The field of neuroimaging and machine learning is rapidly advancing, with a focus on improving disease diagnosis and progression modeling. Recent studies have demonstrated the effectiveness of deep learning techniques, such as graph neural networks and transformers, in analyzing medical images and predicting disease outcomes. For example, researchers have developed models that can accurately predict breast cancer sites and segment tumors from dynamic contrast-enhanced MRI images. Additionally, studies have shown that integrating causal inference with graph neural networks can identify brain regions that exert stable causal influence on Alzheimer's disease progression. Noteworthy papers include the development of a deformation-aware graph neural network for real-time prediction of breast cancer sites, and the proposal of a novel framework that uses Large Language Models as expert guides to enhance learning of disease progression from longitudinal patient data. These advances have the potential to significantly improve disease diagnosis and treatment, and highlight the importance of continued research in this area.
Advances in Neuroimaging and Machine Learning for Disease Diagnosis and Progression Modeling
Sources
Forecasting Spoken Language Development in Children with Cochlear Implants Using Preimplantation MRI
LLM enhanced graph inference for long-term disease progression modelling
From Play to Detection: Mini-SPACE as a Serious Game for Unsupervised Cognitive Impairment Screening
Real-time prediction of breast cancer sites using deformation-aware graph neural network
Deep Learning-Based Regional White Matter Hyperintensity Mapping as a Robust Biomarker for Alzheimer's Disease
MRI Embeddings Complement Clinical Predictors for Cognitive Decline Modeling in Alzheimer's Disease Cohorts
Integrating Causal Inference with Graph Neural Networks for Alzheimer's Disease Analysis
DCL-SE: Dynamic Curriculum Learning for Spatiotemporal Encoding of Brain Imaging
BrainRotViT: Transformer-ResNet Hybrid for Explainable Modeling of Brain Aging from 3D sMRI
EVA-Net: Interpretable Brain Age Prediction via Continuous Aging Prototypes from EEG
Externally Validated Multi-Task Learning via Consistency Regularization Using Differentiable BI-RADS Features for Breast Ultrasound Tumor Segmentation
FastSurfer-CC: A robust, accurate, and comprehensive framework for corpus callosum morphometry
Acquisition Time-Informed Breast Tumor Segmentation from Dynamic Contrast-Enhanced MRI