A Sequence Agnostic Multimodal Preprocessing for Clogged Blood Vessel Detection in Alzheimer's Diagnosis
This work addresses a domain-specific problem in medical imaging for Alzheimer's diagnosis, offering incremental improvements in preprocessing methods.
The paper tackled the problem of detecting clogged blood vessels for Alzheimer's diagnosis by proposing a multimodal preprocessing method that extracts 3D-point clouds and fuses features from Two-Photon Excitation Microscopy images, resulting in improved classification performance on The Clog Loss dataset.
Successful identification of blood vessel blockage is a crucial step for Alzheimer's disease diagnosis. These blocks can be identified from the spatial and time-depth variable Two-Photon Excitation Microscopy (TPEF) images of the brain blood vessels using machine learning methods. In this study, we propose several preprocessing schemes to improve the performance of these methods. Our method includes 3D-point cloud data extraction from image modality and their feature-space fusion to leverage complementary information inherent in different modalities. We also enforce the learned representation to be sequence-order invariant by utilizing bi-direction dataflow. Experimental results on The Clog Loss dataset show that our proposed method consistently outperforms the state-of-the-art preprocessing methods in stalled and non-stalled vessel classification.