A NOVEL AUTOENCODERS-LSTM MODEL FOR STROKE OUTCOME PREDICTION USING MULTIMODAL MRI DATA

Item request has been placed!

Item request cannot be made.

Processing Request

Read More Add to Saved list

Author(s): Hatami, Nima; Mechtouff, Laura; Rousseau, David; Cho, Tae-Hee; Eker, Omer; Berthezène, Yves; Frindel, Carole
Source:
2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)
https://hal.science/hal-04210499
2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), Apr 2023, Cartagena, Colombia. pp.1-5, ⟨10.1109/ISBI53787.2023.10230459⟩
Subject Terms:
Multimodal image fusion Long Short-Term Memory (LSTM) Autoencoder (AE) Stroke outcome prediction Magnetic Resonance Imaging (MRI) modified Rankin Scale (mRS); Multimodal image fusion; Long Short-Term Memory (LSTM); Autoencoder (AE); Stroke outcome prediction; Magnetic Resonance Imaging (MRI); modified Rankin Scale (mRS); [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]; [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Document Type:
conference object
Language:
English

Additional Information
- Contributors:
  Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS); Université Claude Bernard Lyon 1 (UCBL); Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon); Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS); Modeling & analysis for medical imaging and Diagnosis (MYRIAD); Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL); ANR-16-RHUS-0009,MARVELOUS,MARVELOUS(2016); ANR-18-RHUS-0001,BOOSTER,Brain clOt persOnalized therapeutic Strategies for sTroke Emergent Reperfusion(2018)
- Publication Information:
  HAL CCSD
  IEEE
- Publication Date:
  2023
- Collection:
  Université de Lyon: HAL
- Subject Terms:
  Cartagena; Colombia
- Abstract:
  International audience ; 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 AE 2-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 AE 2-LSTM outperforms the existing state-of-the art models by achieving highest AUC=0.71 and lowest MAE=0.34.
- Relation:
  hal-04210499; https://hal.science/hal-04210499; https://hal.science/hal-04210499/document; https://hal.science/hal-04210499/file/ISBI2023.pdf
- Accession Number:
  10.1109/ISBI53787.2023.10230459
- Online Access:
  https://doi.org/10.1109/ISBI53787.2023.10230459
  https://hal.science/hal-04210499
  https://hal.science/hal-04210499/document
  https://hal.science/hal-04210499/file/ISBI2023.pdf
- Rights:
  info:eu-repo/semantics/OpenAccess
- Accession Number:
  edsbas.1ED34FA4

Comments

No Comments.