Automated BI-RADS classification of lesions using pyramid triple deep feature generator technique on breast ultrasound images
- 15 September 2022
- journal article
- research article
- Published by IOP Publishing in Medical Engineering & Physics
- Vol. 108 (1) , 103895
Abstract
Ultrasound (US) is an important imaging modality used to assess breast lesions for malignant features. In the past decade, many machine learning models have been developed for automated discrimination of breast cancer versus normal on US images, but few have classified the images based on the Breast Imaging Reporting and Data System (BI-RADS) classes. This work aimed to develop a model for classifying US breast lesions using a BI-RADS classification framework with a new multi-class US image dataset. We proposed a deep model that combined a novel pyramid triple deep feature generator (PTDFG) with transfer learning based on three pre-trained networks for creating deep features. Bilinear interpolation was applied to decompose the input image into four images of successively smaller dimensions, constituting a four-level pyramid for downstream feature generation with the pre-trained networks. Neighborhood component analysis was applied to the generated features to select each network's 1,000 most informative features, which were fed to support vector machine classifier for automated classification using a ten-fold cross-validation strategy. Our proposed model was validated using a new US image dataset containing 1,038 images divided into eight BI-RADS classes and histopathological results. We defined three classification schemes: Case 1 involved the classification of all images into eight categories; Case 2, classification of breast US images into five BI-RADS classes; and Case 3, classification of BI-RADS 4 lesions into benign versus malignant classes. Our PTDFG-based transfer learning model attained accuracy rates of 79.29%, 80.42%, and 88.67% for Case 1, Case 2, and Case 3, respectively.Keywords
This publication has 25 references indexed in Scilit:
- Comparison of Transferred Deep Neural Networks in Ultrasonic Breast Masses DiscriminationBioMed Research International, 2018
- The Role of Ultrasound in Screening Dense Breasts—A Review of the Literature and Practical Solutions for ImplementationDiagnostics, 2018
- Classification of breast cancer in ultrasound imaging using a generic deep learning analysis software: a pilot studyBritish Journal of Radiology, 2018
- Small-window parametric imaging based on information entropy for ultrasound tissue characterizationScientific Reports, 2017
- Clinical application of S-Detect to breast masses on ultrasonography: a study evaluating the diagnostic performance and agreement with a dedicated breast radiologistUltrasonography, 2017
- Ultrasound as the Primary Screening Test for Breast Cancer: Analysis From ACRIN 6666JNCI: Journal of the National Cancer Institute, 2015
- Going beyond a First Reader: A Machine Learning Methodology for Optimizing Cost and Performance in Breast Ultrasound DiagnosisUltrasound in Medicine & Biology, 2015
- Characteristics of breast cancers detected by ultrasound screening in women with negative mammogramsCancer Science, 2011
- Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech RecognitionIEEE Transactions on Audio, Speech, and Language Processing, 2011
- Intraobserver interpretation of breast ultrasonography following the BI-RADS classificationEuropean Journal of Radiology, 2010