From 4bdfd99e06aceaefbdea84274120f91506c5cb44 Mon Sep 17 00:00:00 2001 From: dorothy-yao <118703034+dorothy-yao@users.noreply.github.com> Date: Sun, 10 Mar 2024 21:03:37 +0800 Subject: [PATCH] Update readme.MD --- readme.MD | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/readme.MD b/readme.MD index 42f2175..0e9ba45 100644 --- a/readme.MD +++ b/readme.MD @@ -9,6 +9,16 @@ Furthermore, we address the modal inconsistency issue via a disease-wise attenti ![Overview](https://github.com/dorothy-yao/drfuse/blob/main/overview.png "overview_framework") **Overview**：DrFuse consists of two major components. Subfigure (a): A shared representation and a distinct representation are learned from EHR and CXR, where the shared ones are aligned by minimizing the Jensen–Shannon divergence (JSD). A novel logit pooling is proposed to fuse the shared representations. Subfigure (b): The \textit{disease-aware attention fusion} module captures the patient-specific modal significance for different prediction targets by minimizing a ranking loss. +## Acknowledgements +Some parts of the codes are adapted from [MedFuse](https://github.com/nyuad-cai/MedFuse). We thank the authors for their work. + +## Reproduction +To reproduce the results, please follow the following procedures: + +- Obtain [MIMIC-IV](https://physionet.org/content/mimiciv/1.0/) and [MIMIC-CXR-JPG](https://physionet.org/content/mimic-cxr-jpg/2.0.0/) datasets; +- Follow the data pre-processing procedures in https://github.com/nyuad-cai/MedFuse to prepare the datasets +- Run the code by `python main.py ` + ## Citation If you find the paper or the implementation helpful, please cite the following paper: @@ -23,13 +33,3 @@ If you find the paper or the implementation helpful, please cite the following p year={2024} } ``` - -## Acknowledgements -Some parts of the codes are adapted from [MedFuse](https://github.com/nyuad-cai/MedFuse). - -## Reproduction -To reproduce the results, please follow the following procedures: - -- Obtain [MIMIC-IV](https://physionet.org/content/mimiciv/1.0/) and [MIMIC-CXR-JPG](https://physionet.org/content/mimic-cxr-jpg/2.0.0/) datasets; -- Follow the data pre-processing procedures in https://github.com/nyuad-cai/MedFuse to prepare the datasets -- Run the code by `python main.py `