Assessment of performance and reproducibility of applying a content‐based image retrieval scheme for classification of breast lesions. Issue 7 (18th June 2015)

• Record Type: Journal Article
• Authors: Gundreddy, Rohith Reddy; Tan, Maxine; Qiu, Yuchen; Cheng, Samuel; Liu, Hong; Zheng, Bin
• Is Part Of: Medical physics. Volume 42:Issue 7(2015)
• Page Start: 4241
• Page End: 4249
• Publication Date: 2015-06-18
• Subjects: cancer -- content‐based retrieval -- feature extraction -- image classification -- image retrieval -- mammography -- medical image processing -- tumours; Mammography -- Cancer; Biological material, e.g. blood, urine; Haemocytometers -- Information retrieval; Database structures therefor -- Digital computing or data processing equipment or methods, specially adapted for specific applications -- Image data processing or generation, in general -- Content retrieval operation within server, e.g. reading video streams from disk arrays; content‐based image retrieval (CBIR) -- interactive computer‐aided diagnosis (ICAD) -- classification of breast lesions -- reproducibility of CAD schemes; Testing procedures -- Medical image segmentation -- Computer aided diagnosis -- Radiologists -- Databases -- Digital mammography -- Watershed -- Cancer; Medical physics -- Periodicals; Medical physics; Geneeskunde; Natuurkunde; Toepassingen; Biophysics; Periodicals; Periodicals; Electronic journals; 610.153
• DOI: 10.1118/1.4922681
• Languages: English
• ISSNs: 0094-2405

Abstract

Abstract : Purpose: To develop a new computer‐aided diagnosis (CAD) scheme using a content‐based image retrieval (CBIR) approach for classification between the malignant and benign breast lesions depicted on the digital mammograms and assess CAD performance and reproducibility. Methods: An image dataset including 820 regions of interest (ROIs) was used. Among them, 431 ROIs depict malignant lesions and 389 depict benign lesions. After applying an image preprocessing process to define the lesion center, two image features were computed from each ROI. The first feature is an average pixel value of a mapped region generated using a watershed algorithm. The second feature is an average pixel value difference between a ROI's center region and the rest of the image. A two‐step CBIR approach uses these two features sequentially to search for ten most similar reference ROIs for each queried ROI. A similarity based classification score was then computed to predict the likelihood of the queried ROI depicting a malignant lesion. To assess the reproducibility of the CAD scheme, we selected another independent testing dataset of 100 ROIs. For each ROI in the testing dataset, we added four randomly queried lesion center pixels and examined the variation of the classification scores. Results: The area under the ROC curve (AUC) = 0.962 ± 0.006 was obtained when applying a leave‐one‐out validation method to 820 ROIs. Using the independent testing dataset, the initial AUC value was 0.832 ± 0.040, and using the median classification score of each ROI with five queried seeds, AUC value increased to 0.878 ± 0.035. Conclusions: The authors demonstrated that (1) a simple and efficient CBIR scheme using two lesion density distribution related features achieved high performance in classifying breast lesions without actual lesion segmentation and (2) similar to the conventional CAD schemes using global optimization approaches, improving reproducibility is also one of the challenges in developing CAD schemes using a CBIR based regional optimization approach.