Automatic tumor segmentation in breast ultrasound images using a dilated fully convolutional network combined with an active contour model

Abstract

Purpose: Due to the low contrast, blurry boundaries, and large amount of shadows in breast ultrasound (BUS) images, automatic tumor segmentation remains a challenging task. Deep learning provides a solution to this problem, since it can effectively extract representative features from lesions and the background in BUS images. Methods: A novel automatic tumor segmentation method is proposed by combining a dilated fully convolutional network (DFCN) with a phase-based active contour (PBAC) model. The DFCN is an improved fully convolutional neural network with dilated convolution in deeper layers, fewer parameters, and batch normalization techniques; and has a large receptive field that can separate tumors from background. The predictions made by the DFCN are relatively rough due to blurry boundaries and variations in tumor sizes; thus, the PBAC model, which adds both region-based and phase-based energy functions, is applied to further improve segmentation results. The DFCN model is trained and tested in dataset 1 which contains 570 BUS images from 89 patients. In dataset 2, a 10-fold support vector machine (SVM) classifier is employed to verify the diagnostic ability using 460 features extracted from the segmentation results of the proposed method. Results: Advantages of the present method were compared with three state-of-the-art networks; the FCN-8s, U-net, and dilated residual network (DRN). Experimental results from 170 BUS images show that the proposed method had a Dice Similarity coefficient of 88.97 AE 10.01%, a Hausdorff distance (HD) of 35.54 AE 29.70 pixels, and a mean absolute deviation (MAD) of 7.67 AE 6.67 pixels, which showed the best segmentation performance. In dataset 2, the area under curve (AUC) of the 10-fold SVM classifier was 0.795 which is similar to the classification using the manual segmentation results. Conclusions: The proposed automatic method may be sufficiently accurate, robust, and efficient for medical ultrasound applications.

Overview of radiomics in breast cancer diagnosis and prognostication

“…Supervised machine learning methods for radiomics include, for example, standard feature-based multi-layer perceptrons [29] , [30] , [31] and regularization networks that require the optimal minimization of functionals made of two terms: one describing the ability of the algorithm to fit the historical data and the other one describing its generalization power [21] , [22] , [23] . Ensemble methods represent a more modern approach to radiomics and, in particular, Random Forest [ 25 , 33 ] works as a large collection of decorrelated decision trees (a decision tree classifier organizes a series of test questions and conditions in a tree structure, recursively splitting training samples into subsets based on the value of a single attribute).…”

Breast tumor segmentation in 3D automatic breast ultrasound using Mask scoring R‐CNN

“…For example, Hu et al reported DSC of 0.9338 AE 0.0370 and 0.9364 AE 0.0248 for interobserver and intraobserver variability on two radiologists contouring breast tumor on ultrasound. 47 Averaged contour or consensus contour from multiple observers are thus preferred to serve as a training dataset in order to mitigate the bias and uncertainty in the segmentation results. The evaluation of the proposed method in this study showed a large SD with HD95.…”

Multi-Task Refined Boundary-Supervision U-Net (MRBSU-Net) for Gastrointestinal Stromal Tumor Segmentation in Endoscopic Ultrasound (EUS) Images

“…To evaluate the proposed approach, 545 test images are used. The Dice similarity coefficient (DSC), mean absolute deviation (MAD), and Hausdorff distance (HD) are applied to evaluate the results of the proposed method [15].…”

“…The encoder part in U-net is lower as well as the decoder part in the U-net has too many feature channels to propagate trashy information to higher resolution layers by the skip connections. For instance, the noise and shadows would be magnified and propagated in the decoder part [15]. RU-net reduce the concatenation between the previous layer and higher resolution layer, which could avoid the shadow information propagating to the higher resolution layers.…”