{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T07:29:19Z","timestamp":1781422159429,"version":"3.54.1"},"reference-count":207,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T00:00:00Z","timestamp":1538352000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/tnnls.2017.2766168","type":"journal-article","created":{"date-parts":[[2017,11,22]],"date-time":"2017-11-22T19:18:38Z","timestamp":1511378318000},"page":"4550-4568","source":"Crossref","is-referenced-by-count":376,"title":["Deep Learning in Microscopy Image Analysis: A Survey"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0982-8675","authenticated-orcid":false,"given":"Fuyong","family":"Xing","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanpu","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hai","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1461-3567","authenticated-orcid":false,"given":"Fujun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref170","year":"2017","journal-title":"The Cancer Genome Altas"},{"key":"ref172","first-page":"3642","article-title":"Multi-column deep neural networks for image classification","author":"ciresan","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1038\/ng.2653"},{"key":"ref174","first-page":"1","article-title":"The rise of crowdsourcing","volume":"14","author":"howe","year":"2006","journal-title":"Wired Mag"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.06.023"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1177\/0165551512437638"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref177","first-page":"625","article-title":"Why does unsupervised pre-training help deep learning?","volume":"11","author":"erhan","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref168","first-page":"160","article-title":"The importance of stain normalization in colorectal tissue classification with convolutional networks","author":"ciompi","year":"2017","journal-title":"Proc IEEE Int Symp Biomed Imag"},{"key":"ref169","first-page":"404","article-title":"Robust selection-based sparse shape model for lung cancer image segmentation","volume":"8151","author":"xing","year":"2013","journal-title":"Proc Int Conf Med Image Comput Comput Assist Intervent (MICCAI)"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2481436"},{"key":"ref38","first-page":"411","article-title":"Mitosis detection in breast cancer histology images with deep neural networks","volume":"8150","author":"cire?an","year":"2013","journal-title":"Proc 16th Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2346443"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2009.2034865"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref37","first-page":"676","article-title":"Detecting 10,000 cells in one second","author":"xu","year":"2016","journal-title":"Proc 19th Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref36","first-page":"632","article-title":"Cutting out the middleman: Measuring nuclear area in histopathology slides without segmentation","author":"veta","year":"2016","journal-title":"Proc 19th Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2013.2295804"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2014.2303852"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2307532"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2183645"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2228231"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007330508534"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2528162"},{"key":"ref182","first-page":"3320","article-title":"How transferable are features in deep neural networks?","volume":"27","author":"yosinski","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2246188"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2006.17"},{"key":"ref187","first-page":"445","article-title":"Cost-sensitive learning with neural networks","author":"kukar","year":"1998","journal-title":"Proc 13th Eur Conf Artif Intell"},{"key":"ref186","first-page":"973","article-title":"The foundations of cost-sensitive learning","volume":"2","author":"elkan","year":"2001","journal-title":"Proc 17th Int Joint Conf Artif Intell"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2010.938364"},{"key":"ref27","author":"nielsen","year":"2015","journal-title":"Neural Networks and Deep Learning"},{"key":"ref179","doi-asserted-by":"crossref","first-page":"1275","DOI":"10.1109\/TNNLS.2014.2336852","article-title":"Blind image quality assessment via deep learning","volume":"26","author":"hou","year":"2015","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"ref20","first-page":"1440","article-title":"Fast R-CNN","author":"girshick","year":"2015","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2553401"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref24","first-page":"609","article-title":"Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations","author":"lee","year":"2009","journal-title":"Proc 26th Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2010.5537907"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2001269.2001295"},{"key":"ref50","first-page":"iii-1319","article-title":"Maxout networks","volume":"28","author":"goodfellow","year":"2013","journal-title":"Proc 30th Int Conf Int Conf Mach Learn"},{"key":"ref51","first-page":"549","article-title":"Multi-dimensional recurrent neural networks","author":"graves","year":"2007","journal-title":"Proc 17th Int Conf Artif Neural Netw"},{"key":"ref154","author":"krishna","year":"2016","journal-title":"Visual genome Connecting language and vision using crowdsourced dense image annotations"},{"key":"ref153","year":"2016","journal-title":"Tensor processing unit"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1422953112"},{"key":"ref155","first-page":"3729","article-title":"Interleaved text\/image deep mining on a large-scale radiology database for automated image interpretation","volume":"17","author":"shin","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2016.7418007"},{"key":"ref152","first-page":"243","article-title":"EIE: Efficient inference engine on compressed deep neural network","author":"han","year":"2016","journal-title":"Proc ACM\/IEEE Annu Int Symp Comput Archit"},{"key":"ref151","first-page":"1","article-title":"Scalable energy-efficient, low-latency implementations of trained spiking deep belief networks on SpiNNaker","author":"stromatias","year":"2015","journal-title":"Proc Int Joint Conf Neural Netw"},{"key":"ref146","first-page":"161","article-title":"Optimizing FPGA-based accelerator design for deep convolutional neural networks","author":"zhang","year":"2015","journal-title":"Proc ACM\/SIGDA Int Symp Field Program Gate Arrays (FPGA)"},{"key":"ref147","first-page":"26","article-title":"Going deeper with embedded FPGA platform for convolutional neural network","author":"qiu","year":"2016","journal-title":"Proc ACM\/SIGDA Int Symp Field Program Gate Arrays (FPGA)"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2010.5537908"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001165"},{"key":"ref59","first-page":"226","article-title":"Neutrophils identification by deep learning and Voronoi diagram of clusters","author":"wang","year":"2015","journal-title":"Proc 18th Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref58","first-page":"190","article-title":"Iteratively training classifiers for circulating tumor cell detection","author":"mao","year":"2015","journal-title":"Proc IEEE Int Symp Biomed Imag"},{"key":"ref57","first-page":"183","article-title":"Transfer shape modeling towards high-throughput microscopy image segmentation","volume":"9902","author":"xing","year":"2016","journal-title":"Proc 19th Int Conf Med Image Comput Comput -Assist Intervent (MICCAI)"},{"key":"ref56","first-page":"332","article-title":"Fast cell segmentation using scalable sparse manifold learning and affine transform-approximated active contour","volume":"9351","author":"xing","year":"2015","journal-title":"Proc 18th Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref55","first-page":"1","article-title":"Mitosis detection in breast cancer histological images an ICPR 2012 contest","volume":"4","author":"roux","year":"2013","journal-title":"J Pathol Inf"},{"key":"ref54","first-page":"185","article-title":"Spatial clockwork recurrent neural network for muscle perimysium segmentation","volume":"9901","author":"xie","year":"2016","journal-title":"Proc 19th Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298977"},{"key":"ref52","first-page":"545","article-title":"Offline handwriting recognition with multidimensional recurrent neural networks","author":"graves","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","first-page":"349","article-title":"A novel cell detection method using deep convolutional neural network and maximum-weight independent set","volume":"9351","author":"liu","year":"2015","journal-title":"Proc 18th Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2016.05.003"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2476509"},{"key":"ref165","first-page":"4406","article-title":"Scale normalization of histopathological images for batch invariant cancer diagnostic models","author":"kothari","year":"2012","journal-title":"Proc Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2014.2303294"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2818.2010.03443.x"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2012-001540"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.06.037"},{"key":"ref160","first-page":"1","article-title":"Ask your neurons: A neural-based approach to answering questions about images","author":"malinowski","year":"2015","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2461451"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2520964"},{"key":"ref6","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2360060"},{"key":"ref49","first-page":"281","article-title":"Minimizing computation in convolutional neural networks","author":"cong","year":"2014","journal-title":"Proc 24th Int Conf Artif Neural Netw Artif Neural Netw Mach Learn (ICANN)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2359471"},{"key":"ref157","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","volume":"27","author":"malinowski","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref158","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/MMUL.2014.29","article-title":"Joint video and text parsing for understanding events and answering queries","volume":"21","author":"tu","year":"2014","journal-title":"IEEE Multimedia"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1561\/2000000039"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2458702"},{"key":"ref48","first-page":"4820","article-title":"Quantized convolutional neural networks for mobile devices","author":"wu","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2535302"},{"key":"ref42","first-page":"1","article-title":"Microscopy cell counting with fully convolutional regression networks","author":"xie","year":"2015","journal-title":"Proc 1st Workshop Deep Learn Med Image Anal (MICCAI)"},{"key":"ref41","first-page":"358","article-title":"Beyond classification: Structured regression for robust cell detection using convolutional neural network","volume":"9351","author":"xie","year":"2015","journal-title":"Proc 18th Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2528120"},{"key":"ref43","first-page":"374","article-title":"Deep voting: A robust approach toward nucleus localization in microscopy images","volume":"9351","author":"xie","year":"2015","journal-title":"Proc 18th Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2015.7163850"},{"key":"ref72","first-page":"55","article-title":"Region segmentation in histopathological breast cancer images using deep convolutional neural network","author":"su","year":"2015","journal-title":"Proc IEEE Int Symp Biomed Imag"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.60"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2015.2430895"},{"key":"ref76","first-page":"766","article-title":"Discriminative unsupervised feature learning with convolutional neural networks","author":"dosovitskiy","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btu080"},{"key":"ref74","first-page":"383","article-title":"Robust cell detection and segmentation in histopathological images using sparse reconstruction and stacked denoising autoencoders","volume":"9351","author":"su","year":"2015","journal-title":"Proc 18th Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref75","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","volume":"9351","author":"ronneberger","year":"2015","journal-title":"Proc 18th Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref78","first-page":"1167","article-title":"Deep contextual networks for neuronal structure segmentation","author":"chen","year":"2016","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref79","first-page":"153","article-title":"Greedy layer-wise training of deep networks","volume":"19","author":"bengio","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref60","first-page":"772","article-title":"Deep learning for automatic cell detection in wide-field microscopy zebrafish images","author":"dong","year":"2015","journal-title":"Proc IEEE Int Symp Biomed Imag"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2525803"},{"key":"ref61","first-page":"743","article-title":"Automatic detection of cell divisions (mitosis) in live-imaging microscopy images using convolutional neural networks","author":"shkolyar","year":"2015","journal-title":"Proc Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"ref63","first-page":"1324","article-title":"Learning to count objects in images","author":"lempitsky","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2526689"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2204190"},{"key":"ref66","first-page":"2843","article-title":"Deep neural networks segment neuronal membranes in electron microscopy images","author":"ciresan","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btw165"},{"key":"ref68","first-page":"4069","article-title":"Watershed merge forest classification for electron microscopy image stack segmentation","author":"liu","year":"2013","journal-title":"Proc IEEE Int Conf Image Process"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.852470"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1098\/rsos.140501"},{"key":"ref198","first-page":"437","article-title":"Predicting semantic descriptions from medical images with convolutional neural networks","author":"schlegl","year":"2015","journal-title":"Proc Int Conf Inf Process Med Imag"},{"key":"ref199","first-page":"320","article-title":"TandemNet: Distilling knowledge from medical images using diagnostic reports as optional semantic references","author":"zhang","year":"2017","journal-title":"Proc 20th Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref193","first-page":"2424","article-title":"Patch-based convolutional neural network for whole slide tissue image classification","author":"hou","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref194","doi-asserted-by":"crossref","first-page":"30","DOI":"10.4103\/jpi.jpi_34_17","article-title":"Deep learning for classification of colorectal polyps on whole-slide images","volume":"8","author":"korbar","year":"2017","journal-title":"J Pathol Inf"},{"key":"ref195","first-page":"7234","article-title":"WSISA: Making survival prediction from whole slide histopathological images","author":"zhu","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.12102294"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref94","first-page":"947","article-title":"Deep convolutional activation features for large scale brain tumor histopathology image classification and segmentation","author":"xu","year":"2015","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.81"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1002\/9781118646106"},{"key":"ref92","article-title":"Deep learning in label-free cell classification","volume":"6","author":"chen","year":"2016","journal-title":"Sci Rep"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1097\/JTO.0b013e3181fc0878"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2016.2526603"},{"key":"ref90","first-page":"1185","article-title":"Sparse feature learning for deep belief networks","volume":"20","author":"ranzato","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref98","first-page":"570","article-title":"A framework for multiple-instance learning","volume":"10","author":"maron","year":"1998","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref99","first-page":"1417","article-title":"Multiple instance boosting for object detection","volume":"18","author":"viola","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref96","first-page":"1","article-title":"A theoretical analysis of feature pooling in visual recognition","author":"boureau","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn"},{"key":"ref97","first-page":"1626","article-title":"Deep learning of feature representation with multiple instance learning for medical image analysis","author":"xu","year":"2014","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522428"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btm247"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-016-3262-5"},{"key":"ref80","first-page":"562","article-title":"Deeply-supervised nets","author":"lee","year":"2015","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref89","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"vincent","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2007.893452"},{"key":"ref86","first-page":"2980","article-title":"Parallel multi-dimensional lstm, with application to fast biomedical volumetric image segmentation","volume":"28","author":"stollenga","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref87","first-page":"1863","article-title":"A clockwork RNN","volume":"32","author":"koutn\u00edk","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref200","first-page":"6428","article-title":"MDNet: A semantically and visually interpretable medical image diagnosis network","author":"zhang","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref101","author":"kavukcuoglu","year":"2010","journal-title":"Fast inference in sparse coding algorithms with applications to object recognition"},{"key":"ref100","first-page":"403","article-title":"A deep learning architecture for image representation, visual interpretability and automated basal-cell carcinoma cancer detection","author":"cruz-roa","year":"2013","journal-title":"Proc 16th Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref203","first-page":"770","article-title":"Deep residual learning for image recognition","author":"he","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref204","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.1.3.034003"},{"key":"ref202","author":"simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref207","first-page":"146","article-title":"Unsupervised anomaly detection with generative adversarial networks to guide marker discovery","author":"schlegl","year":"2017","journal-title":"Proc Int Conf Inf Process Med Imag"},{"key":"ref205","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref206","first-page":"417","article-title":"Medical image synthesis with context-aware generative adversarial networks","author":"nie","year":"2017","journal-title":"Proc 20th Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref127","first-page":"1223","article-title":"Large scale distributed deep networks","volume":"25","author":"dean","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref126","first-page":"1","article-title":"Torch7: A MATLAB-like environment for machine learning","author":"collobert","year":"2011","journal-title":"NIPS Workshop BigLearn"},{"key":"ref125","author":"abadi","year":"2015","journal-title":"TensorFlow Large-Scale Machine Learning on Heterogeneous Systems"},{"key":"ref124","year":"2016","journal-title":"Theano A Python framework for fast computation of mathematical expressions"},{"key":"ref129","first-page":"583","article-title":"Scaling distributed machine learning with the parameter server","author":"li","year":"2014","journal-title":"Proc USENIX Symp Oper Syst Design Implementation"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553486"},{"key":"ref130","first-page":"693","article-title":"Hogwild: A lock-free approach to parallelizing stochastic gradient descent","volume":"24","author":"recht","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref133","author":"chetlur","year":"2014","journal-title":"cuDNN Efficient Primitives for Deep Learning"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2283730"},{"key":"ref131","first-page":"1337","article-title":"Deep learning with COTS HPC systems","author":"coates","year":"2013","journal-title":"Proc 30th Int Conf Mach Learn"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1145\/1365490.1365500"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2335852"},{"key":"ref135","first-page":"878","article-title":"An FPGA-based stream processor for embedded real-time vision with convolutional networks","author":"farabet","year":"2009","journal-title":"Proc IEEE 12th Int Conf Comput Vis Workshops"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1049\/el.2013.3235"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2310494"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1049\/el.2014.0611"},{"key":"ref140","first-page":"63","article-title":"Highly parallel framework for HEVC motion estimation on many-core platform","author":"yan","year":"2013","journal-title":"Proc Data Compress Conf (DCC)"},{"key":"ref141","author":"lacey","year":"2016","journal-title":"Deep learning on FPGAs Past present and future"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2545298"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/4.121550"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-28487-7_5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2010.936730"},{"key":"ref145","author":"ovtcharov","year":"2015","journal-title":"Accelerating deep convolutional neural networks using specialized hardware"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1242\/jcs.123604"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2008.12-07-661"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2008.04-07-510"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2296046"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2293637"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2580741"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.1993.342465"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.28"},{"key":"ref102","first-page":"91","article-title":"Characterization of tissue histopathology via predictive sparse decomposition and spatial pyramid matching","author":"chang","year":"2013","journal-title":"Proc 16th Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2496947"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2308519"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2387439"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2550532"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2016.2515127"},{"key":"ref12","first-page":"851","article-title":"Deep learning in bioinformatics","volume":"18","author":"min","year":"2017","journal-title":"Briefings Bioinform"},{"key":"ref13","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3389\/fnana.2015.00142"},{"key":"ref118","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"Proc Eur Conf Comp Vis (ECCV)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2014.11.010"},{"key":"ref117","first-page":"5188","article-title":"Understanding deep image representations by inverting them","author":"mahendran","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1021\/ci500747n"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref119","first-page":"1","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"simonyan","year":"2014","journal-title":"Proc Workshop Int Conf Learn Represent"},{"key":"ref19","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"girshick","year":"2014","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2469673"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2541681"},{"key":"ref116","author":"szegedy","year":"0","journal-title":"Intriguing properties of neural networks"},{"key":"ref115","article-title":"Understanding representations learned in deep architectures","author":"erhan","year":"2010"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2599820"},{"key":"ref122","first-page":"265","article-title":"On optimization methods for deep learning","author":"le","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref123","author":"jia","year":"2014","journal-title":"Caffe Convolutional Architecture for Fast Feature Embedding"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/8468244\/08118310.pdf?arnumber=8118310","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:28:58Z","timestamp":1642004938000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8118310\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":207,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2017.2766168","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10]]}}}