Dynamic noise index and segmentation algorithm for breast ultrasound tumor

Haipeng Zou; Xun Gong; Bijie Hu; Jun Luo

doi:10.11834/jig.200245

Ultrasound Image | Views : 0 下载量: 19 CSCD: 0

PDF
Export
Share
Collection
Album

Dynamic noise index and segmentation algorithm for breast ultrasound tumor
Vol. 25, Issue 10, Pages: 2229-2237(2020)
Received：31 May 2020，

Revised：2020-7-7，

Accepted：14 July 2020，

Published：2020-10
DOI： 10.11834/jig.200245
稿件说明：

移动端阅览

DOI：

Haipeng Zou, Xun Gong, Bijie Hu, Jun Luo. Dynamic noise index and segmentation algorithm for breast ultrasound tumor[J]. Journal of Image and Graphics, 2020, 25(10): 2229-2237. DOI： 10.11834/jig.200245.

摘要

目的

深度学习在各种语义分割任务中取得了优异的性能，但需要大量带有准确标注的训练样本。乳腺超声由于其成像特点，导致图像对比度和分辨率低、斑点噪声较高、组织间边界模糊等，这些问题导致精确标注十分困难。超声分割数据集中存在较多非准确的标注，这些数据即标注噪声。若训练集中包含一定量的噪声，将会极大地影响网络的分割准确度。为了解决该问题，提出了一种针对超声图像的动态噪声指数及分割算法，实现在乳腺超声数据包含噪声的情况下肿瘤区域的准确分割。

方法

针对超声图像的噪声特点提出动态噪声指数（dynamic noise index，DNI）；在网络训练过程中实时更新DNI，并在每次迭代结束后计算整个训练集的DNI分布，进而实现对噪声数据的可检测；提出一个改进的损失函数以增强网络噪声检测性能，同时结合DNI降低噪声对训练反向传播的影响。最后本文将动态噪声指数和改进的损失函数联合形成一个噪声容忍框架，该框架可以应用于其他分割网络。

结果

本文将噪声容忍框架和多种分割网络进行结合，并在两个数据集上进行实验。公开数据集的实验结果显示，增加噪声容忍框架的网络相比于原网络各指标提高了8%~12%。本文构建了一个包含1 805幅图像的乳腺超声肿瘤分割数据集，结合噪声容忍框架之后的网络各指标也取得了4%~7%的提升。

结论

本文提出的动态噪声指数及分割算法针对不同噪声比例的训练数据集，对噪声均能有效地抑制，并取得稳定的分割性能。

Abstract

Objective

Breast cancer has become one of the highest mortality rates in women. The incidence rate of breast cancer has been increasing in recent years. Early diagnosis of breast cancer is the key to treatment and control. Clinical data show that early diagnosis can reduce the mortality by 40%. Medical ultrasound has high accuracy

without trauma and radiation to the body

and requires extremely low cost. Therefore

ultrasound is often used as the first choice in medical diagnosis. Computer-aided diagnosis combines the powerful analysis and calculation ability of computers with medical image processing

thereby immensely improving the working efficiency and reducing the missed diagnosis and misdiagnosis. Deep learning has achieved excellent performance in various semantic segmentation tasks

and its accuracy is far beyond the traditional method. A common application of deep learning is focus segmentation. The focus area is the location of the lesion

which is usually part of the entire ultrasound image. Before diagnosis

the focus area is divided as the region of interest. On the one hand

it can reduce the amount of computation to improve the speed of the algorithm. On the other hand

it can reduce the background interference to improve the accuracy of the algorithm. The training of deep learning needs a large number of training samples with accurate labels. The precise location and segmentation of the focus area need to be manually labeled. Breast ultrasound results in low contrast and resolution

high speckle noise

and blurry boundary between tissues because of its imaging characteristics. These problems make accurate labeling extremely difficult. At present

breast ultrasound is the common method for experienced doctors to accurately label the focus area. However

this labor-intensive work aggravates the workload of doctors and seriously affects the diagnosis efficiency of doctors. Thus

studying the automatic location and segmentation of the focus area in ultrasound images is of great significance. Although the ultrasonic segmentation data set marked by doctors is uncleaned many times

many inaccurate marks are found in the data set

which are called mark noise. The training set will immensely affect the accuracy of network segmentation when it contains a certain amount of noise. To solve this problem

this paper proposes a dynamic noise index (DNI) and a novel loss function to achieve the segmentation of breast ultrasound tumor in noisy environment.

Method

In this paper

DNI is proposed to realize the detectability of noise. The DNI is then updated in real time during network training. At the end of each iteration

the DNI distribution of the entire training set is calculated. The detection of noise data is realized through the monitoring of data distribution. This paper proposes an improved loss function to enhance the performance of network noise detection. This loss function combines DNI to reduce the influence of noise on training back propagation. To verify the effectiveness of the algorithm

the DNI and the improved loss function are combined to form a noise tolerance framework. The framework can be applied to all types of segmented networks. The experiment is designed into two datasets

namely

open breast tumor segmentation dataset of Breast Ultrasound Images (DBUI) and Noisy Breast Ultrasound Image Dataset (NBUID). NBUID consists of 1 305 rough labeled breast tumor images. The validation and test sets consist of 500 exact annotation samples. Five hundred samples cover different nodule shapes (round

elliptical

irregular

lobulated

etc.)

different nodule sizes

different nodule boundaries

different internal echoes

and different growth sites. 350 of them are test sets

and 150 are verification sets.

Result

In this paper

the noise tolerance framework is combined with three segmentation networks

namely

U-net

PSPNet

and FastFCN. The test results of DBUI30 show that the network with noise tolerance framework is 8%~12% higher than the original network. This paper constructs a data set of 1 805 images of breast ultrasound tumor segmentation. Combined with the noise tolerance framework

the performance of the network is improved by 4%~7%.

Conclusion

The proposed DNI and segmentation algorithm can effectively suppress noise and achieve stable segmentation performance for training data sets with different noise ratios.

关键词

Keywords

references

Al-Dhabyani W, Gomaa M, Khaled H and Fahmy A. 2020. Dataset of breast ultrasound images. Data in Brief, 28:104863[DOI:10.1016/j.dib.2019.104863]

Chen L C, Zhu Y K, Papandreou G, Schroff F and Adam H. 2018. Encoder-decoder with atrous separable convolution for semantic image segmentation//Proceedings of the 15th European Conference on Computer Vision. Cham: Springer: 833-851[ DOI:10.1007/978-3-030-01234-2_49 http://dx.doi.org/10.1007/978-3-030-01234-2_49 ]

Cheng H D, Shan J, Ju W, Guo Y H and Zhang L. 2010. Automated breast cancer detection and classification using ultrasound images:a survey. Pattern Recognition, 43(1):299-317[DOI:10.1016/j.patcog.2009.05.012]

Goldberger J and Ben-Reuven E. 2016. Training deep neural-networks using a noise adaptation layer[EB/OL].[2020-05-15] . http://www.eng.biu.ac.il/goldbej/files/2012/05/ICLR2017.pdf http://www.eng.biu.ac.il/goldbej/files/2012/05/ICLR2017.pdf

Hu M Y, Han H, Shan S G and Chen X L. 2019a. Multi-label learning from noisy labels with non-linear feature transformation//Proceedings of the 14th Asian Conference on Computer Vision. Cham: Springer: 404-419[ DOI:10.1007/978-3-030-20873-8_26 http://dx.doi.org/10.1007/978-3-030-20873-8_26 ]

Hu W, Huang Y Y, Zhang F and Li R R. 2019b. Noise-tolerant paradigm for training face recognition CNNs//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE: 11879-11888[ DOI:10.1109/CVPR.2019.01216 http://dx.doi.org/10.1109/CVPR.2019.01216 ]

Huang K, Cheng H D, Zhang Y T, Zhang B Y, Xing P and Ning C P. 2018. Medical knowledge constrained semantic breast ultrasound image segmentation//Proceedings of the 24th International Conference on Pattern Recognition. Beijing: IEEE: 1193-1198[ DOI:10.1109/ICPR.2018.8545272 http://dx.doi.org/10.1109/ICPR.2018.8545272 ]

Huang Q H, Huang Y H, Luo Y Z, Yuan F N and Li X L. 2020. Segmentation of breast ultrasound image with semantic classification of superpixels. Medical Image Analysis, 61:101657[DOI:10.1016/j.media.2020.101657]

Krizhevsky A, Sutskever I and Hinton G E. 2012. ImageNet classification with deep convolutional neural networks//Proceedings of the 25th International Conference on Neural Information Processing Systems. Red Hook: ACM: 1097-1105

LeCun Y, Bottou L, Bengio Y and Haffner P. 1998. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278-2324[DOI:10.1109/5.726791]

Lin T Y, Goyal P, Girshick R, He K M and Dollár P. 2017. Focal loss for dense object detection//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy: IEEE: 2999-3007[ DOI:10.1109/ICCV.2017.324 http://dx.doi.org/10.1109/ICCV.2017.324 ]

Liu W Y, Wen Y D, Yu Z D, Li M, Raj B and Song L. 2017. SphereFace: deep hypersphere embedding for face recognition//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE: 6738-6746[ DOI:10.1109/CVPR.2017.713 http://dx.doi.org/10.1109/CVPR.2017.713 ]

Ronneberger O, Fischer P and Brox T. 2015. U-Net: convolutional networks for biomedical image segmentation//Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich: Springer: 234-241[ DOI:10.1007/978-3-319-24574-4_28 http://dx.doi.org/10.1007/978-3-319-24574-4_28 ]

Wu H K, Zhang J G, Huang K Q, Liang K M and Yu Y Z. 2019. FastFCN: rethinking dilated convolution in the backbone for semantic segmentation[EB/OL].[2020-05-15] . http://arxiv.org/pdf/1903.11816.pdf http://arxiv.org/pdf/1903.11816.pdf

Wu X, He R, Sun Z N and Tan T N. 2018. A light CNN for deep face representation with noisy labels. IEEE Transactions on Information Forensics and Security, 13(11):2884-2896[DOI:10.1109/TIFS.2018.2833032]

Yap M H, Pons G, Martí J, Ganau S, Sentís M, Zwiggelaar R, Davison A K and Martí R. 2018. Automated breast ultrasound lesions detection using convolutional neural networks. IEEE Journal of Biomedical and Health Informatics, 22(4):1218-1226[DOI:10.1109/JBHI.2017.2731873]

Yi K and Wu J X. 2019. Probabilistic end-to-end noise correction for learning with noisy labels//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE: 7010-7018[ DOI:10.1109/CVPR.2019.00718 http://dx.doi.org/10.1109/CVPR.2019.00718 ]

Zhang C Y, Bengio S, Hardt M, Recht B and Vinyals O. 2016. Understanding deep learning requires rethinking generalization[EB/OL].[2020-05-15] . https://arxiv.org/pdf/1611.03530.pdf https://arxiv.org/pdf/1611.03530.pdf

Zhao H S, Shi J P, Qi X J, Wang X G and Jia J Y. 2017. Pyramid scene parsing network//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE: 6230-6239[ DOI:10.1109/CVPR.2017.660 http://dx.doi.org/10.1109/CVPR.2017.660 ]

Alert me when the article has been cited

提交

Tooth segmentation network for low-dose CT

Semantic Laplacian pyramids network for multicenter breast tumor segmentation

Classification method for samples that are easy to be confused in breast ultrasound images

Enhanced attention-based joint semantic instance segmentation network for point clouds

Recent progress in rotation-invariant point cloud networks