Artificial Intelligence in Medicine (AIM)
The Artificial Intelligence in Medicine (AIM) program is a research program of the Department of Medicine at Cedars-Sinai Medical Center. The AIM program seeks to develop software to allow computers to process and analyze three-dimensional images of the heart in much the same way an experienced human operator would. The program applies artificial intelligence techniques to the measurement of parameters critical to understanding the state and behavior of the human heart. This automated approach allows information to be obtained very quickly that is quantitatively accurate and does not suffer from intra-observer or inter-observer variability.
The software and algorithms developed by the AIM program are widely considered to represent the gold standard in nuclear cardiology. They can perform a totally automated, push-button sequence of actions relating to imaging processing and analysis.
Through the AIM program, algorithms have been developed to:
- Take raw digital data output by the gamma camera, identify where the heart is, reconstruct it into tomographic images and re-orient those images to make them perpendicular to the heart's axis - all without operator interaction.
- Take tomographic images of the heart, evaluate the signals from several hundred portions of the myocardium, comparing the strength of the signals with those expected in a normal heart and generate an exact quantitative measurement of the location, extent and severity of perfusion abnormalities of the heart. This gives the physician objective information to help select or rule out more invasive treatment.
- Analyze the dynamic functioning of the heart (i.e., the way it contracts and thickens during its cycle). A dynamic measurement of the heart cavity volume is performed from electrocardiographically gated three-dimensional nuclear cardiology images by automatically identifying the endocardial and epicardial surfaces and following their motion throughout the cardiac cycle.