Imaging: Artificial Intelligence in Medical Imaging
C Schaeffer1*, S Leon1*, N Mistry2*, J Vaishnav3*, R Bammer4*, A Dresner5*, (1) University of Florida, Gainesville, FL, (2) Siemens Healthineers GmbH, Erlangen, BY, DE, (3) Canon Medical Systems, USA, Tustin, CA, (4) Rapidai, Redwood City, CA, (5) Philips Healthcare
Presentations
Artificial Intelligence in Medical Imaging - S Leon, Presenting Author
1:30 PM Artificial Intelligence in Medical Imaging – Progresses in Radiation Oncology - N Mistry, Presenting Author
1:50 PM Deep Learning in Medical Imaging: From Image Generation to Workflow Automation - J Vaishnav, Presenting Author
2:10 PM Embracing Artificial Intelligence and Machine Learning in Radiology to Streamline Emergent Care - R Bammer, Presenting Author
2:30 PM Next Generation Synthetic CT for MR-Only Brain Radiotherapy Planning - A Dresner, Presenting Author
2:50 PM Q&A - C Schaeffer, Presenting Author
TU-CD-TRACK 8-0 (Tuesday, 7/27/2021) 1:00 PM - 3:00 PM [Eastern Time (GMT-4)]
In the last few years, artificial intelligence (AI) has emerged as powerful tool in the field of diagnostic medical imaging with applications in areas such as image processing, image reconstruction, and image interpretation. AI is a multidisciplinary field that takes ideas from computer science and neuroscience to try to replicate human intelligence in machines with the idea of solving complex problems typically requiring human intelligence. Machine learning (ML) is a subset of AI where the algorithm is designed to learn from data without explicit programming. A popular ML algorithm is the artificial neural network (ANN) which was designed to mimic the neural networking in the human brain. Deep learning (DL) is a further subset of ML involving very deep neural network models with many layers. When applied to medical images, a popular variant of the ANN is the convolutional neural network (CNN) which can learn image patterns and features from training images. These learned features can then be used to solve a wide array of problems such as classification or segmentation.
Current and potential AI applications in diagnostic radiology may include improving image quality, reducing radiation dose, decreasing MRI imaging time, enhancing technical protocols, standardizing the detection and characterization of image findings, and improving workflow. With an ever-increasing amount of data, the potential for AI in the field of diagnostic medical imaging is greater than ever.
Learning objectives:
1. Understand the basics concepts of Artificial Intelligence (AI) and it’s relation with Machine Learning (ML) and Deep Learning (DL)
2. Understand primary components of DL architectures and neural network.
3. Understand selected AI applications in diagnostic radiology.
References:
1.Rrik R. Ranschaert, Sergey Morozov, Paul R. Algra, “Artificial Intelligence in Medical Imaging, Springer, 2019.
2.Ahmed Hosny, Chintan Parmar, John Quackenbush, et al, “Artificial Intelligence in Radiology”, Nat Rev Cancer, 2018 August; 18(8): 500-510. Doi: 10.1038/s41568-018-0016-5.
Handouts
- 166-60164-15651646-179576-1250442549.pdf (Colin Schaeffer)
- 166-60222-15651646-180687-581137064.pdf (Jay Vaishnav)
- 166-60224-15651646-178143-816132400.pdf (Alex Dresner)
Keywords
Not Applicable / None Entered.
Taxonomy
Not Applicable / None Entered.
Contact Email