Original ContributionComputer-Aided Diagnosis for Breast Ultrasound Using Computerized BI-RADS Features and Machine Learning Methods
Introduction
Breast cancer is the leading cause of cancer-related death in women (Cheng et al. 2010). In 2014, approximately 232,670 new cases of breast cancer were diagnosed and resulted in approximately 40,000 deaths in the United States (Siegel et al. 2014). Screening mammography is widely used and recommended for the early detection of breast cancer. Studies have indicated that the addition of ultrasound can increase the overall cancer detection rate and reduce the number of unnecessary biopsies (Costantini et al., 2006, Hwang et al., 2005). Screening ultrasound is becoming an important addition to routine breast cancer screening because of its superior ability in imaging dense breast tissue and its lack of ionizing radiation.
Despite its many advantages, however, the quality of ultrasound has been relatively low because of the intrinsic speckle noise and low contrast between different tissue types. Digital image processing techniques and machine learning methods have been applied to improve detection rate and increase specificity (Chen et al., 2003, Huang et al., 2006, Segyeong et al., 2004). Advances in the field of medical image processing has improved the ability of computer-aided diagnosis (CAD) to reduce background noise, improve image contrast, detect regions of interest, differentiate a tumor from background and therefore help differentiate benign from worrisome lesions (Drukker et al., 2006, Moon et al., 2013a; Shen et al. 2007). Among all these functionalities of CAD systems, classifying a tumor into benign or worrisome categories is the ultimate objective.
The performance of machine learning methods relies heavily on how well the characteristics of tumors are represented by digital features, which can be separated into two categories: knowledge based and statistic based. Knowledge-based features are derived from the Breast Imaging Reporting and Data System (BI-RADS) lexicon (Mendelson et al. 2013), which is used to characterize lesions based on shape, margin, orientation, echo pattern and acoustic shadowing (Chen et al., 2003, Moon et al., 2013a, Song et al., 2005). The other category of features is obtained from statistical computation, such as auto-covariance coefficients and frequency domain features (Huang and Chen, 2005, Mogatadakala et al., 2006). These features capture the correlation between pixels and do not necessarily correspond to any observable features in ultrasound images.
The BI-RADS lexicon aims to standardize mammography and ultrasound reports so that reports are clear, succinct and consistent among readers. Although all BI-RADS terms are descriptive, not quantitative, they need to be “translated” into computerized features so a CAD system can compute these features automatically. Several groups have proposed approaches to quantify BI-RADS features (André et al., 2007, Mainiero et al., 2005, Moon et al., 2013b), including a comprehensive study by Alam et al. (2011). For example, the most commonly used ultrasound BI-RADS feature is the “parallel” orientation, which corresponds to the “long axis of a lesion paralleling the skin line.” To quantify this feature, an equivalent ellipse of the lesion was identified, and the ratio between the horizontal axis and the vertical axis of the ellipse was computed (Chen et al., 2004, Moon et al., 2013a, Sahiner, 2007). If the ratio is larger than one, the tumor is more likely benign; if the ratio is less than one, it is more likely malignant.
For this study, we performed a complete translation of the entire ultrasound BI-RADS lexicon into digital features, which are used in machine learning methods for the purpose of developing an effective CAD system for breast ultrasound. We have proposed new and validated digital features to distinguish benign from worrisome lesions with the ultimate goal of improving the accuracy of breast cancer diagnosis.
Section snippets
Methods
The database used in this study contains 283 breast ultrasound images. The images were collected subsequently without excluding any data by the Second Affiliated Hospital of Harbin Medical University (Harbin, China), using a VIVID 7 (GE, Horten, Norway) with a 5- to 14-MHz linear probe. The aperture of the transducer is 4 cm. To obtain the original ultrasound images, the techniques harmonics, spatial compounding and speckle reduction were not used. The average size of the images is 500 × 420
Student's t-test for computerized BI-RADS features
The mean value and standard deviation of each computerized BI-RADS feature for the benign and malignant groups are listed in Table 2. According to Student's t-test, seven features differed statistically between the benign and malignant groups, at significance level of 0.01 (p < 0.01): (f1) ADEE, (f2) height/width, (f3) AvgDiff, (f4) NumPeaks, (f5) AvgPeaks, (f6) ADCH and (f8) entropy. The other three features did not significantly differ at level 0.01, including (f7) echogenicity, (f9) shadow
Discussion and Conclusions
Computer-aided diagnosis for breast ultrasound is a field that has been extensively studied. A crucial task for a CAD system is discovering efficient computerized features to distinguish benign and malignant tumors. The fifth edition of the Ultrasound BI-RADS lexicon (Mendelson et al. 2013) was quantified into computerized features and evaluated using Student's t-test. Multiple features were combined to serve as input for machine learning methods, and the bottom-up feature selection procedure
Acknowledgments
Thanks are due to radiologists Dr. Jiawei Tian and Dr. Yanxin Su from the Second Affiliated Hospital of Harbin Medical University (China) for their efforts in collecting the images and labeling the database.
References (23)
- et al.
Automated breast cancer detection and classification using ultrasound images: A survey
Pattern Recog
(2010) - et al.
Support vector machines in sonography: Application to decision making in the diagnosis of breast cancer
Clin Imaging
(2005) - et al.
Computer-aided diagnosis of breast masses using quantified BI-RADS findings
Comput Methods Programs Biomed
(2013) - et al.
Breast ultrasound computer-aided diagnosis using BI-RADS features
Acad Radiol
(2007) - et al.
Ultrasonic multi-feature analysis procedure for computer-aided diagnosis of solid breast lesions
Ultrason Imaging
(2011) - et al.
Diagnostic performance of a computer-aided image analysis system for breast ultrasound
Acoust Imaging
(2007) - et al.
Breast lesions on sonograms: Computer-aided diagnosis with nearly setting-independent features and artificial neural networks
Radiology
(2003) - et al.
Analysis of sonographic features for the differentiation of benign and malignant breast tumors of different sizes
Ultrasound Med Biol
(2004) - et al.
Characterization of solid breast masses use of the sonographic breast imaging reporting and data system lexicon
J Ultrasound Med
(2006) - et al.
Robustness of computerized lesion detection and classification scheme across different breast US platforms
Radiology
(2006)
The WEKA data mining software: An update
SIGKDD Explorations
Cited by (131)
Diagnostic Performance of Deep Learning in Video-Based Ultrasonography for Breast Cancer: A Retrospective Multicentre Study
2024, Ultrasound in Medicine and BiologyA novel image-to-knowledge inference approach for automatically diagnosing tumors
2023, Expert Systems with ApplicationsDGANet: A Dual Global Attention Neural Network for Breast Lesion Detection in Ultrasound Images
2023, Ultrasound in Medicine and BiologyA validation of an entropy-based artificial intelligence for ultrasound data in breast tumors
2024, BMC Medical Informatics and Decision Making