Reduction of false-positive recalls using a computerized mammographic image feature analysis scheme

Tan, Maxine; Pu, Jiantao

doi:10.1088/0031-9155/59/15/4357

Cited by 32 publications

(30 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since this image data collection remains active to date, new cases are continually being added to our study database. Different subsets of this database have been used in a number of our previous studies (e.g., (Wang et al , 2012; Zheng et al , 2012b; Tan et al , 2013; Tan et al , 2014b)). In this study, we assembled a dataset that includes 1896 cases.…”

Section: Methodsmentioning

confidence: 99%

“…We recently developed and preliminarily tested a new CAD scheme to detect and analyze global bilateral mammographic image features of both CC and MLO views of the left and right breasts (Tan et al , 2014b). We applied this scheme to test its feasibility of helping distinguish between true-positive (cancer) and false-positive recalled (benign) cases.…”

Section: Methodsmentioning

confidence: 99%

“…The detailed description of each feature definition and computational method has been reported in our previous study (Tan et al , 2014b). Basically, these features are divided into the following categories: (1) the statistical pixel value (or intensity) based features (i.e., mean, standard deviation, skewness, and kurtosis of the pixel gray values) (Wang et al , 2011), (2) fractal dimension based features to quantitatively assess breast tissue composition and mammographic density (Chang et al , 2002), (3) gray level run length based texture features computed from the gray level resolution reduced images (from 4095 to 256 gray levels) along four different directions (Tang, 1998), (4) the first-order statistics of the x -axis and y -axis histogram (cumulative projection) based features presented by Tzikopoulos et al (Tzikopoulos et al , 2011), (5) the gray level co-occurrence matrix (GLCM) based texture features proposed by Haralick et al (Haralick et al , 1973), (6) segmented breast area size, and (7) a percentage density (PD) measure (Byng et al , 1994).…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

A new approach to develop computer-aided detection schemes of digital mammograms

Tan

Qian

et al. 2015

Phys. Med. Biol.

Self Cite

View full text Add to dashboard Cite

The purpose of this study is to develop a new global mammographic image feature analysis based computer-aided detection (CAD) scheme and evaluate its performance in detecting positive screening mammography examinations. A dataset that includes images acquired from 1896 full-field digital mammography (FFDM) screening examinations was used in this study. Among them, 812 cases were positive for cancer and 1084 were negative or benign. After segmenting the breast area, a computerized scheme was applied to compute 92 global mammographic tissue density based features on each of four mammograms of the craniocaudal (CC) and mediolateral oblique (MLO) views. After adding three existing popular risk factors (woman’s age, subjectively rated mammographic density, and family breast cancer history) into the initial feature pool, we applied a Sequential Forward Floating Selection (SFFS) feature selection algorithm to select relevant features from the bilateral CC and MLO view images separately. The selected CC and MLO view image features were used to train two artificial neural networks (ANNs). The results were then fused by a third ANN to build a two-stage classifier to predict the likelihood of the FFDM screening examination being positive. CAD performance was tested using a ten-fold cross-validation method. The computed area under the receiver operating characteristic curve was AUC=0.779±0.025 and the odds ratio monotonically increased from 1 to 31.55 as CAD-generated detection scores increased. The study demonstrated that this new global image feature based CAD scheme had a relatively higher discriminatory power to cue the FFDM examinations with high risk of being positive, which may provide a new CAD-cueing method to assist radiologists in reading and interpreting screening mammograms.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A new approach to develop computer-aided detection schemes of digital mammograms

Tan

Qian

et al. 2015

Phys. Med. Biol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…From an existing fully-anonymized full-field digital mammography (FFDM) image database used in our previous studies [18,19], we assembled an independent reference dataset for developing and testing a new CBIR scheme in this study. The dataset includes 227 regions of interest (ROIs) that were extracted from the original images of 227 FFDM examinations.…”

Section: Methodsmentioning

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

“…From an existing fully anonymized full-field digital mammography (FFDM) image database used in our previous studies, 27,28 we assembled a reference dataset for developing and testing a new CBIR scheme in this study. The dataset includes 820 ROIs that were extracted from the original images of 820 independent FFDM examination cases.…”

Section: A Two Image Datasetsmentioning

confidence: 99%

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

Reduction of false-positive recalls using a computerized mammographic image feature analysis scheme

Cited by 32 publications

References 68 publications

A new approach to develop computer-aided detection schemes of digital mammograms

A new approach to develop computer-aided detection schemes of digital mammograms

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

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

Contact Info

Product

Resources

About