This website requires JavaScript.

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

Nima HatamiLaura MechtouffDavid Rousseau ...+3 Carole Frindel
Mar 2023
摘要
Patient outcome prediction is critical in management of ischemic stroke. Inthis paper, a novel machine learning model is proposed for stroke outcomeprediction using multimodal Magnetic Resonance Imaging (MRI). The proposedmodel consists of two serial levels of Autoencoders (AEs), where different AEsat level 1 are used for learning unimodal features from different MRImodalities and a AE at level 2 is used to combine the unimodal features intocompressed multimodal features. The sequences of multimodal features of a givenpatient are then used by an LSTM network for predicting outcome score. Theproposed AE2-LSTM model is proved to be an effective approach for betteraddressing the multimodality and volumetric nature of MRI data. Experimentalresults show that the proposed AE2-LSTM outperforms the existing state-of-theart models by achieving highest AUC=0.71 and lowest MAE=0.34.
展开全部
图表提取

暂无人提供速读十问回答

论文十问由沈向洋博士提出,鼓励大家带着这十个问题去阅读论文,用有用的信息构建认知模型。写出自己的十问回答,还有机会在当前页面展示哦。

Q1论文试图解决什么问题?
Q2这是否是一个新的问题?
Q3这篇文章要验证一个什么科学假设?
0
被引用
笔记
问答