摘要
深度学习是目前人工智能领域备受关注和极具应用前景的机器学习算法,有望革新传统计算机辅助诊断(CAD)系统,在精准影像诊断中发挥重要作用。就人工智能、机器学习、深度学习、卷积神经网络、迁移学习的基本概念,以及基于深度学习的CAD系统在肺、乳腺、心脏、颅脑、肝脏、前列腺、骨骼的影像及病理学中的研究现状予以综述。
Deep learning is a machine learning algorithm which has attracted great attention and has great potentials in the field of artificial intelligence. It is expected to innovate the traditional computer aided diagnosis system and play an important role in precision medical imaging. In this paper, we reviewed the basic conceptions about artificial intelligence,machine learning, deep learning, convolutional neural network, transfer learning, as well as the research status of computer aided diagnosis system based on deep learning in imaging diagnosis related to lung, breast, heart, brain, liver, prostate,skeleton, and pathological diagnosis.
引文
[1]Moor J.The Dartmouth college artificial intelligence conference:the next fifty years[J].Ai Magazine,2006,27:87-89.
[2]Foster KR,Koprowski R,Skufca JD.Machine learning,medical diagnosis,and biomedical engineering research-commentary[J].Biomed Eng Online,2014,13:94.
[3]Loh BCS,Then PHH.Deep learning for cardiac computer-aided diagnosis:benefits,issues&solutions[J].Mhealth,2017,3:45.
[4]Wang X,Yang W,Weinreb J,et al.Searching for prostate cancer by fully automated magnetic resonance imaging classification:deep learning versus non-deep learning[J].Sci Rep,2017,7:15415.
[5]Lee H,Tajmir S,Lee J,et al.Fully automated deep learning system for bone age assessment[J].J Digit Imaging,2017,30:427-441.
[6]Forsberg D,Sj觟blom E,Sunshine JL.Detection and labeling of vertebrae in MR images using deep learning with clinical annotations as training data[J].J Digit Imaging,2017,30:406-412.
[7]Anthimopoulos M,Christodoulidis S,Ebner L,et al.Lung pattern classification for interstitial lung diseases using a deep convolutional neural network[J].IEEE Trans Med Imaging,2016,35:1207-1216.
[8]Webb S.Deep learning for biology[J].Nature,2018,554:555-557.
[9]Kermany DS,Goldbaum M,Cai W,et al.Identifying medical diagnoses and treatable diseases by image-based deep learning[J].Cell,2018,172:1122-1131.e9.
[10]Christodoulidis S,Anthimopoulos M,Ebner L,et al.Multisource transfer learning with convolutional neural networks for lung pattern analysis[J].IEEE J Biomed Health Inform,2017,21:76-84.
[11]Yang W,Chen Y,Liu Y,et al.Cascade of multi-scale convolutional neural networks for bone suppression of chest radiographs in gradient domain[J].Med Image Anal,2017,35:421-433.
[12]van Ginneken B.Fifty years of computer analysis in chest imaging:rule-based,machine learning,deep learning[J].Radiol Phys Technol,2017,10:23-32.
[13]Ciompi F,Chung K,van Riel SJ,et al.Towards automatic pulmonary nodule management in lung cancer screening with deep learning[J].Sci Rep,2017,7:46479.
[14]Shin HC,Roth HR,Gao M,et al.Deep convolutional neural networks for computer-aided detection:CNN architectures,dataset characteristics and transfer learning[J].IEEE Trans Med Imaging,2016,35:1285-1298.
[15]Lehman CD,Wellman RD,Buist DS,et al.Diagnostic accuracy of digital screening mammography with and without computer-aided detection[J].JAMA Intern Med,2015,175:1828-1837.
[16]Al-Masni MA,Al-Antari MA,Park JM,et al.Simultaneous detection and classification of breast masses in digital mammograms via a deep learning YOLO-based CAD system[J].Comput Methods Programs Biomed,2018,157:85-94.
[17]Chougrad H,Zouaki H,Alheyane O.Deep Convolutional Neural Networks for breast cancer screening[J].Comput Methods Programs Biomed,2018,157:19-30.
[18]Wang J,Ding H,Bidgoli FA,et al.Detecting cardiovascular disease from mammograms with deep learning[J].IEEE Trans Med Imaging,2017,36:1172-1181.
[19]Dalm MU,Litjens G,Holland K,et al.Using deep learning to segment breast and fibroglandular tissue in MRI volumes[J].Med Phys,2017,44:533-546.
[20]Avendi MR,Kheradvar A,Jafarkhani H.A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI[J].Med Image Anal,2016,30:108-119.
[21]Madani A,Arnaout R,Mofrad M,et al.Fast and accurate view classification of echocardiograms using deep learning[J].NP J Digital Medicine,2018,1:6.
[22]Pereira S,Pinto A,Alves V,et al.Brain tumor segmentation using convolutional neural networks in MRI images[J].IEEE Trans Med Imaging,2016,35:1240-1251.
[23]Hsieh KL,Lo CM,Hsiao CJ.Computer-aided grading of gliomas based on local and global MRI features[J].Comput Methods Programs Biomed,2017,139:31-38.
[24]Lu D,Popuri K,Ding GW,et al.Multimodal and multiscale deep neural networks for the early diagnosis of Alzheimer’s disease using structural MR and FDG-PET images[J].Sci Rep,2018,8:5697.
[25]Zeng LL,Wang H,Hu P,et al.Multi-site diagnostic classification of schizophrenia using discriminant deep learning with functional connectivity MRI[J].EBioMedicine,2018,30:74-85.
[26]Yasaka K,Akai H,Abe O,et al.Deep learning with convolutional neural network for differentiation of liver masses at dynamic contrast-enhanced CT:a preliminary study[J].Radiology,2018,286:887-896.
[27]Kim Y,Furlan A,Borhani AA,et al.Computer-aided diagnosis program for classifying the risk of hepatocellular carcinoma on MR images following liver imaging reporting and data system(LI-RADS)[J].J Magn Reson Imaging,2018,47:710-722.
[28]Giannini V,Mazzetti S,Armando E,et al.Multiparametric magnetic resonance imaging of the prostate with computer-aided detection:experienced observer performance study[J].Eur Radiol,2017,27:4200-4208.
[29]Thon A,Teichgr覿ber U,Tennstedt-Schenk C,et al.Computer aided detection in prostate cancer diagnostics:a promising alternative to biopsy?A retrospective study from 104 lesions with histological ground truth[J].PLoS One,2017,12:e0185995.
[30]Tiulpin A,Thevenot J,Rahtu E,et al.Automatic knee osteoarthritis diagnosis from plain radiographs:a deep learning-based approach[J].Sci Rep,2018,8:1727.
[31]Griffith JF,Wang D,Shi L,et al.Computer-aided assessment of spinal inflammation on magnetic resonance images in patients with spondyloarthritis[J].Arthritis Rheumatol,2015,67:1789-1797.
[32]Huang L,Xia W,Zhang B,et al.MSFCN-multiple supervised fully convolutional networks for the osteosarcoma segmentation of CT images[J].Comput Methods Programs Biomed,2017,143:67-74.
[33]Litjens G,Sánchez CI,Timofeeva N,et al.Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis[J].Sci Rep,2016,6:26286.
[34]Ehteshami BB,Veta M,Johannes van DP,et al.Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer[J].JAMA,2017,318:2199-2210.