Assessment of performance and reproducibility of applying a content‐based image retrieval scheme for classification of breast lesions

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. C 2015 American Association of Physicists in Medicine. [http://dx

A new approach to develop computer-aided diagnosis scheme of breast mass classification using deep learning technology

“…Second, although developing CAD schemes without lesion segmentation has also been previously developed and tested using a content-based image retrieval (CBIR) based CAD schemes [26, 35], the deep learning approach is different and may also have advantage. Unlike the CBIR based CAD schemes, which typically use a k -nearest neighborhood (KNN) based “lazy” learning concept and can be very computational intensive or inefficient in generating a classification score for each testing ROI [36], the deep learning network is pre-trained and its global optimization function (similar to a conventional artificial neural network) can be directly applied to all testing cases (ROIs).…”

“…The detailed description of the image database has been reported in a number of our previous studies [6, 26]. In brief, all FFDM images were acquired using Hologic Selenia FFDM machines and downloaded directly from the clinical PACS system after an image de-identification process.…”

Computer-aided classification of mammographic masses using visually sensitive image features

“…This study is part of our continuing effort to develop and evaluate computer-aided quantitative image feature analysis schemes to assist predicting cancer risk [27], improving tumor detection [28] and diagnosis [29, 30], and assessing patient prognosis or treatment efficacy [31-33]. Among them, developing a more effective CAD tool to assist classifying between malignant and benign soft breast tissue masses is also important to help increase efficacy of screening mammography.…”

Breast Imaging in the Era of Big Data: Structured Reporting and Data Mining

“…The wealth of information in images could be harnessed if the algorithms for automatically extracting information were more robust. A large warehouse of images and data and facts extracted from images can be used to apply new data- mining algorithms and to extract further knowledge [49, 50]. Many aspects of radiology are moving toward quantitative imaging with definitive metrics delivered as part of the imaging examination.…”