Advances and Applications of AI in Pediatric Radiology
Presentations
(Monday, 3/28/2022) 8:00 AM - 10:00 AM [Central Time (GMT-5)]
Room: Celestin ABC
Artificial intelligence (AI) uses computers to mimic cognitive functions of the human brain, allowing inferences to be made from generally large datasets. Traditional machine learning (e.g., decision tree analysis, support vector machines) and deep learning (e.g., convolutional neural networks) are two commonly employed AI approaches both outside and within the field of medicine. Such techniques can be used to evaluate medical images for the purposes of automated detection and segmentation, classification tasks (including diagnosis, lesion or tissue characterization, and prediction), image reconstruction (image quality improvement, and image presentation).
The most common application of Artificial intelligence (AI) in radiology is largely focused on the use of deep learning convolutional neural networks (CNNs) used to recognize patterns in images and are primarily employed to limit stochastic noise in reconstructed images, namely quantum noise in CT, echogenic noise in ultrasound; and radiofrequency (RF) noise in MRI. Deep learning reconstruction (DLR) algorithms can be used for image quality improvement, ionizing radiation dose reduction, and examination time reduction (in MRI). Additionally, there are a multitude of AI models being developed and investigated for use within the normal workflow of a radiology reading room. Such models as: automated organ segmentation and analysis (e.g., liver size, morphology, fat fraction, etc.), diagnosis (pediatric bone age from a radiograph of the hand), and patient positioning during DR imaging (to make sure the image(s) were acquired in the proper orientation); these models are being employed as tools to improve radiologist efficiency in the reading room and reduce the need for a radiologist to perform disruptive tasks such as image checks. This session will highlight current AI methods applied to various imaging modalities (e.g., CT, MRI, and ultrasound), the role of the medical physicist in the implementation of these technologies, key considerations when encountering a new AI system in the clinic and the impact these technologies are having in the clinic.
Learning Objectives:
1. Describe the role of AI in medical imaging
2. Summarize different AI methods as applied to imaging modalities
3. Identify the role of the medical physicist in implementing AI in the clinic
Keywords
Not Applicable / None Entered.
Taxonomy
Not Applicable / None Entered.
Contact Email