Computer‐aided detection of breast masses: Four‐view strategy for screening mammography

Abstract

Purpose:To improve the performance of a computer-aided detection ͑CAD͒ system for mass detection by using four-view information in screening mammography. Methods: The authors developed a four-view CAD system that emulates radiologists' reading by using the craniocaudal and mediolateral oblique views of the ipsilateral breast to reduce false positives ͑FPs͒ and the corresponding views of the contralateral breast to detect asymmetry. The CAD system consists of four major components: ͑1͒ Initial detection of breast masses on individual views, ͑2͒ information fusion of the ipsilateral views of the breast ͑referred to as two-view analysis͒, ͑3͒ information fusion of the corresponding views of the contralateral breast ͑referred to as bilateral analysis͒, and ͑4͒ fusion of the four-view information with a decision tree. The authors collected two data sets for training and testing of the CAD system: A mass set containing 389 patients with 389 biopsy-proven masses and a normal set containing 200 normal subjects. All cases had four-view mammograms. The true locations of the masses on the mammograms were identified by an experienced MQSA radiologist. The authors randomly divided the mass set into two independent sets for cross validation training and testing. The overall test performance was assessed by averaging the free response receiver operating characteristic ͑FROC͒ curves of the two test subsets. The FP rates during the FROC analysis were estimated by using the normal set only. The jackknife free-response ROC ͑JAFROC͒ method was used to estimate the statistical significance of the difference between the test FROC curves obtained with the single-view and the four-view CAD systems. Results: Using the single-view CAD system, the breast-based test sensitivities were 58% and 77% at the FP rates of 0.5 and 1.0 per image, respectively. With the four-view CAD system, the breast-based test sensitivities were improved to 76% and 87% at the corresponding FP rates, respectively. The improvement was found to be statistically significant ͑p Ͻ 0.0001͒ by JAFROC analysis. Conclusions:The four-view information fusion approach that emulates radiologists' reading strategy significantly improves the performance of breast mass detection of the CAD system in comparison with the single-view approach.

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

“…In the last two decades, various computer-aided detection (CAD) schemes of mammograms, which function as a “second reader” to radiologists, have also been developed and tested (Wei et al , 2011b; Zheng et al , 2006; Zheng et al , 2012; Eltonsy et al , 2007; Varela et al , 2007; Kom et al , 2007; Catarious et al , 2006; Velikova et al , 2009; Qian et al , 2007). The majority of these schemes including the commercialized CAD schemes are single image based schemes that focus on detecting more subtle cancers with high false-positive rates.…”

“…Thus, in order to improve CAD performance, many investigators have also developed and tested different methods of combining multiple view images into the classification process to improve CAD performance in detection and classification of mammographic abnormalities. These efforts include more accurately locating the breast masses and/or FP detections on two ipsilateral (CC and MLO) views (Zheng et al , 2006; Zheng et al , 2009; van Engeland and Karssemeijer, 2007; Wei et al , 2009; Yuan et al , 2008) and more effectively combining the information detected from different image views (Liu et al , 2005; Wang et al , 2011; Wei et al , 2011b). Despite these research efforts, multi-view based CAD schemes have not been accepted and used in the clinical practice to date.…”

A Radiomic feature–based Nipple Detection Algorithm on Digital Mammography

“…Multiview scanning are acquired for the mammographic, typically including craniocaudal (CC) and mediolateral oblique (MLO) views. Studies show that multiview analysis can improve the accuracy of computerized lesion detection on mammograms.…”

A Modified Undecimated Discrete Wavelet Transform Based Approach to Mammographic Image Denoising

“…Mammography is one of the most effective and reliable methods for early breast cancer detection [3][4][5][6]. However, mammography is still far from being ideal, with its sensitivity only ranging from 70 % to 90 % [7]. The clinical significance of early breast cancer diagnosis and a clear need to reduce false-negative rate of screening mammography have motivated the development of computer-aided detection (CADe) systems for decision support [8][9][10][11][12][13][14][15][16][17].…”