Premium
Computer‐assisted detection of mammographic masses: A template matching scheme based on mutual information
Author(s) -
Tourassi Georgia D.,
VargasVoracek Rene,
Catarious David M.,
Floyd Carey E.
Publication year - 2003
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.1589494
Subject(s) - cad , computer science , similarity (geometry) , matching (statistics) , mammography , metric (unit) , region of interest , artificial intelligence , ground truth , computer aided diagnosis , pattern recognition (psychology) , sampling (signal processing) , receiver operating characteristic , template matching , data mining , computer vision , mathematics , image (mathematics) , statistics , machine learning , breast cancer , filter (signal processing) , cancer , medicine , operations management , engineering drawing , engineering , economics
The purpose of this study was to develop a knowledge‐based scheme for the detection of masses on digitized screening mammograms. The computer‐assisted detection (CAD) scheme utilizes a knowledge databank of mammographic regions of interest (ROIs) with known ground truth. Each ROI in the databank serves as a template. The CAD system follows a template matching approach with mutual information as the similarity metric to determine if a query mammographic ROI depicts a true mass. Based on their information content, all similar ROIs in the databank are retrieved and rank‐ordered. Then, a decision index is calculated based on the query's best matches. The decision index effectively combines the similarity indices and ground truth of the best‐matched templates into a prediction regarding the presence of a mass in the query mammographic ROI. The system was developed and evaluated using a database of 1465 ROIs extracted from the Digital Database for Screening Mammography. There were 809 ROIs with confirmed masses (455 malignant and 354 benign) and 656 normal ROIs. CAD performance was assessed using a leave‐one‐out sampling scheme and Receiver Operating Characteristics analysis. Depending on the formulation of the decision index, CAD performance as high as A z= 0.87 ± 0.01 was achieved. The CAD detection rate was consistent for both malignant and benign masses. In addition, the impact of certain implementation parameters on the detection accuracy and speed of the proposed CAD scheme was studied in more detail.