Interpreting extracted rules from ensemble of trees: Application to computer-aided diagnosis of breast MRI
This addresses the need for interpretable CAD tools in medical imaging for radiologists, but it appears incremental as it focuses on improving comprehensibility rather than introducing a new diagnostic paradigm.
The authors tackled the problem of making computer-aided diagnosis (CAD) systems more interpretable for radiologists in breast MRI screening, by developing a system that uses rule extraction and graph visualization to classify lesions as cancerous or non-cancerous, though no concrete performance numbers are provided.
High predictive performance and ease of use and interpretability are important requirements for the applicability of a computer-aided diagnosis (CAD) to human reading studies. We propose a CAD system specifically designed to be more comprehensible to the radiologist reviewing screening breast MRI studies. Multiparametric imaging features are combined to produce a CAD system for differentiating cancerous and non-cancerous lesions. The complete system uses a rule-extraction algorithm to present lesion classification results in an easy to understand graph visualization.