Breast lesion classification based on supersonic shear-wave elastography and automated lesion segmentation from B-mode ultrasound images

Abstract Background Shear wave elastography (SWE) is an important method in the diagnosis of breast lesions. The purpose of this study was to evaluate the value of tissue stiffness around breast lesion and stiff rim sign for the differentiation of benign and malignant lesions. Methods 192 patients (mean age, 44.6 ± 13.6 years) with 199 breast lesions proven by pathological examination underwent shear wave elastography (SWE). We first observed if there was a stiff rim sign. Then the shell around the breast lesion on SWE was automatically drawn by machine, with width of 1mm, 2mm and 3mm. Elasticity modulus of the lesion and surrounding tissue were recorded, including maximum elasticity (Emax), mean elasticity (Emean), minimum elasticity (Emin) and elasticity ratio (shell/lesion ratio). The optimal thresholds of elasticity modulus were calculated according to receiver operating characteristic (ROC) curve. Results There were 75 malignant lesions and 124 benign lesions. The average Emax, Emean of lesion and shell were significantly higher in the malignant group than in the benign group (P<0.05). The optimal cut-off value of Emax for diagnosing malignant lesion was 101.7 Kpa, with a sensitivity of 66.3% and specificity of 87.9%. The optimal cut-off value of Emean was 29.1 Kpa, with a sensitivity of 65.3% and specificity of 79.8%. The stiff rim sign had a highest diagnostic performance for malignancy than other elastic parameters, with an accuracy of 88.4%. However, measuring peritumoral tissue stiffness can achieve a relatively high sensitivity, whereas specificity was not improved significantly. Conclusion The stiffness of tissue surrounding breast malignancy was significantly higher than benign lesion. Stiff rim sign has the potential to improve the diagnostic performance of breast lesions.

Download Full-text

BGM-Net: Boundary-Guided Multiscale Network for Breast Lesion Segmentation in Ultrasound

Frontiers in Molecular Biosciences ◽

10.3389/fmolb.2021.698334 ◽

2021 ◽

Vol 8 ◽

Author(s):

Yunzhu Wu ◽

Ruoxin Zhang ◽

Lei Zhu ◽

Weiming Wang ◽

Shengwen Wang ◽

...

Keyword(s):

Breast Lesion ◽

Speckle Noise ◽

Breast Ultrasound ◽

Ultrasound Images ◽

Lesion Segmentation ◽

Low Contrast ◽

Feature Enhancement ◽

Boundary Map ◽

Weak Boundaries ◽

Feature Pyramid

Automatic and accurate segmentation of breast lesion regions from ultrasonography is an essential step for ultrasound-guided diagnosis and treatment. However, developing a desirable segmentation method is very difficult due to strong imaging artifacts e.g., speckle noise, low contrast and intensity inhomogeneity, in breast ultrasound images. To solve this problem, this paper proposes a novel boundary-guided multiscale network (BGM-Net) to boost the performance of breast lesion segmentation from ultrasound images based on the feature pyramid network (FPN). First, we develop a boundary-guided feature enhancement (BGFE) module to enhance the feature map for each FPN layer by learning a boundary map of breast lesion regions. The BGFE module improves the boundary detection capability of the FPN framework so that weak boundaries in ambiguous regions can be correctly identified. Second, we design a multiscale scheme to leverage the information from different image scales in order to tackle ultrasound artifacts. Specifically, we downsample each testing image into a coarse counterpart, and both the testing image and its coarse counterpart are input into BGM-Net to predict a fine and a coarse segmentation maps, respectively. The segmentation result is then produced by fusing the fine and the coarse segmentation maps so that breast lesion regions are accurately segmented from ultrasound images and false detections are effectively removed attributing to boundary feature enhancement and multiscale image information. We validate the performance of the proposed approach on two challenging breast ultrasound datasets, and experimental results demonstrate that our approach outperforms state-of-the-art methods.

Download Full-text