IEEE Transactions on Medical Imaging · 2002 · 64 citations · 28 references
ComputingComputer ScienceRadiologyComputer VisionDiagnostic ImagingMachine LearningCancer DetectionComputer-aided DiagnosisMedical ImagingNeural NetworksObject DetectionPattern RecognitionBreast Microcalcification AnalysisCalcification Detection On MammographyClinical Utility AnalysisClinical Utility AssessmentComputer-aided Detection Of CalcificationsContextual RelationshipHierarchical Network StructureMulti-scale Object Detection
This paper describes a pattern recognition architecture, which we term hierarchical pyramid/neural network (HPNN), that learns to exploit image structure at multiple resolutions for detecting clinically significant features in digital/digitized mammograms. The HPNN architecture consists of a hierarchy of neural networks, each network receiving feature inputs at a given scale as well as features constructed by networks lower in the hierarchy. Networks are trained using a novel error function for the supervised learning of image search/detection tasks when the position of the objects to be found is uncertain or ill defined. We have evaluated the HPNN's ability to eliminate false positive (FP) regions of interest generated by the University of Chicago's (UofC) Computer-aided diagnosis (CAD) systems for microcalcification and mass detection. Results show that the HPNN architecture, trained using the uncertain object position (UOP) error function, reduces the FP rate of a mammographic CAD system by approximately 50% without significant loss in sensitivity. Investigation into the types of FPs that the HPNN eliminates suggests that the pattern recognizer is automatically learning and exploiting contextual information. Clinical utility is demonstrated through the evaluation of an integrated system in a clinical reader study. We conclude that the HPNN architecture learns contextual relationships between features at multiple scales and integrates these features for detecting microcalcifications and breast masses.
28
Handbook of Mathematical Functions
Donald A. McQuarrie · American Journal of Physics · 1966 · 40.9K citations
Neural networks for pattern recognition
Choice Reviews Online · 1994 · 18.7K citations
Handbook of Mathematical Functions
Milton Abramowitz, I. A. Stegun · 1972 · 15.4K citations
Handwritten Digit Recognition with a Back-Propagation Network
Yann LeCun, Bernhard E. Boser, John S. Denker et al. · neural information processing systems · 1989 · 3.6K citations