Virtual radiologists: current status of deep learning in radiology and its future trends
104th Scientific Assembly and Annual Meeting of the Radiological Society of North America (RSNA)
Abstract
An abstract is not available in the lab archive. View the paper at its source.
This RSNA 2018 digital education exhibit surveyed deep-learning methods and radiology applications in segmentation, detection and classification, alongside challenges and potential directions. The official meeting archive lists it as exhibit IN137-ED-X.
Summary
Presented as a digital education exhibit at the Radiological Society of North America (RSNA) 2018 Scientific Assembly and Annual Meeting, this work outlined deep-learning approaches and applications across radiology. The meeting archive describes coverage of segmentation, detection and classification tasks, with examples spanning cardiac, brain, pulmonary, abdominal, prostate and breast imaging.
The exhibit also addressed challenges including data scarcity, architecture selection, weakly and unsupervised learning, visualization, active learning and cross-modality learning. The source identifies this as educational content and does not report a clinical validation study or diagnostic performance results.
- Sarfaraz Hussein
- Aliasghar Mortazi
- Harish Raviprakash
- Naji Khosravan
- Georgios Z. Papadakis
- Uygar Teomete
- Ulas Bagci
Cite this work
Sarfaraz Hussein, Aliasghar Mortazi, Harish Raviprakash, Naji Khosravan, Georgios Z. Papadakis, Uygar Teomete, Ulas Bagci (2018). Virtual radiologists: current status of deep learning in radiology and its future trends. 104th Scientific Assembly and Annual Meeting of the Radiological Society of North America (RSNA) https://archive.rsna.org/2018/ArtificialIntelligence.pdf
BibTeX