1
|
Ren J, Zhao J, Wang Y, Xu M, Liu XY, Jin ZY, He YL, Li Y, Xue HD. Value of deep-learning image reconstruction at submillisievert CT for evaluation of the female pelvis. Clin Radiol 2023; 78:e881-e888. [PMID: 37620170 DOI: 10.1016/j.crad.2023.07.016] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2023] [Revised: 06/26/2023] [Accepted: 07/26/2023] [Indexed: 08/26/2023]
Abstract
AIM To assess the value of deep-learning reconstruction (DLR) at submillisievert computed tomography (CT) for the evaluation of the female pelvis, with standard dose (SD) hybrid iterative reconstruction (IR) images as reference. MATERIALS AND METHODS The present study enrolled 50 female patients consecutively who underwent contrast-enhanced abdominopelvic CT for clinically indicated reasons. Submillisievert pelvic images were acquired using a noise index of 15 for low-dose (LD) scans, which were reconstructed with DLR (body and body sharp), hybrid-IR, and model-based IR (MBIR). Additionally, SD scans were reconstructed with a noise index of 7.5 using hybrid-IR. Radiation dose, quantitative image quality, overall image quality, image appearance using a five-point Likert scale (1-5: worst to best), and lesion evaluation in both SD and LD images were analysed and compared. RESULTS The submillisievert pelvic CT examinations showed a 61.09 ± 4.13% reduction in the CT dose index volume compared to SD examinations. Among the LD images, DLR (body sharp) had the highest quantitative quality, followed by DLR (body), MBIR, and hybrid-IR. LD DLR (body) had overall image quality comparable to the reference (p=0.084) and favourable image appearance (p=0.209). In total, 40 pelvic lesions were detected in both SD and LD images. LD DLR (body and body sharp) exhibited similar diagnostic confidence (p=0.317 and 0.096) compared with SD hybrid-IR. CONCLUSION DLR algorithms, providing comparable image quality and diagnostic confidence, are feasible in submillisievert abdominopelvic CT. The DLR (body) algorithm with favourable image appearance is recommended in clinical settings.
Collapse
Affiliation(s)
- J Ren
- Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, PR China
| | - J Zhao
- Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, PR China
| | - Y Wang
- Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, PR China
| | - M Xu
- Cannon Medical System, Beijing, PR China
| | - X-Y Liu
- Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, PR China
| | - Z-Y Jin
- Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, PR China
| | - Y-L He
- Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, PR China.
| | - Y Li
- Department of Obstetrics and Gynecology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, National Clinical Research Center for Obstetric & Gynecologic Diseases, Beijing, PR China.
| | - H-D Xue
- Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, PR China.
| |
Collapse
|
2
|
Nishikawa M, Machida H, Shimizu Y, Kariyasu T, Morisaka H, Adachi T, Nakai T, Sakaguchi K, Saito S, Matsumoto S, Koyanagi M, Yokoyama K. Image quality and radiologists' subjective acceptance using model-based iterative and deep learning reconstructions as adjuncts to ultrahigh-resolution CT in low-dose contrast-enhanced abdominopelvic CT: phantom and clinical pilot studies. Abdom Radiol (NY) 2022; 47:891-902. [PMID: 34914007 PMCID: PMC8807451 DOI: 10.1007/s00261-021-03373-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/01/2021] [Revised: 11/29/2021] [Accepted: 11/29/2021] [Indexed: 12/02/2022]
Abstract
Purpose In contrast-enhanced abdominopelvic CT (CE-APCT) for oncologic follow-up, ultrahigh-resolution CT (UHRCT) may improve depiction of fine lesions and low-dose scans are desirable for minimizing the potential adverse effects by ionizing radiation. We compared image quality and radiologists’ acceptance of model-based iterative (MBIR) and deep learning (DLR) reconstructions of low-dose CE-APCT by UHRCT. Methods Using our high-resolution (matrix size: 1024) and low-dose (tube voltage 100 kV; noise index: 20–40 HU) protocol, we scanned phantoms to compare the modulation transfer function and noise power spectrum between MBIR and DLR and assessed findings in 36 consecutive patients who underwent CE-APCT (noise index: 35 HU; mean CTDIvol: 4.2 ± 1.6 mGy) by UHRCT. We used paired t-test to compare objective noise and contrast-to-noise ratio (CNR) and Wilcoxon signed-rank test to compare radiologists’ subjective acceptance regarding noise, image texture and appearance, and diagnostic confidence between MBIR and DLR using our routine protocol (matrix size: 512; tube voltage: 120 kV; noise index: 15 HU) for reference. Results Phantom studies demonstrated higher spatial resolution and lower low-frequency noise by DLR than MBIR at equal doses. Clinical studies indicated significantly worse objective noise, CNR, and subjective noise by DLR than MBIR, but other subjective characteristics were better (P < 0.001 for all). Compared with the routine protocol, subjective noise was similar or better by DLR, and other subjective characteristics were similar or worse by MBIR. Conclusion Image quality, except regarding noise characteristics, and acceptance by radiologists were better by DLR than MBIR in low-dose CE-APCT by UHRCT. Graphical abstract ![]()
Collapse
|
3
|
He Y, Zeng L, Yu W, Gong C. Noise suppression-guided image filtering for low-SNR CT reconstruction. Med Biol Eng Comput 2020; 58:2621-2629. [PMID: 32839918 DOI: 10.1007/s11517-020-02246-1] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2019] [Accepted: 08/16/2020] [Indexed: 10/23/2022]
Abstract
In practical computed tomography (CT) applications, projections with low signal-to-noise ratio (SNR) are often encountered due to the reduction of radiation dose or device limitations. In these situations, classical reconstruction algorithms, like simultaneous algebraic reconstruction technique (SART), cannot reconstruct high-quality CT images. Block-matching and 3D filtering (BM3D)-based iterative reconstruction algorithm (POCS-BM3D) has remarkable effect in dealing with CT reconstruction from noisy projections. However, BM3D may restrain noise with excessive loss of details in the case of low-SNR CT reconstruction. In order to achieve a preferable trade-off between noise suppression and edge preservation, we introduce guided image filtering (GIF) into low-SNR CT reconstruction, and propose noise suppression-guided image filtering reconstruction (NSGIFR) algorithm. In each iteration of NSGIFR, the output image of SART reserves more details and is used as input image of GIF, while the image denoised by BM3D serves as guidance image of GIF. Experimental results indicate that the proposed algorithm displays outstanding performance on preserving structures and suppressing noise for low-SNR CT reconstruction. NSGIFR can achieve more superior image quality than SART, POCS-TV and POCS-BM3D in terms of visual effect and quantitative analysis. Graphical abstract Block-matching and 3D filtering (BM3D)-based iterative reconstruction algorithm (POCS-BM3D) has remarkable effect in dealing with CT reconstruction from noisy projections. However, BM3D may restrain noise with excessive loss of details in the case of low-SNR CT reconstruction. In order to achieve a preferable trade-off between noise suppression and edge preservation, we introduce guided image filtering (GIF) into low-SNR CT reconstruction, and propose noise suppression-guided image filtering reconstruction (NSGIFR) algorithm.
Collapse
Affiliation(s)
- Yuanwei He
- College of Mathematics and Statistics, Chongqing University, Chongqing, 401331, China.,Engineering Research Center of Industrial Computed Tomography Nondestructive Testing of the Education Ministry of China, Chongqing University, Chongqing, 400044, China
| | - Li Zeng
- College of Mathematics and Statistics, Chongqing University, Chongqing, 401331, China. .,Engineering Research Center of Industrial Computed Tomography Nondestructive Testing of the Education Ministry of China, Chongqing University, Chongqing, 400044, China.
| | - Wei Yu
- School of Biomedical Engineering, Hubei University of Science and Technology, Xianning, 437100, China
| | - Changcheng Gong
- Engineering Research Center of Industrial Computed Tomography Nondestructive Testing of the Education Ministry of China, Chongqing University, Chongqing, 400044, China.,Key Laboratory of Optoelectronic Technology and System of the Education Ministry of China, Chongqing University, Chongqing, 400044, China
| |
Collapse
|
4
|
Zhang L, Chen YF, Che YX, Xu YF, Zheng J, Yu SJ. The impact of adaptive iterative dose reduction 3D on the improvement of shoulder image quality in head and neck CTA. Curr Med Res Opin 2019; 35:887-891. [PMID: 30366505 DOI: 10.1080/03007995.2018.1541446] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 10/28/2022]
Abstract
OBJECTIVE The aim of this study was to determine the impact of adaptive iterative dose reduction 3 D (AIDR3D) on the improvement of shoulder image quality in low-radiographic dose head and neck CT angiography (CTA). MATERIALS AND METHODS Ninety patients who underwent CTA examination were randomly divided into two groups, namely group A (n = 45) and B (n = 45). Patients in group A were scanned under 120 kV and 300 mA, with images reconstructed by filtered back projection (FBP), and patients in group B were scanned under 80 kV and auto mA with images reconstructed by AIDR3D. Image quality was accessed by two experienced radiologists. The noise, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of common carotid artery (CCA) at C7 level, and radiation dosage were compared between the two groups. RESULTS The score of CCA in group B was significantly higher than group A (p < 0.05), and there were no significant differences in the scores of carotid sinus and internal carotid artery between the two groups (p > 0.05). The score of intracranial artery in group B was lower than that of group A, however, the image quality in group B can meet the requirement of clinical diagnosis. The noise value of CCA at C7 level in group B was significantly lower than that of group A (p < 0.05). SNR and CNR values of CCA at C7 level in group B were significantly higher than those of group A (p < 0.05). Effective radiation dose in group B was significantly decreased compared with group A (p < 0.05). CONCLUSION AIDR3D remarkably improved image quality in low-radiographic dose head and neck CTA over FBP, which made the low-dose CTA images meet the requirement of clinical diagnosis.
Collapse
Affiliation(s)
- Li Zhang
- a Department of CT Diagnosis , Cangzhou Central Hospital , Cangzhou , Hebei 061001 , PR China
| | - Yue-Feng Chen
- a Department of CT Diagnosis , Cangzhou Central Hospital , Cangzhou , Hebei 061001 , PR China
| | - Yan-Xu Che
- a Department of CT Diagnosis , Cangzhou Central Hospital , Cangzhou , Hebei 061001 , PR China
| | - Yan-Feng Xu
- a Department of CT Diagnosis , Cangzhou Central Hospital , Cangzhou , Hebei 061001 , PR China
| | - Jing Zheng
- a Department of CT Diagnosis , Cangzhou Central Hospital , Cangzhou , Hebei 061001 , PR China
| | - Shu-Jing Yu
- a Department of CT Diagnosis , Cangzhou Central Hospital , Cangzhou , Hebei 061001 , PR China
| |
Collapse
|
5
|
Yu W, Wang C, Nie X, Zeng D. Sparsity-induced dynamic guided filtering approach for sparse-view data toward low-dose x-ray computed tomography. ACTA ACUST UNITED AC 2018; 63:235016. [DOI: 10.1088/1361-6560/aaeea6] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/12/2023]
|
6
|
Kim SY, Cho JY, Lee J, Hwang SI, Moon MH, Lee EJ, Hong SS, Kim CK, Kim KA, Park SB, Sung DJ, Kim Y, Kim YM, Jung SI, Rha SE, Kim DW, Lee H, Shim Y, Hwang I, Woo S, Choi HJ. Low-Tube-Voltage CT Urography Using Low-Concentration-Iodine Contrast Media and Iterative Reconstruction: A Multi-Institutional Randomized Controlled Trial for Comparison with Conventional CT Urography. Korean J Radiol 2018; 19:1119-1129. [PMID: 30386143 PMCID: PMC6201985 DOI: 10.3348/kjr.2018.19.6.1119] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/26/2017] [Accepted: 06/07/2018] [Indexed: 01/29/2023] Open
Abstract
Objective To compare the image quality of low-tube-voltage and low-iodine-concentration-contrast-medium (LVLC) computed tomography urography (CTU) with iterative reconstruction (IR) with that of conventional CTU. Materials and Methods This prospective, multi-institutional, randomized controlled trial was performed at 16 hospitals using CT scanners from various vendors. Patients were randomly assigned to the following groups: 1) the LVLC-CTU (80 kVp and 240 mgI/mL) with IR group and 2) the conventional CTU (120 kVp and 350 mgI/mL) with filtered-back projection group. The overall diagnostic acceptability, sharpness, and noise were assessed. Additionally, the mean attenuation, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and figure of merit (FOM) in the urinary tract were evaluated. Results The study included 299 patients (LVLC-CTU group: 150 patients; conventional CTU group: 149 patients). The LVLC-CTU group had a significantly lower effective radiation dose (5.73 ± 4.04 vs. 8.43 ± 4.38 mSv) compared to the conventional CTU group. LVLC-CTU showed at least standard diagnostic acceptability (score ≥ 3), but it was non-inferior when compared to conventional CTU. The mean attenuation value, mean SNR, CNR, and FOM in all pre-defined segments of the urinary tract were significantly higher in the LVLC-CTU group than in the conventional CTU group. Conclusion The diagnostic acceptability and quantitative image quality of LVLC-CTU with IR are not inferior to those of conventional CTU. Additionally, LVLC-CTU with IR is beneficial because both radiation exposure and total iodine load are reduced.
Collapse
Affiliation(s)
- Sang Youn Kim
- Department of Radiology, Seoul National University Hospital, Seoul National University College of Medicine, Seoul 03080, Korea
| | - Jeong Yeon Cho
- Department of Radiology, Seoul National University Hospital, Seoul National University College of Medicine, Seoul 03080, Korea.,Institute of Radiation Medicine and Kidney Research Institute, Seoul National University, Seoul 03080, Korea
| | - Joongyub Lee
- Medical Research Collaborating Center, Seoul National University Hospital, Seoul National University College of Medicine, Seoul 03080, Korea
| | - Sung Il Hwang
- Department of Radiology, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seongnam 13621, Korea
| | - Min Hoan Moon
- Department of Radiology, SMG-SNU Boramae Medical Center, Seoul National University College of Medicine, Seoul 07061, Korea
| | - Eun Ju Lee
- Department of Radiology, Ajou University Hospital, Ajou University School of Medicine, Suwon 16499, Korea
| | - Seong Sook Hong
- Department of Radiology, Soonchunhyang University Seoul Hospital, Seoul 04401, Korea
| | - Chan Kyo Kim
- Department of Radiology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul 06351, Korea
| | - Kyeong Ah Kim
- Department of Radiology, Korea University Guro Hospital, Korea University College of Medicine, Seoul 08308, Korea
| | - Sung Bin Park
- Department of Radiology, Chung-Ang University Hospital, Chung-Ang University College of Medicine, Seoul 06973, Korea
| | - Deuk Jae Sung
- Department of Radiology, Korea University Anam Hospital, Korea University College of Medicine, Seoul 02841, Korea
| | - Yongsoo Kim
- Department of Radiology, Hanyang University Guri Hospital, Guri 11923, Korea
| | - You Me Kim
- Department of Radiology, Dankook University Hospital, Dankook University College of Medicine, Cheonan 31116, Korea
| | - Sung Il Jung
- Department of Radiology, Konkuk University Medical Center, Konkuk University School of Medicine, Seoul 05030, Korea
| | - Sung Eun Rha
- Department of Radiology, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Korea
| | - Dong Won Kim
- Department of Radiology, Dong-A University College of Medicine, Busan 49201, Korea
| | - Hyun Lee
- Department of Radiology, Hallym University Sacred Heart Hospital, Anyang 14068, Korea
| | - Youngsup Shim
- Department of Radiology, Gachon University, Gil Medical Center, Incheon 21565, Korea
| | - Inpyeong Hwang
- Department of Radiology, Cheongyang-gun Health Center and County Hospital, Cheongyang 33324, Korea
| | - Sungmin Woo
- Department of Radiology, Armed Forces Daejeon Hospital, Daejeon 34059, Korea
| | - Hyuck Jae Choi
- Department of Radiology, Sheikh Khalifa Specialty Hospital, Ras al Khaimah, UAE
| |
Collapse
|
7
|
Zhao Y, Suo H, Wu Y, Zuo Z, Zhao S, Cheng S. Noise indices adjusted to body mass index and an iterative reconstruction algorithm maintain image quality on low-dose contrast-enhanced liver CT. JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY 2017; 25:XST16222. [PMID: 28387698 DOI: 10.3233/xst-16222] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/07/2023]
Abstract
OBJECTIVES Since body mass index (BMI) affects medical imaging quality or noise due to penetration of the radiation through bodies with varying sizes, this study aims to investigate and determine the optimal BMI-adjusted noise index (NI) setting on the contrast-enhanced liver CT scans obtained using 3D Smart mA technology with adaptive statistical iterative reconstruction (ASIR 2.0) algorithm. MATERIALS AND METHODS A total of 320 patients who had contrast-enhanced liver CT scans were divided into two equal-sized groups: A (18.5 kg/m2≤BMI<24.9 kg/m2) and B (24.9 kg/m2 ≤ BMI ≤34.9 kg/m2). The two groups were randomly divided into four subgroups with an NI of 11, 13, 15, and 17. All images were reconstructed with 50% ASIR 2.0. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated after the late arterial, portal venous, and equilibrium phases were completed. Images were evaluated by two radiologists using a subjective 0 -5 scale. Mean CT dose index of volume, dose-length product, and effective dose (ED) were calculated and compared using one-way ANOVA. RESULTS In group A, the best-quality images obtained at the lowest ED were scanned at an NI of 15 in the late arterial phase, and at an NI of 17 in the portal venous and equilibrium phases. In group B, the best results were obtained at an NI of 13 in the late arterial phase, and at an NI of 15 in the portal venous and equilibrium phases. CONCLUSION Adjusting NI and iterative reconstruction algorithm based on body mass index can help improve image quality on contrast-enhanced liver CT scans, even at low radiation dose.
Collapse
Affiliation(s)
- Yongxia Zhao
- The Affiliated Hospital of Hebei University, Baoding, Hebei Province, China
| | - Hongna Suo
- Medicine School of Hebei University, Baoding, Hebei Province, China
| | - Yanmin Wu
- The Affiliated Hospital of Hebei University, Baoding, Hebei Province, China
| | - Ziwei Zuo
- The Affiliated Hospital of Hebei University, Baoding, Hebei Province, China
| | - Sisi Zhao
- The Affiliated Hospital of Hebei University, Baoding, Hebei Province, China
| | - Shujie Cheng
- The Affiliated Hospital of Hebei University, Baoding, Hebei Province, China
| |
Collapse
|