深度学习在医学影像中的研究进展及发展趋势

doi:10.11959/j.issn.2096-0271.2020056

摘要/Abstract

摘要：

医学影像是临床诊断的重要辅助工具，医学影像数据占临床数据的90%，因此，充分挖掘医学影像信息将对临床智能诊断、智能决策以及预后起到重要的作用。随着深度学习的出现，利用深度神经网络分析医学影像已成为目前研究的主流。根据医学影像分析的流程，从医学影像数据的产生、医学影像的预处理，到医学影像的分类预测，充分阐述了深度学习在每一环节的应用研究现状，并根据其面临的问题，对未来的发展趋势进行了展望。

关键词: 深度学习, 医学影像, 图像处理, 人工智能, 卷积神经网络

Abstract:

Medical imaging is an important auxiliary tool for clinical diagnosis.Medical images occupy almost 90% of clinical data.Therefore,mining medical image information will be beneficial for intelligent diagnosis,decision-making and prognosis prediction.With the emergence of deep learning,using deep neural networks to analyze medical images has become a hot research topic.Following the process of medical image analysis,from the image acquisition,the image pre-processing to the classification and prediction,the state-of-the-art applications of deep learning in each step of medical image analysis was elaborated,and according to the existed issues and the challenges,the future perspectives were finally discussed.

Key words: deep learning, medical imaging, image processing, artificial intelligence, convolutional neural network

中图分类号:

TP183

王丽会, 秦永彬. 深度学习在医学影像中的研究进展及发展趋势[J]. 大数据, 2020, 6(6): 83-104.

Lihui WANG, Yongbin QIN. State of the art and future perspectives of the applications of deep learning in the medical image analysis[J]. Big Data Research, 2020, 6(6): 83-104.

图/表 8

图1

图2

图3

图4

表1

表2

图5

表3

参考文献 123

[1]	GONDARA L , . Medical image denoising using convolutional denoising autoencoders[C]// 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW).[S.l.:s.n]. 2016: 241-246.
[2]	CHEN H , ZHANG Y , KALRA M K ,et al. Low-dose CT with a residual encoderdecoder convolutional neural network[J]. IEEE Transactions on Medical Imaging, 2017,36(12): 2524-2535.
[3]	KANG E , MIN J H , YE J C . A deep convolutional neural network using directional wavelets for low‐dose X‐ray CT reconstruction[J]. Medical Physics, 2017,44(10): 360-375.
[4]	YANG Q S , YAN P K , ZHANG Y B ,et al. Low-dose CT image denoising using a generative adversarial network with Wasserstein distance and perceptual loss[J]. IEEE Transactions on Medical Imaging, 2018,37(6): 1348-1357.
[5]	YOU C Y , YANG Q S , SHAN H M ,et al. Structurally-sensitive multi-scale deep neural network for low-dose CT denoising[J]. IEEE Access, 2018,6: 41839-41855.
[6]	MA Y J , WEI B , FENG P ,et al. Low-dose CT image denoising using a generative adversarial network with a hybrid loss function for noise learning[J]. IEEE Access, 2020,8: 67519-67529.
[7]	YIN X R , ZHAO Q L , LIU J ,et al. Domain progressive 3D residual convolution network to improve low-dose CT imaging[J]. IEEE Transactions on Medical Imaging, 2019,38(12): 2903-2913.
[8]	WU D F , GONG K , KIM K ,et al. Consensus neural network for medical imaging denoising with only noisy training samples[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention.[S.l.:s.n]. ], 2019: 741-749.
[9]	GEORGESCU M I , IONESCU R T , VERGA N . Convolutional neural networks with intermediate loss for 3D super-resolution of CT and MRI scans[J]. IEEE Access, 2020,8: 49112-49124.
[10]	OKTAY O , BAI W J , LEE M ,et al. Multiinput cardiac image super-resolution using convolutional neural networks[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham:Springer, 2016: 246-254.
[11]	PHAM C H,DíEZ C T , MEUNIER H ,et al. Multiscale brain MRI super-resolution using deep 3D convolutional networks[J]. Computerized Medical Imaging and Graphics, 2019:77.
[12]	MCDONAGH S , HOU B , ALANSARYET A ,et al. Context-sensitive super-resolution for fast fetal magnetic resonance imaging[C]// Molecular Imaging,Reconstruction and Analysis of Moving Body Organs,and Stroke Imaging and Treatment. Cham:Springer, 2017: 116-126.
[13]	ZHENG Y , ZHEN B , CHEN A ,et al. A hybrid convolutional neural network for super-resolution reconstruction of MR images[J]. Medical Physics, 2020,47(7): 3013-3022.
[14]	ZHAO X L , ZHANG Y L , ZHANG T ,et al. Channel splitting network for single MR image super-resolution[J]. IEEE Transactions on Image Processing, 2019,28(11): 5649-5662.
[15]	TANNO R , WORRALL D E , GHOSH A ,et al. Bayesian image quality transfer with CNNs:exploring uncertainty in dMRI super-resolution[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham:Springer, 2017: 611-619.
[16]	PENG C , LIN W A , LIAO H F ,et al. SAINT:spatially aware interpolation network for medical slice synthesis[C]// The IEEE/CVF Conference on Computer Vision and Pattern Recognition.[S.l.:s.n]. 2020: 7750-7759.
[17]	SHI J , LIU Q P , WANG C F ,et al. Superresolution reconstruction of MR image with a novel residual learning network algorithm[J]. Physics in Medicine ＆Biology, 2018,63(8):85011.
[18]	LYU Q , SHAN H M , STEBER C ,et al. Multi-contrast super-resolution MRI through a progressive network[J]. IEEE Transactions on Medical Imaging, 2020,39(9): 2738-2749.
[19]	YANG Y , SUN J , LI H B ,et al. ADMMCSNet:a deep learning approach for image compressive sensing[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020,42(3): 521-538.
[20]	ADLER J,?KTEM O . Learned primaldual reconstruction[J]. IEEE Transactions on Medical Imaging, 2018,37(6): 1322-1332.
[21]	CHENG J , WANG H F , YING L ,et al. Model learning:primal dual networks for fast MR imaging[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention.[S.l.:s.n]. 2019: 21-29.
[22]	ZHANG H M , DONG B , LIU B D . JSRNet:a deep network for joint spatial-radon domain CT reconstruction from incomplete data[C]// IEEE International Conference on Acoustics,Speech and Signal Processing.[S.l.:s.n]. 2019: 3657-3661.
[23]	LEE D , YOO J , YE J C . Deep residual learning for compressed sensing MRI[C]// 2017 IEEE 14th International Symposium on Biomedical Imaging. Piscataway:IEEE Press, 2017: 15-18.
[24]	LEE D , YOO J , TAK S ,et al. Deep residual learning for accelerated MRI using magnitude and phase networks[J]. IEEE Transactions on Biomedical Engineering, 2018,65(9): 1985-1995.
[25]	SCHLEMPER J , CABALLERO J , HAJNAL J V ,et al. A deep cascade of convolutional neural networks for dynamic MR image reconstruction[J]. IEEE Transactions on Medical Imaging, 2017,37(2): 491-503.
[26]	HAN Y , YOO J , KIM H H ,et al. Deep learning with domain adaptation for accelerated projection‐reconstruction MR[J]. Magnetic Resonance in Medicine, 2018,80(3): 1189-1205.
[27]	EO T , JUN Y , KIM T ,et al. KIKI‐Net:cross‐domain convolutional neural networks for reconstructing undersampled magnetic resonance images[J]. Magnetic Resonance in Medicine, 2018,80(5): 2188-2201.
[28]	BAO L J , YE F Z , CAI C B ,et al. Undersampled MR image reconstruction using an enhanced recursive residual network[J]. Journal of Magnetic Resonance, 2019,305: 232-246.
[29]	DAI Y X , ZHUANG P X . Compressed sensing MRI via a multi-scale dilated residual convolution network[J]. Journal of Magnetic Resonance Imaging, 2019,63: 93-104.
[30]	YANG G , YU S M , DONG H ,et al. DAGAN:deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction[J]. IEEE Transactions on Medical Imaging, 2017,37(6): 1310-1321.
[31]	QUAN T M , NGUYEN-DUC T , JEONG W K . Compressed sensing MRI reconstruction using a generative adversarial network with a cyclic loss[J]. IEEE Transactions on Medical Imaging, 2018,37(6): 1488-1497.
[32]	MARDANI M , GONG E H , CHENG J Y ,et al. Deep generative adversarial neural networks for compressive sensing MRI[J]. IEEE Transactions on Medical Imaging, 2019,38(1): 167-179.
[33]	KITCHEN A , SEAH J . Deep generative adversarial neural networks for realistic prostate lesion MRI synthesis[J]. arXiv preprint,2017,arXiv:1708.00129,
[34]	SCHLEGL T , SEEB?CK P , WALDSTEIN S M ，et al. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery[C]// International Conference on Information Processing in Medical Imaging. Cham:Springer, 2017: 146-157.
[35]	CHUQUICUSMA M J M , HUSSEIN S , BURT J ,et al. How to fool radiologists with generative adversarial networks? A visual turing test for lung cancer diagnosis[C]// 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).[S.l.:s.n]. 2018: 240-244.
[36]	FRID-ADAR M , DIAMANT I , KLANG E ,et al. GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification[J]. Neurocomputing, 2018,321: 321-331.
[37]	BERMUDEZ C , PLASSARD A J , DAVIS L T ,et al. Learning implicit brain MRI manifolds with deep learning[C]// SPIE Medical Imaging Conference.[S.l.:s.n]. 2018.
[38]	BAUR C , ALBARQOUNI S , NAVAB N . MelanoGANs:high resolution skin lesion synthesis with GANs[J]. arXiv preprint,2018,arXiv:1804.04338,
[39]	KORKINOF D , RIJKEN T,O’NEILL M ,et al. High-resolution mammogram synthesis using progressive generative adversarial networks[J]. arXiv preprint,2018,arXiv:1807.03401,
[40]	KANG E , CHANG W , YOO J ,et al. Deep convolutional framelet denosing for lowdose CT via wavelet residual network[J]. IEEE Transactions on Medical Imaging, 2018,37(6): 1358-1369.
[41]	WOLTERINK J M , LEINER T , VIERGEVER M A ,et al. Generative adversarial networks for noise reduction in low-dose CT[J]. IEEE Transactions on Medical Imaging, 2017,36(12): 2536-2545.
[42]	BAHRAMI K , SHI F , ZONG X P ,et al. Reconstruction of 7T-like images from 3T MRI[J]. IEEE Transactions on Medical Imaging, 2016,35(9): 2085-2097.
[43]	BAHRAMI K , REKIK I , SHI F ,et al. Joint reconstruction and segmentation of 7T-like MR images from 3T MRI based on cascaded convolutional neural networks[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention.[S.l.:s.n]. 2017: 764-772.
[44]	NIE D , CAO X H , GAO Y Z ,et al. Estimating CT image from MRI data using 3D fully convolutional networks[C]// Deep Learning and Data Labeling for Medical Applications. Cham:Springer, 2016: 170-178.
[45]	NIE D , TRULLO R , PETITJEAN C ,et al. Medical image synthesis with context-aware generative adversarial networks[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention.[S.l.:s.n]. 2017: 417-425.
[46]	ISOLA P , ZHU J Y , ZHOU T ,et al. Image-to-image translation with conditional adversarial networks[C]// The IEEE Conference on Computer Vision and Pattern Recognition.[S.l.:s.n]. 2017: 1125-1134.
[47]	ZHU J Y , PARK T , ISOLA P ,et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]// The IEEE International Conference on Computer Vision. Piscataway:IEEE Press, 2017: 2223-2232.
[48]	MASPERO M , SAVENIJE M , DINKLA A M ,et al. Dose evaluation of fast synthetic-CT generation using a generative adversarial network for general pelvis MR-only radiotherapy[J]. Physics in Medicine ＆ Biology, 2018,63(18):185001
[49]	CHOI H , LEE D S . Generation of structural MR images from amyloid PET:application to MR-less quantification[J]. Journal of Nuclear Medicine, 2018,59(7): 1111-1117.
[50]	WOLTERINK J M , DINKLA A M , SAVENIJE M H F ,et al. Deep MR to CT synthesis using unpaired data[C]// International Workshop on Simulation and Synthesis in Medical Imaging. Cham:Springer, 2017: 14-23.
[51]	CHARTSIAS A , JOYCE T , DHARMAKUMAR R ,et al. Adversarial image synthesis for unpaired multimodal cardiac data[C]// International Workshop on Simulation and Synthesis in Medical Imaging.[S.l.:s.n]. 2017: 3-13.
[52]	ZHENG J M , CAO J W , WANG Z X ,et al. Semi-automatic synthetic computed tomography generation for abdomens using transfer learning and semisupervised classification[J]. Journal of Medical Imaging and Health Informatics, 2019,9(9): 1878-1886.
[53]	JIN C B , JUNG W , JOO S ,et al. Deep CT to MR synthesis using paired and unpaired data[J]. Sensors, 2019,19(10):2361.
[54]	HIASA Y , OTAKE Y , TAKAO M ,et al. Cross-modality image synthesis from unpaired data using CycleGAN[C]// International Workshop on Simulation and Synthesis in Medical Imaging.[S.l.:s.n]. 2018: 31-41.
[55]	CHENG X , ZHANG L , ZHENG Y F . Deep similarity learning for multimodal medical images[J]. Computer Methods in Biomechanics and Biomedical Engineering:Imaging ＆ Visualization, 2018,6(3): 248-252.
[56]	SEDGHI A , LUO J , MEHRTASH A ,et al. Semi-supervised deep metrics for image registration[J]. arXiv preprint,2018,arXiv:1804.01565.,
[57]	SIMONOVSKY M , GUTIéRREZBECKER B , MATEUS D ，et al. A deep metric for multimodal registration[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention.[S.l.:s.n]. 2016: 10-18.
[58]	MIAO S , WANG Z J , ZHENG Y F ,et al. Real-time 2D/3D registration viaCNN regression[C]// 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI). Piscataway:IEEE Press, 2016: 1430-1434.
[59]	MIAO S , WANG Z J , LIAO R . A CNN regression approach for real-time 2D/3D registration[J]. IEEE Transactions on Medical Imaging, 2016,35(5): 1352-1363.
[60]	SALEHI S S M , KHAN S , ERDOGMUS D ,et al. Real-time deep pose estimation with geodesic loss for image-totemplate rigid registration[J]. IEEE Transactions on Medical Imaging, 2018,38(2): 470-481.
[61]	ZHENG J N , MIAO S , WANG Z J ,et al. Pairwise domain adaptation module for CNN-based 2-D/3-D registration[J]. Journal of Medical Imaging, 2018,5(2):21204.
[62]	YANG X , KWITT R , STYNER M ,et al. Quicksilver:fast predictive image registration–a deep learning approach[J]. Neuroimage, 2017,158: 378-396.
[63]	HU Y P , GIBSON E , GHAVAMI N ,et al. Label-driven weakly-supervised learning for multimodal deformable image registration[C]// 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).[S.l.:s.n]. 2018: 1070-1074.
[64]	HERING A , KUCKERTZ S , HELDMANN S ,et al. Enhancing label-driven deep deformable image registration with local distance metrics for state-ofthe-art cardiac motion tracking[M]// Bildverarbeitung für die Medizin 2019. Wiesbaden:Springer Vieweg, 2019: 309-314.
[65]	CAO X H , YANG J H , WANG L ,et al. Deep learning based inter-modality image registration supervised by intramodality similarity[C]// International Workshop on Machine Learning in Medical Imaging. Cham:Springer, 2018: 55-63.
[66]	FAN J F , CAO X H , YAP P T ,et al. BIRNet:brain image registration using dual-supervised fully convolutional networks[J]. Medical Image Analysis, 2019,54: 193-206.
[67]	JADERBERG M , SIMONYAN K , ZISSERMAN A . Spatial transformer networks[C]// The 28th International Conference on Neural Information Processing Systems. New York:ACM Press, 2015: 2017-2025.
[68]	YOO I , HILDEBRAND D G C , TOBIN W F ,et al. ssEMnet:serial-section electron microscopy image registration using a spatial transformer network with learned features[C]// Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Cham:Springer, 2017: 249-257.
[69]	BALAKRISHNAN G , ZHAO A , SABUNCU M R ,et al. VoxelMorph:a learning framework for deformable medical image registration[J]. IEEE Transactions on Medical Imaging, 2019,38(8): 1788-1800.
[70]	ZHAO A , BALAKRISHNAN G , DURAND F ,et al. Data augmentation using learned transformations for one-shot medical image segmentation[C]// The IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2019: 8543-8553.
[71]	KUANG D , SCHMAH T . FAIM–a ConvNet method for unsupervised 3D medical image registration[M]// Machine Learning in Medical Imaging.[S.l.:s.n]. 2019: 646-654.
[72]	ZHANG J . Inverse-consistent deep networks for unsupervised deformable image registration[J]. arXiv preprint,2018,arXiv1809.03443,
[73]	TANG K , LI Z , TIAN L L ,et al. ADMIR–affine and deformable medical image registration for drug-addicted brain images[J]. IEEE Access, 2020,8: 70960-70968.
[74]	YAN P K , XU S , RASTINEHAD A R ,et al. Adversarial image registration with application for MR and TRUS image fusion[C]// International Workshop on Machine Learning in Medical Imaging. Cham:Springer, 2018: 197-204.
[75]	MAHAPATRA D , ANTONY B , SEDAI S ,et al. Deformable medical image registration using generative adversarial networks[C]// 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). Piscataway:IEEE Press, 2018: 1449-1453.
[76]	TANNER C , OZDEMIR F , PROFANTER R ,et al. Generative adversarial networks for MR-CT deformable image registration[J]. arXiv preprint,2018,arXiv:1807.07349,
[77]	MOESKOPS P , WOLTERINK J M , VAN DER VELDEN B H M ,et al. Deep learning for multi-task medical image segmentation in multiple modalities[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham:Springer, 2016: 478-486.
[78]	LI X M , DOU Q , CHEN H ,et al. 3D multi-scale FCN with random modality voxel dropout learning for intervertebral disc localization and segmentation from multi-modality MR images[J]. Medical Image Analysis, 2018,45: 41-54.
[79]	BI L , KIM J , KUMAR A ,et al. Stacked fully convolutional networks with multichannel learning:application to medical image segmentation[J]. The Visual Computer:International Journal of Computer Graphics, 2017,33(6-8): 1061-1071.
[80]	ZHOU X Y , SHEN M , RIGA C ,et al. Focal FCN:towards small object segmentation with limited training data[J]. arXiv preprint,2017,arXiv:1711.01506,
[81]	ZENG G D , ZHENG G Y . Multistream 3D FCN with multi-scale deep supervision for multi-modality isointense infant brain MR image segmentation[C]// 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). Piscataway:IEEE Press, 2018: 136-140.
[82]	POUDEL R P K , LAMATA P , MONTANA G . Recurrent fully convolutional neural networks for multi-slice MRI cardiac segmentation[C]// Reconstruction,Segmentation,and Analysis of Medical Images. Cham:Springer, 2016: 83-94.
[83]	ZHOU Z W , SIDDIQUEE M M R , TAJBAKHSH N ,et al. Unet++:a nested U-Net architecture for medical image segmentation[C]// Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Cham:Springer, 2018: 3-11.
[84]	MILLETARI F , NAVAB N , AHMADI S A . V-Net:fully convolutional neural networks for volumetric medical image segmentation[C]// 2016 4th International Conference on 3D Vision(3DV). Piscataway:IEEE Press, 2016: 565-571.
[85]	ALOM M Z , HASAN M , YAKOPCIC C ,et al. Recurrent residual convolutional neural network based on U-Net (R2UNet) for medical image segmentation[J]. arXiv preprint,2018,arXiv:1802.06955,
[86]	XIE Y P , ZHANG Z Z , SAPKOTA M ,et al. Spatial clockwork recurrent neural network for muscle perimysium segmentation[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham:Springer, 2016: 185-193.
[87]	AZAD R , ASADI-AGHBOLAGHI M , FATHY M ，et al. Bi-directional ConvLSTM U-net with densley connected convolutions[C]// 2019 IEEE/CVF International Conference on Computer Vision Workshop. Piscataway:IEEE Press, 2019: 406-415.
[88]	CHEN J X , YANG L , ZHANG Y Z ,et al. Combining fully convolutional and recurrent neural networks for 3D biomedical image segmentation[C]// Advances in Neural Information Processing Systems.[S.l.:s.n]. 2016: 3036-3044.
[89]	XUE Y , XU T , ZHANG H ,et al. SegAN:adversarial network with multi-scale L₁ loss for medical image segmentation[J]. Neuroinformatics, 2018,16(3-4): 383-392.
[90]	SINGH V K , RASHWAN H A , ROMANI S ,et al. Breast tumor segmentation and shape classification in mammograms using generative adversarial and convolutional neural network[J]. Expert Systems with Applications, 2020,139:112855.
[91]	ZHANG C Y , SONG Y , LIU S D ,et al. MSGAN:GAN-based semantic segmentation of multiple sclerosis lesions in brain magnetic resonance imaging[C]// 2018 Digital Image Computing:Techniques and Applications (DICTA). Piscataway:IEEE Press, 2018: 1-8.
[92]	TAGHANAKI S A , ZHENG Y F , ZHOU S K ,et al. Combo loss:handling input and output imbalance in multi-organ segmentation[J]. Computerized Medical Imaging and Graphics, 2019,75: 24-33.
[93]	韩冬, 李其花, 蔡巍 ,等. 人工智能在医学影像中的研究与应用[J]. 大数据, 2019,5(1): 39-67.
	HAN D , LI Q H , CAI W ,et al. Research and application of artificial intelligence in medical imaging[J]. Big Data Research, 2019,5(1): 39-67.
[94]	SHANTHI T , SABEENIAN R S . Modified AlexNet architecture for classification of diabetic retinopathy images[J]. Computers＆ Electrical Engineering, 2019,76: 56-64.
[95]	LI X C , SHEN L L , XIE X P ,et al. Multiresolution convolutional networks for chest X-ray radiograph based lung nodule detection[J]. Artificial Intelligence in Medicine, 2020,103:101744.
[96]	MAHBOD A , SCHAEFER G , ELLINGER I ,et al. Fusing fine-tuned deep features for skin lesion classification[J]. Computerized Medical Imaging and Graphics, 2019,71: 19-29.
[97]	CHRISTODOULIDIS S , ANTHIMOPOULOS M , EBNER L ,et al. Multisource transfer learning with convolutional neural networks for lung pattern analysis[J]. IEEE Journal of Biomedical and Health Informatics, 2016,21(1): 76-84.
[98]	HARSONO I W , LIAWATIMENA S , CENGGORO T W . Lung nodule detection and classification from thorax CT-scan using RetinaNet with transfer learning[J]. Journal of King Saud UniversityComputer and Information Sciences,2020:Accepted,
[99]	ALKHALEEFAH M , MA S C , CHANG Y L ,et al. Double-shot transfer learning for breast cancer classification from X-ray images[J]. Applied Sciences, 2020,10(11):3999.
[100]	ABBAS A , ABDELSAMEA M M , GABER M M . Detrac:transfer learning of class decomposed medical images in convolutional neural networks[J]. IEEE Access, 2020,8: 74901-74913.
[101]	OKSUZ I , RUIJSINK B , PUYOLANTóN E ,et al. Automatic CNN-based detection of cardiac MR motion artefacts using k-space data augmentation and curriculum learning[J]. Medical Image Analysis, 2019,55: 136-147.
[102]	GUAN Q J , HUANG Y P , ZHONG Z ,et al. Diagnose like a radiologist:attention guided convolutional neural network for thorax disease classification[J]. arXiv preprint,2018,arXiv:1801.09927..
[103]	GONZáLEZ-DíAZ I . Dermaknet:incorporating the knowledge of dermatologists to convolutional neural networks for skin lesion diagnosis[J]. IEEE Journal of Biomedical and Health Informatics, 2018,23(2): 547-559.
[104]	LI L , XU M , WANG X F ,et al. Attention based glaucoma detection:a largescale database and CNN model[C]// The IEEE Conference on Computer Vision and Pattern Recognition.[S.l.:s.n]. 2019: 10571-10580.
[105]	FANG L Y , WANG C , LI S T ,et al. Attention to lesion:Lesion-aware convolutional neural network for retinal optical coherence tomography image classification[J]. IEEE Transactions on Medical Imaging, 2019,38(8): 1959-1970.
[106]	MITSUHARA M , FUKUI H , SAKASHITA Y ,et al. Embedding human knowledge in deep neural network via attention map[J]. arXiv preprint,2019,arXiv:1905.03540.
[107]	MAJTNER T , YILDIRIM-YAYILGAN S , HARDEBERG J Y . Combining deep learning and hand-crafted features for skin lesion classification[C]// 2016 6th International Conference on Image Processing Theory,Tools and Applications. Piscataway:IEEE Press, 2016: 1-6.
[108]	CHAI Y D , LIU H Y , XU J . Glaucoma diagnosis based on both hidden features and domain knowledge through deep learning models[J]. Knowledge-Based Systems, 2018,161: 147-156.
[109]	XIE Y T , XIA Y , ZHANG J P ,et al. Knowledge-based collaborative deep learning for benign-malignant lung nodule classification on chest CT[J]. IEEE Transactions on Medical Imaging, 2018,38(4): 991-1004.
[110]	YAN K , WANG X S , LU L ,et al. DeepLesion:automated mining of large-scale lesion annotations and universal lesion detection with deep learning[J]. Journal of Medical Imaging, 2018,5(3):36501.
[111]	XUE Z , JAEGER S , ANTANI S ,et al. Localizing tuberculosis in chest radiographs with deep learning[C]// Medical Imaging 2018:Imaging Informatics for Healthcare,Research,and Applications.[S.l.:s.n]. 2018.
[112]	DING J , LI A X , HU Z Q ,et al. Accurate pulmonary nodule detection in computed tomography images using deep convolutional neural networks[C]// International Conference on Medical Image Computing and ComputerAssisted Intervention. Cham:Springer, 2017: 559-567.
[113]	LIN T Y , GOYAL P , GIRSHICK R ,et al. Focal loss for dense object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017,42(2): 318-327.
[114]	LOTTER W , DIAB A R , HASLAM B ,et al. Robust breast cancer detection in mammography and digital breast tomosynthesis using annotationefficient deep learning approach[J]. arXiv preprint,2019,arXiv:1912.11027,
[115]	MERCAN C , BALKENHOL M , VAN DER LAAK J ,et al. From point annotations to epithelial cell detection in breast cancer histopathology using RetinaNet[C]// International Conference on Medical Imaging with Deep Learning-Extended Abstract Track.[S.l.:s.n]. 2019.
[116]	ZLOCHA M , DOU Q , GLOCKER B . Improving RetinaNet for CT lesion detection with dense masks from weak RECIST labels[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention.[S.l.:s.n]. 2019: 402-410.
[117]	SANTERAMO R , WITHEY S , MONTANA G . Longitudinal detection of radiological abnormalities with timemodulated LSTM[C]// Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Cham:Springer, 2018: 326-333.
[118]	SU Y T , LU Y , CHEN M ,et al. Spatiotemporal joint mitosis detection using CNN-LSTM network in time-lapse phase contrast microscopy images[J]. IEEE Access, 2017,5: 18033-18041.
[119]	GAO R Q , HUO Y K , BAO S X ,et al. Distanced LSTM:time-distanced gates in long short-term memory models for lung cancer detection[C]// International Workshop on Machine Learning in Medical Imaging.[S.l.:s.n]. 2019: 310-318.
[120]	SHIN H C , ROTH H R , GAO M C ,et al. Deep convolutional neural networks for computer-aided detection:CNN architectures,dataset characteristics and transfer learning[J]. IEEE Transactions on Medical Imaging, 2016,35(5): 1285-1298.
[121]	ZHANG R K , ZHENG Y L , MAK T W C ,et al. Automatic detection and classification of colorectal polyps by transferring low-level CNN features from nonmedical domain[J]. IEEE Journal of Biomedical and Health Informatics, 2016,21(1): 41-47.
[122]	JESSON A , GUIZARD N , GHALEHJEGH S H ,et al. CASED:curriculum adaptive sampling for extreme data imbalance[C]// International Conference on Medical Image Computing and ComputerAssisted Intervention. Cham:Springer, 2017: 639-646.
[123]	LIU J Y , CAO L L , AKIN O ,et al. 3DFPNHS 2:3D feature pyramid network based high sensitivity and specificity pulmonary nodule detection[C]// Medical Image Computing and Computer Assisted Intervention-MICCAI 2019. Cham:Springer, 2019: 513-521.

模型类型	配准类型	数据集	变形场来源	器官	模型	评价指标	文献
有监督配准模型	刚体配准	内部数据集	合成形变场	骨骼X-ray	CNN	mTREproj:0.282 mm	[69-70]
	刚体配准	内部数据集	合成形变场	脊柱CT和X-ray	PDA	TRE:5.65 mm	[61]
	非线性配准	LBPA40、ISBR18、CUMC12、MGH10	真实形变场	脑部MR	3D-CNN		[62]
	非线性配准	内部数据集	真实形变场	前列腺超声和MR	CNN	TRE=8.5 mm	[63]
						Dice=0.86
	非线性配准	ACDC dataset	分割监督	心脏MR	CNN	Dice=0.865	[64]
	非线性配准	内部数据集	标签监督	前列腺CT和MR	CNN	ASD=1.58 mm	[65]
						Dice=0.873
	非线性配准	IBSR18、CUMC12、MGH10、IXI30	双监督学习形变场	脑部MR	BIRNet	Dice>0.728 （分脑区比较）	[66]
无监督配准模型	非线性配准	ADNI、OASIS、ABIDE、ADHD200、MCIC、PPMI、HABS、Harvard GSP		脑部MR	VoxelMorph	Dice=0.78	[69]
	非线性配准	Mindboggle101		脑部MR	FAIM	Dice=0.533（左上顶叶）	[71]
	非线性配准	ADNI		脑部MR	ICNet	Dice=0.88	[72]
						ASD=0.71 mm
						HD=12.71 mm（白质）
	非线性配准	内部数据集		脑部MR	ADMIR	Dice=0.91	[73]
						HD=2.68
						ASD=0.59
	非线性配准	内部数据集		前列腺MR和超声	AirNet	TRE=3.48 mm	[74]
	非线性配准	内部数据集、Sunybrook		视网膜图像、心脏MR	GAN	Dice=0.887/0.79HD=8.0/5.12	[75]
						（视网膜/心脏）
	非线性配准	VISCERAL Anatomy3 benchmark		全身MR、CT	GAN	Dice=0.757 （胸部）Dice=0.783（腹部）	[76]

数据集	模型	器官	损失	精度	文献
内部数据集	2.5D CNN	脑部、乳腺MR，心脏血管造影图像	交叉熵损失		[77]
2016 MICCAI IVDs挑战赛数据集	3D FCN	椎间盘MR	加权交叉熵损失	Dice=0.912	[78]
2017 MICCAI grand challenge on infant brain MRI	Multistream 3D FCN	脑部MR	似然损失	Dice=0.954	[81]
				ASD=0.127
				MHD=9.62 （脑脊液）
MICCAI 2009 LV Segmentation Challenge	Recurrent FCN	心脏MR	交叉熵损失	Dice=0.90	[82]
				APD=2.05
TCIA(ProstateX,QINHEADNECK)	U-Net	多器官	Combo损失	Dice=0.92	[92]
DRIVE、STARE、CHASH_DB1	R2 U-Net	多器官	二值交叉熵损失	Dice=0.86	[85]
PROMISE 2012 challenge	V-Net	前列腺MR	Dice损失	Dice=0.87	[84]
				HD=5.71 mm
DRIVE Dataset、ISIC 2018	Bi-LSTM	多器官	二值交叉熵损失	F1-Score>0.99	[87]
MICCAI BRATS 2013,2015	SegGAN	头部MR	多尺度L₁范数损失	Dice=0.84/0.85（BRATS 2013数据集/BRATS 2015数据集）	[100]
INbreast dataset,DDSM dataset	cGAN	乳腺钼靶图像	Dice以及对抗损失	Dice=0.94（INbreast）	[90]

器官	数据集	方法	目标	精度	文献
肺	LIDC-IDRI、ANODE09 challenge、DLCST	卷积神经网络	结节分类	Sensitivity=0.854	[95]
	LIDC-IDRI	知识学习	结节分类	AUC=0.957	[109]
	Chest X-ray 14	注意力卷积神经网络	肺部疾病分类	AUC=0.871	[102]
	HUG database	迁移学习	间质性肺疾病分类	F1-score=0.88	[97]
	LIDC以及内部数据集	迁移学习	肺结节检测	AUC=0.812	[98]
	LIDC-IDRI	知识学习	肺结节分类	AUC=0.957	[109]
	LIDC-IDRI	流形学习	肺结节分类	ACC=0.90	[110]
乳腺	DDSM、MIAS、BCDR	迁移学习	乳腺癌分类	AUC=0.997（MIAS） AUC=0.956（BCDR）	[99]
皮肤	ISIC 2016,2017	迁移学习	皮肤病分类	AUC=0.914	[96]
	2017 ISBI Challenge on Skin Lesion Analysis Towards Melanoma Detection、EDRA、ISIC	知识学习	皮肤病分类	AUC=0.917	[103]
	ISIC	人工与学习特征结合	皮肤病分类	AUC=0.780	[107]
眼底	Messidor	AlexNet	糖尿病视网膜病变分级	ACC=0.966	[94]
	内部数据集	注意力卷积神经网络	青光眼分类	AUC=0.975	[104]
	UCSD、NEH	病变感知卷积神经网络	眼底疾病分类	AUC>0.96	[103]
	内部数据集	知识学习	青光眼分类	ACC=0.915	[108]