Abstract
Purpose
Detecting breast lesions using ultrasound imaging is an important application of computer-aided diagnosis systems. Several automatic methods have been proposed for breast lesion detection and segmentation; however, due to the ultrasound artefacts, and to the complexity of lesion shapes and locations, lesion or tumor segmentation from ultrasound breast images is still an open problem. In this paper, we propose using a lesion detection stage prior to the segmentation stage in order to improve the accuracy of the segmentation.
Methods
We used a breast ultrasound imaging dataset which contained 163 images of the breast with either benign lesions or malignant tumors. First, we used a U-Net to detect the lesions and then used another U-Net to segment the detected region. We could show when the lesion is precisely detected, the segmentation performance substantially improves; however, if the detection stage is not precise enough, the segmentation stage also fails. Therefore, we developed a test-time augmentation technique to assess the detection stage performance.
Results
By using the proposed two-stage approach, we could improve the average Dice score by 1.8% overall. The improvement was substantially more for images wherein the original Dice score was less than 70%, where average Dice score was improved by 14.5%.
Conclusions
The proposed two-stage technique shows promising results for segmentation of breast US images and has a much smaller chance of failure.
This is a preview of subscription content, log in via an institution to check access.
References
Chen CM, Chou YH, Han KC, Hung GS, Tiu CM, Chiou HJ, Chiou SY (2003) Breast lesions on sonograms: computer-aided diagnosis with nearly setting-independent features and artificial neural networks. Radiology 226(2):504–514
Drukker K, Giger ML, Horsch K, Kupinski MA, Vyborny CJ, Mendelson EB (2002) Computerized lesion detection on breast ultrasound. Med Phys 29(7):1438–1446
Gal Y, Ghahramani Z (2016) Dropout as a bayesian approximation: representing model uncertainty in deep learning. In: Proceedings of the 33rd international conference on international conference on machine learning, vol 48, pp 1050–1059
Girshick RB, Donahue J, Darrell T, Malik J (2013) Rich feature hierarchies for accurate object detection and semantic segmentation. In: CoRR. arXiv:1311.2524
Goceri E, Goceri N (2017) Deep learning in medical image analysis: recent advances and future trends. IADIS international conference big data analytics, data mining and computational intelligence 2017 (part of MCCSIS 2017). pp 305–310
Goceri E, Songul C (2018) Biomedical information technology: image based computer aided diagnosis systems. International conference on advanced technologies
Gomez W, Leija L, Alvarenga AV, Infantosi AFC, Pereira WCA (2010) Computerized lesion segmentation of breast ultrasound based on marker-controlled watershed transformation. Med Phys 37(1):82–95
Horsch K, Giger ML, Venta LA, Vyborny CJ (2002) Computerized diagnosis of breast lesions on ultrasound. Med Phys 29(2):157–164
Huang Q, Luo Y, Zhang Q (2017) Breast ultrasound image segmentation: a survey. Int J Comput Assist Radiol Surg 12(3):493–507. https://doi.org/10.1007/s11548-016-1513-1
Huang QH, Lee SY, Liu LZ, Lu MH, Jin LW, Li AH (2012) A robust graph-based segmentation method for breast tumors in ultrasound images. Ultrasonics 52(2):266–275
Leclerc S, Smistad E, Pedrosa J, Ostvik A, Cervenansky F, Espinosa F, Espeland T, Berg EAR, Jodoin P, Grenier T, Lartizien C, D’hooge J, Lovstakken L, Bernard O (2019) Deep learning for segmentation using an open large-scale dataset in 2D echocardiography. IEEE Trans Med Imaging 38(9):2198–2210
Liu B, Cheng H, Huang J, Tian J, Liu J, Tang X (2009) Automated segmentation of ultrasonic breast lesions using statistical texture classification and active contour based on probability distance. Ultrasound Med Biol 35(8):1309–1324. https://doi.org/10.1016/j.ultrasmedbio.2008.12.007
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) SSD: single shot multibox detector. Lecture notes in computer science, pp 21–37
Moon WK, Lo CM, Chen RT, Shen YW, Chang JM, Huang CS, Chen JH, Hsu WW, Chang RF (2014) Tumor detection in automated breast ultrasound images using quantitative tissue clustering. Med Phys 41(4):042901
Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: IEEE conference on computer vision and pattern recognition (CVPR)
Reza SMS, Roy S, Park DM, Pham DL, Butman JA (2019) Cascaded convolutional neural networks for spine chordoma tumor segmentation from MRI. In: Proceedings SPIE 10953, medical imaging 2019: biomedical applications in molecular, structural, and functional imaging
Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer assisted intervention (MICCAI)
Sahiner B, Chan HP, Roubidoux MA, Hadjiiski LM, Helvie MA, Paramagul C, Bailey J, Nees AV, Blane C (2010) Malignant and benign breast masses on 3D US volumetric images: effect of computer-aided diagnosis on radiologist accuracy. Radiology 242:716–724
Shan J, Cheng HD, Wang Y (2012) A novel segmentation method for breast ultrasound images based on neutrosophic l-means clustering. Med Phys 39(9):5669–5682
Shi H, Liu J, Liao H (2019) A classification and segmentation combined two-stage CNN model for automatic segmentation of brainstem. World Congr Med Phys Biomed Eng 2018:159–163
Wang C, MacGillivray T, Macnaught G, Yang G, Newby DE (2018) A two-stage 3D U-Net framework for multi-class segmentation on full resolution image. ArXiv arXiv:1804.04341
Xia C, Li J, Chen X, Zheng A, Zhang Y (2017) What is and what is not a salient object? learning salient object detector by ensembling linear exemplar regressors. In: IEEE conference on computer vision and pattern recognition (CVPR) pp 4399–4407
Yap MH, Pons G, Marti RM, Ganau S, Sentis M, Zwiggelaar R, Davison AK, Marti R (2018) Automated breast ultrasound lesions detection using convolutional neural networks. IEEE J Biomed Health Inf 22:1218–1226
Yu DRC (2004) Watershed segmentation for breast tumor in 2D sonography. Ultrasound Med Biol 30:625–632
Zhao N, Tong N, Ruan D, Sheng K (2019) Fully automated pancreas segmentation with two-stage 3D convolutional neural networks. In: International conference on medical image computing and computer assisted intervention (MICCAI)
Zhou Z, Wu W, Wu S, Tsui PH, Lin CC, Zhang L, Wang T (2014) Semi-automatic breast ultrasound image segmentation based on mean shift and graph cuts. Ultrason Imaging 36(4):256–276
Funding
This work was supported by Natural Science and Engineering Research Council of Canada (NSERC) Discovery Grant RGPIN-04136 and by Richard and Edith Strauss Foundation.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Amiri, M., Brooks, R., Behboodi, B. et al. Two-stage ultrasound image segmentation using U-Net and test time augmentation. Int J CARS 15, 981–988 (2020). https://doi.org/10.1007/s11548-020-02158-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-020-02158-3