The field of medical imaging and neuroscience is rapidly advancing, driven by innovations in deep learning, diffusion models, and physics-informed approaches. A key direction is the integration of domain knowledge and data-driven models to improve the accuracy and robustness of image analysis and reconstruction. This is evident in the development of novel frameworks that combine anatomical priors with deep learning models to achieve state-of-the-art performance in tasks such as brain MRI segmentation and diffusion-weighted imaging. Another important trend is the use of generative models to simulate clinical-grade images, such as PET images from MRI data, which has the potential to improve diagnostic accuracy and reduce costs. Noteworthy papers in this area include the introduction of diffusion bridge networks for simulating PET images from MRI data, and the development of a predictive-corrective paradigm for anatomy-informed brain MRI segmentation. These advances have the potential to transform the field of medical imaging and neuroscience, enabling more accurate and efficient diagnosis and treatment of diseases.
Advances in Medical Imaging and Neuroscience
Sources
Deep generative priors for 3D brain analysis
Robust High-Resolution Multi-Organ Diffusion MRI Using Synthetic-Data-Tuned Prompt Learning
Rethinking Convergence in Deep Learning: The Predictive-Corrective Paradigm for Anatomy-Informed Brain MRI Segmentation
Diffusion Bridge Networks Simulate Clinical-grade PET from MRI for Dementia Diagnostics
A multilayer level-set method for eikonal-based traveltime tomography
BARL: Bilateral Alignment in Representation and Label Spaces for Semi-Supervised Volumetric Medical Image Segmentation
CausalMamba: Scalable Conditional State Space Models for Neural Causal Inference
Step-Aware Residual-Guided Diffusion for EEG Spatial Super-Resolution
Predicting before Reconstruction: A generative prior framework for MRI acceleration
Dictionary learning methods for brain activity mapping with MEG data
BrainPuzzle: Hybrid Physics and Data-Driven Reconstruction for Transcranial Ultrasound Tomography
Understanding Mechanistic Role of Structural and Functional Connectivity in Tau Propagation Through Multi-Layer Modeling
A Structured Review and Quantitative Profiling of Public Brain MRI Datasets for Foundation Model Development
Resounding Acoustic Fields with Reciprocity