Application of MRI segmentation in tumor radiotherapy
Sun Jiawei1,2, Bi Hui3, Ni Xinye1,2
1Affiliated Changzhou No.2 People′s Hospital of Nanjing Medical University, Changzhou 213003, China; 2Center of Medical Physics, Nanjing Medical University, Changzhou 213003, China; 3Changzhou University, Changzhou 213164, China
Abstract：Magnetic resonance imaging (MRI) is a technology with no radiation and high resolution of soft tissues. Therefore, MRI-guided radiotherapy has become a hot spot in the field of radiotherapy. It is of great importance to accurately delineate the targets in radiation oncology. Currently, the delineation of targets is mostly completed by manual segmentation, which is time-consuming, subjective and inconsistent. Automatic segmentation can improve the efficiency and consistency without sacrificing the accuracy of segmentation. In this article, the automatic segmentation methods of MRI applied in radiotherapy were reviewed. The goals, challenges and methods of automatic segmentation for different radiotherapy sites including prostate, nasopharyngeal carcinoma, brain tumors and other organs were analyzed and discussed.
[1] Dolz J, Gopinath K, Yuan J, et al. HyperDense-Net:a hyper-densely connected CNN for multi-modal image segmentation[J]. IEEE Trans Med Imaging, 2019,38(5):1116-1126. DOI:10.1109/TMI.2018.2878669. [2] Karimi D, Samei G, Kesch C, et al. Prostate segmentation in MRI using a convolutional neural network architecture and training strategy based on statistical shape models[J]. Int J Comput Assist Radiol Surg, 2018, 13(8):1211-1219. DOI:10.1007/s11548-018-1785-8. [3] Drozdzal M, Chartrand G, Vorontsov E, et al. Learning normalized inputs for iterative estimation in medical image segmentation[J]. Med Image Anal, 2018, 44(1):1-13. DOI:10.1016/j.media.2017.11.005. [4] Wang B, Lei Y, Tian S, et al. Deeply supervised 3D fully convolutional networks with group dilated convolution for automatic MRI prostate segmentation[J]. Med Phys, 2019, 46(4):1707-1718. DOI:10.1002/mp.13416. [5] Yan K, Wang X, Kim J, et al. A propagation-DNN:Deep combination learning of multi-level features for MR prostate segmentation[J]. Compu. Methods Programs Biomed, 2019, 170(1):11-21. DOI:10.1016/j.cmpb.2018.12.031. [6] Jia H, Xia Y, Song Y, et al. 3D APA-Net:3D adversarial pyramid anisotropic convolutional network for prostate segmentation in MR images[J]. IEEE Trans Med Imaging, 2020, 39(2):447-457. DOI:10.1109/TMI.2019.2928056. [7] Wang Y, Zu C, Hu G, et al. Automatic tumor segmentation with deep convolutional neural networks for radiotherapy applications[J]. Neural Process Lett, 2018, 48(3):1323-1334. DOI:10.1007/s11063-017-9759-3. [8] Chen H, Qi Y, Yin Y, et al. MMFNet:a multi-modality MRI fusion network for segmentation of nasopharyngeal carcinoma[J]. Neurocomputing, 2020, 39(1)4:27-40. DOI:10.1016/j.neucom.2020.02.002. [9] Ke L, Deng Y, Xia W, et al. Development of a self-constrained 3D DenseNet model in automatic detection and segmentation of nasopharyngeal carcinoma using magnetic resonance images[J]. Oral Oncol, 2020, 110:104862. DOI:10.1016/j.oraloncology.2020.104862. [10] Jiang Z, Changxing D. Two-stage cascaded U-Net:1st place solution to BraTS challenge 2019 segmentation task[C]. In: MICCAI 2019. Cham:Springer, 2020. [11] Zhao Y, Zhang Y, Liu C. Bag of tricks for 3D MRI brain tumor segmentation[C]. In: MICCAI 2019. Cham:Springer, 2020. [12] Wang F, Jiang R, Zheng L, et al. 3D U-Net based brain tumor segmentation and survival days prediction[C]. In: MICCAI 2019. Cham:Springer, 2020. [13] Vu MH, Nyholm T, Löfstedt T.TuNet:end-to-end hierarchical brain tumor segmentation using cascaded networks[C]. In: MICCAI 2019. Cham:Springer, 2020. [14] Charron O, Lallement A, Jarnet D, et al. Automatic detection and segmentation of brain metastases on multimodal MR images with a deep convolutional neural network[J]. Comput Biol Med, 2018, 95(1):43-54. DOI:10.1016/j.compbiomed.2018.02.004. [15] Xue J, Wang B, Ming Y, et al. Deep learning-based detection and segmentation-assisted management of brain metastases[J]. Neuro-Oncol, 2020, 22(4):505-514. DOI:10.1093/neuonc/noz234. [16] Yang X, Wu N, Cheng G, et al. Automated segmentation of the parotid gland based on atlas registration and machine learning:a longitudinal MRI study in head-and-neck radiation therapy[J]. Int J Radiat Oncol Biol Phys, 2014, 90(5):1225-1233. DOI:10.1016/j.ijrobp.2014.08.350. [17] Wang J, Lu J, Qin G, et al. Technical note:a deep learning-based autosegmentation of rectal tumors in MR images[J]. Med Phys, 2018, 45(6):2560-2564. DOI:10.1002/mp.12918. [18] Fu Y, Mazur TR, Wu X, et al. A novel MRI segmentation method using CNN-based correction network for MRI-guided adaptive radiotherapy[J]. Med Phys, 2018, 45(11):5129-5137. DOI:10.1002/mp.13221. [19] Wang C, Tyagi N, Rimner A, et al. Segmenting lung tumors on longitudinal imaging studies via a patient-specific adaptive convolutional neural network[J]. Radiother Oncol, 2019, 131(1):101-107. DOI:10.1016/j.radonc.2018.10.037. [20] Yao Y, Gou S, Wang M. Segmentation of venous vessel in MRI using transferred convolutional neural network[C]. In:ACM international conference proceeding series, 2019. New York:ACM, 2019. [21] Chen W, Boqiang L, Peng S, et al. S3D-UNet:separable 3D U-Net for brain tumor segmentation[C]. In:Brainles 2018. Cham:Springer, 2019. [22] Seo H, Badiei-Khuzani M, Vasudevan V, et al. Machine learning techniques for biomedical image segmentation:An overview of technical aspects and introduction to state-of-art applications[J]. Med Phys, 2020, 47(5):e148-e167. DOI:10.1002/mp.13649. [23] Akkus Z, Galimzianova A, Hoogi A, et al. Deep learning for brain MRI segmentation:state of the art and future directions[J]. J Digit Imag, 2017, 30(4):449-459. DOI:10.1007/s10278-017-9983-4. [24] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[C]. In:2015 IEEE conference on computer vision and pattern recognition (CVPR). Washington:IEEE, 2015. [25] Ronneberger O, Philipp F. U-Net:convolutional networks for biomedical image segmentation[C]. In:MICCAI 2015. Cham:Springer, 2015. [26] Çiçcekö, Abdulkadir A, Lienkamp S, et al. 3D U-Net:learning dense volumetric segmentation from sparse annotation[C]. In:MICCAI 2016. Cham:Springer,2016. [27] Milletari F, Navab N, Ahmadi S. V-Net:fully convolutional neural networks for volumetric medical image segmentation[C]. In:2016 fourth international conference on 3D vision (3DV). Washington:IEEE, 2016. [28] Xiao X, Lian S, Luo Z, et al. Weighted Res-UNet for high-quality retina vessel segmentation[C]. In:9th International Conference on Information Technology in Medicine and Education (ITME). Washington:IEEE, 2018. [29] Almeida G, Tavares JMRS. Deep learning in radiation oncology treatment planning for prostate cancer:a systematic review[J]. J Med Syst, 2020, 44(10):179. DOI:10.1007/s10916-020-01641-3. [30] Pathmanathan AU, van As NJ, Kerkmeijer L, et al. Magnetic resonance imaging-guided adaptive radiation therapy:a"game changer" for prostate treatment?[J]. Int J Radiat Oncol Biol Phys, 2018, 100(2):361-373. DOI:10.1016/j.ijrobp.2017.10.020. [31] Alvarez C, Martínez F, Romero E. A multiresolution prostate representation for automatic segmentation in magnetic resonance images[J]. Med Phys, 2017, 44(4):1312-1323. DOI:10.1002/mp.12141. [32] Girum KB, Créhange G, Hussain R, et al. Deep generative model-driven multimodal prostate segmentation in radiotherapy[J]. Lect Notes Comput Sc, 2019, 11850(1):119-127. DOI:10.1007/978-3-030-32486-5_15. [33] Savenije MHF, Maspero M, Sikkes GG, et al. Clinical implementation of MRI-based organs-at-risk auto-segmentation with convolutional networks for prostate radiotherapy[J]. Radiat Oncol, 2020, 15(1):104. DOI:10.1186/s13014-020-01528-0. [34] 王继平,李鑫,陈传喜,等.3D U-net应用于鼻咽癌危及器官自动分割的研究[J]. 医疗卫生装备,2020, 41(11):17-20, 45. DOI:10.19745/j.1003-8868.2020243. Wang JP, Li X, Chen CX, et al. Application of 3D U-net in automatic segmentation of OARs in nasopharyngeal carcinoma[J]. Chin Med Equip J, 2020, 41(1):17-20, 45. DOI:10.19745/j.1003-8868.2020243. [35] Huang W, Chan KL, Zhou J. Region-based nasopharyngeal carcinoma lesion segmentation from MRI using clustering-and classification-based methods with learning[J]. J Digit Imaging, 2013, 26(3):472-482. DOI:10.1007/s10278-012-9520-4. [36] Huang K, Zhao Z, Gong Q, et al. Nasopharyngeal carcinoma segmentation via HMRF-EM with maximum entropy[C]. In:2015 37th annual international conference of the ieee engineering in medicine and biology society (EMBC). Washington:IEEE, 2015. [37] Wang Y, Yu B, Wang L, et al. Tumor segmentation via multi-modality joint dictionary learning[C]. In:ISBI 2018. Washington:IEEE, 2018. [38] Militello C, Rundo L, Vitabile S, et al. Gamma Knife treatment planning:MR brain tumor segmentation and volume measurement based on unsupervised Fuzzy C-Means clustering[J]. Int J Imag Syst Tech, 2015, 25(3):213-225. DOI:10.1002/ima.22139. [39] Rundo L, Militello C, Russo G, et al. GTVcut for neuro-radiosurgery treatment planning:an MRI brain cancer seeded image segmentation method based on a cellular automata model[J]. Nat Comput, 2018, 17(3):521-536. DOI:10.1007/s11047-017-9636-z. [40] Kanas VG, Zacharaki EI, Davatzikos C, et al. A low cost approach for brain tumor segmentation based on intensity modeling and 3D random walker[J]. Biomed Signal Proces, 2015, 22(1):19-30. DOI:10.1016/j.bspc.2015.06.004. [41] Yu Y, Lee D H, Peng S L, et al. Assessment of glioma response to radiotherapy using multiple MRI biomarkers with manual and semiautomated segmentation algorithms[J]. J Neuroimaging, 2016, 26(6):626-634. DOI:10.1111/jon.12354. [42] Chen H, Lu W, Chen M, et al. A recursive ensemble organ segmentation (REOS) framework:application in brain radiotherapy[J]. Phys Med Biol, 2019, 64(2):025015. DOI:10.1088/1361-6560/aaf83c. [43] Wardman K, Prestwich RJD, Gooding MJ, et al. The feasibility of atlas-based automatic segmentation of MRI for H&N radiotherapy planning[J]. J Appl Clin Med Phys, 2016, 17(4):146-154. DOI:10.1120/jacmp.v17i4.6051.
2021, Vol. 30 
