Assessment of a Four-View Mammographic Image Feature Based Fusion Model to Predict Near-Term Breast Cancer Risk

Abstract

The purpose of this study was to develop and assess a new quantitative four-view mammographic image feature based fusion model to predict the near-term breast cancer risk of the individual women after a negative screening mammography examination of interest. The dataset included fully-anonymized mammograms acquired on 870 women with two sequential full-field digital mammography (FFDM) examinations. For each woman, the first “prior” examination in the series was interpreted as negative (not recalled) during the original image reading. In the second “current” examination, 430 women were diagnosed with pathology verified cancers and 440 remained negative (“cancer-free”). For each of four bilateral craniocaudal and mediolateral oblique view images of left and right breasts, we computed and analyzed eight groups of global mammographic texture and tissue density image features. A risk prediction model based on three artificial neural networks was developed to fuse image features computed from two bilateral views of four images. The risk model performance was tested using a ten-fold cross-validation method and a number of performance evaluation indices including the area under the receiver operating characteristic curve (AUC) and odds ratio (OR). The highest AUC = 0.725±0.026 was obtained when the model was trained by gray-level run length statistics (RLS) texture features computed on dense breast regions, which was significantly higher than the AUC values achieved using the model trained by only two bilateral one-view images (p < 0.02). The adjustable OR values monotonically increased from 1.0 to 11.8 as model-generated risk score increases. The regression analysis of OR values also showed a significant increase trend in slope (p < 0.01). As a result, this preliminary study demonstrated that a new four-view mammographic image feature based risk model could provide useful and supplementary image information to help predict the near-term breast cancer risk.

Applying a new bilateral mammographic density segmentation method to improve accuracy of breast cancer risk prediction

“…In addition, we also segmented the dense breast region from each image. In the previous studies, the dense breast region of each image (left or right mammographic image) was defined as the region that encompasses the pixel values above the median value of the whole breast region[7,21–22]. In these studies, dense regions of left and right mammographic images were segmented using their respective medians as thresholds.…”

“…Although many epidemiology study-based breast cancer risk models, such as Gail, Claus, and Tyrer-Cuzick model [6] have been developed, they typically aim to assess the risk of a woman developing breast cancer in a long term or lifetime. Thus, it is required to develop new models that have higher discriminatory power in predicting the risk of individual women developing breast cancer in the near-term [7]. Based on the computed quantitative image features, several research groups have developed and tested a number of new risk stratification models to predict breast cancer risk [8–12].…”

A new paradigm of dielectric relaxation spectroscopy for non-invasive detection of breast abnormalities: a preliminary feasibility analysis

“…However, the efficacy of a uniform population-based mammography screening paradigm is very low and quite controversial with cancer detection yields less than 0.5% as well as false-positive recall rates around or higher than 10% [1][2][3]. Thus, in order to improve efficacy of current breast cancer screening methods (including mammography), developing and establishing a new and better, personalized, paradigm for breast-cancer screening has been attracting wide interest in the research community [4][5][6]. The basic goal is to develop an accurate prescreening-tool and/or risk prediction model to stratify women into two groups namely, high and low risk for having or developing mammography-detectable cancers in a short (or near) term.…”

Computer-aided global breast MR image feature analysis for prediction of tumor response to chemotherapy: performance assessment

“…In our research group, we recently have been working on developing new quantitative image markers or prediction models to assist cancer screening, diagnosis and prognosis assessment [8][9][10][11][12]. For example, in the last year SPIE Medical Imaging (Computer-aided diagnosis) conference, we presented a new CAD-supported prediction model that used kinetic image features computed from the segmented breast tumor regions and tested its performance using a small dataset of 68 patients [13].…”