智能科学与技术学报 ›› 2023, Vol. 5 ›› Issue (3): 293-312.doi: 10.11959/j.issn.2096-6652.202328
余唯一1, 陈涛1, 张军平2, 单洪明1
修回日期:
2023-07-12
出版日期:
2023-09-01
发布日期:
2023-09-26
作者简介:
余唯一(1998- ),女,复旦大学类脑智能科学与技术研究院硕士生,主要研究方向为深度学习和医学图像处理基金资助:
Weiyi YU1, Tao CHEN1, Junping ZHANG2, Hongming SHAN1
Revised:
2023-07-12
Online:
2023-09-01
Published:
2023-09-26
Supported by:
摘要:
脑卒中病灶自动分割方法成为近几年的研究热点。为了全面研究用于MRI脑卒中病灶分割的深度学习方法的现状,针对脑卒中治疗的临床问题,进一步阐述了基于深度学习的病灶分割的研究背景及其挑战性,并介绍脑卒中病灶分割的常用公共数据集(ISLES和ATLAS)。然后,重点阐述了基于深度学习的脑卒中病灶分割方法的创新与进展,从网络结构、训练策略、损失函数这3个角度对研究进展进行了归纳,并且对比了各种方法的优缺点。最后,讨论了该研究存在的困难和挑战以及未来的发展趋势。
中图分类号:
余唯一, 陈涛, 张军平, 等. 基于深度学习的MRI脑卒中病灶分割方法综述[J]. 智能科学与技术学报, 2023, 5(3): 293-312.
Weiyi YU, Tao CHEN, Junping ZHANG, et al. A survey of deep learning-based MRI stroke lesion segmentation methods[J]. Chinese Journal of Intelligent Science and Technology, 2023, 5(3): 293-312.
表2
深度学习用于脑卒中病灶分割的现有方法"
年份 | 方法 | 特点 | 是否公开代码 |
2017年 | EDD Net and MUSCLE Net[ | 提出双阶段训练策略,先获得初步分割结果,再进行细化 | 否 |
2018年 | uResNet[ | 利用残差连接优化卷积模型 | 否 |
2018年 | Res-FCN[ | 利用残差连接优化卷积模型 | 否 |
2019年 | X-Net[ | 提出特征相似度模块以捕获上下文信息 | 是 |
2019年 | D-UNet[ | 设计维度转换模块以融合3D和2D图像特征 | 否 |
2019年 | Multi-path 2.5D CNN[ | 在轴状面、矢状面和冠状面方向上做2D分割后再融合,并进行3D后处理 | 是 |
2019年 | MSDF-Net[ | 将空洞空间金字塔池化用于医学影像分割框架 | 否 |
2019年 | CLCI-Net[ | 1.在UNet结构的编码器和解码器之间嵌入了空洞空间金字塔池化; | 是 |
2.提出跨层特征融合策略以整合各层特征 | |||
2020年 | MI-UNet[ | 利用大变形微分同胚度量映射算法[ | 否 |
2020年 | A 3D+2D CNN approach[ | 先用3D U-net获取病灶概率图,再用2D UNet获得最终预测结果 | 否 |
2020年 | 3D residual CNN[ | 采用“放大&缩小训练策略” | 否 |
2020年 | MUDCap3[ | 用胶囊网络代替卷积层和池化层 | 否 |
2020年 | Multi-task[ | 图像重建和图像分割的多任务学习 | 否 |
2020年 | Hybrid Dice loss[ | 结合Dice损失与BCE损失,应对正负样本不平衡问题 | 否 |
2021年 | DFENet[ | 提出特征融合边界,引导网络进行2D-3D特征融合 | 否 |
2021年 | Variational mode decomposition[ | 利用变分模态分解做预处理 | 否 |
2021年 | ME-Net[ | 1.在UNet结构的编码器和解码器之间嵌入空洞空间金字塔池化; | 否 |
2.提出残差编码器,用于提取高维度特征 | |||
2021年 | Priors from healthy subjects[ | 将健康被试图像作为先验辅助分割 | 否 |
2021年 | MDAN[ | 针对大脑“伪对称”的形状特点设计专门的网络结构 | 否 |
2022年 | 3D UNet[ | 3D医学影像分割 | 是 |
2022年 | e-UNets[ | 设计全局特征注意力模块,以获得全局特征 | 否 |
2022年 | STHarDNet[ | 用HarDNet[ | 否 |
2022年 | AGMR-Net[ | 1.在解码器阶段设计粗糙粒度块注意力模块,应对类内不一致问题; | 否 |
2.设计维度特征融合模块,应对类内不确定问题 | |||
2022年 | METranse[ | 利用4种不同尺度的编码器提取多尺度特征,再利用Transformer进行全局特征建模 | 否 |
2022年 | MAPPING [ | 提出一种新的分割后处理策略 | 是 |
2022年 | MLiRA-Net[61] | 设计多尺度长距离区域关注模块,在多尺度层面提取全局信息 | 否 |
2023年 | CarveMix[ | 随机组合两张医学影像作为数据增强 | 否 |
2023年 | ICI loss[ | 将Dice损失与实例级和实例中心损失结合,以减轻实例不平衡问题 | 是 |
2023年 | TSRL-Net[ | 1.设计粗糙粒度残差学习模块修正残差连接,令解码器更关注于未预测区域;2.提出一种新的目标感知损失,通过调节聚焦因子扩展聚焦样本区域 | 是 |
2023年 | Fine-grained segmentation[ | 将中风影响区域定义为常规定义病变的详细子区域,并据此定义细粒度的分割任务 | 否 |
2023年 | SQMLP-net[ | 同时进行脑卒中病变分割和TICI评级 | 否 |
提出一种新颖的双阶段病灶分割方法,利用CNN和Transformer作为骨架网络: | |||
2023年 | W-Net[ | 1.一阶段利用CNN的局部信息提取能力获得大致病变分割图,第二个阶段利用Transformer的强大全局上下文建模能力对边界进行细致分割; | 否 |
2.设计边界变形模块和边界约束模块来应对模糊边界的苛刻条件 | |||
2023年 | SAN-Net[ | 针对不同中心影像分布差异设计域适应分割算法: | |
1.提出自适应实例归一化(masked adaptive instance normalization,MAIN)算法; | 是 | ||
2.利用梯度反转层迫使UNet编码器使用域分类器学习域不变表示 | |||
2023年 | FAN-Net[ | 针对不同中心影像分布差异,设计域适应分割算法,提出基于傅里叶的自适应标准化模块 | 否 |
表3
深度学习用于脑卒中病灶分割的现有方法在公共数据集上的性能对比"
数据集 | 受试者个数n | 验证方式 | 方法 | 实验结果(Dice系数) |
229 | 留一域法交叉验证 | SAN-Net[ | 0.5711 | |
229 | 留一域法交叉验证 | FAN-Net[ | 0.5591 | |
239 | 六折交叉验证 | W-Net[ | 0.6176 | |
229 | 五折交叉验证 | X-Net[ | 0.4867 | |
54 + 45 | 五折交叉验证 | Multi-path 2.5D CNN[ | 0.62 | |
229 | 五折交叉验证 | MI-UNet[ | 0.5672 | |
229 | 五折交叉验证 | A 3D+2D CNN approach[ | 0.5625 | |
239 | 五折交叉验证 | Hybrid Dice loss[ | 0.5738 | |
229 | 五折交叉验证 | DFENet[ | 0.5457 | |
229 | 五折交叉验证 | MDAN[ | 0.5662 | |
220 | 五折交叉验证 | MLiRA-Net[ | 0.6119 | |
304 | 五折交叉验证 | METranse[ | 0.931 | |
229 | 80%训练、20%测试 | D-UNet[ | 0.5349 | |
ATLAS | 229 | 80%训练、20%测试 | e-UNets[ | 0.592 |
229 | 80%训练、20%测试 | AGMR-Net[ | 0.594 | |
229 | 80%训练、20%测试 | TSRL-Net[ | 0.634 | |
239 | 60%训练、20%验证、20%测试 | Variational mode decomposition[ | 0.6684 | |
229 | 70%训练、30%测试 | MSDF-Net[ | 0.6875 | |
229 | 70%训练、30%测试 | MUDCap3[ | 0.67 | |
229 | 52%训练、18%验证、30%测试 | CLCI-Net[ | 0.581 | |
229 | 52%训练、18%验证、30%测试 | Multi-task[ | 0.518 | |
239 | 76%训练、11%验证、13%测试 | 3D residual CNN[ | 0.64 | |
229 | 80%训练、10%验证、10%测试 | ME-Net[ | 0.6353 | |
220 | 77%训练、23%测试 | Priors from healthy subjects[ | 0.6256 | |
229 | 77%训练、23%测试 | STHarDNet[ | 0.5547 | |
220 | 77%训练、23%测试 | CarveMix[ | 0.6391 | |
220 + 60 | 80%训练、10%验证、10%测试 | Fine-grained segmentation[ | 0.5596 | |
655 | 五折交叉验证 | 3D UNet[ | 0.65 | |
ATLAS R2.0 | 955 | 655训练、300测试 | MAPPING [ | 0.6667 |
955 | 600训练、55验证、300测试 | ICI loss[ | 0.5817 | |
655 | 80%训练、20%测试 | SQMLP-net[ | 0.7098 | |
64 | 五折交叉验证 | AGMR-Net[ | 0.614 | |
ISLES | 64 | 五折交叉验证 | METranse[ | 0.793 |
28 | 五折交叉验证 | TSRL-Net[ | 0.640 |
表4
ATLAS v1.2数据来源(来自文献[68])"
中心信息 | 位置 | 扫描仪 | 患者人数 |
Medical University General Hospital | 中国天津 | GE 750 Discovery | 55 |
University of Tübingen | 德国图宾根 | GE Signa Excite | 34 |
Sunnaas Rehabilitation Hospital | 挪威内索登 | Siemens Trio | 27 |
NORMENT and KG Jebsen Centrefor Psychosis Research | 挪威奥斯陆 | Siemens Trio | 12 |
Department of Psychology | 挪威菲利普斯 | Phillips Achieva | 27 |
Child Mind Institute | 美国纽约 | Siemens Trio | 14 |
Nathan S.Kline Institutefor Psychiatric Research | 美国奥兰治堡 | Siemens Trio | 11 |
University of Texas Medical Branch | 美国加尔维斯顿 | GE 750 Discovery | 35 |
University of Michigan | 美国安娜堡 | Siemens Trio | 14 |
[44] | ZHANG Y , WU J , LIU Y ,et al. A 3d+ 2d cnn approach incorporating boundary loss for stroke lesion segmentation[C]// Proceedings of the 11th International Workshop on Machine Learning in Medical Imaging. Cham:Springer, 2020: 101-110. |
[45] | TOMITA N , JIANG S , MAEDER M E ,et al. Automatic post-stroke lesion segmentation on MR images using 3D residual convolutional neural network[J]. NeuroImage:Clinical, 2020,27:102276. |
[46] | SAHAYAM S , ABIRAMI A , JAYARAMAN U . A novel modified Ushaped 3D capsule network (MUDCap3) for stroke lesion segmentation from brain MRI[C]// Proceedings of the 2020 IEEE 4th International Conference on Information and Communication Technology. Piscataway:IEEE, 2020: 1-6. |
[47] | QI K , GONG Y , LIU X ,et al. Multi-task MR imaging with iterative teacher forcing and re-weighted deep learning[EB]. arXiv preprint, 2020,arXiv:2011.13614. |
[48] | LU Y , ZHOU J H , GUAN C . Minimizing hybrid Dice loss for highly imbalanced 3D neuroimage segmentation[C]// Proceedings of the 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society. Piscataway:IEEE, 2020: 1059-1062. |
[49] | BASAK H , HUSSAIN R , RANA A . DFENet:a novel dimension fusion edge guided network for brain mri segmentation[J]. SN Computer Science, 2021,2: 1-11. |
[50] | PAING M P , TUNGJITKUSOLMUN S , BUI T H ,et al. Automated segmentation of infarct lesions in T1-weighted MRI scans using variational mode decomposition and deep learning[J]. Sensors, 2021,21(6): 1952. |
[51] | ZHANG X , XU H , LIU Y ,et al. A multiple encoders network for stroke lesion segmentation[C]// Proceedings of the 4th Chinese Conference on Pattern Recognition and Computer Vision. Cham:Springer, 2021: 524-535. |
[52] | LIU C , ZENG X , LIANG K ,et al. Improved brain lesion segmentation with anatomical priors from healthy subjects[C]// Proceedings of the 24th International Conference on Medical Image Computing and ComputerAssisted Intervention. Cham:Springer, 2021: 186-195. |
[53] | BAO Q , MI S , GANG B ,et al. MDAN:mirror difference aware network for brain stroke lesion segmentation[J]. IEEE Journal of Biomedical and Health Informatics, 2021,26(4): 1628-1639. |
[54] | VERMA K , KUMAR S , PAYDARFAR D . Automatic segmentation and quantitative assessment of stroke lesions on MR images[J]. Diagnostics, 2022,12(9): 2055. |
[1] | KAMALAKANNAN S , GUDLAVALLETI A S V , GUDLAVALLETI V S M ,et al. Incidence & prevalence of stroke in India:a systematic review[J]. The Indian Journal of Medical Research, 2017,146(2): 175-185. |
[2] | VIRANI S S , ALONSO A , APARICIO H J ,et al. Heart disease and stroke statistics-2021 update:a report from the American heart association[J]. Circulation, 2021,143(8): e254-e743. |
[3] | DONKOR E S . Stroke in the 21st century:a snapshot of the burden,epidemiology and quality of life[J]. Stroke Research and Treatment, 2018,2018: 1-10. |
[4] | WAJNGARTEN M , SILVA G S . Hypertension and stroke:update on treatment[J]. European Cardiology, 2019,14(2): 111-115. |
[5] | YANG F , ZHAO J N , XU H D . Characteristics of hemorrhagic stroke following spine and joint surgeries[J]. BioMed Research International, 2017,2017: 1-5. |
[6] | SAVER J L . Penumbral salvage and thrombolysis outcome:a drop of brain,a week of life[J]. Brain, 2017,140(3): 519-522. |
[7] | EL-KOUSSY M , SCHROTH G , BREKENFELD C ,et al. Imaging of acute ischemic stroke[J]. European Neurology, 2014,72(5-6): 309-316. |
[8] | MAIR G , WARDLAW J M . Imaging of acute stroke prior to treatment:current practice and evolving techniques[J]. The British Journal of Radiology, 2014,87(1040): 20140216. |
[9] | KIM J , CHHOUR P , HSU J ,et al. Use of nanoparticle contrast agents for cell tracking with computed tomography[J]. Bioconjugate Chemistry, 2017,28(6): 1581-1597. |
[10] | VILELA P , ROWLEY H A . Brain ischemia:CT and MRI techniques in acute ischemic stroke[J]. European Journal of Radiology, 2017,96: 162-172. |
[11] | QIU W , KUANG H , TELEG E ,et al. Machine learning for detecting early infarction in acute stroke with non-contrast-enhanced CT[J]. Radiology, 2020,294(3): 638-644. |
[55] | SHIN H , AGYEMAN R , RAFIQ M ,et al. Automated segmentation of chronic stroke lesion using efficient U-Net architecture[J]. Biocybernetics and Biomedical Engineering, 2022,42(1): 285-294. |
[56] | GU Y , PIAO Z , YOO S J . STHarDNet:swin transformer with hardNet for MRI segmentation[J]. Applied Sciences, 2022,12(1): 468. |
[57] | CHAO P , KAO C Y , RUAN Y S ,et al. Hardnet:a low memory traffic network[C]// Proceedings of the 2019 IEEE International Conference on Computer Vision. Piscataway:IEEE, 2019: 3552-3561. |
[58] | DU X , MA K , SONG Y . AGMR-Net:attention-guided multiscale recovery framework for stroke segmentation[J]. Computerized Medical Imaging and Graphics, 2022,101:102120. |
[59] | WANG J , WANG S , LIANG W . METrans:multi-encoder transformer for ischemic stroke segmentation[J]. Electronics Letters, 2022,58(9): 340-342. |
[60] | HUO J , CHEN L , LIU Y ,et al. MAPPING:model average with postprocessing for stroke lesion segmentation[EB]. arXiv preprint, 2022,arXiv:2211.15486. |
[61] | WU Z , ZHANG X , LI F ,et al. Multi-scale long-range interactive and regional attention network for stroke lesion segmentation[J]. Computers and Electrical Engineering, 2022,103:108345. |
[62] | ZHANG X , LIU C , OU N ,et al. CarveMix:a simple data augmentation method for brain lesion segmentation[J]. Neuro Image, 2023,271:120041. |
[63] | RACHMADI M F , POON C , SKIBBE H . Improving segmentation of objects with varying sizes in biomedical images using instance-wise and center-of-instance segmentation loss function[J]. arXiv preprint, 2023,arXiv:2304.06229. |
[64] | LI L , MA K , SONG Y ,et al. TSRL-Net:target-aware supervision residual learning for stroke segmentation[J]. Computers in Biology and Medicine, 2023,159:106840. |
[65] | LEE J , LEE M , LEE J ,et al. Fine-grained brain tissue segmentation for brain modeling of stroke patient[J]. Computers in Biology and Medicine, 2023,153:106472. |
[12] | LIANG K , HAN K , LI X ,et al. Symmetry-enhanced attention network for acute ischemic infarct segmentation with non-contrast CT images[C]// Proceedings of the 24th International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham:Springer, 2021: 432-441. |
[13] | 施俊, 汪琳琳, 王珊珊 ,等. 深度学习在医学影像中的应用综述[J]. 中国图象图形学报, 2020,25(10): 1953-1981. |
SHI J , WANG L L , WANG S S ,et al. Applications of deep learning in medical imaging:a survey[J]. Journal of Image and Graphics, 2020,25(10): 1953-1981. | |
[14] | YEDAVALLI V S , TONG E , MARTIN D ,et al. Artificial intelligence in stroke imaging:current and future perspectives[J]. Clinical Imaging, 2021,69: 246-254. |
[15] | 秦海强, 张亚清, 张婧 ,等. 人工智能在缺血性卒中诊断与治疗中的应用[J]. 中国现代神经疾病杂志, 2021,21(1): 21-24. |
QIN H Q , ZHANG Y Q , ZHANG J ,et al. Application of artificial intelligence in diagnosis and treatment of ischemic stroke[J]. Chinese Journal of Contemporary Neurology and Neurosurgery, 2021,21(1): 21-24. | |
[16] | 于长申, 巫嘉陵 . 人工智能在脑卒中管理中的研究进展[J]. 中国现代神经疾病杂志, 2021,21(1): 14-20. |
YU C S , WU J L . Research progress of artificial intelligence in stroke management[J]. Chinese Journal of Contemporary Neurology and Neurosurgery, 2021,21(1): 14-20. | |
[17] | TYAN Y S , WU M C , CHIN C L ,et al. Ischemic stroke detection system with a computer-aided diagnostic ability using an unsupervised feature perception enhancement method[J]. International Journal of Biomedical Imaging,2014, 2014:947539. |
[18] | KARTHIK R , MENAKA R , JOHNSON A ,et al. Neuroimaging and deep learning for brain stroke detection-a review of recent advancements and future prospects[J]. Computer Methods and Programs in Biomedicine, 2020,197:105728. |
[19] | CASTILLO D , LAKSHMINARAYANAN V , RODRIGUEZ-ALVAREZ M J . MR images,brain lesions and deep learning[J]. Applied Sciences, 2021,11(4): 1675. |
[66] | LIU L , CHANG J , LIANG G ,et al. Simulated quantum mechanicsbased joint learning network for stroke lesion segmentation and TICI grading[J]. IEEE Journal of Biomedical and Health Informatics, 2023,27(7): 3372-3383. |
[67] | WU Z , ZHANG X , LI F ,et al. W-Net:a boundary-enhanced segmentation network for stroke lesions[J]. Expert Systems with Applications, 2023:120637. |
[68] | YU W , HUANG Z , ZHANG J ,et al. SAN-Net:learning generalization to unseen sites for stroke lesion segmentation with self-adaptive normalization[J]. Computers in Biology and Medicine, 2023,156:106717. |
[69] | YU W , LEI Y , SHAN H . FAN-Net:fourier-based adaptive normalization for cross-domain stroke lesion segmentation[J]. arXiv preprint, 2023,arXiv:2304.11557. |
[70] | LECUN Y , BOSER B , DENKER J S ,et al. Backpropagation applied to handwritten zip code recognition[J]. Neural Computation, 1989,1(4): 541-551. |
[71] | LONG J , SHELHAMER E , DARRELL T . Fully convolutional networks for semantic segmentation[C]// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2015: 3431-3440. |
[72] | RONNEBERGER O , FISCHER P , BROX T . U-Net:convolutional networks for biomedical image segmentation[C]// Proceedings of the 18th International Conference on Medical Image Computing and ComputerAssisted Intervention. Cham:Springer, 2015: 234-241. |
[73] | LIU L , CHENG J , QUAN Q ,et al. A survey on U-shaped networks in medical image segmentations[J]. Neurocomputing, 2020,409: 244-258. |
[74] | 罗恺锴, 王婷, 叶芳芳 . 引入注意力机制和多视角融合的脑肿瘤MR图像U-Net分割模型[J]. 中国图象图形学报, 2021,26(9): 2208-2218. |
LUO K K , WANG T , YE F F . U-Net segmentation model of brain tumor MR image based on attention mechanism and multi-view fusion[J]. Journal of Image and Graphics, 2021,26(9): 2208-2218. | |
[75] | NIU Z , ZHONG G , YU H . A review on the attention mechanism of deep learning[J]. Neurocomputing, 2021,452: 48-62. |
[20] | SOUN J E , CHOW D S , NAGAMINE M ,et al. Artificial intelligence and acute stroke imaging[J]. American Journal of Neuroradiology, 2021,42(1): 2-11. |
[21] | MAIER O , MENZE B H , VON DER GABLENTZ J ,et al. ISLES 2015a public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI[J]. Medical Image Analysis, 2017,35: 250-269. |
[22] | LIEW S L , ANGLIN J M , BANKS N W ,et al. A large,open source dataset of stroke anatomical brain images and manual lesion segmentations[J]. Scientific Data, 2018,5(1): 1-11. |
[23] | LIEW S L , LO B P , DONNELLY M R ,et al. A large,curated,opensource stroke neuroimaging dataset to improve lesion segmentation algorithms[J]. Scientific Data, 2022,9(1): 320. |
[24] | LIU X , FAES L , KALE A U ,et al. A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging:a systematic review and meta-analysis[J]. The Lancet Digital Health, 2019,1(6): e271-e297. |
[25] | HUANG S C , PAREEK A , SEYYEDI S ,et al. Fusion of medical imaging and electronic health records using deep learning:a systematic review and implementation guidelines[J]. NPJ Digital Medicine, 2020,3(1): 136. |
[26] | WANG T , LEI Y , FU Y ,et al. A review on medical imaging synthesis using deep learning and its clinical applications[J]. Journal of Applied Clinical Medical Physics, 2021,22(1): 11-36. |
[27] | 陈朝一, 许波, 吴英 ,等. 医学图像处理中的注意力机制研究综述[J]. 计算机工程与应用, 2021,58(5): 23-3. |
CHEN Z Y , XU B , WU Y ,et al. Overview of research on attention mechanism in medical image processing[J]. Computer Engineering and Applications, 2021,58(5): 23-3. | |
[28] | 陈弘扬, 高敬阳, 赵地 ,等. 深度学习与生物医学图像分析2020年综述[J]. 中国图象图形学报, 2021,26(3): 475-486. |
CHEN H Y , GAO J Y , ZHAO D ,et al. Review of the research progress in deep learning and biomedical image analysis till 2020[J]. Journal of Image and Graphics, 2021,26(3): 475-486. | |
[76] | HU J , SHEN L , SUN G . Squeeze-and-excitation networks[C]// Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2018: 7132-7141. |
[77] | WANG X , GIRSHICK R , GUPTA A ,et al. Non-local neural networks[C]// Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2018: 7794-7803. |
[78] | FU J , LIU J , TIAN H ,et al. Dual attention network for scene segmentation[C]// Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2019: 3146-3154. |
[79] | WOO S , PARK J , LEE J Y ,et al. Cbam:convolutional block attention module[C]// Proceedings of the 2018 European Conference on Computer Vision. Cham:Springer, 2018: 3-19. |
[80] | WANG R , FAN J , LI Y . Deep multi-scale fusion neural network for multi-class arrhythmia detection[J]. IEEE Journal of Biomedical and Health Informatics, 2020,24(9): 2461-2472. |
[81] | SINHA A , DOLZ J . Multi-scale self-guided attention for medical image segmentation[J]. IEEE Journal of Biomedical and Health Informatics, 2020,25(1): 121-130. |
[82] | LIANG X , LI N , ZHANG Z ,et al. Incorporating the hybrid deformable model for improving the performance of abdominal CT segmentation via multi-scale feature fusion network[J]. Medical Image Analysis, 2021,73:102156. |
[83] | LIU X , YANG L , CHEN J ,et al. Region-to-boundary deep learning model with multi-scale feature fusion for medical image segmentation[J]. Biomedical Signal Processing and Control, 2022,71:103165. |
[84] | 陈舞, 孙军梅, 李秀梅 . 融合多尺度残差和注意力机制的特发性肺纤维化进展预测[J]. 中国图象图形学报, 2022,27(3): 812-826. |
CHEN W , SUN J M , LI X M . Multi-scale residual and attention mechanism fusion based prediction for the progression of idiopathic pulmonary fibrosis[J]. Journal of Image and Graphics, 2022,27(3): 812-826. | |
[85] | CHEN L C , ZHU Y , PAPANDREOU G ,et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]// Proceedings of the 2018 European Conference on Computer Vision. Cham:Springer, 2018: 801-818. |
[29] | TAJBAKHSH N , JEYASEELAN L , LI Q ,et al. Embracing imperfect datasets:a review of deep learning solutions for medical image segmentation[J]. Medical Image Analysis, 2020,63:101693. |
[30] | LIU X , SONG L , LIU S ,et al. A review of deep-learning-based medical image segmentation methods[J]. Sustainability, 2021,13(3): 1224. |
[31] | FU Y , LEI Y , WANG T ,et al. A review of deep learning based methods for medical image multi-organ segmentation[J]. Physica Medica, 2021,85: 107-122. |
[32] | 冯龙锋, 陈英, 周滔辉 ,等. CT图像肺及肺病变区域分割方法综述[J]. 中国图象图形学报, 2022,27(3): 722-749. |
FENG L F , CHEN Y , ZHOU T H ,et al. Review of human lung and lung lesion regions segmentation methods based on CT images[J]. Journal of Image and Graphics, 2022,27(3): 722-749. | |
[33] | 周涛, 董雅丽, 霍兵强 ,等. U-Net网络医学图像分割应用综述[J]. 中国图象图形学报, 2021,26(9): 2058-2077. |
ZHOU T , DONG Y L , HUO B Q ,et al. U-Net and its applications in medical image segmentation:a review[J]. Journal of Image and Graphics, 2021,26(9): 2058-2077. | |
[34] | CHEN L , BENTLEY P , RUECKERT D . Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks[J]. NeuroImage:Clinical, 2017,15: 633-643. |
[35] | GUERRERO R , QIN C , OKTAY O ,et al. White matter hyperintensity and stroke lesion segmentation and differentiation using convolutional neural networks[J]. NeuroImage:Clinical, 2018,17: 918-934. |
[36] | LIU Z , CAO C , DING S ,et al. Towards clinical diagnosis:automated stroke lesion segmentation on multi-spectral MR image using convolutional neural network[J]. IEEE Access, 2018,6: 57006-57016. |
[37] | QI K , YANG H , LI C ,et al. X-Net:brain stroke lesion segmentation based on depthwise separable convolution and long-range dependencies[C]// Proceedings of the 22th International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham:Springer, 2019: 247-255. |
[86] | ABULNAGA S M , RUBIN J . Ischemic stroke lesion segmentation in CT perfusion scans using pyramid pooling and focal loss[C]// Proceedings of the 4th International Workshop on Brainlesion:Glioma,Multiple Sclerosis,Stroke and Traumatic Brain Injuries. Cham,Springer, 2019: 352-363. |
[87] | LIAO H , TANG Y , FUNKA-LEA G , et al . More knowledge is better:cross-modality volume completion and 3D+ 2D segmentation for intracardiac echocardiography contouring[C]// Proceedings of the 21th International Conference on Medical Image Computing and ComputerAssisted Intervention. Cham:Springer, 2018: 535-543. |
[88] | TRAN D , WANG H , TORRESANI L ,et al. A closer look at spatiotemporal convolutions for action recognition[C]// Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2018: 6450-6459. |
[89] | GAN W , WANG H , GU H ,et al. Automatic segmentation of lung tumors on CT images based on a 2D & 3D hybrid convolutional neural network[J]. The British Journal of Radiology, 2021,94:20210038. |
[90] | USHINSKY A , BARDIS M , GLAVIS-BLOOM J , ,et al. A 3D-2D hybrid U-net convolutional neural network approach to prostate organ segmentation of multiparametric MRI[J]. American Journal of Roentgenology, 2021,216(1): 111-116. |
[91] | HE K , ZHANG X , REN S ,et al. Deep residual learning for image recognition[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2016: 770-778. |
[92] | SHANG W , SOHN K , ALMEIDA D ,et al. Understanding and improving convolutional neural networks via concatenated rectified linear units[C]// Proceedings of the 2016 International Conference on Machine Learning. New York:PMLR, 2016: 2217-2225. |
[93] | SABOUR S , FROSST N , HINTON G E . Dynamic routing between capsules[J]. Advances in Neural Information Processing Systems, 2017,30. |
[94] | HUANG G , LIU Z , VAN DER MAATEN L ,et al. Densely connected convolutional networks[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2017: 4700-4708. |
[95] | LIU Z , LIN Y , CAO Y ,et al. Swin transformer:hierarchical vision transformer using shifted windows[C]// Proceedings of the 2021 IEEE International Conference on Computer Vision. Piscataway:IEEE, 2021: 10012-10022. |
[96] | CHLAP P , MIN H , VANDENBERG N ,et al. A review of medical image data augmentation techniques for deep learning applications[J]. Journal of Medical Imaging and Radiation Oncology, 2021,65(5): 545-563. |
[97] | NALEPA J , MARCINKIEWICZ M , KAWULOK M . Data augmentation for brain-tumor segmentation:a review[J]. Frontiers in Computational Neuroscience, 2019,13:83. |
[98] | ZHANG H , CISSE M , DAUPHIN Y N ,et al. Mixup:beyond empirical risk minimization[EB]. arXiv preprint, 2017,arXiv:1710.09412. |
[99] | YUN S , HAN D , OH S J ,et al. Cutmix:regularization strategy to train strong classifiers with localizable features[C]// Proceedings of the 2019 IEEE International Conference on Computer Vision. Piscataway:IEEE, 2019: 6023-6032. |
[100] | LAHMIRI S . Image characterization by fractal descriptors in variational mode decomposition domain:application to brain magnetic resonance[J]. Physica A:Statistical Mechanics and its Applications, 2016,456: 235-243. |
[101] | GUDIGAR A , RAGHAVENDRA U , CIACCIO E J ,et al. Automated categorization of multi-class brain abnormalities using decomposition techniques with MRI images:a comparative study[J]. IEEE Access, 2019,7: 28498-28509. |
[102] | ACHARYA U R , MEIBURGER K M , FAUST O ,et al. Automatic detection of ischemic stroke using higher order spectra features in brain MRI images[J]. Cognitive Systems Research, 2019,58: 134-142. |
[103] | CHLEMPER J S , CABALLERO J , HAJNAL J ,et al. A deep cascade of convolutional neural networks for dynamic MR image reconstructio[J]. IEEE Transactions on Medical Imaging, 2017,37: 491-503. |
[104] | KERVADEC H , BOUCHTIBA J , DESROSIERS C ,et al. Boundary loss for highly unbalanced segmentation[C]// Proceedings of 2019 International Conference on Medical Imaging with Deep Learning. New York:PMLR, 2019: 285-296. |
[105] | KOFLER F , SHIT S , EZHOV I ,et al. Blob loss:instance imbalance aware loss functions for semantic segmentation[EB]. arXiv preprint, 2022,arXiv:2205.08209. |
[106] | ZHANG H , ZHANG J , LI C ,et al. ALL-Net:anatomical information lesion-wise loss function integrated into neural network for multiple sclerosis lesion segmentation[J]. NeuroImage:Clinical, 2021,32:102854. |
[107] | LIN T Y , GOYAL P , GIRSHICK R ,et al. Focal loss for dense object detection[C]// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway:IEEE, 2017: 2980-2988. |
[108] | PIHUR V , DATTA S , DATTA S . Weighted rank aggregation of cluster validation measures:a monte carlo cross-entropy approach[J]. Bioinformatics, 2007,23(13): 1607-1615. |
[109] | XIE S , TU Z . Holistically-nested edge detection[C]// Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway:IEEE, 2015: 1395-1403. |
[110] | HUANG S W , LIN C T , CHEN S P ,et al. Auggan:cross domain adaptation with gan-based data augmentation[C]// Proceedings of the 2018 European Conference on Computer Vision. Cham:Springer, 2018: 718-731. |
[111] | BISSOTO A , VALLE E , AVILA S . Gan-based data augmentation and anonymization for skin-lesion analysis:a critical review[C]// Proceedings of the 2021 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2021: 1847-1856. |
[112] | ZHOU Y , HE X , HUANG L ,et al. Collaborative learning of semisupervised segmentation and classification for medical images[C]// Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2019: 2079-2088. |
[113] | OLSSON V , TRANHEDEN W , PINTO J ,et al. Classmix:segmentation-based data augmentation for semi-supervised learning[C]// Proceedings of the 2021 IEEE Winter Conference on Applications of Computer Vision. Piscataway:IEEE, 2021: 1369-1378. |
[114] | SINGH A , CHAKRABORTY O , VARSHNEY A ,et al. Semi-supervised action recognition with temporal contrastive learning[C]// Proceedings of the 2021 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2021: 10389-10399. |
[115] | ZHANG X , OU N , LIU C ,et al. Unsupervised brain tumor segmentation with image-based prompts[EB]. arXiv preprint, 2023,arXiv:2304.01472. |
[116] | OU Y , HUANG S X , WONG K K ,et al. BBox-guided segmentor:leveraging expert knowledge for accurate stroke lesion segmentation using weakly supervised bounding box prior[J]. Computerized Medical Imaging and Graphics, 2023:102236. |
[117] | WANG S , CHEN Z , YOU S ,et al. Brain stroke lesion segmentation using consistent perception generative adversarial network[J]. Neural Computing and Applications, 2022,34(11): 8657-8669. |
[118] | CHEN C , DOU Q , CHEN H ,et al. Synergistic image and feature adaptation:towards cross-modality domain adaptation for medical image segmentation[C]// Proceedings of the 2019 AAAI Conference on Artificial Intelligence. CA:AAAI, 2019,33(01): 865-872. |
[119] | LIU L , ZHANG Z , LI S ,et al. S-CUDA:self-cleansing unsupervised domain adaptation for medical image segmentation[J]. Medical Image Analysis, 2021,74:102214. |
[120] | WANG R , CHAUDHARI P , DAVATZIKOS C . Embracing the disharmony in medical imaging:a simple and effective framework for domain adaptation[J]. Medical Image Analysis, 2022,76:102309. |
[121] | LI X , YU L , JIN Y ,et al. Difficulty-aware meta-learning for rare disease diagnosis[C]// Proceedings of the 23th International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham:Springer, 2020: 357-366. |
[122] | LIU Q , CHEN C , QIN J ,et al. Feddg:federated domain generalization on medical image segmentation via episodic learning in continuous frequency space[C]// Proceedings of the 2021 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2021: 1013-1023. |
[123] | SANABRIA A R , ZAMBONELLI F , Ye J . Unsupervised domain adaptation in activity recognition:a GAN-based approach[J]. IEEE Access, 2021,9: 19421-19438. |
[124] | LIU Q , DOU Q , HENG P A . Shape-aware meta-learning for generalizing prostate MRI segmentation to unseen domains[C]// Proceedings of the 23th International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham:Springer, 2020: 475-485. |
[125] | ZHANG P , LI J , WANG Y ,et al. Domain adaptation for medical image segmentation:a meta-learning method[J]. Journal of Imaging, 2021,7(2): 31. |
[126] | ESTEBAN O , BIRMAN D , SCHAER M ,et al. MRIQC:advancing the automatic prediction of image quality in MRI from unseen sites[J]. PLoS One, 2017,12(9): e0184661. |
[127] | REINHOLD J C , DEWEY B E , CARASS A ,et al. Evaluating the impact of intensity normalization on MR image synthesis[C]// Proceedings of the Medical Imaging 2019:Image Processing. Washington:SPIE, 2019,9: 890-898. |
[128] | HAN Y , HUANG G , SONG S ,et al. Dynamic neural networks:a survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021,44(11): 7436-7456. |
[129] | GANIN Y , LEMPITSKY V . Unsupervised domain adaptation by backpropagation[C]// Proceedings of 2015 International Conference on Machine Learning. New York:PMLR, 2015: 1180-1189. |
[130] | GANIN Y , USTINOVA E , AJAKAN H ,et al. Domain-adversarial training of neural networks[J]. The Journal of Machine Learning Research, 2016,17(1): 2096-2030. |
[131] | NG D , LAN X , YAO M M S ,et al. Federated learning:a collaborative effort to achieve better medical imaging models for individual sites that have small labelled datasets[J]. Quantitative Imaging in Medicine and Surgery, 2021,11(2): 852. |
[132] | SHELLER M J , EDWARDS B , REINA G A ,et al. Federated learning in medicine:facilitating multi-institutional collaborations without sharing patient data[J]. Scientific Reports, 2020,10(1): 1-12. |
[133] | SARMA K V , HARMON S , SANFORD T ,et al. Federated learning improves site performance in multicenter deep learning without data sharing[J]. Journal of the American Medical Informatics Association, 2021,28(6): 1259-1264. |
[134] | WANG B , LI G , WU C ,et al. A framework for self-supervised federated domain adaptation[J]. EURASIP Journal on Wireless Communications and Networking, 2022,2022(1): 1-17. |
[135] | YU T , KUMAR S , GUPTA A ,et al. Gradient surgery for multi-task learning[C]// Proceedings of the Advances in Neural Information Processing Systems. Cambridge:MIT Press, 2020,33: 5824-5836. |
[136] | DENG L , LI G , HAN S ,et al. Model compression and hardware acceleration for neural networks:a comprehensive survey[J]. Proceedings of the IEEE, 2020,108(4): 485-532. |
[137] | CHO J H , HARIHARAN B . On the efficacy of knowledge distillation[C]// Proceedings of the 2019 IEEE International Conference on Computer Vision. Piscataway:IEEE, 2019: 4794-4802. |
[138] | BEYER L , ZHAI X , ROYER A ,et al. Knowledge distillation:a good teacher is patient and consistent[C]// Proceedings of the 2022 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2022: 10925-10934. |
[139] | DING X , ZHANG X , MA N ,et al. Repvgg:making vgg-style convnets great again[C]// Proceedings of the 2021 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2021: 13733-13742. |
[140] | WU J , FANG H , ZHANG Y ,et al. Medsegdiff:medical image segmentation with diffusion probabilistic model[EB]. arXiv preprint, 2022,arXiv:2211.00611. |
[38] | ZHOU Y , HUANG W , DONG P ,et al. D-UNet:a dimension-fusion U shape network for chronic stroke lesion segmentation[J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2019,18(3): 940-950. |
[39] | XUE Y , FARHAT F G , BOUKRINA O ,et al. A multi-path 2.5 dimensional convolutional neural network system for segmenting stroke lesions in brain MRI images[J]. NeuroImage:Clinical, 2020,25:102118. |
[40] | LIU X , YANG H , QI K ,et al. MSDF-Net:multi-scale deep fusion network for stroke lesion segmentation[J]. IEEE Access, 2019,7: 178486-178495. |
[41] | YANG H , HUANG W , QI K ,et al. CLCI-Net:cross-level fusion and context inference networks for lesion segmentation of chronic stroke[C]// Proceedings of the 22th International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham:Springer, 2019: 266-274. |
[42] | ZHANG Y , WU J , LIU Y ,et al. MI-UNet:multi-inputs U-net incorporating brain parcellation for stroke lesion segmentation from T1weighted magnetic resonance images[J]. IEEE Journal of Biomedical and Health Informatics, 2020,25(2): 526-535. |
[43] | WU J , TANG X . A large deformation diffeomorphic framework for fast brain image registration via parallel computing and optimization[J]. Neuroinformatics, 2020,18: 251-266. |
[141] | WU J , FU R , FANG H ,et al. Medsegdiff-v2:diffusion based medical image segmentation with transformer[EB]. arXiv preprint, 2023,arXiv:2301.11798. |
[142] | CHEN T , WANG C , SHAN H ,et al. BerDiff:conditional bernoulli diffusion model for medical image segmentation[EB]. arXiv preprint, 2023,arXiv:2304.04429. |
[143] | HE S , BAO R , LI J ,et al. Accuracy of segment-anything model (sam) in medical image segmentation tasks[J]. arXiv preprint, 2023,arXiv:2304.09324. |
[144] | MA J , WANG B . Segment anything in medical images[EB]. arXiv preprint, 2023,arXiv:2304.12306. |
[145] | BUTOI V I , ORTIZ J J G , Ma T ,et al. Universeg:universal medical image segmentation[EB]. arXiv preprint, 2023,arXiv:2304.06131. |
[1] | 项凤涛, 罗俊仁, 谷学强, 苏炯铭, 张万鹏. 群视角下的多智能体强化学习方法综述[J]. 智能科学与技术学报, 2023, 5(3): 313-329. |
[2] | 靳聪, 王洁, 郭子淳, 王晶. 融合音画同步的唇形合成研究[J]. 智能科学与技术学报, 2023, 5(3): 397-405. |
[3] | 缪青海, 王雨桐, 吕宜生, 那晓翔, 王飞跃. McCulloch-Pitts人工神经元模型80周年纪念:思想、方法与意义[J]. 智能科学与技术学报, 2023, 5(2): 133-142. |
[4] | 黄峻, 田永林, 戴星原, 王晓, 平之行. 基于深度学习的自动驾驶多模态轨迹预测方法:现状及展望[J]. 智能科学与技术学报, 2023, 5(2): 180-199. |
[5] | 黄哲, 王永才, 李德英. 3D目标检测方法研究综述[J]. 智能科学与技术学报, 2023, 5(1): 7-31. |
[6] | 罗欣欢, 王奕璇, 李炜, 陈曦. 基于显著性信息的Fit CutMix数据增强算法在医学影像上的应用[J]. 智能科学与技术学报, 2023, 5(1): 58-68. |
[7] | 顾宙瑜, 於跃成, 者甜甜. Rapider-YOLOX:高效的轻量级目标检测网络[J]. 智能科学与技术学报, 2023, 5(1): 92-103. |
[8] | 卢经纬, 程相, 王飞跃. 求解微分方程的人工智能与深度学习方法:现状及展望[J]. 智能科学与技术学报, 2022, 4(4): 461-476. |
[9] | 丛晓峰, 桂杰, 章军. 基于视觉Transformer的多损失融合水下图像增强网络[J]. 智能科学与技术学报, 2022, 4(4): 522-532. |
[10] | 张俊, 许沛东, 陈思远, 高天露, 戴宇欣, 张科, 赵杭, 高杰迈, 白昱阳, 李金星, 张浩然, 李湘, 陈玖香. 物理-数据-知识混合驱动的人机混合增强智能系统管控方法[J]. 智能科学与技术学报, 2022, 4(4): 571-583. |
[11] | 陈妍, 罗雪琴, 梁伟, 谢永芳. 基于情感信息融合注意力机制的抑郁症识别[J]. 智能科学与技术学报, 2022, 4(4): 600-609. |
[12] | 张永强, 宋美霖, 刘天虎, 满梦华. 混合骨骼特征的三帧间差分手势识别方法研究[J]. 智能科学与技术学报, 2022, 4(4): 592-599. |
[13] | 覃缘琪, 季青原, 葛俊, 戴星原, 陈圆圆, 王晓. 城市交通路网动态短时推理与精准预测研究[J]. 智能科学与技术学报, 2022, 4(3): 380-395. |
[14] | 栗仁武, 张凌霄, 高林, 李淳芃, 蒋浩. 基于点云的类级别物体姿态估计[J]. 智能科学与技术学报, 2022, 4(2): 246-254. |
[15] | 李琳辉, 周彬, 任威威, 连静. 行人轨迹预测方法综述[J]. 智能科学与技术学报, 2021, 3(4): 399-411. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||
|