A decision aid for diagnosis of liver lesions on MRI.


Abdominal magnetic resonance imaging (MRI) plays an important role in the evaluation of liver abnormalities. The interpretation of MR images requires expert training in a rapidly changing field. DAFODILL (Decision Aid for Diagnosing Liver Lesions) is a decision-support tool designed to aid radiologists in the diagnosis of hepatic lesions seen on MRI. DAFODILL uses a knowledge base of MRI findings and a belief-network inference engine to generate probabilistic differential diagnoses of the most commonly encountered hepatic lesions. DAFODILL performs limited image processing to identify clinically relevant features, which are presented to the user for confirmation before they are used by the network. Preliminary evaluation of an initial version of the system suggests that DAFODILL may be a useful tool for radiology residents and nonexpert radiologists in interpreting MR images of the liver.


Citations per Year

230 Citations

Semantic Scholar estimates that this publication has 230 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Tombropoulos1993ADA, title={A decision aid for diagnosis of liver lesions on MRI.}, author={Rhea Tombropoulos and Smadar Shiffman and Charles Davidson}, journal={Proceedings. Symposium on Computer Applications in Medical Care}, year={1993}, pages={439-43} }