A similarity study of content‐based image retrieval system for breast cancer using decision tree. Issue 1 (19th December 2012)

• Record Type: Journal Article
• Authors: Cho, Hyun‐chong; Hadjiiski, Lubomir; Sahiner, Berkman; Chan, Heang‐Ping; Helvie, Mark; Paramagul, Chintana; Nees, Alexis V.
• Is Part Of: Medical physics. Volume 40:Issue 1(2013)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2012-12-19
• Subjects: Ultrasonography -- Numerical optimization -- Mammography -- Linear algebra -- Combinatorics; graph theory; biological organs -- biomedical ultrasonics -- cancer -- decision trees -- feature extraction -- image retrieval -- image segmentation -- mammography -- medical image processing -- optimisation -- vectors; breast masses -- computer‐aided diagnosis -- content‐based image retrieval -- decision tree -- ultrasonography; Diagnosis using ultrasonic, sonic or infrasonic waves -- Digital computing or data processing equipment or methods, specially adapted for specific applications -- Image data processing or generation, in general; Medical imaging -- Ultrasonography -- Radiologists -- Decision trees -- Computer aided diagnosis -- Laser Doppler velocimetry -- Cancer -- Mammography -- Retrieval systems -- Optimization; Medical physics -- Periodicals; Medical physics; Geneeskunde; Natuurkunde; Toepassingen; Biophysics; Periodicals; Periodicals; Electronic journals; 610.153
• DOI: 10.1118/1.4770277
• Languages: English
• ISSNs: 0094-2405

Abstract

Abstract : Purpose: : We are developing a decision tree content‐based image retrieval (DTCBIR) CADx system to assist radiologists in characterization of breast masses on ultrasound images. Methods: : Three DTCBIR configurations, including decision tree with boosting (DTb), decision tree with full leaf features (DTL), and decision tree with selected leaf features (DTLs) were compared. For DTb, features of a query mass were combined first into a merged feature score and then masses with similar scores were retrieved. For DTL and DTLs, similar masses were retrieved based on the Euclidean distance between feature vectors of the query and those of selected references. For each DTCBIR configuration, we investigated the use of full feature set and subset of features selected by the stepwise linear discriminant analysis (LDA) and simplex optimization method, resulting in six retrieval methods and selected five, DTb‐lda, DTL‐lda, DTb‐full, DTL‐full, and DTLs‐full, for the observer study. Three MQSA radiologists rated similarities between the query mass and computer‐retrieved three most similar masses using nine‐point similarity scale (9 = very similar). Results: : For DTb‐lda, DTL‐lda, DTb‐full, DTL‐full, and DTLs‐full, average A z values were 0.90 ± 0.03, 0.85 ± 0.04, 0.87 ± 0.04, 0.79 ± 0.05, and 0.71 ± 0.06, respectively, and average similarity ratings were 5.00, 5.41, 4.96, 5.33, and 5.13, respectively. Conclusions: : The DTL‐lda is a promising DTCBIR CADx configuration which had simple tree structure, good classification performance, and highest similarity rating.