Deep learning-based and hybrid-type iterative reconstructions for CT: comparison of capability for quantitative and qualitative image quality improvements and small vessel evaluation at dynamic CE-abdominal CT with ultra-high and standard resolutions

Purpose To determine the image quality improvement including vascular structures using deep learning reconstruction (DLR) for ultra-high-resolution CT (UHR-CT) and area-detector CT (ADCT) compared to a commercially available hybrid-iterative reconstruction (IR) method. Materials and method Thirty-two patients suspected of renal cell carcinoma underwent dynamic contrast-enhanced (CE) CT using UHR-CT or ADCT systems. CT value and contrast-to-noise ratio (CNR) on each CT dataset were assessed with region of interest (ROI) measurements. For qualitative assessment of improvement for vascular structure visualization, each artery was assessed using a 5-point scale. To determine the utility of DLR, CT values and CNRs were compared among all UHR-CT data by means of ANOVA followed by Bonferroni post hoc test, and same values on ADCT data were also compared between hybrid IR and DLR methods by paired t test. Results For all arteries except the aorta, the CT value and CNR of the DLR method were significantly higher compared to those of the hybrid-type IR method in both CT systems reconstructed as 512 or 1024 matrixes ( p  < 0.05). Conclusion DLR has a higher potential to improve the image quality resulting in a more accurate evaluation for vascular structures than hybrid IR for both UHR-CT and ADCT.

[1]  K. Katada,et al.  Ultra-High-Resolution Computed Tomography Angiography for Assessment of Coronary Artery Stenosis. , 2018, Circulation journal : official journal of the Japanese Circulation Society.

[2]  Alain Vlassenbroek,et al.  Low contrast detectability and spatial resolution with model-based Iterative reconstructions of MDCT images: a phantom and cadaveric study , 2017, European Radiology.

[3]  H. Svanholm,et al.  Reproducibility of histomorphologic diagnoses with special reference to the kappa statistic , 1989, APMIS : acta pathologica, microbiologica, et immunologica Scandinavica.

[4]  Y. Ohno,et al.  Dynamic Contrast-Enhanced Perfusion Area-Detector CT: Preliminary Comparison of Diagnostic Performance for N Stage Assessment With FDG PET/CT in Non-Small Cell Lung Cancer. , 2017, AJR. American journal of roentgenology.

[5]  Wei Wei,et al.  Evaluation of Abdominal Computed Tomography Image Quality Using a New Version of Vendor-Specific Model-Based Iterative Reconstruction , 2017, Journal of computer assisted tomography.

[6]  Y. Ohno,et al.  Capability of abdominal 320-detector row CT for small vasculature assessment compared with that of 64-detector row CT. , 2011, European journal of radiology.

[7]  D. Utsunomiya,et al.  Ultra-high-resolution computed tomography can demonstrate alveolar collapse in novel coronavirus (COVID-19) pneumonia , 2020, Japanese Journal of Radiology.

[8]  K. Yamashita,et al.  Ultrahigh-resolution CT scan of the temporal bone , 2018, European Archives of Oto-Rhino-Laryngology.

[9]  J. Schuijf,et al.  Diagnostic performance of coronary CT angiography with ultra-high-resolution CT: Comparison with invasive coronary angiography. , 2018, European journal of radiology.

[10]  Y. Ohno,et al.  Comparison of capability of abdominal 320-detector row CT and of 16-detector row CT for small vasculature assessment. , 2010, The Kobe journal of medical sciences.

[11]  T. Ichikawa,et al.  Effect of Ultra High-Resolution Computed Tomography and Model-Based Iterative Reconstruction on Detectability of Simulated Submillimeter Artery. , 2020, Journal of computer assisted tomography.

[12]  Jian Zhou,et al.  Deep learning reconstruction improves image quality of abdominal ultra-high-resolution CT , 2019, European Radiology.

[13]  Y. Ohno,et al.  Differentiation of malignant and benign pulmonary nodules with quantitative first-pass 320-detector row perfusion CT versus FDG PET/CT. , 2011, Radiology.

[14]  K. Togashi,et al.  Quantitative measurement of airway dimensions using ultra-high resolution computed tomography. , 2018, Respiratory investigation.

[15]  Yuko Nakamura,et al.  Improvement of image quality at CT and MRI using deep learning , 2018, Japanese Journal of Radiology.

[16]  K. Katada,et al.  Initial clinical experience of a prototype ultra-high-resolution CT for assessment of small intracranial arteries , 2019, Japanese Journal of Radiology.

[17]  Ioannis Sechopoulos,et al.  Physical evaluation of an ultra-high-resolution CT scanner , 2020, European Radiology.

[18]  K. Ichikawa,et al.  Technical Note: Performance Comparison of Ultra-High-Resolution Scan Modes of Two Clinical Computed Tomography Systems. , 2019, Medical physics.

[19]  D. Altman,et al.  STATISTICAL METHODS FOR ASSESSING AGREEMENT BETWEEN TWO METHODS OF CLINICAL MEASUREMENT , 1986, The Lancet.

[20]  K. Katada,et al.  Visualization of Lenticulostriate Arteries on CT Angiography Using Ultra-High-Resolution CT Compared with Conventional-Detector CT , 2019, American Journal of Neuroradiology.

[21]  Yuko Nakamura,et al.  Deep Learning Reconstruction at CT: Phantom Study of the Image Characteristics. , 2020, Academic radiology.

[22]  Y. Korogi,et al.  The usefulness of full-iterative reconstruction algorithm for the visualization of cystic artery on CT angiography , 2019, Japanese Journal of Radiology.

[23]  A. Beckett,et al.  AKUFO AND IBARAPA. , 1965, Lancet.

[24]  O. Honda,et al.  Subjective and objective comparisons of image quality between ultra-high-resolution CT and conventional area detector CT in phantoms and cadaveric human lungs , 2018, European Radiology.

[25]  Y. Ohno,et al.  Solitary pulmonary nodule: Comparison of quantitative capability for differentiation and management among dynamic CE-perfusion MRI at 3 T system, dynamic CE-perfusion ADCT and FDG-PET/CT. , 2019, European journal of radiology.

[26]  Yasuo Saito,et al.  Ultra-high-resolution CT angiography of the artery of Adamkiewicz: a feasibility study , 2017, Neuroradiology.

[27]  S. Matsumoto,et al.  Solitary pulmonary nodules: Comparison of dynamic first-pass contrast-enhanced perfusion area-detector CT, dynamic first-pass contrast-enhanced MR imaging, and FDG PET/CT. , 2015, Radiology.

[28]  O. Honda,et al.  Ultra high-resolution computed tomography with 1024-matrix: Comparison with 512-matrix for the evaluation of pulmonary nodules. , 2020, European journal of radiology.

[29]  O. Honda,et al.  Influence of gantry rotation time and scan mode on image quality in ultra-high-resolution CT system. , 2018, European journal of radiology.

[30]  K. Awai,et al.  Deep learning reconstruction of drip-infusion cholangiography acquired with ultra-high-resolution computed tomography , 2020, Abdominal Radiology.

[31]  T. Yamashiro,et al.  Quantitative Emphysema Measurement On Ultra-High-Resolution CT Scans , 2019, International journal of chronic obstructive pulmonary disease.

[32]  K. Togashi,et al.  Direct evaluation of peripheral airways using ultra-high-resolution CT in chronic obstructive pulmonary disease. , 2019, European journal of radiology.

[33]  Kazuo Awai,et al.  Ultra-High-Resolution Computed Tomography of the Lung: Image Quality of a Prototype Scanner , 2015, PloS one.

[34]  Noriyuki Tomiyama,et al.  Effect of Matrix Size on the Image Quality of Ultra-high-resolution CT of the Lung: Comparison of 512 × 512, 1024 × 1024, and 2048 × 2048. , 2018, Academic radiology.

[35]  K. Awai,et al.  Deep learning–based image restoration algorithm for coronary CT angiography , 2019, European Radiology.