Tong Wu1,2, Laith R Sultan2, Jiawei Tian3, Theodore W Cary2, Chandra M Sehgal4. 1. Department of Ultrasound, Second Affiliated Hospital of Harbin Medical University, 246 Xuefu Road, Harbin City, 150086, Heilongjiang Province, People's Republic of China. 2. Ultrasound Research Lab, Department of Radiology, University of Pennsylvania, 168B John Morgan Building, 3620 Hamilton Walk, Philadelphia, PA, 19104, USA. 3. Department of Ultrasound, Second Affiliated Hospital of Harbin Medical University, 246 Xuefu Road, Harbin City, 150086, Heilongjiang Province, People's Republic of China. jwtian2004@163.com. 4. Ultrasound Research Lab, Department of Radiology, University of Pennsylvania, 168B John Morgan Building, 3620 Hamilton Walk, Philadelphia, PA, 19104, USA. chandra.sehgal@uphs.upenn.edu.
Abstract
PURPOSE: Early diagnosis of triple-negative (TN) breast cancer is important due to its aggressive biological characteristics, poor clinical outcomes, and limited options for therapy. The goal of this study is to evaluate the potential of machine learning with quantitative ultrasound image features for the diagnosis of TN breast cancer. METHODS: Ultrasonic and clinical data of 140 surgically confirmed breast cancer cases were analyzed retrospectively for the diagnosis of TN and non-TN (NTN) subtypes. The subtypes were classified based on the expression of estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2). Ultrasound image features were measured from the grayscale and color Doppler images and used with logistic regression for classification by machine learning. Leave-one-out cross validation was used to train and test the differentiation. Diagnostic performance was measured by the area under receiver operating characteristic (ROC) curve, and sensitivity and specificity determined at the Youdons index. RESULTS: Of the twelve grayscale and Doppler features measured, eight were found to be statistically different for the TN and NTN subtypes (p < 0.05). The area under the ROC curve (AUC) of the statistically significant grayscale (GS) and color Doppler (CD) features was 0.85 and 0.65, respectively. The AUC increased to 0.88 when the GS and CD features were used together, with sensitivity of 86.96% and specificity of 82.91%. Consideration of patient age in the analysis did not improve discrimination of TN and NTN. CONCLUSIONS: The analysis of breast ultrasound images by machine learning achieves high level of differentiation between the TN and NTN subtypes, exceeding the diagnostic performance by standard visual assessments of the images.
PURPOSE: Early diagnosis of triple-negative (TN) breast cancer is important due to its aggressive biological characteristics, poor clinical outcomes, and limited options for therapy. The goal of this study is to evaluate the potential of machine learning with quantitative ultrasound image features for the diagnosis of TN breast cancer. METHODS: Ultrasonic and clinical data of 140 surgically confirmed breast cancer cases were analyzed retrospectively for the diagnosis of TN and non-TN (NTN) subtypes. The subtypes were classified based on the expression of estrogen receptor (ER), progesterone receptor (PR), and humanepidermal growth factor receptor 2 (HER2). Ultrasound image features were measured from the grayscale and color Doppler images and used with logistic regression for classification by machine learning. Leave-one-out cross validation was used to train and test the differentiation. Diagnostic performance was measured by the area under receiver operating characteristic (ROC) curve, and sensitivity and specificity determined at the Youdons index. RESULTS: Of the twelve grayscale and Doppler features measured, eight were found to be statistically different for the TN and NTN subtypes (p < 0.05). The area under the ROC curve (AUC) of the statistically significant grayscale (GS) and color Doppler (CD) features was 0.85 and 0.65, respectively. The AUC increased to 0.88 when the GS and CD features were used together, with sensitivity of 86.96% and specificity of 82.91%. Consideration of patient age in the analysis did not improve discrimination of TN and NTN. CONCLUSIONS: The analysis of breast ultrasound images by machine learning achieves high level of differentiation between the TN and NTN subtypes, exceeding the diagnostic performance by standard visual assessments of the images.
Entities:
Keywords:
Breast cancer; Computer-aided diagnosis; Machine learning; Quantitative breast ultrasound; Triple negative breast cancer
Authors: Clement G Yedjou; Solange S Tchounwou; Richard A Aló; Rashid Elhag; BereKet Mochona; Lekan Latinwo Journal: Int J Sci Acad Res Date: 2021-10-30
Authors: Thomas Nind; James Sutherland; Gordon McAllister; Douglas Hardy; Ally Hume; Ruairidh MacLeod; Jacqueline Caldwell; Susan Krueger; Leandro Tramma; Ross Teviotdale; Mohammed Abdelatif; Kenny Gillen; Joe Ward; Donald Scobbie; Ian Baillie; Andrew Brooks; Bianca Prodan; William Kerr; Dominic Sloan-Murphy; Juan F R Herrera; Dan McManus; Carole Morris; Carol Sinclair; Rob Baxter; Mark Parsons; Andrew Morris; Emily Jefferson Journal: Gigascience Date: 2020-09-29 Impact factor: 6.524