Incorporating texture features in a computer-aided breast lesion diagnosis system for automated three-dimensional breast ultrasound

Abstract

Abstract. We investigated the benefits of incorporating texture features into an existing computer-aided diagnosis (CAD) system for classifying benign and malignant lesions in automated three-dimensional breast ultrasound images. The existing system takes into account 11 different features, describing different lesion properties; however, it does not include texture features. In this work, we expand the system by including texture features based on local binary patterns, gray level co-occurrence matrices, and Gabor filters computed from each lesion to be diagnosed. To deal with the resulting large number of features, we proposed a combination of feature-oriented classifiers combining each group of texture features into a single likelihood, resulting in three additional features used for the final classification. The classification was performed using support vector machine classifiers, and the evaluation was done with 10-fold cross validation on a dataset containing 424 lesions (239 benign and 185 malignant lesions). We compared the classification performance of the CAD system with and without texture features. The area under the receiver operating characteristic curve increased from 0.90 to 0.91 after adding texture features (p < 0.001).

Computer-aided diagnosis for distinguishing between triple-negative breast cancer and fibroadenomas based on ultrasound texture features

“…[6][7][8][9][10] Recently, useful texture features have been extracted based on the gray-level co-occurrence matrices (GLCMs) for tumor diagnosis. [11][12][13][14][15] However, for conventional texture analyses, 11,12 the adjustable parameters of US devices 16 result in a weak diagnostic capability for tumor diagnosis. By contrast, applying the ranklet transform and calculating a multiresolution gray-scale invariant texture feature create a robust pattern for distinguishing between malignant and benign tumors.…”

Lesion Segmentation in Ultrasound Using Semi-Pixel-Wise Cycle Generative Adversarial Nets

“…In terms of detection and diagnosis, computers can also assist radiologists to make decisions that improve the effectiveness of ultrasound reading. For example, computer techniques [7]- [12] have been proposed to delineate the contour of lesions or directly detect or diagnose breast lesions. Most of these computer-aided diagnoses or detections include a module of segmentation.…”

Quantitative imaging of cancer in the postgenomic era: Radio(geno)mics, deep learning, and habitats

“…Conventional or human-engineered computational image features can be divided into 4 classes, namely those that describe shape [48][49][50] ; margin sharpness 51,52 ; histogram features (eg, mean, variance, kurtosis, maximum, and minimum); and texture features, [53][54][55][56][57][58][59][60] which describe the spatial variation of gray values within the tumor. Within each class, there are hundreds to thousands of individual features: for example, some texture features quantify the spatial variation of gray values across Cancer December 15, 2018 multiple scales and orientations, and shape features can similarly quantify edge irregularity at multiple scales.…”