Copyright
©The Author(s) 2022.
Artif Intell Med Imaging. Jun 28, 2022; 3(3): 55-69
Published online Jun 28, 2022. doi: 10.35711/aimi.v3.i3.55
Published online Jun 28, 2022. doi: 10.35711/aimi.v3.i3.55
Symbolic AI | Statistical learning (SL) | Deep learning (DL) | |
Entities manipulated | Both symbols and numbers | Numbers (most representing interval data, but some representing categories) | Same as SL, can be applied to the same problems |
Algorithm design | Requires computer-science knowledge & traditional software skills, including user-interface design | Less customization needed, but problem-specific pre-processing of data (e.g., statistical standardization is necessary) | Same as SL |
Domain expert role | Work closely and extensively with software developer, Evaluate output of algorithm for a set of test cases against desired output | To identify variables/features of interest, annotating training data, and evaluating results and individual features’ relative importance. Must evaluate results for novelty | Same as SL, but features can be discovered from raw data, so may not need designation. Annotation is more burdensome because much more data is typically needed |
Data inputs | Expert and software work closely to design software and create test cases | Rows of data, annotated text, or images. For supervised learning, the output variable’s value for each instance is also supplied | Same as SL, in some forms of DL, notably for image processing, features are discovered from raw data |
Partitioning of input data | (Not applicable) | Divided into training data and test data | Same as SL |
Generalizability | Limited to modest: Typically required tailored solutions, especially for the user interface | More generalizable than symbolic AI, but success depends on careful feature selection, choice of method and whether the data matches the method’s assumptions (e.g., Gaussian distribution, additive effects) | DL methods are “non-parametric” and rely on few or no assumptions about the variables/features in the data |
- Citation: Nadkarni P, Merchant SA. Enhancing medical-imaging artificial intelligence through holistic use of time-tested key imaging and clinical parameters: Future insights . Artif Intell Med Imaging 2022; 3(3): 55-69
- URL: https://www.wjgnet.com/2644-3260/full/v3/i3/55.htm
- DOI: https://dx.doi.org/10.35711/aimi.v3.i3.55