Abstract
BackgroundOur aims were to determine if features derived from texture analysis (TA) can distinguish normal, benign, and malignant tissue on automated breast ultrasound (ABUS); to evaluate whether machine learning (ML) applied to TA can categorise ABUS findings; and to compare ML to the analysis of single texture features for lesion classification.MethodsThis ethically approved retrospective pilot study included 54 women with benign (n = 38) and malignant (n = 32) solid breast lesions who underwent ABUS. After manual region of interest placement along the lesions’ margin as well as the surrounding fat and glandular breast tissue, 47 texture features (TFs) were calculated for each category. Statistical analysis (ANOVA) and a support vector machine (SVM) algorithm were applied to the texture feature to evaluate the accuracy in distinguishing (i) lesions versus normal tissue and (ii) benign versus malignant lesions.ResultsSkewness and kurtosis were the only TF significantly different among all the four categories (p < 0.000001). In subsets (i) and (ii), a maximum area under the curve of 0.86 (95% confidence interval [CI] 0.82–0.88) for energy and 0.86 (95% CI 0.82–0.89) for entropy were obtained. Using the SVM algorithm, a maximum area under the curve of 0.98 for both subsets was obtained with a maximum accuracy of 94.4% in subset (i) and 90.7% in subset (ii).ConclusionsTA in combination with ML might represent a useful diagnostic tool in the evaluation of breast imaging findings in ABUS. Applying ML techniques to TFs might be superior compared to the analysis of single TF.
Highlights
Our aims were to determine if features derived from texture analysis (TA) can distinguish normal, benign, and malignant tissue on automated breast ultrasound (ABUS); to evaluate whether machine learning (ML) applied to TA can categorise ABUS findings; and to compare ML to the analysis of single texture features for lesion classification
ABUS was performed in addition to mammography in 39 women with American College of Radiology breast density category c or d [18] undergoing screening examination and as unique imaging examination in 15 women younger than 40 years undergoing routine controls
At the receiver operating characteristic (ROC) analysis, the energy was the texture feature with the maximum area under the curve (AUC) value in the comparison of lesions versus normal tissue (0.86, 95% CI 0.82–0.88) and a total of Lesions
Summary
Our aims were to determine if features derived from texture analysis (TA) can distinguish normal, benign, and malignant tissue on automated breast ultrasound (ABUS); to evaluate whether machine learning (ML) applied to TA can categorise ABUS findings; and to compare ML to the analysis of single texture features for lesion classification. The use of HHUS in the screening setting remains controversial due to its inherent limitations including the lack of standardisation and the necessary level of operator experience [4, 5]. In recent years, automated breast ultrasound (ABUS) has been introduced to overcome some of HHUS limitations. ABUS provides technique standardisation via the acquisition of standardised views as well as scanning parameters and Marcon et al European Radiology Experimental (2019) 3:44 resolves the issue of operator subjectivity and variation [6]. Standardised acquisition in terms of scanning parameters (e.g., focus, gain) offers the opportunity to apply tools for image analysis that can support the characterisation of imaging findings
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
