
浏览全部资源
扫码关注微信
西安交通大学第一附属医院放射科,西安 710000
胡佳雯,Email:hujiawen@stu.xjtu.edu.cn,研究方向:神经影像诊断。
张 明,Email:zhangming01@mail.xjtu.edu.cn。
收稿:2025-07-15,
网络出版:2025-11-18,
移动端阅览
胡佳雯,朱瑞婷,张明.深度神经网络联合神经影像学在脑外伤中的研究进展[J].重庆医科大学学报,
Hu Jiawen,Zhu Ruiting,Zhang Ming.Research advances in the application of deep neural network combined with neuroimaging in traumatic brain injury[J].Journal of Chongqing Medical University,
胡佳雯,朱瑞婷,张明.深度神经网络联合神经影像学在脑外伤中的研究进展[J].重庆医科大学学报, DOI:10.13406/j.cnki.cyxb..
Hu Jiawen,Zhu Ruiting,Zhang Ming.Research advances in the application of deep neural network combined with neuroimaging in traumatic brain injury[J].Journal of Chongqing Medical University, DOI:10.13406/j.cnki.cyxb..
脑外伤(traumatic brain injury,TBI)是1种常见且复杂的神经系统损伤,涵盖从轻度到重度多种类型。轻度脑外伤虽多缺乏明显影像学表现,但目前研究表明,早期容易漏诊或误判的边缘系统等特定脑区微小病灶可能与伤后长期认知障碍及精神心理问题有关;重度脑外伤常伴有复杂病灶及扭曲结构,对颅内出血等关键病灶的快速定量影像诊断有较高需求。传统神经影像学在病灶边界分割、微小病灶识别等方面存在明显局限,有限时间内采集图像的方式和图像信息则进一步限制了急诊状态快速检出、微小病灶精准识别的需求。近年来,深度神经网络在医学影像自动识别与分析中的应用迅速发展,为脑外伤的高效诊断与动态管理提供了新的解决方案。本文系统综述了深度神经网络联合神经影像学在脑外伤中的应用进展,重点关注颅内出血自动分割、脑微出血(cerebral microbleeds,CMBs)的精准检测、图像质量提升等关键领域,并展望未来的发展方向。
Traumatic brain injury(TBI) is a common and complex neurological condition encompassing a wide spectrum from mild to severe injuries. Although mild TBI often shows no significant abnormalities on conventional neuroimaging,recent studies have shown that subtle lesions in specific brain regions,including the limbic system,are easily missed or misinterpreted in the early stage and may be associated with long-term cognitive deficits and neuropsychiatric symptoms,and severe TBI typically presents with complex lesions and distorted brain structures,thus requiring rapid and quantitative imaging assessment for critical pathologies such as intracranial hemorrhage. Traditional neuroimaging approaches face significant limitations in accurate lesion boundary delineation and detection of minute abnormalities,and constraints in imaging speed and quality within a limited time further hinder the rapid identification and precise detection of subtle lesions in emergency settings. In recent years,rapid development has been observed in the application of deep neural networks in automated identification and analysis of medical images,offering new solutions for the efficient diagnosis and dynamic management of TBI. This article systematically reviews the current advances in the application of deep neural networks and neuroimaging in TBI,with a particular focus on key areas including automated intracranial hemorrhage segmentation,precise detection of cerebral microbleeds,and image quality enhancement. This article also discusses the future research directions in this field.
刘思恒 , 李 佳 , 彭贤贵 , 等 . 探索Morphogo在多发性骨髓瘤MRD检测中的应用 [J ] . 重庆医科大学学报 , 2022 , 47 ( 8 ): 948 - 952 .
Liu SH , Li J , Peng XG , et al . Application of Morphogo in the detection of minimal residual disease in multiple myeloma [J ] . J Chongqing Med Univ , 2022 , 47 ( 8 ): 948 - 952 .
Huttner HB , Steiner T , Hartmann M , et al . Comparison of ABC/2 estimation technique to computer-assisted planimetric analysis in warfarin-related intracerebral parenchymal hemorrhage [J ] . Stroke , 2006 , 37 ( 2 ): 404 - 408 .
An J , Wendt L , Wiese G , et al . Deep learning-based automated lesion segmentation on mouse stroke magnetic resonance images [J ] . Sci Rep , 2023 , 13 ( 1 ): 13341 .
Emmert-Streib F , Yang Z , Feng H , et al . An introductory review of deep learning for prediction models with big data [J ] . Front Artif Intell , 2020 , 3 : 4 .
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 .
Jiang L , Xie YF , et al . Development and clinical application of automatic reconstruction technologyfor a three-dimensional visualization model of brain tumors [J ] . J Chongqing Med Univ , 2024 , 49 ( 4 ): 471 - 477 .
尹艺晓 , 马金刚 , 张文凯 , 等 . 从U-Net到Transformer:混合模型在医学图像分割中的应用进展 [J ] . 激光与光电子学进展 , 2025 , 62 ( 2 ): 1 - 23 .
Yin YX , Ma JG , Zhang WK , et al . From U-Net to transformer: progress in the application of hybrid models in medical image segmentation [J ] . Laser Optoelectron Prog , 2025 , 62 ( 2 ): 1 - 23 .
Monteiro M , Newcombe VFJ , Mathieu F , et al . Multiclass semantic segmentation and quantification of traumatic brain injury lesions on head CT using deep learning: an algorithm development and multicentre validation study [J ] . Lancet Digit Health , 2020 , 2 ( 6 ): e314 - e322 .
D’Angelo T , Bucolo GM , Kamareddine T , et al . Accuracy and time efficiency of a novel deep learning algorithm for Intracranial Hemorrhage detection in CT Scans [J ] . Radiol Med , 2024 , 129 ( 10 ): 1499 - 1506 .
Inkeaw P , Angkurawaranon S , Khumrin P , et al . Automatic hemorrhage segmentation on head CT scan for traumatic brain injury using 3D deep learning model [J ] . Comput Biol Med , 2022 , 146 : 105530 .
Yao HM , Williamson C , Gryak J , et al . Automated hematoma segmentation and outcome prediction for patients with traumatic brain injury [J ] . Artif Intell Med , 2020 , 107 : 101910 .
Xu Y , Fu QY , Qu MQ , et al . Automated hematoma detection and outcome prediction in patients with traumatic brain injury [J ] . CNS Neurosci Ther , 2024 , 30 ( 11 ): e70119 .
Tran AT , Desser D , Zeevi T , et al . A hybrid transformer-convolutional neural network for segmentation of intracerebral hemorrhage and perihematomal edema on non-contrast head computed tomography (CT) with uncertainty quantification to improve confidence [J ] . Bioengineering , 2024 , 11 ( 12 ): 1274 .
Phaphuangwittayakul A , Guo Y , Ying FL , et al . An optimal deep learning framework for multi-type hemorrhagic lesions detection and quantification in head CT images for traumatic brain injury [J ] . Appl Intell , 2022 , 52 ( 7 ): 7320 - 7338 .
Dou Q , Chen H , Yu LQ , et al . Automatic detection of cerebral microbleeds from MR images via 3D convolutional neural networks [J ] . IEEE Trans Med Imaging , 2016 , 35 ( 5 ): 1182 - 1195 .
Suwalska A , Wang YZ , Yuan ZY , et al . CMB-HUNT: Automatic detection of cerebral microbleeds using a deep neural network [J ] . Comput Biol Med , 2022 , 151 ( Pt A ): 106233 .
Khaffafi B , Khoshakhalgh H , Keyhanazar M , et al . Automatic cerebral microbleeds detection from MR images via multi-channel and multi-scale CNNs [J ] . Comput Biol Med , 2025 , 189 : 109938 .
Kim JH , Noh Y , Lee H , et al . Toward automated detection of microbleeds with anatomical scale localization using deep learning [J ] . Med Image Anal , 2025 , 101 : 103415 .
Wei ZL , Chen XC , Huang JL , et al . Construction of a medical micro-object cascade network for automated segmentation of cerebral microbleeds in susceptibility weighted imaging [J ] . Front Bioeng Biotechnol , 2022 , 10 : 937314 .
Liu SF , Utriainen D , Chai C , et al . Cerebral microbleed detection using Susceptibility Weighted Imaging and deep learning [J ] . Neuroimage , 2019 , 198 : 271 - 282 .
Duan CH , Xiong YQ , Cheng K , et al . Accelerating susceptibility-weighted imaging with deep learning by complex-valued convolutional neural network (ComplexNet): validation in clinical brain imaging [J ] . Eur Radiol , 2022 , 32 ( 8 ): 5679 - 5687 .
Chen C , Zhao LL , Lang Q , et al . A novel detection and classification framework for diagnosing of cerebral microbleeds using transformer and language [J ] . Bioengineering , 2024 , 11 ( 10 ): 993 .
Al-masni MA , Kim WR , Kim EY , et al . Automated detection of cerebral microbleeds in MR images: A two-stage deep learning approach [J ] . NeuroImage Clin , 2020 , 28 : 102464 .
Koschmieder K , Paul MM , van den Heuvel TLA , et al . Automated detection of cerebral microbleeds via segmentation in susceptibility-weighted images of patients with traumatic brain injury [J ] . Neuroimage Clin , 2022 , 35 : 103027 .
Zhao XY , Zang D , Wang S , et al . sTBI-GAN: An adversarial learning approach for data synthesis on traumatic brain segmentation [J ] . Comput Med Imaging Graph , 2024 , 112 : 102325 .
崔津津 , 张颖冬 , 李 响 , 等 . 基于深度学习的低剂量颅脑CT重建对图像质量及辐射剂量的影响 [J ] . 中华放射学杂志 , 2021 , 55 ( 11 ): 1049 - 1054 .
Cui JJ , Zhang YD , Li X , et al . Deep learning-based reconstruction for low-dose brain CT:improvement of image quality and radiation dose reduction [J ] . Chin J Radiol , 2021 , 55 ( 11 ): 1049 - 1054 .
0
浏览量
1
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