CMViM: Contrastive Masked Vim Autoencoder for 3D Multi-modal Representation Learning for AD classification

G Yang, K Du, Z Yang, Y Du, Y Zheng… - arXiv preprint arXiv …, 2024 - arxiv.org
Alzheimer's disease (AD) is an incurable neurodegenerative condition leading to cognitive
and functional deterioration. Given the lack of a cure, prompt and precise AD diagnosis is …

Coarse-to-fine visual representation learning for medical images via class activation maps

BP Yap, BK Ng - Computers in Biology and Medicine, 2024 - Elsevier
The value of coarsely labeled datasets in learning transferable representations for medical
images is investigated in this work. Compared to fine labels which require meticulous effort …

Pre-training on High Definition X-ray Images: An Experimental Study

X Wang, Y Li, W Wu, J Jin, Y Rong, B Jiang, C Li… - arXiv preprint arXiv …, 2024 - arxiv.org
Existing X-ray based pre-trained vision models are usually conducted on a relatively small-
scale dataset (less than 500k samples) with limited resolution (eg, 224$\times $224) …

ASIMSA: Advanced Semantic Information Guided Multi-Scale Alignment Framework for Medical Vision-Language Pretraining

S Xiao, Y Zhang, L Jiang, Z Wang - 2024 IEEE 9th International …, 2024 - ieeexplore.ieee.org
Medical Visual Language Pretraining (MVLP) utilizes textual reports for weak supervision to
improve the learning of medical visual representations, showing promise in various medical …