
浏览全部资源
扫码关注微信
重庆医科大学附属第一医院神经外科,重庆 400042
刘培龙,Email:891223055@qq.com,研究方向:功能神经外科。
石全红,Email:417149803@qq.com。
收稿:2023-10-14,
修回:2023-12-03,
录用:2024-01-18,
纸质出版:2024-04-28
移动端阅览
刘培龙,蒋理,谢延风,等.脑肿瘤三维可视化模型自动重建技术的开发及临床应用[J].重庆医科大学学报,2024,49(4):471-477.
Liu Peilong,Jiang Li,Xie Yanfeng,et al.Development and clinical application of automatic reconstruction technology for a three-dimensional visualization model of brain tumors[J].Journal of Chongqing Medical University,2024,49(4):471-477.
刘培龙,蒋理,谢延风,等.脑肿瘤三维可视化模型自动重建技术的开发及临床应用[J].重庆医科大学学报,2024,49(4):471-477. DOI: 10.13406/j.cnki.cyxb.003476.
Liu Peilong,Jiang Li,Xie Yanfeng,et al.Development and clinical application of automatic reconstruction technology for a three-dimensional visualization model of brain tumors[J].Journal of Chongqing Medical University,2024,49(4):471-477. DOI: 10.13406/j.cnki.cyxb.003476.
目的
2
研究和开发一种基于头颅多模态核磁共振成像(magnetic resonance imaging,MRI)的影像学数据,自动重建常见脑肿瘤及其周围重要结构的三维可视化模型,并验证其效能及临床适用性。
方法
2
收集常见脑肿瘤头颅多模态核磁共振影像数据,并将其分为训练集、验证集和临床测试集。在训练及验证中,通过3D深度卷积神经网络的算法训练系统自动分割并重建出脑肿瘤及周围结构的能力;在临床测试集中分别用系统及人工手动的方法完成重建,比较本系统自动重建与手动重建之间的重建效率及图像质量。
结果
2
在完成1例肿瘤及周围结构一体化模型重建的时间花费上面,系统用时由人工用时的(5 442±623) s减少至(657±78) s,差异有统计学意义(
t
=27.530,
P
=0.000)。且系统重建出的模型与原始影像学图像具有高度一致性(Dice系数为0.92),系统重建出的图像与人工重建的图像在质量方面并无明显差异。
结论
2
基于多模态影像学数据,运用深度学习等算法对脑肿瘤及周围结构进行自动分割及全自动三维可视化重建,具有准确、高效、可靠的优点,对于脑肿瘤的诊断和手术计划的制定具有重要意义。
Objective
2
To study and develop a three-dimensional visualization model that automatically reconstructs common brain tumors and important structures around them based on multimodal magnetic resonance imaging(MRI) data of the head and to validate its performance and clinical applicability.
Methods
2
Multimodal MRI data of the head with common brain tumors were collected and divided into training set,validation set,and clinical testing set. In the training and verification sets,the system's ability to automatically segment and reconstruct brain tumors and surrounding structures was trained through the algorithm of 3D depth convolutional neural network. In the clinical testing set,the reconstruction was completed by the system and a human,respectively,and the reconstruction efficiency and image quality were compared between the two methods.
Results
2
The time spent on completing the integrated model reconstruction of a tumor and its surrounding structure was significantly reduced from 5442±623 seconds (by a human) to (657±78) seconds(by the system)(
t
=27.530,
P
=0.000). Meanwhile,the model reconstructed by the system had high consistency with the original image(Dice coefficient=0.92),and there was no significant difference in the image quality between the system and human reconstruction.
Conclusion
2
The automatic segmentation and fully automatic 3D visualization reconstruction of brain tumors and their surrounding structures using algorithms such as deep learning based on multimodal imaging data are accurate,efficient,and reliable,which is of great significance in the diagnosis of brain tumors and the formulation of surgical plans.
Dimeco F , Li KW , Casali C , et al . Meningiomas invading the superior sagittal sinus:surgical experience in 108 cases [J ] . Neurosurgery , 2008 , 62 ( 6 ): 1124 - 1135 .
Heros RC . Venous preservation [J ] . J Neurosurg , 2013 , 119 ( 1 ): 71 - 72 .
Jui SL , Zhang SC , Xiong WL , et al . Brain MRI tumor segmentation with 3D intracranial structure deformation features [J ] . IEEE Intell Syst , 2016 , 31 ( 2 ): 66 - 76 .
Akkus Z , Galimzianova A , Hoogi A , et al . Deep learning for brain MRI segmentation:state of the art and future directions [J ] . J Digit Imaging , 2017 , 30 ( 4 ): 449 - 459 .
Virupakshappa , Amarapur B . Cognition-based MRI brain tumor segmentation technique using modified level set method [J ] . Cogn Technol Work , 2019 , 21 ( 3 ): 357 - 369 .
van Garderen KA , van der Voort SR , Versteeg A , et al . EASE:clinical implementation of automated tumor segmentation and volume quantification for adult low-grade glioma [J ] . Front Med , 2021 , 8 : 738425 .
Zhou M , Scott J , Chaudhury B , et al . Radiomics in brain tumor:image assessment,quantitative feature descriptors,and machine-learning approaches [J ] . AJNR Am J Neuroradiol , 2018 , 39 ( 2 ): 208 - 216 .
Shal K , Choudhry MS . Evolution of deep learning algorithms for MRI-based brain tumor image segmentation [J ] . Crit Rev Biomed Eng , 2021 , 49 ( 1 ): 77 - 94 .
Clarke LP , Velthuizen RP , Clark M , et al . MRI measurement of brain tumor response:comparison of visual metric and automatic segmentation [J ] . Magn Reson Imag , 1998 , 16 ( 3 ): 271 - 279 .
Sun JW , Chen W , Peng ST , et al . DRRNet:dense residual refine networks for automatic brain tumor segmentation [J ] . J Med Syst , 2019 , 43 ( 7 ): 221 .
Menze BH , Jakab A , Bauer S , et al . The multimodal brain tumor image segmentation benchmark (BRATS) [J ] . IEEE Trans Med Imaging , 2015 , 34 ( 10 ): 1993 - 2024 .
Kofler F , Berger C , Waldmannstetter D , et al . BraTS toolkit:translating BraTS brain tumor segmentation algorithms into clinical and scientific practice [J ] . Front Neurosci , 2020 , 14 : 125 .
Šteňo A , Hollý V , Mendel P , et al . Navigated 3D-ultrasound versus conventional neuronavigation during awake resections of eloquent low-grade gliomas:a comparative study at a single institution [J ] . Acta Neurochir , 2018 , 160 ( 2 ): 331 - 342 .
Hou XL , Yang DD , Li DJ , et al . A new simple brain segmentation method for extracerebral intracranial tumors [J ] . PLoS One , 2020 , 15 ( 4 ): e0230754 .
Zhang F , Noh T , Juvekar P , et al . SlicerDMRI:diffusion MRI and tractography research software for brain cancer surgery planning and visualization [J ] . JCO Clin Cancer Inform , 2020 , 4 : 299 - 309 .
Isa IS , Sulaiman SN , Mustapha M , et al . Automatic contrast enhancement of brain MR images using Average Intensity Replacement based on Adaptive Histogram Equalization(AIR-AHE) [J ] . Biocybern Biomed Eng , 2017 , 37 ( 1 ): 24 - 34 .
Dill V , Franco AR , Pinho MS . Automated methods for hippocampus segmentation:the evolution and a review of the state of the art [J ] . Neuroinformatics , 2015 , 13 ( 2 ): 133 - 150 .
Saito T , Rehmsmeier M . Precrec:fast and accurate precision-recall and ROC curve calculations in R [J ] . Bioinformatics , 2017 , 33 ( 1 ): 145 - 147 .
Hussain S , Anwar SM , Majid M . Segmentation of glioma tumors in brain using deep convolutional neural network [J ] . Neurocomputing , 2018 , 282 : 248 - 261 .
Yang TJ , Song JK , Li L . A deep learning model integrating SK-TPCNN and random forests for brain tumor segmentation in MRI [J ] . Biocybern Biomed Eng , 2019 , 39 ( 3 ): 613 - 623 .
Li HC , Li A , Wang MH . A novel end-to-end brain tumor segmentation method using improved fully convolutional networks [J ] . Comput Biol Med , 2019 , 108 : 150 - 160 .
Zhao XM , Wu YH , Song GD , et al . A deep learning model integrating FCNNs and CRFs for brain tumor segmentation [J ] . Med Image Anal , 2018 , 43 : 98 - 111 .
Mert A , Kiesel B , Wöhrer A , et al . Introduction of a standardized multimodality image protocol for navigation-guided surgery of suspected low-grade gliomas [J ] . Neurosurg Focus , 2015 , 38 ( 1 ): E4 .
Guo YX , Sun ZP , Liu XJ , et al . Surgical safety distances in the infratemporal fossa:three-dimensional measurement study [J ] . Int J Oral Maxillofac Surg , 2015 , 44 ( 5 ): 555 - 561 .
Zhu ZQ , Chai Y , Yin HP , et al . A novel dictionary learning approach for multi-modality medical image fusion [J ] . Neurocomputing , 2016 , 214 : 471 - 482 .
Kim YI , Lee DH , Cho CB , et al . The usefulness of dual-volume visualization (three-dimensional digital subtraction angiography and cross-sectional imaging) for surgical planning in treating intracranial meningiomas:a case series and technical report [J ] . World Neurosurg , 2019 , 122 : e59 - e66 .
Su JH , Ba YY , Liang ST , et al . Type Ⅲ intraosseous meningioma invading superior sagittal sinus and skull periosteum [J ] . J Craniofac Surg , 2019 , 30 ( 6 ): e561 - e563 .
Fick T , van Doormaal JAM , Tosic L , et al . Fully automatic brain tumor segmentation for 3D evaluation in augmented reality [J ] . Neurosurg Focus , 2021 , 51 ( 2 ): E14 .
Kanaly CW , Ding DL , Mehta AI , et al . A novel method for volumetric MRI response assessment of enhancing brain tumors [J ] . PLoS One , 2011 , 6 ( 1 ): e16031 .
0
浏览量
10
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621