Development of a Deep-Learning-Based Method for Breast Ultrasound Image Segmentation
Authors:
- Rania AlmajalidRARania Almajalid
- Juan ShanJSJuan Shan
- Yaodong DuYDYaodong Du
- Ming ZhangMZMing Zhang
- 1 December 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1103-1108
Abstract
Breast cancer is one of the deadliest cancers that cause women death globally. Ultrasound imaging is one of the commonly used diagnostic tools for detection and classification of breast abnormalities. In the past decades, computer-aided diagnosis (CAD) systems have been developed to improve the accuracy of diagnosis made by radiologists. In particular, automatic breast ultrasound (BUS) image segmentation is a critical step for cancer diagnosis using CAD. However, accurate tumor segmentation is still a challenge as a result of various ultrasound artifacts. This paper developed a novel segmentation framework based on deep learning architecture u-net, for breast ultrasound imaging. U-net is a convolutional neural network architecture designed for biology image segmentation with limited training data. It was originally proposed for neuronal structure segmentation in microscopy images. In our work, we modified and improved the method for BUS image segmentation. On a database of 221 BUS images, we first applied pre-processing techniques including contrast enhancement and speckle reduction to improve the image quality. Then the u-net model was trained and tested through two-fold cross-validation. In order to increase the size of training set, data augmentation strategies including rotation and elastic deformation were applied. Finally, a post-processing step that removed noisy region(s) from the segmentation result finalized the whole method. The area error metrics, dice coefficient, and similarity rate were calculated to evaluate the performance on the testing sets. We compared our method with another two fully automatic segmentation methods on the same dataset. Our method outperformed the other two significantly with the dice coefficient = 0.825 and similarity rate = 0.698. Experiment results showed that the modified u-net method is more robust and accurate in breast tumor segmentation for ultrasound images.Keywords
This publication has 14 references indexed in Scilit:
- Breast-lesion Segmentation Combining B-Mode and Elastography UltrasoundUltrasonic Imaging, 2015
- Fully automatic segmentation of breast ultrasound images based on breast characteristics in space and frequency domainsPattern Recognition, 2015
- Semi-automatic Breast Ultrasound Image Segmentation Based on Mean Shift and Graph CutsUltrasonic Imaging, 2014
- A novel segmentation method for breast ultrasound images based on neutrosophic l‐means clusteringMedical Physics, 2012
- Automated breast cancer detection and classification using ultrasound images: A surveyPattern Recognition, 2010
- A Review of Breast UltrasoundJournal of Mammary Gland Biology and Neoplasia, 2006
- On Shape of Plane Elastic CurvesInternational Journal of Computer Vision, 2006
- Speckle reducing anisotropic diffusionIEEE Transactions on Image Processing, 2002
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Measures of the Amount of Ecologic Association Between SpeciesEcology, 1945