基于nnU-Net的乳腺DCE-MR图像中乳房和腺体自动分割
收稿日期: 2021-01-14
网络出版日期: 2021-03-12
基金资助
国家自然科学基金资助项目(81301282);国家自然科学基金资助项目(81471662);上海市科委科技基金资助项目(13DZ2250300)
Automatic Segmentation of Breast and Fibroglandular Tissues in DCE-MR Images Based on nnU-Net
Received date: 2021-01-14
Online published: 2021-03-12
在乳腺动态增强磁共振（DCE-MR）图像中，乳房分割和腺体分割是进行乳腺癌风险评估的关键步骤.为实现在三维脂肪抑制乳腺DCE-MR图像中乳房和腺体的自动分割，本文提出一种基于nnU-Net的自动分割模型，利用U-Net分层学习图像特征的优势，融合深层特征与浅层特征，得到乳房分割和腺体分割结果.同时，基于nnU-Net策略，所使用的模型能根据图像参数自动进行预处理和数据扩增，并动态调整网络结构和参数配置.实验结果表明，在具有多样化参数的三维脂肪抑制乳腺DCE-MR图像数据集上，该模型能准确、有效地实现乳房和腺体分割，平均Dice相似系数分别达到0.969±0.007和0.893±0.054.
关键词： 乳腺动态增强磁共振图像; 乳房分割; 腺体分割; 深度学习; nnU-Net模型
霍璐 , 胡晓欣 , 肖勤 , 顾雅佳 , 褚旭 , 姜娈 . 基于nnU-Net的乳腺DCE-MR图像中乳房和腺体自动分割[J]. 波谱学杂志, 2021 , 38(3) : 367 -380 . DOI: 10.11938/cjmr20212883
Segmentation of whole breast and fibroglandular tissue (FGT) is an important task for quantitative analysis of breast cancer risk in dynamic contrast enhanced magnetic resonance (DCE-MR) images. In this study, an automated segmentation model based on nnU-Net is proposed to segment the whole breast and FGT in 3D fat-suppressed breast DCE-MR images, taking the advantages of hierarchical image features learning, as well as the fusion of deep features and shallow features. The model could automatically perform preprocessing, data augmentation and dynamic adaptation of network configurations with respect to different imaging parameters. Experimental results show that the method could accurately and efficiently segment the whole breast and FGT in the collected dataset of 3D fat-suppressed breast DCE-MR images with variable imaging characteristics, achieving the average Dice similarity coefficients 0.969±0.007 and 0.893±0.054, respectively, for breast and FGT segmentation.
| 1 | BOYD N F , GUO H , MARTIN L J , et al. Mammographic density and the risk and detection of breast cancer[J]. New Eng J Med, 2007, 356 (1): 227- 236. |
| 2 | KLIFA C , CARBALLIDO-GAMIO J , WILMES L , et al. Magnetic resonance imaging for secondary assessment of breast density in a high-risk cohort[J]. Magn Reson Imaging, 2010, 28 (1): 8- 15. |
| 3 | WU S D , WEINSTEIN S P , CONANT E F , et al. Automated chest wall line detection for whole-breast segmentation in sagittal breast MR images[J]. Med Phys, 2013, 40 (4): 042301. |
| 4 | NIE K , CHEN J H , CHAN S , et al. Development of a quantitative method for analysis of breast density based on three-dimensional automated segmentation of breast in 3-D MR images[J]. Med Phys, 2008, 35 (12): 5253- 5262. |
| 5 | GUBERN-MéRIDA A , KALLENBERG M , MANN R M , et al. Breast segmentation and density estimation in breast MRI: A fully automatic framework[J]. IEEE J Biomed Health, 2015, 19 (1): 349- 357. |
| 6 | IVANOVSKA T , LAQUA R , WANG L , et al. A level set based framework for quantitative evaluation of breast tissue density from MRI data[J]. PLoS One, 2014, 9 (11): e112709. |
| 7 | WU S D , WEINSTEIN S P , CONANT E F , et al. Automated fibroglandular tissue segmentation and volumetric density estimation in breast MRI using an atlas-aided fuzzy C-means method[J]. Med Phys, 2013, 40 (12): 122302. |
| 8 | KOREZ R, LIKAR B, PERNU? F, et al. Model-based segmentation of vertebral bodies from MR images with 3D CNNs[C]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2016. Cham, Switzerland: Springer International Publishing, 2016: 433-441. |
| 9 | MOESKOPS P, WOLTERINK J M, VAN DER VELDEN B H M, et al. Deep learning for multi-task medical image segmentation in multiple modalities[C]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2016. Cham, Switzerland: Springer International Publishing, 2016: 478-486. |
| 10 | RODRIGUEZ-RUIZ A, TEUWEN J, CHUNG K, et al. Pectoral muscle segmentation in breast tomosynthesis with deep learning[C]//Medical Imaging 2018: Computer-Aided Diagnosis. Bellingham, WA: SPIE, 2018: 564-570. |
| 11 | ZHANG J , GAO Y Z , PARK S H , et al. Structured learning for 3-D perivascular space segmentation using vascular features[J]. IEEE T Biomed Eng, 2017, 64 (12): 2803- 2812. |
| 12 | CHRIST P, ETTLINGER F, GRüN F, et al. Automatic liver and tumor segmentation of CT and MRI volumes using cascaded fully convolutional neural networks[EB/OL]. (2017-2-23)[2020-12-19]. https://arxiv.org/pdf/1505.04597v1. |
| 13 | RONNEBERGER O, FISCHER P, BROX T. U-Net: Convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015. Cham, Switzerland: Springer International Publishing, 2015: 234-241. |
| 14 | ZHAO S Y , WANG Y J . Classification of Alzheimer's disease patients based on magnetic resonance images and an improved UNet++ model[J]. Chinese J Magn Reson, 2020, 37 (3): 321- 331. |
| 14 | 赵尚义, 王远军. 基于磁共振图像和改进的UNet++模型区分阿尔茨海默症患者和健康人群[J]. 波谱学杂志, 2020, 37 (3): 321- 331. |
| 15 | KALLENBERG M , PETERSEN K , NIELSEN M , et al. Unsupervised deep learning applied to breast density segmentation and mammographic risk scoring[J]. IEEE Trans Med Imaging, 2016, 35 (5): 1322- 1331. |
| 16 | LIU P , ZHONG Y M , WANG L J . Automatic segmentation of right ventricle in cine cardiac magnetic resonance image based on a dense and multi-scale u-net method[J]. Chinese J Magn Reson, 2020, 37 (4): 456- 468. |
| 16 | 刘鹏, 钟玉敏, 王丽嘉. 基于密集多尺度U-net网络的电影心脏磁共振图像右心室自动分割[J]. 波谱学杂志, 2020, 37 (4): 456- 468. |
| 17 | XIAO L , LOU Y K , ZHOU H Y . A U-Net network-based rapid construction of knee models for specific absorption rate estimation[J]. Chinese J Magn Reson, 2020, 37 (2): 144- 151. |
| 17 | 肖亮, 娄煜堃, 周航宇. 用于SAR估计的基于U-Net网络的快速膝关节模型重建[J]. 波谱学杂志, 2020, 37 (2): 144- 151. |
| 18 | ZHANG Y , CHEN J H , CHANG K T , et al. Automatic breast and fibroglandular tissue segmentation in breast MRI using deep learning by a fully-convolutional residual neural network U-Net[J]. Acad Radiol, 2019, 26 (11): 1526- 1535. |
| 19 | DALMI? M U , LITJENS G , HOLLAND K , et al. Using deep learning to segment breast and fibroglandular tissue in MRI volumes[J]. Med Phys, 2017, 44 (12): 533- 546. |
| 20 | PIANTADOSI G, SANSONE M, SANSONE C. Breast segmentation in MRI via U-Net deep convolutional neural networks[C]//Proceedings of 2018 International Conference on Pattern Recognition (ICPR). Piscataway, NJ: IEEE press, 2018: 3917-3922. |
| 21 | JIANG L , HU X X , XIAO Q , et al. Fully automated segmentation of whole breast using dynamic programming in dynamic contrast enhanced MR images[J]. Med Phys, 2017, 44 (6): 2400- 2414. |
| 22 | ISENSEE F, PETERSEN J, KLEIN A, et al. nnU-Net: Self-adapting framework for U-Net-based medical image segmentation[EB/OL]. (2018-9-27)[2020-12-19]. https://arxiv.org/abs/1809.10486v1 |
| 23 | HELLER N , ISENSEE F , MAIER-HEIN K H , et al. The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 challenge[J]. Med Image Anal, 2021, 67, 101821. |
| 24 | MA J, WANG Y X, AN X L, et al. Toward data-efficient learning: A benchmark for COVID-19 CT lung and infection segmentation[J]. Med Phys, 2020. https://doi.org/10.1002/mp.14676. |
| 25 | PAUL S H . Graphics gems Ⅳ[M]. San Francisco: Margan Kaufmann, 1994, 474- 485. |
| 26 | YUSHKEVICH P A , PIVEN J , HAZLETT H C , et al. User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability[J]. NeuroImage, 2006, 31 (3): 1116- 1128. |
| 27 | LóPEZ-LINARES ROMáN K , GARCíA OCA?A M I , LETE URZELAI N , et al. Medical image segmentation using deep learning[J]. Intelligent Systems Reference Library, 2020, 171, 17- 31. |
/
| 〈 |
|
〉 |