(Sunday, 7/12/2020) 3:30 PM - 4:30 PM [Eastern Time (GMT-4)]
Room: Track 2
With the development of artificial intelligence, especially deep learning, medical image synthesis is increasingly getting traction in the medical imaging and medical physics communities. The promising work on inter-modality synthesis (such as MRI-based synthetic CT, CBCT-based synthetic CT, CBCT/CT-based synthetic MRI, and PET-based synthetic CT) and intra-modality synthesis (such as low-quality image-based synthetic high-quality image) is being performed in PET attenuation correction, MRI-based treatment planning, CBCT-guided adaptive radiotherapy, image segmentation, multimodality image registration, super-resolution image generation, low-dose PET or CT generation, intra-multiparametric MRI transformation, and numerous other areas in radiology and radiation oncology. To maximize the potentials and benefits of medical image synthesis in medical imaging and physics fields, it is critical to understand that a successful application depends as much on the nature of the task as on the nature of the synthesis algorithm and the availability and quality of data. In this session, significance, appropriate use and limitations of various medical synthesis applications will be explored, highlighting specific applications in image segmentation and registration, treatment planning, and image-guided adaptive radiotherapy.
Learning Objectives:
1. Identify the rationale and significance of medical image synthesis in medical physics, radiology and radiation oncology.
2. Learn how medical image synthesis is being implemented and how image synthesis can be utilized in radiology and radiation oncology.
3. Identify the strengths and limitations of image synthesis in radiology and radiation oncology.
Handouts
Keywords
Not Applicable / None Entered.
Taxonomy
Not Applicable / None Entered.
Contact Email
