Author + information
- Received November 1, 2018
- Revision received May 13, 2019
- Accepted June 13, 2019
- Published online August 5, 2019.
- Geert Litjens, PhDa,∗ (, )
- Francesco Ciompi, PhDa,
- Jelmer M. Wolterink, PhDb,
- Bob D. de Vos, PhDb,
- Tim Leiner, MD, PhDd,
- Jonas Teuwen, PhDc,e and
- Ivana Išgum, PhDb
- aDepartment of Pathology, Radboud University Medical Center, Nijmegen, the Netherlands
- bImage Sciences Institute, University Medical Center Utrecht, Utrecht, the Netherlands
- cDepartment of Radiology, Radboud University Medical Center, Nijmegen, the Netherlands
- dDepartment of Radiology, University Medical Center Utrecht, Utrecht, the Netherlands
- eDepartment of Radiation Oncology, Netherlands Cancer Institute, Amsterdam, the Netherlands
- ↵∗Address for correspondence:
Dr. Geert Litjens, Huispost 824, Grooteplein-Zuid 10, 6525GA Nijmegen, the Netherlands.
• Deep learning has revolutionized computer vision and is now seeing application in cardiovascular imaging.
• This paper provides a thorough overview of the state of the art across applications and modalities for clinicians.
• Clinicians should guide the applications of deep learning to have the most meaningful clinical impact.
Cardiovascular imaging is going to change substantially in the next decade, fueled by the deep learning revolution. For medical professionals, it is important to keep track of these developments to ensure that deep learning can have meaningful impact on clinical practice. This review aims to be a stepping stone in this process. The general concepts underlying most successful deep learning algorithms are explained, and an overview of the state-of-the-art deep learning in cardiovascular imaging is provided. This review discusses >80 papers, covering modalities ranging from cardiac magnetic resonance, computed tomography, and single-photon emission computed tomography, to intravascular optical coherence tomography and echocardiography. Many different machines learning algorithms were used throughout these papers, with the most common being convolutional neural networks. Recent algorithms such as generative adversarial models were also used. The potential implications of deep learning algorithms on clinical practice, now and in the near future, are discussed.
Dr. Litjens is supported by grants from the Dutch Cancer Society (KUN 2015-7970), from Netherlands Organization for Scientific Research (NWO) (project number 016.186.152), and from Stichting IT Projecten (project PATHOLOGIE 2); and has received research funding from Philips Digital Pathology Solutions; and has been a consultant for Novartis. Dr. Ciompi has received research grants from the European Union’s Horizon 2020 research and innovation programme under grant agreement number 825292 (ExaMode), and from the Dutch Cancer Society (project number 11917). Dr. Leiner is supported by research grants from NWO/Foundation for Technological Sciences (number 12726 and number P15-26) with industrial participation (Pie Medical Imaging, 3Mensio Medical Imaging, and Philips Healthcare); research grants from the Netherlands Organization for Health Research and Development (FSCAD, number 104003009); industrial research grants from Pie Medical Imaging; and has received grant support from and is a member of the Speakers Bureau for Philips Healthcare and Bayer. Dr. Išgum is supported by research grants from NWO/Foundation for Technological Sciences (number 12726 and number 15-26) with industrial participation (Pie Medical Imaging, 3Mensio Medical Imaging, Philips Healthcare); research grants from the Netherlands Organization for Health Research and Development (FSCAD, number 104003009); research grant from Dutch Cancer Society (UU 2015-7947); and industrial research grants from Pie Medical Imaging; and is the founder and a shareholder of Quantib U. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose.
- Received November 1, 2018.
- Revision received May 13, 2019.
- Accepted June 13, 2019.
- 2019 American College of Cardiology Foundation
This article requires a subscription or purchase to view the full text. If you are a subscriber or member, click Login or the Subscribe link (top menu above) to access this article.