1
|
Detection and size measurements of kidney stones on virtual non-contrast reconstructions derived from dual-layer computed tomography in an ex vivo phantom setup. Eur Radiol 2023; 33:2995-3003. [PMID: 36422646 PMCID: PMC10017605 DOI: 10.1007/s00330-022-09261-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/11/2022] [Revised: 10/18/2022] [Accepted: 10/21/2022] [Indexed: 11/25/2022]
Abstract
OBJECTIVES To systematically investigate the usability of virtual non-contrast reconstructions (VNC) derived from dual-layer CT (DLCT) for detection and size measurements of kidney stones with regards to different degrees of surrounding iodine-induced attenuation and radiation dose. METHODS Ninety-two kidney stones of varying size (3-14 mm) and composition were placed in a phantom filled with different contrast media/water mixtures exhibiting specific iodine-induced attenuation (0-1500 HU). DLCT-scans were acquired using CTDIvol of 2 mGy and 10 mGy. Conventional images (CI) and VNC0H-1500HU were reconstructed. Reference stone size was determined using a digital caliper (Man-M). Visibility and stone size were assessed. Statistical analysis was performed using the McNemar test, Wilcoxon test, and the coefficient of determination. RESULTS All stones were visible on CI0HU and VNC200HU. Starting at VNC400 HU, the detection rate decreased with increasing HU and was significantly lower as compared to CI0HU on VNC≥ 600HU (100.0 vs. 94.0%, p < 0.05). The overall detection rate was higher using 10 mGy as compared to 2 mGy protocol (87.9 vs. 81.8%; p < 0.001). Stone size was significantly overestimated on all VNC compared to Man-M (7.0 ± 3.5 vs. 6.6 ± 2.8 mm, p < 0.001). Again, the 10 mGy protocol tended to show a better correlation with Man-M as compared to 2 mGy protocol (R2 = 0.39-0.68 vs. R2 = 0.31-0.57). CONCLUSIONS Detection and size measurements of kidney stones surrounded by contrast media on VNC are feasible. The detection rate of kidney stones decreases with increasing iodine-induced attenuation and with decreasing radiation dose as well as stone size, while remaining comparable to CI0HU on VNC ≤ 400 HU. KEY POINTS • The detection rate of kidney stones on VNC depends on the surrounding iodine-induced attenuation, the used radiation dose, and the stone size. • The detection rate of kidney stones on VNC decreases with greater iodine-induced attenuation and with lower radiation dose, particularly in small stones. • The visibility of kidney stones on VNC ≤ 400 HU remains comparable to true-non-contrast scans even when using a low-dose technique.
Collapse
|
2
|
Niehoff JH, Carmichael AF, Woeltjen MM, Boriesosdick J, Michael AE, Schmidt B, Panknin C, Flohr TG, Shahzadi I, Piechota H, Borggrefe J, Kroeger JR. Clinical Low-Dose Photon-Counting CT for the Detection of Urolithiasis: Radiation Dose Reduction Is Possible without Compromising Image Quality. Diagnostics (Basel) 2023; 13:diagnostics13030458. [PMID: 36766563 PMCID: PMC9914353 DOI: 10.3390/diagnostics13030458] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2022] [Revised: 01/18/2023] [Accepted: 01/23/2023] [Indexed: 01/28/2023] Open
Abstract
Background: This study evaluated the feasibility of reducing the radiation dose in abdominal imaging of urolithiasis with a clinical photon-counting CT (PCCT) by gradually lowering the image quality level (IQL) without compromising the image quality and diagnostic value. Methods: Ninety-eight PCCT examinations using either IQL70 (n = 31), IQL60 (n = 31) or IQL50 (n = 36) were retrospectively included. Parameters for the radiation dose and the quantitative image quality were analyzed. Qualitative image quality, presence of urolithiasis and diagnostic confidence were rated. Results: Lowering the IQL from 70 to 50 led to a significant decrease (22.8%) in the size-specific dose estimate (SSDE, IQL70 4.57 ± 0.84 mGy, IQL50 3.53 ± 0.70 mGy, p < 0.001). Simultaneously, lowering the IQL led to a minimal deterioration of the quantitative quality, e.g., image noise increased from 9.13 ± 1.99 (IQL70) to 9.91 ± 1.77 (IQL50, p = 0.248). Radiologists did not notice major changes in the image quality throughout the IQLs. Detection rates of urolithiasis (91.3-100%) did not differ markedly. Diagnostic confidence was high and not influenced by the IQL. Conclusions: Adjusting the PCCT scan protocol by lowering the IQL can significantly reduce the radiation dose without significant impairment of the image quality. The detection rate and diagnostic confidence are not impaired by using an ultra-low-dose PCCT scan protocol.
Collapse
Affiliation(s)
- Julius Henning Niehoff
- Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Ruhr University Bochum, 44801 Bochum, Germany
- Correspondence: ; Tel.: +49-571-790-4601; Fax: +49-571-790-294601
| | - Alexandra Fiona Carmichael
- Department of Urology, Johannes Wesling University Hospital, Ruhr University Bochum, 44801 Bochum, Germany
| | - Matthias Michael Woeltjen
- Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Ruhr University Bochum, 44801 Bochum, Germany
| | - Jan Boriesosdick
- Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Ruhr University Bochum, 44801 Bochum, Germany
| | - Arwed Elias Michael
- Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Ruhr University Bochum, 44801 Bochum, Germany
| | | | | | | | | | - Hansjuergen Piechota
- Department of Urology, Johannes Wesling University Hospital, Ruhr University Bochum, 44801 Bochum, Germany
| | - Jan Borggrefe
- Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Ruhr University Bochum, 44801 Bochum, Germany
| | - Jan Robert Kroeger
- Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Ruhr University Bochum, 44801 Bochum, Germany
| |
Collapse
|
3
|
Niehoff JH, Carmichael AF, Woeltjen MM, Boriesosdick J, Lopez Schmidt I, Michael AE, Große Hokamp N, Piechota H, Borggrefe J, Kroeger JR. Clinical Low Dose Photon Counting CT for the Detection of Urolithiasis: Evaluation of Image Quality and Radiation Dose. Tomography 2022; 8:1666-1675. [PMID: 35894003 PMCID: PMC9326560 DOI: 10.3390/tomography8040138] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2022] [Revised: 06/17/2022] [Accepted: 06/20/2022] [Indexed: 11/18/2022] Open
Abstract
The purpose of this study was the evaluation of image quality and radiation dose parameters of the novel photon counting CT (PCCT, Naeotom Alpha, Siemens Healthineers) using low-dose scan protocols for the detection of urolithiasis. Standard CT scans were used as a reference (S40, Somatom Sensation 40, Siemens Healthineers). Sixty-three patients, who underwent CT scans between August and December 2021, were retrospectively enrolled. Thirty-one patients were examined with the PCCT and 32 patients were examined with the S40. Radiation dose parameters, as well as quantitative and qualitative image parameters, were analyzed. The presence of urolithiasis, image quality, and diagnostic certainty were rated on a 5-point-scale by 3 blinded readers. Both patient groups (PCCT and S40) did not differ significantly in terms of body mass index. Radiation dose was significantly lower for examinations with the PCCT compared to the S40 (2.4 ± 1.0 mSv vs. 3.4 ± 1.0 mSv; p < 0.001). The SNR was significantly better on images acquired with the PCCT (13.3 ± 3.3 vs. 8.2 ± 1.9; p < 0.001). The image quality of the PCCT was rated significantly better (4.3 ± 0.7 vs. 2.8 ± 0.6; p < 0.001). The detection rate of kidney or ureter calculi was excellent with both CT scanners (PCCT 97.8% and S40 99%, p = 0.611). In high contrast imaging, such as the depiction of stones of the kidney and the ureter, PCCT allows a significant reduction of radiation dose, while maintaining excellent diagnostic confidence and image quality. Given this image quality with our current protocol, further adjustments towards ultra-low-dose CT scans appear feasible.
Collapse
Affiliation(s)
- Julius Henning Niehoff
- Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Ruhr University Bochum, 44801 Bochum, Germany; (M.M.W.); (J.B.); (I.L.S.); (A.E.M.); (J.B.); (J.R.K.)
- Correspondence: ; Tel.: +49-571-790-4601
| | - Alexandra Fiona Carmichael
- Department of Urology, Johannes Wesling University Hospital, Ruhr University Bochum, 44801 Bochum, Germany; (A.F.C.); (H.P.)
| | - Matthias Michael Woeltjen
- Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Ruhr University Bochum, 44801 Bochum, Germany; (M.M.W.); (J.B.); (I.L.S.); (A.E.M.); (J.B.); (J.R.K.)
| | - Jan Boriesosdick
- Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Ruhr University Bochum, 44801 Bochum, Germany; (M.M.W.); (J.B.); (I.L.S.); (A.E.M.); (J.B.); (J.R.K.)
| | - Ingo Lopez Schmidt
- Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Ruhr University Bochum, 44801 Bochum, Germany; (M.M.W.); (J.B.); (I.L.S.); (A.E.M.); (J.B.); (J.R.K.)
| | - Arwed Elias Michael
- Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Ruhr University Bochum, 44801 Bochum, Germany; (M.M.W.); (J.B.); (I.L.S.); (A.E.M.); (J.B.); (J.R.K.)
| | - Nils Große Hokamp
- Faculty of Medicine and University Hospital Cologne, Institute for Diagnostic and Interventional Radiology, University of Cologne, 50937 Cologne, Germany;
| | - Hansjuergen Piechota
- Department of Urology, Johannes Wesling University Hospital, Ruhr University Bochum, 44801 Bochum, Germany; (A.F.C.); (H.P.)
| | - Jan Borggrefe
- Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Ruhr University Bochum, 44801 Bochum, Germany; (M.M.W.); (J.B.); (I.L.S.); (A.E.M.); (J.B.); (J.R.K.)
| | - Jan Robert Kroeger
- Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Ruhr University Bochum, 44801 Bochum, Germany; (M.M.W.); (J.B.); (I.L.S.); (A.E.M.); (J.B.); (J.R.K.)
| |
Collapse
|
4
|
Reimer RP, Klein K, Rinneburger M, Zopfs D, Lennartz S, Salem J, Heidenreich A, Maintz D, Haneder S, Große Hokamp N. Manual kidney stone size measurements in computed tomography are most accurate using multiplanar image reformatations and bone window settings. Sci Rep 2021; 11:16437. [PMID: 34385563 PMCID: PMC8361194 DOI: 10.1038/s41598-021-95962-z] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/13/2021] [Accepted: 07/19/2021] [Indexed: 12/26/2022] Open
Abstract
Computed tomography in suspected urolithiasis provides information about the presence, location and size of stones. Particularly stone size is a key parameter in treatment decision; however, data on impact of reformatation and measurement strategies is sparse. This study aimed to investigate the influence of different image reformatations, slice thicknesses and window settings on stone size measurements. Reference stone sizes of 47 kidney stones representative for clinically encountered compositions were measured manually using a digital caliper (Man-M). Afterwards stones were placed in a 3D-printed, semi-anthropomorphic phantom, and scanned using a low dose protocol (CTDIvol 2 mGy). Images were reconstructed using hybrid-iterative and model-based iterative reconstruction algorithms (HIR, MBIR) with different slice thicknesses. Two independent readers measured largest stone diameter on axial (2 mm and 5 mm) and multiplanar reformatations (based upon 0.67 mm reconstructions) using different window settings (soft-tissue and bone). Statistics were conducted using ANOVA ± correction for multiple comparisons. Overall stone size in CT was underestimated compared to Man-M (8.8 ± 2.9 vs. 7.7 ± 2.7 mm, p < 0.05), yet closely correlated (r = 0.70). Reconstruction algorithm and slice thickness did not significantly impact measurements (p > 0.05), while image reformatations and window settings did (p < 0.05). CT measurements using multiplanar reformatation with a bone window setting showed closest agreement with Man-M (8.7 ± 3.1 vs. 8.8 ± 2.9 mm, p < 0.05, r = 0.83). Manual CT-based stone size measurements are most accurate using multiplanar image reformatation with a bone window setting, while measurements on axial planes with different slice thicknesses underestimate true stone size. Therefore, this procedure is recommended when impacting treatment decision.
Collapse
Affiliation(s)
- Robert Peter Reimer
- Department of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str. 62, 50937, Cologne, Germany.
| | - Konstantin Klein
- Department of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| | - Miriam Rinneburger
- Department of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| | - David Zopfs
- Department of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| | - Simon Lennartz
- Department of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
- Department of Radiology, Harvard Medical School, Massachusetts General Hospital, 55 Fruit St, White 270, Boston, MA, 02114, USA
| | - Johannes Salem
- Department of Urology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| | - Axel Heidenreich
- Department of Urology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| | - David Maintz
- Department of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| | - Stefan Haneder
- Department of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| | - Nils Große Hokamp
- Department of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| |
Collapse
|
5
|
Wang X, Zheng F, Xiao R, Liu Z, Li Y, Li J, Zhang X, Hao X, Zhang X, Guo J, Zhang Y, Xue H, Jin Z. Comparison of image quality and lesion diagnosis in abdominopelvic unenhanced CT between reduced-dose CT using deep learning post-processing and standard-dose CT using iterative reconstruction: A prospective study. Eur J Radiol 2021; 139:109735. [PMID: 33932717 DOI: 10.1016/j.ejrad.2021.109735] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2021] [Revised: 04/06/2021] [Accepted: 04/19/2021] [Indexed: 11/24/2022]
Abstract
PURPOSE To compare image quality and lesion diagnosis between reduced-dose abdominopelvic unenhanced computed tomography (CT) using deep learning (DL) post-processing and standard-dose CT using iterative reconstruction (IR). METHOD Totally 251 patients underwent two consecutive abdominopelvic unenhanced CT scans of the same range, including standard and reduced doses, respectively. In group A, standard-dose data were reconstructed by (blend 30 %) IR. In group B, reduced-dose data were reconstructed by filtered back projection reconstruction to obtain group B1 images, and post-processed using the DL algorithm (NeuAI denosing, Neusoft medical, Shenyang, China) with 50 % and 100 % weights to obtain group B2 and B3 images, respectively. Then, CT values of the liver, the second lumbar vertebral centrum, the erector spinae and abdominal subcutaneous fat were measured. CT values, noise levels, signal-to-noise ratios (SNRs), contrast-to-noise ratios (CNRs), radiation doses and subjective scores of image quality were compared. Subjective evaluations of low-density liver lesions were compared by diagnostic results from enhanced CT or Magnetic Resonance Imaging. RESULTS Groups B3 and B1 showed the lowest and highest noise levels, respectively (P < 0.001). The SNR and CNR in group B3 were highest (P < 0.001). The radiation dose in group B was reduced by 71.5 % on average compared to group A. Subjective scores in groups A and B2 were highest (P < 0.001). Diagnostic sensitivity and confidence for liver metastases in groups A and B2 were highest (P < 0.001). CONCLUSIONS Reduced-dose abdominopelvic unenhanced CT combined with DL post-processing could ensure image quality and satisfy diagnostic needs.
Collapse
Affiliation(s)
- Xiao Wang
- From the Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China
| | - Fuling Zheng
- From the Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China
| | - Ran Xiao
- From the Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China
| | - Zhuoheng Liu
- From CT Business Unit, Neusoft Medical System Company, Shenyang, China
| | - Yutong Li
- From CT Business Unit, Neusoft Medical System Company, Shenyang, China
| | - Juan Li
- From the Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China
| | - Xi Zhang
- From the Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China
| | - Xuemin Hao
- From the Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China
| | - Xinhu Zhang
- From the Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China
| | - Jiawu Guo
- From the Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China
| | - Yan Zhang
- From the Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China
| | - Huadan Xue
- From the Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China.
| | - Zhengyu Jin
- From the Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China.
| |
Collapse
|
6
|
Size and volume of kidney stones in computed tomography: Influence of acquisition techniques and image reconstruction parameters. Eur J Radiol 2020; 132:109267. [PMID: 32949914 DOI: 10.1016/j.ejrad.2020.109267] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2020] [Revised: 08/26/2020] [Accepted: 08/28/2020] [Indexed: 12/31/2022]
Abstract
PURPOSE Computed tomography (CT) is routinely used to assess suspected urolithiasis. Information obtained from CT include presence, location and size of stones, with the latter frequently determining treatment strategy. While there is consensus regarding measurements procedures of kidney stones, influence of radiation dose and reconstruction techniques on stone measurements are unknown. The purpose of this study was to systematically evaluate the influence of these technical determinants on kidney stone size measurements. METHOD 47 kidney stones of different composition were scanned using a 64-row-multi-detector CT in a 3D-printed, semi-anthropomorphic phantom. Reference stone sizes were measured manually with a digital caliper (Man-M). Stones were imaged with 2 and 10 mGy CTDI. Images were reconstructed using filtered-back-projection, hybrid-iterative and model-based-iterative reconstruction algorithms (FBP, HIR, MBIR) in combination with different kernels and denoising levels. All stones underwent semi-automatic, threshold-based segmentation for computation of maximum diameter and volume. Statistics were conducted using ANOVA ± correction for multiple comparisons. RESULTS Overall stone size as compared to manual measurements was overestimated in CT (10.0 ± 3.1 vs. 8.8 ± 2.9 mm, p < 0.05) yet showing a good correlation (R2 = 0.66). Radiation dose and denoising levels did not significantly influence measurements (p > 0.05). MBIR and sharp kernels showed closest agreement with Man-M (9.3 ± 3.1 vs. 8.8 ± 2.9 mm, p < 0.05). Differences within single stones were as high as 40 % (e.g. Man-M: 5.9 mm, CT: 7.3-12.0 mm). CONCLUSIONS CT-based measurements of kidney stone size appear unaffected by radiation dose and denoising technique, whereas reconstruction algorithms and kernels demonstrate a relevant impact on size measurements. Smallest differences were found using MBIR with a sharp kernel.
Collapse
|
7
|
Große Hokamp N, Lennartz S, Salem J, Pinto Dos Santos D, Heidenreich A, Maintz D, Haneder S. Dose independent characterization of renal stones by means of dual energy computed tomography and machine learning: an ex-vivo study. Eur Radiol 2019; 30:1397-1404. [PMID: 31773296 DOI: 10.1007/s00330-019-06455-7] [Citation(s) in RCA: 16] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2019] [Revised: 07/26/2019] [Accepted: 09/12/2019] [Indexed: 12/17/2022]
Abstract
OBJECTIVES To predict the main component of pure and mixed kidney stones using dual-energy computed tomography and machine learning. METHODS 200 kidney stones with a known composition as determined by infrared spectroscopy were examined using a non-anthropomorphic phantom on a spectral detector computed tomography scanner. Stones were of either pure (monocrystalline, n = 116) or compound (dicrystalline, n = 84) composition. Image acquisition was repeated twice using both, normal and low-dose protocols, respectively (ND/LD). Conventional images and low and high keV virtual monoenergetic images were reconstructed. Stones were semi-automatically segmented. A shallow neural network was trained using data from ND1 acquisition split into training (70%), testing (15%) and validation-datasets (15%). Performance for ND2 and both LD acquisitions was tested. Accuracy on a per-voxel and a per-stone basis was calculated. RESULTS Main components were: Whewellite (n = 80), weddellite (n = 21), Ca-phosphate (n = 39), cysteine (n = 20), struvite (n = 13), uric acid (n = 18) and xanthine stones (n = 9). Stone size ranged from 3 to 18 mm. Overall accuracy for predicting the main component on a per-voxel basis attained by ND testing dataset was 91.1%. On independently tested acquisitions, accuracy was 87.1-90.4%. CONCLUSIONS Even in compound stones, the main component can be reliably determined using dual energy CT and machine learning, irrespective of dose protocol. KEY POINTS • Spectral Detector Dual Energy CT and Machine Learning allow for an accurate prediction of stone composition. • Ex-vivo study demonstrates the dose independent assessment of pure and compound stones. • Lowest accuracy is reported for compound stones with struvite as main component.
Collapse
Affiliation(s)
- Nils Große Hokamp
- Faculty of Medicine and University Hospital Cologne, Institute for Diagnostic and Interventional Radiology, University of Cologne, Kerpener Str. 62, 50937, Cologne, Germany.
| | - Simon Lennartz
- Faculty of Medicine and University Hospital Cologne, Institute for Diagnostic and Interventional Radiology, University of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
- Else Kröner Forschungskolleg Clonal Evolution in Cancer, University Hospital Cologne, Cologne, Germany
| | - Johannes Salem
- Faculty of Medicine and University Hospital Cologne, Department of Urology, University of Cologne, Cologne, Germany
| | - Daniel Pinto Dos Santos
- Faculty of Medicine and University Hospital Cologne, Institute for Diagnostic and Interventional Radiology, University of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| | - Axel Heidenreich
- Faculty of Medicine and University Hospital Cologne, Department of Urology, University of Cologne, Cologne, Germany
| | - David Maintz
- Faculty of Medicine and University Hospital Cologne, Institute for Diagnostic and Interventional Radiology, University of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| | - Stefan Haneder
- Faculty of Medicine and University Hospital Cologne, Institute for Diagnostic and Interventional Radiology, University of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| |
Collapse
|