1
|
Ohtake Y, Yasaka K, Hamada A, Fujita N, Abe O. Effect of Deep Learning Reconstruction on Evaluating Cervical Spinal Canal Stenosis With Computed Tomography. J Comput Assist Tomogr 2023; 47:996-1001. [PMID: 37948377 DOI: 10.1097/rct.0000000000001490] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
OBJECTIVE Magnetic resonance imaging (MRI) is commonly used to evaluate cervical spinal canal stenosis; however, some patients are ineligible for MRI. We aimed to assess the effect of deep learning reconstruction (DLR) in evaluating cervical spinal canal stenosis using computed tomography (CT) compared with hybrid iterative reconstruction (hybrid IR). METHODS This retrospective study included 33 patients (16 male patients; mean age, 57.7 ± 18.4 years) who underwent cervical spine CT. Images were reconstructed using DLR and hybrid IR. In the quantitative analyses, noise was recorded by placing the regions of interest on the trapezius muscle. In the qualitative analyses, 2 radiologists evaluated the depiction of structures, image noise, overall image quality, and degree of cervical canal stenosis. We additionally evaluated the agreement between MRI and CT in 15 patients for whom preoperative cervical MRI was available. RESULTS Image noise was less with DLR than hybrid IR in the quantitative ( P ≤ 0.0395) and subjective analyses ( P ≤ 0.0023), and the depiction of most structures was improved ( P ≤ 0.0052), which resulted in better overall quality ( P ≤ 0.0118). Interobserver agreement in the assessment of spinal canal stenosis with DLR (0.7390; 95% confidence interval [CI], 0.7189-0.7592) was superior to that with hybrid IR (0.7038; 96% CI, 0.6846-0.7229). As for the agreement between MRI and CT, significant improvement was observed for 1 reader with DLR (0.7910; 96% CI, 0.7762-0.8057) than hybrid IR (0.7536; 96% CI, 0.7383-0.7688). CONCLUSIONS Deep learning reconstruction provided better quality cervical spine CT images in the evaluation of cervical spinal stenosis than hybrid IR.
Collapse
Affiliation(s)
- Yuta Ohtake
- From the Department of Radiology, The University of Tokyo Hospital, Tokyo, Japan
| | | | | | | | | |
Collapse
|
2
|
Ruder TD, Kuhnen SC, Zech WD, Klaus JB, Lombardo P, Ith M. Standards of practice in forensic age estimation with CT of the medial clavicular epiphysis-a systematic review. Int J Legal Med 2023; 137:1757-1766. [PMID: 37691040 PMCID: PMC10567934 DOI: 10.1007/s00414-023-03061-7] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/20/2023] [Accepted: 07/08/2023] [Indexed: 09/12/2023]
Abstract
The AGFAD (Arbeitsgemeinschaft für Forensische Alterdiagnostik, Study Group on Forensic Age Diagnostics) has published several recommendations regarding both technical aspects of computed tomography (CT) of the medial clavicular epiphysis (MCE) and the process of reading and interpreting the CT images for forensic age estimations (FAE). There are, however, no published recommendations regarding CT scan protocols and no dose reference values for CT of the MCE. The objective of this analysis was to assess adherence to AGFAD recommendations among practitioners of FAE and analyse reported dose-relevant CT scan parameters with the objective of helping to establish evidence-based dose reference values for FAE. A systematic literature search was conducted in PubMed and in Google Scholar with specific MeSH terms to identify original research articles on FAE with CT of the MCE from 1997 to 2022. A total of 48 studies were included. Adherence to AGFAD recommendations among practitioners of FAE is high regarding the use of Schmeling main stages (93%), bone window (79%), ≤ 1 mm CT slices (67%), axial/coronal CT images (65%), and Kellinghaus sub-stages (59%). The reporting of CT technique and CT dose-relevant scan parameters is heterogeneous and often incomplete in the current literature. Considering the success achieved by the AGFAD in creating standards of practice of FAE in living subjects, there is potential for the AGFAD to establish standards for radiation protection in FAE as well.
Collapse
Affiliation(s)
- Thomas D Ruder
- Institute of Diagnostic, Interventional and Pediatric Radiology, InselspitaI, Bern University Hospital, University of Bern, Freiburgstrasse, CH-3010, Bern, Switzerland.
| | - Saskia C Kuhnen
- Institute of Diagnostic, Interventional and Pediatric Radiology, InselspitaI, Bern University Hospital, University of Bern, Freiburgstrasse, CH-3010, Bern, Switzerland
| | - Wolf-Dieter Zech
- Institute of Forensic Medicine, University of Bern, Bern, Switzerland
| | - Jeremias B Klaus
- Institute of Diagnostic, Interventional and Pediatric Radiology, InselspitaI, Bern University Hospital, University of Bern, Freiburgstrasse, CH-3010, Bern, Switzerland
- Institute of Forensic Medicine, University of Bern, Bern, Switzerland
- Roentgen Institute Thun, Thun, Switzerland
| | - Paolo Lombardo
- Institute of Diagnostic, Interventional and Pediatric Radiology, InselspitaI, Bern University Hospital, University of Bern, Freiburgstrasse, CH-3010, Bern, Switzerland
| | - Michael Ith
- Institute of Diagnostic, Interventional and Pediatric Radiology, InselspitaI, Bern University Hospital, University of Bern, Freiburgstrasse, CH-3010, Bern, Switzerland
- Radiation Protection, Image Processing Systems & Radiological Processes, Hirslanden Private Hospital Group, Zurich, Switzerland
| |
Collapse
|
3
|
Computed Tomography of the Spine. Clin Neuroradiol 2022; 33:271-291. [DOI: 10.1007/s00062-022-01227-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/10/2022] [Accepted: 10/10/2022] [Indexed: 11/24/2022]
Abstract
AbstractThe introduction of the first whole-body CT scanner in 1974 marked the beginning of cross-sectional spine imaging. In the last decades, the technological advancement, increasing availability and clinical success of CT led to a rapidly growing number of CT examinations, also of the spine. After initially being primarily used for trauma evaluation, new indications continued to emerge, such as assessment of vertebral fractures or degenerative spine disease, preoperative and postoperative evaluation, or CT-guided interventions at the spine; however, improvements in patient management and clinical outcomes come along with higher radiation exposure, which increases the risk for secondary malignancies. Therefore, technical developments in CT acquisition and reconstruction must always include efforts to reduce the radiation dose. But how exactly can the dose be reduced? What amount of dose reduction can be achieved without compromising the clinical value of spinal CT examinations and what can be expected from the rising stars in CT technology: artificial intelligence and photon counting CT? In this article, we try to answer these questions by systematically reviewing dose reduction techniques with respect to the major clinical indications of spinal CT. Furthermore, we take a concise look on the dose reduction potential of future developments in CT hardware and software.
Collapse
|
4
|
Cao J, Xie N, Qian P, Hu M, Tu J. Feasibility analysis of high pitch cervical spine CT in uncooperative patients with acute cervical spine trauma: An initial experience. Medicine (Baltimore) 2022; 101:e30785. [PMID: 36181071 PMCID: PMC9524935 DOI: 10.1097/md.0000000000030785] [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] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/05/2023] Open
Abstract
Cervical computed tomography (CT) often suffers from examination failure in uncooperative patients with acute cervical spinal trauma. Therefore, this study aimed to evaluate the feasibility of using high-pitch cervical CT (HP-CT) in such populations. A total of 95 patients with acute neck/head-neck trauma who underwent HP-CT (n = 29) or standard cervical CT (SD-CT, n = 66) from October 2020 to June 2021 were included in this study. Differences in patient characteristics between the HP-CT group and the SD-CT group were firstly compared. Then, the objective image quality based on the mean score of the signal-to-noise ratio (SNR)/contrast noise ratio (CNR) was evaluated, while double-blind five-point scoring was adopted for the subjective evaluation. Finally, radiation doses in HP-CT and SD-CT were compared. Furthermore, the Student t test and/or Mann-Whitney U test were performed to analyze differences in patient characteristics, image quality, and radiation dose between the two regimes. A total of 17 cases of cervical spine fractures were found in 95 patients, including 6 cases in the HP-CT group and 11 cases in the SD-CT group. The average age of patients who received HP-CT was higher than that of those who received SD-CT, and the scan time using HP-CT was shorter than that SD-CT. The differences were statistically significant (both, P < .05). In addition, there was no significant difference between HP-CT and SD-CT in terms of sex, body mass index, field of view (FOV), and scan length (all P > .05). The SNR/CNR at the middle and upper neck was not significantly different between HP-CT and SD-CT (all P > .05). However, the SNR/CNR at the lower neck in HP-CT was lower than that in SD-CT (all P < .05). There was no significant difference in the subjective scores between HP-CT and SD-CT images in both the soft tissue and bone window (P = .129 and 0.649, respectively). The radiation dose in HP-CT was lower than that in SD-CT (all P < .05). With a scan time reduction of 73%, radiation dose reduction of 10%, and similar image quality, high-pitch cervical CT was of feasibility to evaluate cervical spine injury in uncooperative patients with acute cervical spine trauma.
Collapse
Affiliation(s)
- Juntao Cao
- Department of Radiology, Kunshan Hospital of Traditional Chinese Medicine, Jiangsu Province, China
| | - Na Xie
- Department of Medical Imaging, Kunshan Maternal and Child Health Hospital, China
| | - Pingkang Qian
- Trauma Center, Kunshan Hospital of Traditional Chinese Medicine, China
| | - Ming Hu
- Department of Radiology, Kunshan Hospital of Traditional Chinese Medicine, Jiangsu Province, China
| | - Jianchun Tu
- Department of Radiology, Kunshan Hospital of Traditional Chinese Medicine, Jiangsu Province, China
- *Correspondence: Jianchun TU, Department of Radiology, Kunshan Hospital of Traditional Chinese Medicine. No. 189, Chaoyangxi Road, Kunshan City 215300, Jiangsu Province, China (e-mail: )
| |
Collapse
|
5
|
Is It Possible to Replace Conventional Radiography (CR) with a Dose Neutral Computed Tomography (CT) of the Cervical Spine in Emergency Radiology—An Experimental Cadaver Study. Diagnostics (Basel) 2022; 12:diagnostics12081872. [PMID: 36010222 PMCID: PMC9406668 DOI: 10.3390/diagnostics12081872] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2022] [Revised: 07/28/2022] [Accepted: 07/29/2022] [Indexed: 11/11/2022] Open
Abstract
The purpose of this experimental study on recently deceased human cadavers was to investigate whether (I) the radiation exposure of the cervical spine CT can be reduced comparable to a dose level of conventional radiography (CR); and (II) whether and which human body parameters can be predictive for higher dose reduction potential (in this context). Materials and Methods: Seventy serial CT scans of the cervical spine of 10 human cadavers undergoing postmortem virtual autopsy were taken using stepwise decreasing upper limits of the tube current (300 mAs, 150 mAs, 110 mAs, 80 mAs, 60 mAs, 40 mAs, and 20 mAs) at 120 kVp. An additional scan acquired at a fixed tube current of 300 mAs served as a reference. Images were reconstructed with filtered back projection and the upper (C1-4) and lower (C4-7) cervical spine were evaluated by three blinded readers for image quality, regarding diagnostic value and resolution of anatomical structures according to a semiquantitative three-point-scale. Dose values and individual physical parameters were recorded. The relationship of diagnostic IQ, dose reduction level, and patients’ physical parameters were investigated. The high-contrast resolution of the applied CT protocols was tested in an additional phantom study. Results: The IQ of the upper cervical spine was diagnostic at 1.69 ± 0.58 mGy (CTDI) corresponding to 0.20 ± 0.07 mSv (effective dose) in all cadavers. IQ of the lower cervical spine was diagnostic at 4.77 ± 1.86 mGy corresponding to 0.560 ± 0.21 mSv (effective dose) in seven cadavers and at 2.60 ± 0.93 mGy corresponding to 0.31 ± 0.11 mSv in four cadavers. Significant correlation was detected for BMI (0.8366; p = 0.002548) and the anteroposterior (a.p.) chest diameter (0.8363; p = 0.002566), shoulder positioning (0.79799; p = 0.00995), and radiation exposure. Conclusions: Conventional radiography can be replaced with a nearly dose-neutral CT scan of the cervical spine.
Collapse
|
6
|
Alla Takam C, Tchagna Kouanou A, Samba O, Mih Attia T, Tchiotsop D. Big Data Framework Using Spark Architecture for Dose Optimization Based on Deep Learning in Medical Imaging. ARTIF INTELL 2021. [DOI: 10.5772/intechopen.97746] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
Abstract
Deep learning and machine learning provide more consistent tools and powerful functions for recognition, classification, reconstruction, noise reduction, quantification and segmentation in biomedical image analysis. Some breakthroughs. Recently, some applications of deep learning and machine learning for low-dose optimization in computed tomography have been developed. Due to reconstruction and processing technology, it has become crucial to develop architectures and/or methods based on deep learning algorithms to minimize radiation during computed tomography scan inspections. This chapter is an extension work done by Alla et al. in 2020 and explain that work very well. This chapter introduces the deep learning for computed tomography scan low-dose optimization, shows examples described in the literature, briefly discusses new methods for computed tomography scan image processing, and provides conclusions. We propose a pipeline for low-dose computed tomography scan image reconstruction based on the literature. Our proposed pipeline relies on deep learning and big data technology using Spark Framework. We will discuss with the pipeline proposed in the literature to finally derive the efficiency and importance of our pipeline. A big data architecture using computed tomography images for low-dose optimization is proposed. The proposed architecture relies on deep learning and allows us to develop effective and appropriate methods to process dose optimization with computed tomography scan images. The real realization of the image denoising pipeline shows us that we can reduce the radiation dose and use the pipeline we recommend to improve the quality of the captured image.
Collapse
|
7
|
Tozakidou M, Meister RL, Well L, Petersen KU, Schindera S, Jopp-van Well E, Püschel K, Herrmann J. CT of the medial clavicular epiphysis for forensic age estimation: hands up? Int J Legal Med 2021; 135:1581-1587. [PMID: 33625576 PMCID: PMC8206049 DOI: 10.1007/s00414-021-02516-z] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/16/2020] [Accepted: 01/27/2021] [Indexed: 11/30/2022]
Abstract
Purpose The aim of this study was to assess the impact of arm position in computed tomography (CT) of the clavicle performed for forensic age estimation on clavicular position, image noise, and radiation dose. Methods and materials Forty-seven CT scans of the medial clavicular epiphysis performed for forensic age estimation were conducted with either hands and arms held upwards (CTHU, 28 persons) or positioned at the body (CTHD, 19 persons). Presets were identical for both positions (70 mAs/140 kVp; Brilliance iCT, Philips). Each CT scan was reconstructed with an iterative algorithm (i-Dose 4) and evaluated at the middle of the sternoclavicular joint. Clavicular angle was measured on a.p. topograms in relation to a horizontal line. Quantitative image noise was measured in air at the level of medial clavicular epiphysis. Effective dose and scan length were recorded. Results Hands-up position compared with hands-down position resulted in a lower lateral body diameter (CTHU 41.1 ± 3.6 cm vs. CTHD 44.6 ± 3.1 cm; P = 0.03), a reduced quantitative image noise (CTHU: 39.5 ± 9.2; CTHD: 46.2 ± 8.3; P = 0.02), and lower CTDIvol (5.1 ± 1.4 mGy vs. 6.7 ± 1.8 mGy; P = 0.001). Scan length was longer in patients examined with hands up (HU: 8.5 ± 3.4 cm; HD: 6.2 ± 2.1 cm; P = 0.006). Mean effective dose for CTHU was 0.79 ± 0.32 mSv compared with 0.95 ± 0.38 mSv in CTHD (P = 0.12). Clavicular angle was 17° ± 6° in patients with hands down and 32° ± 7° in patients with hands up (P < 0.001). Conclusion By elevated arm positioning, the image quality of clavicular CT scans can be improved while maintaining radiation dose compared with hands down. Clavicular position differs according to the hand position. Thus, positioning patients with elevated hands is advisable for forensic clavicular CT examinations, but multiplanar CT reconstructions should be adjusted to clavicular position and scan length should be reduced to a minimum.
Collapse
Affiliation(s)
- Magdalini Tozakidou
- Section of Pediatric Radiology, Department of Diagnostic and Interventional Radiology and Nuclear Medicine, University Medical Center Hamburg-Eppendorf, Martinistraße 52, 20246, Hamburg, Germany.
| | - Rieke L Meister
- Section of Pediatric Radiology, Department of Diagnostic and Interventional Radiology and Nuclear Medicine, University Medical Center Hamburg-Eppendorf, Martinistraße 52, 20246, Hamburg, Germany
| | - Lennart Well
- Department of Diagnostic and Interventional Radiology and Nuclear Medicine, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Kay U Petersen
- Department of Psychiatry and Psychotherapy, University Hospital Tübingen, Tübingen, Germany
| | | | - Eilin Jopp-van Well
- Department of Forensic Medicine, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Klaus Püschel
- Department of Forensic Medicine, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Jochen Herrmann
- Section of Pediatric Radiology, Department of Diagnostic and Interventional Radiology and Nuclear Medicine, University Medical Center Hamburg-Eppendorf, Martinistraße 52, 20246, Hamburg, Germany
| |
Collapse
|
8
|
Alla Takam C, Samba O, Tchagna Kouanou A, Tchiotsop D. Spark Architecture for deep learning-based dose optimization in medical imaging. INFORMATICS IN MEDICINE UNLOCKED 2020. [DOI: 10.1016/j.imu.2020.100335] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/07/2023] Open
|