An Interactive System for Computer-Aided Diagnosis of Breast Masses

Wang, Xingwei; Li, Lihua; Liu, Wei; Xu, Weidong; Lederman, Dror

doi:10.1007/s10278-012-9451-0

Cited by 20 publications

(12 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The study has a number of unique characteristics and experimental observations. First, to realize a fast (or "real time") reference image retrieval and compute a classification score for a queried ROI in CAD or particularly in the interactive CAD application, 26 a set of image features is typically precomputed from all selected ROIs in the reference image database. In most of the previous studies, T III.…”

Section: Discussionmentioning

confidence: 99%

“…Due to the large variation of breast lesions and 3D tissue overlap on the 2D projection based mammograms, fully automated computerized schemes often fail to accurately segment subtle lesions. 23,26 Thus, the errors and inconsistencies in the computed lesion morphological and density distribution features can negatively impact or reduce the performance of the CBIR based CAD schemes. To avoid the impact of lesion segmentation error, some researchers have tested other CBIR approaches without lesion segmentation [i.e., using mutual information of the entire ROI (Ref.…”

Section: Discussionmentioning

confidence: 99%

“…When using a CBIR based CAD scheme in an interactive environment, 26 a suspicious lesion depicted on the mammogram is typically queried by an observer (e.g., a radiologist) who determines and marks a seed (pixel) as the lesion center. Starting from this marked seed, the scheme extracts a ROI surrounding the queried lesion, computes image features, retrieves the similar reference ROIs, and then generates a final classification score.…”

Section: B a Cbir Based Cad Schemementioning

confidence: 99%

“…First, we developed and tested a new CBIR scheme that sequentially uses two lesion density distribution pattern based image features (contents) as the image retrieval comparison indices without performing lesion segmentation. Second, we assessed the reproducibility of this CBIR approach when it is used in an interactive computeraided diagnosis (ICAD) environment 26 and also proposed a new approach to improve the reproducibility of the scheme classification performance. The detailed study procedure and experimental results are reported in Secs.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

et al. 2015

Self Cite

View full text Add to dashboard Cite

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

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: B a Cbir Based Cad Schemementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

et al. 2015

Self Cite

View full text Add to dashboard Cite

show abstract

“…On the other hand, many CBIR algorithms based on regional image features can avoid the lesion segmentation [14], but they require longer computation time. However, when the CBIR is used in an interactive CAD system [15], different users (e.g., radiologists) subjectively query the lesion center using a computer mouse, which results in the lesion center positon shift. The variation of the lesion center (or growth seed) for the CAD scheme to extract ROI or segment lesion region may result in retrieving different similar reference ROIs and thus generating different classification scores because CAD schemes can be highly sensitive to the small variation of pixel value distributions [16,17].…”

Section: Introductionmentioning

confidence: 99%

A new Fourier transform based CBIR scheme for mammographic mass classification: a preliminary invariance assessment

2015

Self Cite

View full text Add to dashboard Cite

The purpose of this study is to develop and test a new content-based image retrieval (CBIR) scheme that enables to achieve higher reproducibility when it is implemented in an interactive computer-aided diagnosis (CAD) system without significantly reducing lesion classification performance. This is a new Fourier transform based CBIR algorithm that determines image similarity of two regions of interest (ROI) based on the difference of average regional image pixel value distribution in two Fourier transform mapped images under comparison. A reference image database involving 227 ROIs depicting the verified soft-tissue breast lesions was used. For each testing ROI, the queried lesion center was systematically shifted from 10 to 50 pixels to simulate inter-user variation of querying suspicious lesion center when using an interactive CAD system. The lesion classification performance and reproducibility as the queried lesion center shift were assessed and compared among the three CBIR schemes based on Fourier transform, mutual information and Pearson correlation. Each CBIR scheme retrieved 10 most similar reference ROIs and computed a likelihood score of the queried ROI depicting a malignant lesion. The experimental results shown that three CBIR schemes yielded very comparable lesion classification performance as measured by the areas under ROC curves with the p-value greater than 0.498. However, the CBIR scheme using Fourier transform yielded the highest invariance to both queried lesion center shift and lesion size change. This study demonstrated the feasibility of improving robustness of the interactive CAD systems by adding a new Fourier transform based image feature to CBIR schemes.

show abstract