Clinical super-resolution computed tomography of bone microstructure: application in musculoskeletal and dental imaging

Objectives Clinical cone-beam computed tomography (CBCT) devices are limited to imaging features of half a millimeter in size. Hence, they do not allow clinical quantification of bone microstructure, which plays an important role in osteoarthritis, osteoporosis and fracture risk. For maxillofacial imaging, changes in small mineralized structures are important for dental, periodontal and ossicular chain diagnostics as well as treatment planning. Deep learning (DL)-based super-resolution (SR) models could allow for better evaluation of these microstructural details. In this study, we demonstrate a widely applicable method for increasing the spatial resolution of clinical CT images using DL, which only requires training on a limited set of data that are easy to acquire in a laboratory setting from e.g. cadaver knees. Our models are assessed rigorously for technical image quality, ability to predict bone microstructure, as well as clinical image quality of the knee, wrist, ankle and dentomaxillofacial region. Materials and methods Knee tissue blocks from five cadavers and six total knee replacement patients as well as 14 extracted teeth from eight patients were scanned using micro-computed tomography. The images were used as training data for the developed DL-based SR technique, inspired by previous studies on single-image SR. The technique was benchmarked with an ex vivo test set, consisting of 52 small osteochondral samples imaged with clinical and laboratory CT scanners, to quantify bone morphometric parameters. A commercially available quality assurance phantom was imaged with a clinical CT device, and the technical image quality was quantified with a modulation transfer function. To visually assess the clinical image quality, CBCT studies from wrist, knee, ankle, and maxillofacial region were enhanced with SR and contrasted to interpolated images. A dental radiologist and dental surgeon reviewed maxillofacial CBCT studies of nine patients and corresponding SR predictions. Results The SR models yielded a higher Pearson correlation to bone morphological parameters on the ex vivo test set compared to the use of a conventional image processing pipeline. The phantom analysis confirmed a higher spatial resolution on the images enhanced by the SR approach. A statistically significant increase of spatial resolution was seen in the third, fourth, and fifth line pair patterns. However, the predicted grayscale values of line pair patterns exceeded those of uniform areas. Musculoskeletal CBCT images showed more details on SR predictions compared to interpolation. Averaging predictions on orthogonal planes improved visual quality on perpendicular planes but could smear the details for morphometric analysis. SR in dental imaging allowed to visualize smaller mineralized structures in the maxillofacial region, however, some artifacts were observed near the crown of the teeth. The readers assessed mediocre overall scores in all categories for both CBCT and SR. Although not statistically significant, the dental radiologist slightly preferred the original CBCT images. The dental surgeon scored one of the SR models slightly higher compared to CBCT. The interrater variability κ was mostly low to fair. The source code (https://doi.org/10.5281/zenodo.8041943) and pretrained SR networks (https://doi.org/10.17632/4xvx4p9tzv.1) are publicly available. Conclusions Utilizing experimental laboratory imaging modalities in model training could allow pushing the spatial resolution limit beyond state-of-the-art clinical musculoskeletal and dental CBCT imaging. Implications of SR include higher patient throughput, more precise diagnostics, and disease interventions at an earlier state. However, the grayscale distribution of the images is modified, and the predictions are limited to depicting the mineralized structures rather than estimating density or tissue composition. Finally, while the musculoskeletal images showed promising results, a larger maxillofacial dataset would be recommended for training SR models in dental applications.

[1]  K. Tsujioka,et al.  Performance evaluation of micro-vessels imaging by deep learning reconstruction targeting ultra-high-resolution CT (UHR-CT) , 2022, Journal of Medical Imaging and Radiation Sciences.

[2]  N. Segal,et al.  WBCT and its evolving role in OA research and clinical practice , 2022, Osteoarthritis Imaging.

[3]  Shuo Wang,et al.  Large-factor Micro-CT super-resolution of bone microstructure , 2022, Frontiers in Physics.

[4]  Brian Nett,et al.  A Review of Deep Learning CT Reconstruction: Concepts, Limitations, and Promise in Clinical Practice , 2022, Current Radiology Reports.

[5]  Daniel Wessling,et al.  Deep learning-based super-resolution gradient echo imaging of the pancreas: Improvement of image quality and reduction of acquisition time. , 2022, Diagnostic and interventional imaging.

[6]  J. Laredo,et al.  MRI UNDERESTIMATES PRESENCE AND SIZE OF KNEE OSTEOPHYTES USING CT AS A REFERENCE STANDARD , 2022, Osteoarthritis and Cartilage.

[7]  Matthew J. Colbrook,et al.  The difficulty of computing stable and accurate neural networks: On the barriers of deep learning and Smale’s 18th problem , 2022, Proceedings of the National Academy of Sciences of the United States of America.

[8]  G. Zaharchuk,et al.  Clinical Assessment of Deep Learning-based Super-Resolution for 3D Volumetric Brain MRI. , 2022, Radiology. Artificial intelligence.

[9]  S. Meher,et al.  An improved Image Interpolation technique using OLA e-spline , 2021, Egyptian Informatics Journal.

[10]  J. Beregi,et al.  Comparison of two deep learning image reconstruction algorithms in chest CT images: A task-based image quality assessment on phantom data. , 2021, Diagnostic and interventional imaging.

[11]  Hongwei Li,et al.  Micro-Ct Synthesis and Inner Ear Super Resolution via Generative Adversarial Networks and Bayesian Inference , 2021, 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI).

[12]  Matthew J. Colbrook,et al.  The difficulty of computing stable and accurate neural networks: On the barriers of deep learning and Smale’s 18th problem , 2021, Proceedings of the National Academy of Sciences of the United States of America.

[13]  E. Berkhout,et al.  Cone-Beam CT Compared to Multi-Slice CT for the Diagnostic Analysis of Conductive Hearing Loss: A Feasibility Study. , 2020, The journal of international advanced otology.

[14]  A. Guermazi,et al.  State of the Art: Imaging of Osteoarthritis-Revisited 2020. , 2020, Radiology.

[15]  B. Jeurissen,et al.  Super-Resolution Magnetic Resonance Imaging of the Knee Using 2-Dimensional Turbo Spin Echo Imaging , 2020, Investigative radiology.

[16]  C. Rudin,et al.  PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Eric K. Gibbons,et al.  Utility of deep learning super‐resolution in the context of osteoarthritis MRI biomarkers , 2020, Journal of magnetic resonance imaging : JMRI.

[18]  M. Haapea,et al.  Quantifying Subresolution 3D Morphology of Bone with Clinical Computed Tomography , 2019, Annals of Biomedical Engineering.

[19]  Zhao Zhang,et al.  Deep Learning-Based Point-Scanning Super-Resolution Imaging , 2019, Nature Methods.

[20]  Jay Wu,et al.  Improving the prediction of the trabecular bone microarchitectural parameters using dental cone-beam computed tomography , 2019, BMC Medical Imaging.

[21]  Jeff Wood,et al.  Super‐resolution musculoskeletal MRI using deep learning , 2018, Magnetic resonance in medicine.

[22]  Choirul Anam,et al.  An algorithm for automated modulation transfer function measurement using an edge of a PMMA phantom: Impact of field of view on spatial resolution of CT images , 2018, Journal of applied clinical medical physics.

[23]  Miika T. Nieminen,et al.  Osteoarthritis year in review 2018: imaging. , 2019, Osteoarthritis and cartilage.

[24]  Cornel Zachiu,et al.  Non-rigid CT/CBCT to CBCT registration for online external beam radiotherapy guidance , 2017, Physics in medicine and biology.

[25]  Alexei A. Efros,et al.  Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[26]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Vincent Dumoulin,et al.  Deconvolution and Checkerboard Artifacts , 2016 .

[28]  Simo Saarakkala,et al.  Association between subchondral bone structure and osteoarthritis histopathological grade , 2016, Journal of orthopaedic research : official publication of the Orthopaedic Research Society.

[29]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

[30]  F O Bochud,et al.  Image quality in CT: From physical measurements to model observers. , 2015, Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics.

[31]  J. Leipsic,et al.  State of the Art: Iterative CT Reconstruction Techniques. , 2015, Radiology.

[32]  Walter Huda,et al.  X-ray-based medical imaging and resolution. , 2015, AJR. American journal of roentgenology.

[33]  Sébastien Ourselin,et al.  Toward adaptive radiotherapy for head and neck patients: Feasibility study on using CT-to-CBCT deformable registration for "dose of the day" calculations. , 2014, Medical physics.

[34]  C. H. Coyle,et al.  Early diagnosis to enable early treatment of pre-osteoarthritis , 2012, Arthritis Research & Therapy.

[35]  Daniel Kolditz,et al.  Iterative reconstruction methods in X-ray CT. , 2012, Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics.

[36]  P. Phal,et al.  Imaging the oral cavity: key concepts for the radiologist. , 2011, The British journal of radiology.

[37]  Ralph Müller,et al.  Guidelines for assessment of bone microstructure in rodents using micro–computed tomography , 2010, Journal of bone and mineral research : the official journal of the American Society for Bone and Mineral Research.

[38]  H. K. Genant,et al.  Advanced CT bone imaging in osteoporosis , 2008, Rheumatology.

[39]  S. N. Friedman,et al.  A moving slanted-edge method to measure the temporal modulation transfer function of fluoroscopic systems. , 2008, Medical physics.

[40]  Jean-Baptiste Thibault,et al.  A three-dimensional statistical approach to improved image quality for multislice helical CT. , 2007, Medical physics.

[41]  R L Morin,et al.  A practical method to measure the MTF of CT scanners. , 1982, Medical physics.

[42]  D Brüllmann,et al.  Spatial resolution in CBCT machines for dental/maxillofacial applications-what do we know today? , 2015, Dento maxillo facial radiology.

[43]  A. Parsa,et al.  Diagnostic imaging of trabecular bone microstructure for oral implants: a literature review. , 2013, Dento maxillo facial radiology.

[44]  Judith E. Adams,et al.  Advances in bone imaging for osteoporosis , 2012, Nature Reviews Endocrinology.

[45]  Markus Voelter,et al.  State of the Art , 1997, Pediatric Research.

[46]  N. Otsu A threshold selection method from gray level histograms , 1979 .