarks…
M2Diff: Multi-Modality Multi-Task Enhanced Diffusion Model for MRI-Guided Low-Dose PET Enhancement
Ghulam Nabi Ahmad Hassan Yar, Himashi Peiris, Victoria Mar +2
Positron emission tomography (PET) scans expose patients to radiation, which can be mitigated by reducing the dose, albeit at the cost of diminished quality. This makes low-dose (L…
Segment Any Tumour: An Uncertainty-Aware Vision Foundation Model for Whole-Body Analysis
Himashi Peiris, Sizhe Wang, Gary Egan +3
Prompt-driven vision foundation models, such as the Segment Anything Model, have recently demonstrated remarkable adaptability in computer vision. However, their direct application…
MedNet-PVS: A MedNeXt-Based Deep Learning Model for Automated Segmentation of Perivascular Spaces
Zhen Xuen Brandon Low, Rory Zhang, Hang Min +20
Enlarged perivascular spaces (PVS) are increasingly recognized as biomarkers of cerebral small vessel disease, Alzheimer's disease, stroke, and aging-related neurodegeneration. How…
D2Diff : A Dual Domain Diffusion Model for Accurate Multi-Contrast MRI Synthesis
Sanuwani Dayarathna, Himashi Peiris, Kh Tohidul Islam +2
Multi contrast MRI synthesis is inherently challenging due to the complex and nonlinear relationships among different contrasts. Each MRI contrast highlights unique tissue properti…