Summary of Trustworthy Enhanced Multi-view Multi-modal Alzheimer’s Disease Prediction with Brain-wide Imaging Transcriptomics Data, by Shan Cong et al.
Trustworthy Enhanced Multi-view Multi-modal Alzheimer’s Disease Prediction with Brain-wide Imaging Transcriptomics Data
by Shan Cong, Zhoujie Fan, Hongwei Liu, Yinghan Zhang, Xin Wang, Haoran Luo, Xiaohui Yao
First submitted to arxiv on: 21 Jun 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Image and Video Processing (eess.IV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed TMM framework is a trusted multiview multimodal graph attention approach for Alzheimer’s disease (AD) diagnosis. It integrates brain-wide transcriptomics and imaging data to predict AD, incorporating interaction information from both biomolecular and imaging perspectives. The framework constructs view-specific brain regional co-function networks (RRIs) using transcriptomics and radiomics data, applies graph attention processing to each RRI network, and fuses the resulting embeddings using cross-modal attention. A novel true-false-harmonized class probability (TFCP) strategy assesses and adjusts prediction confidence for AD diagnosis. The method outperforms state-of-the-arts in identifying AD, EMCI, and LMCI when evaluated on the AHBA and ADNI databases. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The TMM framework is a new way to diagnose Alzheimer’s disease by combining information from brain imaging and gene activity. It works by looking at how different parts of the brain work together, using data from both types of sources. The method is better than current approaches at identifying people with early-stage AD and other forms of cognitive decline. |
Keywords
» Artificial intelligence » Attention » Probability
