detalle del documento
IDENTIFICACIÓN
oai:arXiv.org:2311.14902
Tema
Computer Science - Computer Vision...Autor
Ding, Jun-En Hsu, Chien-Chin Liu, FengCategoría
Computer Science
Año
2023
fecha de cotización
28/8/2024
Palabras clave
pd features imagesResumen
Parkinson's Disease (PD) affects millions globally, impacting movement.
Prior research utilized deep learning for PD prediction, primarily focusing on medical images, neglecting the data's underlying manifold structure.
This work proposes a multimodal approach encompassing both image and non-image features, leveraging contrastive cross-view graph fusion for PD classification.
We introduce a novel multimodal co-attention module, integrating embeddings from separate graph views derived from low-dimensional representations of images and clinical features.
This enables more robust and structured feature extraction for improved multi-view data analysis.
Additionally, a simplified contrastive loss-based fusion method is devised to enhance cross-view fusion learning.
Our graph-view multimodal approach achieves an accuracy of 0.91 and an area under the receiver operating characteristic curve (AUC) of 0.93 in five-fold cross-validation.
It also demonstrates superior predictive capabilities on non-image data compared to solely machine learning-based methods.
Ding, Jun-En,Hsu, Chien-Chin,Liu, Feng, 2023, Parkinson's Disease Classification Using Contrastive Graph Cross-View Learning with Multimodal Fusion of SPECT Images and Clinical Features
Sparse-to-Dense LiDAR Point Generation by LiDAR-Camera Fusion for 3D Object Detection
detection features detecting computer information generation semantic data objects
Evaluation of spinopelvic parameters in patients with lumbosacral transitional vertebra: a cross sectional and comparative study
lordosis lumbar study patients ache compared low lstv parameters lumbosacral pelvic vertebra transitional
