Generative models: an upcoming innovation in musculoskeletal radiology? A preliminary test in spine imaging

被引：32

作者：

Galbusera F. ^{[1
]}

Bassani T. ^{[1
]}

Casaroli G. ^{[1
]}

Gitto S. ^{[2
]}

Zanchetta E. ^{[2
]}

Costa F. ^{[3
]}

Sconfienza L.M. ^{[2
,4
]}

机构：

[1] Laboratory of Biological Structures Mechanics, IRCCS Istituto Ortopedico Galeazzi, via Galeazzi 4, Milan

[2] Unit of Diagnostic and Interventional Radiology, IRCCS Istituto Ortopedico Galeazzi, via Galeazzi 4, Milan

[3] Department of Neurosurgery, Humanitas Clinical and Research Hospital, Via Manzoni 56, Rozzano

[4] Department of Biomedical Sciences for Health, Università degli Studi di Milano, via Carlo Pascal 36, Milan

来源：

European Radiology Experimental | / 2卷 / 1期

关键词：

Lumbar vertebrae; Machine learning (deep learning); Magnetic resonance imaging; Neural network (computer); X-rays;

D O I：

10.1186/s41747-018-0060-7

中图分类号：

学科分类号：

摘要：

Background: Deep learning is a ground-breaking technology that is revolutionising many research and industrial fields. Generative models are recently gaining interest. Here, we investigate their potential, namely conditional generative adversarial networks, in the field of magnetic resonance imaging (MRI) of the spine, by performing clinically relevant benchmark cases. Methods: First, the enhancement of the resolution of T2-weighted (T2W) images (super-resolution) was tested. Then, automated image-to-image translation was tested in the following tasks: (1) from T1-weighted to T2W images of the lumbar spine and (2) vice versa; (3) from T2W to short time inversion-recovery (STIR) images; (4) from T2W to turbo inversion recovery magnitude (TIRM) images; (5) from sagittal standing x-ray projections to T2W images. Clinical and quantitative assessments of the outputs by means of image quality metrics were performed. The training of the models was performed on MRI and x-ray images from 989 patients. Results: The performance of the models was generally positive and promising, but with several limitations. The number of disc protrusions or herniations showed good concordance (κ = 0.691) between native and super-resolution images. Moderate-to-excellent concordance was found when translating T2W to STIR and TIRM images (κ ≥ 0.842 regarding disc degeneration), while the agreement was poor when translating x-ray to T2W images. Conclusions: Conditional generative adversarial networks are able to generate perceptually convincing synthetic images of the spine in super-resolution and image-to-image translation tasks. Taking into account the limitations of the study, deep learning-based generative methods showed the potential to be an upcoming innovation in musculoskeletal radiology. © 2018, The Author(s).

引用

共 40 条

[1]

Najafabadi M.M., Villanustre F., Khoshgoftaar T.M., Seliya N., Wald R., Muharemagic E., Deep learning applications and challenges in big data analytics, J Big Data, 2, 1, (2015)

[2]

Deng L., Yu D., Deep learning: methods and applications, Found Trends Signal Process, 7, pp. 197-387, (2014)

[3]

Salakhutdinov R., Learning deep generative models, Annu Rev Stat Appl, 2, pp. 361-385, (2015)

[4]

Isola P., Zhu J., Zhou T., Efros A.A., Image-To-Image Translation with Conditional Adversarial Networks, (2017)

[5]

Goodfellow I., NIPS 2016 tutorial: generative adversarial networks, (2016)

[6]

Liu Y., Qin Z., Wan T., Luo Z., Auto-painter: Cartoon image generation from sketch by using conditional Wasserstein generative adversarial networks, Neurocomputing, 311, pp. 78-87, (2018)

[7]

Galbusera F., Bassani T., Costa F., Brayda-Bruno M., Zerbi A., Wilke H.-J., Artificial neural networks for the recognition of vertebral landmarks in the lumbar spine, Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 6, 4, pp. 447-452, (2016)

[8]

Jamaludin A., Lootus M., Kadir T., Et al., ISSLS PRIZE IN BIOENGINEERING SCIENCE 2017: Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist, Eur Spine J, 26, pp. 1374-1383, (2017)

[9]

Koh J., Chaudhary V., Dhillon G., Disc herniation diagnosis in MRI using a CAD framework and a two-level classifier, Int J Comput Assist Radiol Surg, 7, pp. 861-869, (2012)

[10]

Azimi P., Benzel E.C., Shahzadi S., Azhari S., Mohammadi H.R., Use of artificial neural networks to predict surgical satisfaction in patients with lumbar spinal canal stenosis, Journal of Neurosurgery: Spine, 20, 3, pp. 300-305, (2014)

← 1 2 3 4 →