Abstract
Recently, deep learning has been exploited in the field of medical image analysis. However, the training of deep learning models with medical images is time-consuming since most medical image data are three-dimensional volumes or high-resolution two-dimensional images. Moreover, the optimization of numerous hyperparameters strongly affects the performance of deep learning. If a framework for training deep learning with hyperparameter optimization on a supercomputer system can be realized, it is expected to accelerate the training of deep learning with medical images. In this study, we described our novel environment for training deep learning with medical images on the supercomputer system in our institute (Reedbush-H supercomputer system) based on asynchronous parallel Bayesian optimization. We trained two types of automated lesion detection application in a constructed environment. The constructed environment enabled us to train deep learning with hyperparameter tuning in a short time.
Similar content being viewed by others
References
Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M (2016) TensorFlow: large-scale machine learning on heterogeneous distributed systems. arXiv e-prints arXiv:1603.04467
Armato RSG, McLennan G, Bidaut L, McNitt-Gray MF, Meyer CR, Reeves AP, Zhao B, Aberle DR, Henschke CI, Hoffman EA, Kazerooni EA, MacMahon H, van Beeke EJ, Yankelevitz D, Biancardi AM, Bland PH, Brown MS, Engelmann RM, Laderach GE, Max D, Pais RC, Qing DP, Roberts RY, Smith AR, Starkey A, Batrah P, Caligiuri P, Farooqi A, Gladish GW, Jude CM, Munden RF, Petkovska I, Quint LE, Schwartz LH, Sundaram B, Dodd LE, Fenimore C, Gur D, Petrick N, Freymann J, Kirby J, Hughes B, Casteele AV, Gupte S, Sallamm M, Heath MD, Kuhn MH, Dharaiya E, Burns R, Fryd DS, Salganicoff M, Anand V, Shreter U, Vastagh S, Croft BY (2011) The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on ct scans. Med Phys 38(2):915–31. https://doi.org/10.1118/1.3528204
Balaprakash P, Salim M, Uram TD, Vishwanath V, Wild SM (2018) Deephyper: asynchronous hyperparameter search for deep neural networks. In: 2018 IEEE 25th international conference on high performance computing (HiPC), pp 42–51
Bergstra J, Bengio Y (2012) Random search for hyper-parameter optimization. J Mach Learn Res 13(Feb):281–305
Chakraborty DP, Berbaum KS (2004) Observer studies involving detection and localization: modeling, analysis, and validation. Med Phys 31(8):2313–30. https://doi.org/10.1118/1.1769352
Chollet F (2015) Keras. https://github.com/fchollet/keras. Accessed 19 Jan 2020
Contal E, Perchet V, Vayatis N (2014) Gaussian process optimization with mutual information. In: Proceedings of the 31st international conference on machine learning, vol 32, pp 253–261
Gerard P, Kapadia N, Chang PT, Acharya J, Seiler M, Lefkovitz Z (2013) Extended outlook: description, utilization, and daily applications of cloud technology in radiology. AJR Am J Roentgenol 201(6):W809–11. https://doi.org/10.2214/ajr.12.9673
He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. arXiv e-prints arXiv:1512.03385
Hiraishi T, Abe T, Iwashita T, Nakashima H (2012) Xcrypt: a perl extension for job level parallel programming. In: Proceedings of the WHIST 2012
Kagadis GC, Kloukinas C, Moore K, Philbin J, Papadimitroulas P, Alexakos C, Nagy PG, Visvikis D, Hendee WR (2013) Cloud computing in medical imaging. Med Phys 40(7):070901. https://doi.org/10.1118/1.4811272
Kandasamy K, Krishnamurthy A, Schneider J, Poczos B (2018) Parallelised Bayesian optimisation via Thompson sampling. In: Proceedings of the 21st international conference on artificial intelligence and statistics, pp 133–142
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv e-prints arXiv:1412.6980
Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, van der Laak JAWM, van Ginneken B, Sánchez CI (2017) A survey on deep learning in medical image analysis. Med Image Anal. https://doi.org/10.1016/j.media.2017.07.005
Masutani Y, Nemoto M, Nomura Y, Hayashi N (2013) Clinical machine learning in action: cad system design, development, tuning, and long-term experience. In: Suzuki K (ed) Image processing: concepts, methodologies, tools, and applications. IGI Global, Philadelphia, pp 621–638
Metz CE (2006) Receiver operating characteristic analysis: a tool for the quantitative evaluation of observer performance and imaging systems. J Am Coll Radiol 3(6):413–22. https://doi.org/10.1016/j.jacr.2006.02.021
Milletari F, Navab N, Ahmadi SA (2016) V-Net: fully convolutional neural networks for volumetric medical image segmentation. arXiv e-prints arXiv:1606.04797
Mockus J, Tiesis V, Zilinskas A (1978) The application of Bayesian methods for seeking the extremum. Towards Glob Optim 2:117–129
Neary P (2018) Automatic hyperparameter tuning in deep convolutional neural networks using asynchronous reinforcement learning. In: 2018 IEEE international conference on cognitive computing (ICCC), pp 73–77
Nomura Y, Masutani Y, Miki S, Nemoto M, Hanaoka S, Yoshikawa T, Hayashi N, Ohtomo K (2014) Performance improvement in computerized detection of cerebral aneurysms by retraining classifier using feedback data collected in routine reading environment. J Biomed Graph Comput 4(4):12–21. https://doi.org/10.5430/jbgc.v4n4p12
Nomura Y, Hayashi N, Hanaoka S, Takenaga T, Nemoto M, Miki S, Yoshikawa T, Abe O (2019) Can the spherical gold standards be used as an alternative to painted gold standards for the computerized detection of lesions using voxel-based classification? Jpn J Radiol 37(3):264–273. https://doi.org/10.1007/s11604-018-0784-6
Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. arXiv e-prints arXiv:1505.04597
Sahiner B, Pezeshk A, Hadjiiski LM, Wang X, Drukker K, Cha KH, Summers RM, Giger ML (2019) Deep learning in medical imaging and radiation therapy. Med Phys 46(1):e1–e36. https://doi.org/10.1002/mp.13264
Snoek J, Larochelle H, Adams RP (2012) Practical bayesian optimization of machine learning algorithms. In: Advances in neural information processing systems, pp 2951–2959
Srinivas N, Krause A, Kakade S, Seeger M (2010) Gaussian process optimization in the bandit setting: no regret and experimental design. In: Proceedings of the 27th international conference on machine learning, Omnipress, USA, ICML’10, pp 1015–1022, http://dl.acm.org/citation.cfm?id=3104322.3104451
Tokui S, Oono K, Hido S, Clayton J (2015) Chainer: a next-generation open source framework for deep learning. In: Proceedings of workshop on machine learning systems (learningsys) in the 29th annual conference on neural information processing systems (NIPS), vol 5, pp 1–6
Tsujii O, Freedman MT, Mun SK (1998) Automated segmentation of anatomic regions in chest radiographs using an adaptive-sized hybrid neural network. Med Phys 25(6):998–1007. https://doi.org/10.1118/1.598277
Ueda D, Shimazaki A, Miki Y (2019) Technical and clinical overview of deep learning in radiology. Jpn J Radiol 37(1):15–33. https://doi.org/10.1007/s11604-018-0795-3
Wozniak JM, Jain R, Balaprakash P, Ozik J, Collier NT, Bauer J, Xia F, Brettin T, Stevens R, Mohd-Yusof J, Cardona CG, Baughman BVEM (2018) Candle/supervisor: a workflow framework for machine learning applied to cancer research. BMC Bioinform 19(18):491. https://doi.org/10.1186/s12859-018-2508-4
Wu G, Zhang X, Luo S, Hu Q (2015) Lung segmentation based on customized active shape model from digital radiography chest images. J Med Imaging Health Info 5(2):184–191. https://doi.org/10.1166/jmihi.2015.1382
Yasaka K, Akai H, Kunimatsu A, Kiryu S, Abe O (2018) Deep learning with convolutional neural network in radiology. Jpn J Radiol 36(4):257–272. https://doi.org/10.1007/s11604-018-0726-3
Zhong Z, Zheng L, Kang G, Li S, Yang Y (2017) Random erasing data augmentation. arXiv e-prints arXiv:1708.04896
Acknowledgements
The Department of Computational Radiology and Preventive Medicine, The University of Tokyo Hospital, is sponsored by HIMEDIC Inc. and Siemens Healthcare K.K. This work was supported by the Joint Usage/Research Center for Interdisciplinary Large-scale Information Infrastructures and High Performance Computing Infrastructure projects in Japan (Project IDs: jh170036-DAH, jh180073-DAH, and jh190047-DAH).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Nomura, Y., Sato, I., Hanawa, T. et al. Development of training environment for deep learning with medical images on supercomputer system based on asynchronous parallel Bayesian optimization. J Supercomput 76, 7315–7332 (2020). https://doi.org/10.1007/s11227-020-03164-7
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-020-03164-7