|
|
基于深度学习的乳房MRI体积分割框架
|
Abstract:
乳腺癌是女性常见恶性肿瘤之一，严重威胁女性健康。在乳腺癌手术中，准确测量乳房和切除组织的体积对于手术规划和乳腺重建至关重要。本研究构建了一个基于深度学习的分割框架，用于乳房和切除组织的MRI体积分割。该框架不仅展现了良好的分割精度，还涵盖了偏置场矫正这一关键预处理步骤。我们收集并手动标注了一个包含47例患者的MRI数据集，这些数据涵盖了不同的年龄、乳房大小和四类采集参数。在交叉验证中，U-Net网络在全乳分割和切除组织分割任务中表现最佳，平均Dice系数分别为96.54和92.37。在测试集上，U-Net网络同样展现了优异的分割效果，平均Dice系数分别为94.23和84.53。实验结果表明，所提出的框架能够精准且高效地量化全乳体积和切除组织体积，为临床乳腺手术提供数据支持。
Breast cancer is one of the most common malignant tumors in women, which seriously threatens women’s health. In breast cancer surgery, accurate measurement of breast and excised tissue volume is critical for surgical planning and breast reconstruction. This study developed a deep learning based segmentation framework for MRI volume segmentation of breasts and excised tissues. This framework not only demonstrates good segmentation accuracy, but also covers the key preprocessing step of bias field correction. We collected and manually annotated an MRI dataset containing 47 patients, covering different ages, breast sizes, and four types of acquisition parameters. In cross validation, the U-Net network performed the best in both whole milk segmentation and excised tissue segmentation tasks, with average Dice coefficients of 96.54 and 92.37, respectively. On the test set, the U-Net network also demonstrated excellent segmentation performance, with average Dice coefficients of 94.23 and 84.53, respectively. The experimental results indicate that the proposed framework can accurately and efficiently quantify total breast volume and excised tissue volume, providing data support for clinical breast surgery.
| [1] | Giaquinto, A.N., Sung, H., Miller, K.D., Kramer, J.L., Newman, L.A., Minihan, A., et al. (2022) Breast Cancer Statistics, 2022. CA: A Cancer Journal for Clinicians, 72, 524-541. https://doi.org/10.3322/caac.21754 |
| [2] | Lovelace, D.L., McDaniel, L.R. and Golden, D. (2019) Long‐Term Effects of Breast Cancer Surgery, Treatment, and Survivor Care. Journal of Midwifery & Women's Health, 64, 713-724. https://doi.org/10.1111/jmwh.13012 |
| [3] | Burguin, A., Diorio, C. and Durocher, F. (2021) Breast Cancer Treatments: Updates and New Challenges. Journal of Personalized Medicine, 11, Article No. 808. https://doi.org/10.3390/jpm11080808 |
| [4] | Kaidar-Person, O., Offersen, B.V., Boersma, L.J., de Ruysscher, D., Tramm, T., Kühn, T., et al. (2021) A Multidisciplinary View of Mastectomy and Breast Reconstruction: Understanding the Challenges. The Breast, 56, 42-52. https://doi.org/10.1016/j.breast.2021.02.004 |
| [5] | Ilonzo, N., Tsang, A., Tsantes, S., Estabrook, A. and Thu Ma, A.M. (2017) Breast Reconstruction after Mastectomy: A Ten-Year Analysis of Trends and Immediate Postoperative Outcomes. The Breast, 32, 7-12. https://doi.org/10.1016/j.breast.2016.11.023 |
| [6] | Cordeiro, P.G. (2008) Breast Reconstruction after Surgery for Breast Cancer. New England Journal of Medicine, 359, 1590-1601. https://doi.org/10.1056/nejmct0802899 |
| [7] | Wei, D., Weinstein, S., Hsieh, M., Pantalone, L. and Kontos, D. (2019) Three-Dimensional Whole Breast Segmentation in Sagittal and Axial Breast MRI with Dense Depth Field Modeling and Localized Self-Adaptation for Chest-Wall Line Detection. IEEE Transactions on Biomedical Engineering, 66, 1567-1579. https://doi.org/10.1109/tbme.2018.2875955 |
| [8] | Boyd, N.F., Guo, H., Martin, L.J., Sun, L., Stone, J., Fishell, E., et al. (2007) Mammographic Density and the Risk and Detection of Breast Cancer. New England Journal of Medicine, 356, 227-236. https://doi.org/10.1056/nejmoa062790 |
| [9] | Wang, L., Platel, B., Ivanovskaya, T., Harz, M. and Hahn, H.K. (2012) Fully Automatic Breast Segmentation in 3D Breast MRI. 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI), Barcelona, 2-5 May 2012, 1024-1027. https://doi.org/10.1109/isbi.2012.6235732 |
| [10] | Wu, S., Weinstein, S.P., Conant, E.F., Schnall, M.D. and Kontos, D. (2013) Automated Chest Wall Line Detection for Whole‐Breast Segmentation in Sagittal Breast MR Images. Medical Physics, 40, Article ID: 042301. https://doi.org/10.1118/1.4793255 |
| [11] | Ivanovska, T., Laqua, R., Wang, L., Liebscher, V., Völzke, H. and Hegenscheid, K. (2014) A Level Set Based Framework for Quantitative Evaluation of Breast Tissue Density from MRI Data. PLOS ONE, 9, e112709. https://doi.org/10.1371/journal.pone.0112709 |
| [12] | Gubern-Merida, A., Kallenberg, M., Mann, R.M., Marti, R. and Karssemeijer, N. (2015) Breast Segmentation and Density Estimation in Breast MRI: A Fully Automatic Framework. IEEE Journal of Biomedical and Health Informatics, 19, 349-357. https://doi.org/10.1109/jbhi.2014.2311163 |
| [13] | Khalvati, F., Gallego-Ortiz, C., Balasingham, S. and Martel, A.L. (2015) Automated Segmentation of Breast in 3-D MR Images Using a Robust Atlas. IEEE Transactions on Medical Imaging, 34, 116-125. https://doi.org/10.1109/tmi.2014.2347703 |
| [14] | Lin, M., Chen, J., Wang, X., Chan, S., Chen, S. and Su, M. (2013) Template‐Based Automatic Breast Segmentation on MRI by Excluding the Chest Region. Medical Physics, 40, Article ID: 122301. https://doi.org/10.1118/1.4828837 |
| [15] | Martel, A.L., Gallego-Ortiz, C. and Lu, Y. (2016) Breast Segmentation in MRI Using Poisson Surface Reconstruction Initialized with Random Forest Edge Detection. Medical Imaging 2016: Image Processing, 9784, 351-356. https://doi.org/10.1117/12.2214416 |
| [16] | Ronneberger, O., Fischer, P. and Brox, T. (2015) U-net: Convolutional Networks for Biomedical Image Segmentation. Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference, Munich, 5-9 October 2015, 234-241. https://doi.org/10.1007/978-3-319-24574-4_28 |
| [17] | Dalmış, M.U., Litjens, G., Holland, K., Setio, A., Mann, R., Karssemeijer, N., et al. (2017) Using Deep Learning to Segment Breast and Fibroglandular Tissue in MRI Volumes. Medical Physics, 44, 533-546. https://doi.org/10.1002/mp.12079 |
| [18] | Zhang, Y., Chen, J., Chang, K., Park, V.Y., Kim, M.J., Chan, S., et al. (2019) Automatic Breast and Fibroglandular Tissue Segmentation in Breast MRI Using Deep Learning by a Fully-Convolutional Residual Neural Network U-Net. Academic Radiology, 26, 1526-1535. https://doi.org/10.1016/j.acra.2019.01.012 |
| [19] | Ma, X., Wang, J., Zheng, X., Liu, Z., Long, W., Zhang, Y., et al. (2020) Automated Fibroglandular Tissue Segmentation in Breast MRI Using Generative Adversarial Networks. Physics in Medicine & Biology, 65, Article ID: 105006. https://doi.org/10.1088/1361-6560/ab7e7f |
| [20] | Ha, R., Chang, P., Mema, E., Mutasa, S., Karcich, J., Wynn, R.T., et al. (2018) Fully Automated Convolutional Neural Network Method for Quantification of Breast MRI Fibroglandular Tissue and Background Parenchymal Enhancement. Journal of Digital Imaging, 32, 141-147. https://doi.org/10.1007/s10278-018-0114-7 |
| [21] | Liu, Y., Yang, Y., Jiang, W., Wang, T. and Lei, B. (2021) 3D Deep Attentive U-Net with Transformer for Breast Tumor Segmentation from Automated Breast Volume Scanner. 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 31 October-4 November 2021, 4011-4014. https://doi.org/10.1109/embc46164.2021.9629523 |
| [22] | Crespi, L., Loiacono, D. and Sartori, P. (2022) Are 3D Better than 2D Convolutional Neural Networks for Medical Imaging Semantic Segmentation? 2022 International Joint Conference on Neural Networks (IJCNN), Padua, 18-23 July 2022, 1-8. https://doi.org/10.1109/ijcnn55064.2022.9892850 |
| [23] | Kayar, R. and Çilengiroğlu, Ö.V. (2015) Breast Volume Asymmetry Value, Ratio, and Cancer Risk. Breast Cancer: Basic and Clinical Research, 9, 87-92. https://doi.org/10.4137/bcbcr.s32789 |
| [24] | Dovrou, A., Nikiforaki, K., Zaridis, D., Manikis, G.C., Mylona, E., Tachos, N., et al. (2023) A Segmentation-Based Method Improving the Performance of N4 Bias Field Correction on T2weighted MR Imaging Data of the Prostate. Magnetic Resonance Imaging, 101, 1-12. https://doi.org/10.1016/j.mri.2023.03.012 |
| [25] | Fang, L. and Wang, X. (2022) Brain Tumor Segmentation Based on the Dual-Path Network of Multi-Modal MRI Images. Pattern Recognition, 124, Article ID: 108434. https://doi.org/10.1016/j.patcog.2021.108434 |
| [26] | Ullah, F., Ansari, S.U., Hanif, M., Ayari, M.A., Chowdhury, M.E.H., Khandakar, A.A., et al. (2021) Brain MR Image Enhancement for Tumor Segmentation Using 3D U-Net. Sensors, 21, Article No. 7528. https://doi.org/10.3390/s21227528 |
| [27] | Mengqiao, W., Jie, Y., Yilei, C. and Hao, W. (2017) The Multimodal Brain Tumor Image Segmentation Based on Convolutional Neural Networks. 2017 2nd IEEE International Conference on Computational Intelligence and Applications (ICCIA), Beijing, 8-11 September 2017, 336-339. https://doi.org/10.1109/ciapp.2017.8167234 |
| [28] | Saman, S. and Narayanan, S.J. (2021) Active Contour Model Driven by Optimized Energy Functionals for MR Brain Tumor Segmentation with Intensity Inhomogeneity Correction. Multimedia Tools and Applications, 80, 21925-21954. https://doi.org/10.1007/s11042-021-10738-x |
| [29] | Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F. and Adam, H. (2018) Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C. and Weiss, Y., Eds., Computer Vision - ECCV 2018, Springer, 833-851. https://doi.org/10.1007/978-3-030-01234-2_49 |
