About this Research Topic
Today’s digital health aims to provide an improved efficiency of healthcare delivery, personalized, and timely disease care. Cardiovascular Disease Care (CVD) is a leading cause of death worldwide. In the United States, 1 out of 3 adults have some form of CVD. It is projected that almost half of the US population will have at least one type of CVD by 2035 with total direct and indirect costs potentially crossing the $1 trillion. Today’s medical imaging data include multiple modalities that are mainly utilized in silos i.e. Computed Tomography (CT), Magnetic Resonance Imaging (MRI), CT-derived fractional flow reserve (CT-FFR), cardiac MRI, whole-heart dynamic 3D cardiac MRI perfusion, 3D cardiac MRI late gadolinium enhancement, cardiac positron emission tomography (PET). However, very few hybrid modalities are used, including Cardiac Positron Emission Tomography combined with Computed Tomography (PET/CT), Cardiac Single-Photon Emission Computed Tomography combined with CT (SPECT/CT), Echocardiography and invasive angiography electrography.
Integrating these imaging data becomes a burden on clinicians with the additional risk of inaccuracy and increased cost of care. In this Research Topic, we are interested in research directions that focus on fusion techniques that enable integration and modeling of these multiple modalities to provide complementary information that will help improve CVD care. These modalities will use Machine Learning (ML) and Deep Learning (DL) techniques as well as other state of the art techniques.
The large amount of available medical imaging data and the advanced techniques of Artificial Intelligence (AI) /DL enable the automation of CVD delivery and makes it more timely, accurate, and precise. The techniques used to fuse multimodal imaging data aim to integrate values of different scales and distributions of the data into a global latent feature space where all modalities will have uniform representation.
Thorough research was done on applying AI on each of the imaging modalities for the matter of CVD diagnosis and treatments. However, researchers aspire to integrate different imaging modalities for improving CVD care including early detection of CVD and recommending personalized treatment based on these imaging modalities.
We welcome articles that cover potential topics including but not limited to the following:
● The use of state of the art AI/DL technique for modeling multiple imaging modalities for the matter of automatic diagnosis of various CVD
● The use of state of the art AI/DL technique for modeling multiple imaging modalities for recommending the personalized treatments for various CVD
● Comparing the performance of state of the art AI/DL techniques on single imaging modalities to the performance using the fused multiple modalities
● Proposing state of the art fusion techniques that will improve the diagnosis of various CVD
● To what extent the use of textual medical modalities such as Electronic Health Record(EHR)data can help in improving the performance of state of the art AI/DL techniques when fused together with multimodal imaging data
● Review papers on the use of multimodal imaging data on various CVD diseases such as Coronary Artery Disease, Heart Failure and others
● Reviews on the state of the art AI/DL techniques used for modeling multimodal imaging data that are used for CVD diagnosis
● Some specific case studies of research that uses AI with multimodal imaging data for the evaluation of the following diseases that nowadays are integrated based on the clinical staff knowledge:
○ Aortic stenosis valve and Mitral valve disease - modalities as CT, echocardiography and Angiogram
○ Heart failure
● Research areas that explore how to integrate Hemodynamics modality which are data stream together with multimodal imaging data
We would like to acknowledge Dr. Saeed Amal an Assistant Research Professor at Northeastern University and a member of The Roux Institute as the Topic Coordinator who has contributed to the preparation of the proposal for this Research Topic. Dr. Amal's research interest includes the applications of artificial intelligence and multimodal data to improve healthcare, specifically care for cardiovascular disease.
Dr. Amal was a Postdoctoral Fellow at the Stanford University School of Medicine where he focused on the use of artificial intelligence and multimodal data for the diagnosis and personalized treatment recommendations for cardiovascular disease. Dr. Amal has vast leadership experience in applied research from the tech industry and is a former VP of an R&D data medical startup in the field of cardiology.
Integrating these imaging data becomes a burden on clinicians with the additional risk of inaccuracy and increased cost of care. In this Research Topic, we are interested in research directions that focus on fusion techniques that enable integration and modeling of these multiple modalities to provide complementary information that will help improve CVD care. These modalities will use Machine Learning (ML) and Deep Learning (DL) techniques as well as other state of the art techniques.
The large amount of available medical imaging data and the advanced techniques of Artificial Intelligence (AI) /DL enable the automation of CVD delivery and makes it more timely, accurate, and precise. The techniques used to fuse multimodal imaging data aim to integrate values of different scales and distributions of the data into a global latent feature space where all modalities will have uniform representation.
Thorough research was done on applying AI on each of the imaging modalities for the matter of CVD diagnosis and treatments. However, researchers aspire to integrate different imaging modalities for improving CVD care including early detection of CVD and recommending personalized treatment based on these imaging modalities.
We welcome articles that cover potential topics including but not limited to the following:
● The use of state of the art AI/DL technique for modeling multiple imaging modalities for the matter of automatic diagnosis of various CVD
● The use of state of the art AI/DL technique for modeling multiple imaging modalities for recommending the personalized treatments for various CVD
● Comparing the performance of state of the art AI/DL techniques on single imaging modalities to the performance using the fused multiple modalities
● Proposing state of the art fusion techniques that will improve the diagnosis of various CVD
● To what extent the use of textual medical modalities such as Electronic Health Record(EHR)data can help in improving the performance of state of the art AI/DL techniques when fused together with multimodal imaging data
● Review papers on the use of multimodal imaging data on various CVD diseases such as Coronary Artery Disease, Heart Failure and others
● Reviews on the state of the art AI/DL techniques used for modeling multimodal imaging data that are used for CVD diagnosis
● Some specific case studies of research that uses AI with multimodal imaging data for the evaluation of the following diseases that nowadays are integrated based on the clinical staff knowledge:
○ Aortic stenosis valve and Mitral valve disease - modalities as CT, echocardiography and Angiogram
○ Heart failure
● Research areas that explore how to integrate Hemodynamics modality which are data stream together with multimodal imaging data
We would like to acknowledge Dr. Saeed Amal an Assistant Research Professor at Northeastern University and a member of The Roux Institute as the Topic Coordinator who has contributed to the preparation of the proposal for this Research Topic. Dr. Amal's research interest includes the applications of artificial intelligence and multimodal data to improve healthcare, specifically care for cardiovascular disease.
Dr. Amal was a Postdoctoral Fellow at the Stanford University School of Medicine where he focused on the use of artificial intelligence and multimodal data for the diagnosis and personalized treatment recommendations for cardiovascular disease. Dr. Amal has vast leadership experience in applied research from the tech industry and is a former VP of an R&D data medical startup in the field of cardiology.
Keywords: Medical Imaging, Cardiovascular Disease, Multimodal data, Artificial Intelligence
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
