arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.09484cs.CVcs.LG
收藏

基于多模态MRI数据的Autoencoders-LSTM脑卒中预后预测模型

A Novel Autoencoders-LSTM Model for Stroke Outcome Prediction using Multimodal MRI Data

CREATIS(CREATIS实验室);Université Lyon 1(里昂第一大学);INSA-Lyon(里昂国立应用科学学院);Hospices Civils de Lyon(里昂民用医院);CarMeN(CarMeN实验室);LARIS(LARIS实验室);Universite d’Angers(昂热大学)

Nima Hatami, Laura Mechtouff, David Rousseau, Tae-Hee Cho, Omer Eker, Yves Berthezene, Carole Frindel

摘要:

患者预后预测在缺血性卒中的管理中至关重要。在本文中,提出了一种新的机器学习模型,用于使用多模态磁共振成像(MRI)预测卒中结局。所提出的模型由两个串行级别的自动编码器(AE),其中不同的AE在1级用于学习单峰功能,从不同的MRI模态和AE在2级用于将单峰功能压缩成多模态功能。然后,给定患者的多模态特征序列被LSTM网络用于预测结果评分。所提出的AE 2-LSTM模型被证明是更好地解决MRI数据的多模态和体积性质的有效方法。实验结果表明,所提出的AE 2-LSTM通过实现最高AUC=0.71和最低MAE=0.34而优于现有的最先进模型。

英文摘要:

Patient outcome prediction is critical in management of ischemic stroke. In this paper, a novel machine learning model is proposed for stroke outcome prediction using multimodal Magnetic Resonance Imaging (MRI). The proposed model consists of two serial levels of Autoencoders (AEs), where different AEs at level 1 are used for learning unimodal features from different MRI modalities and a AE at level 2 is used to combine the unimodal features into compressed multimodal features. The sequences of multimodal features of a given patient are then used by an LSTM network for predicting outcome score. The proposed AE2-LSTM model is proved to be an effective approach for better addressing the multimodality and volumetric nature of MRI data. Experimental results show that the proposed AE2-LSTM outperforms the existing state-of-the art models by achieving highest AUC=0.71 and lowest MAE=0.34.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑