1
|
Li Y, Liu S, Zhang Y, Zhang M, Jiang C, Ni M, Jin D, Qian Z, Wang J, Pan X, Yuan H. Deep Learning-enhanced Opportunistic Osteoporosis Screening in Ultralow-Voltage (80 kV) Chest CT: A Preliminary Study. Acad Radiol 2025:S1076-6332(24)00937-1. [PMID: 40318972 DOI: 10.1016/j.acra.2024.11.062] [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: 11/12/2024] [Revised: 11/23/2024] [Accepted: 11/24/2024] [Indexed: 05/07/2025]
Abstract
RATIONALE AND OBJECTIVES To explore the feasibility of deep learning (DL)-enhanced, fully automated bone mineral density (BMD) measurement using the ultralow-voltage 80 kV chest CT scans performed for lung cancer screening. MATERIALS AND METHODS This study involved 987 patients who underwent 80 kV chest and 120 kV lumbar CT from January to July 2024. Patients were collected from six CT scanners and divided into the training, validation, and test sets 1 and 2 (561: 177: 112: 137). Four convolutional neural networks (CNNs) were employed for automated segmentation (3D VB-Net and SCN), region of interest extraction (3D VB-Net), and BMD calculation (DenseNet and ResNet) of the target vertebrae (T12-L2). The BMD values of T12-L2 were obtained using 80 and 120 kV quantitative CT (QCT), the latter serving as the standard reference. Linear regression and Bland-Altman analyses were used to compare BMD values between 120 kV QCT and 80 kV CNNs, and between 120 kV QCT and 80 kV QCT. Receiver operating characteristic curve analysis was used to assess the diagnostic performance of the 80 kV CNNs and 80 kV QCT for osteoporosis and low BMD from normal BMD. RESULTS Linear regression and Bland-ltman analyses revealed a stronger correlation (R2=0.991-0.998 and 0.990-0.991, P<0.001) and better agreement (mean error, -1.36 to 1.62 and 1.72 to 2.27 mg/cm3; 95% limits of agreement, -9.73 to 7.01 and -5.71 to 10.19mg/cm3) for BMD between 120 kV QCT and 80 kV CNNs than between 120 kV QCT and 80 kV QCT. The areas under the curve of the 80 kV CNNs and 80 kV QCT in detecting osteoporosis and low BMD were 0.997-1.000 and 0.997-0.998, and 0.998-1.000 and 0.997, respectively. CONCLUSION The DL method could achieve fully automated BMD calculation for opportunistic osteoporosis screening with high accuracy using ultralow-voltage 80 kV chest CT performed for lung cancer screening.
Collapse
Affiliation(s)
- Yali Li
- Department of Radiology, Peking University Third Hospital, 49 Huayuan N Rd, Haidian District, Beijing, China (Y.L., S.L., Y.Z., CC.J., M.N., D.J., J.W., X.P., H.Y.)
| | - Suwei Liu
- Department of Radiology, Peking University Third Hospital, 49 Huayuan N Rd, Haidian District, Beijing, China (Y.L., S.L., Y.Z., CC.J., M.N., D.J., J.W., X.P., H.Y.)
| | - Yan Zhang
- Department of Radiology, Peking University Third Hospital, 49 Huayuan N Rd, Haidian District, Beijing, China (Y.L., S.L., Y.Z., CC.J., M.N., D.J., J.W., X.P., H.Y.)
| | - Mengze Zhang
- The Institute of Intelligent Diagnostics, Beijing United-Imaging Research Institute of Intelligent Imaging, Building 3-4F, 9 Yongteng N. Road, Beijing, China (M.Z., Z.Q.)
| | - Chenyu Jiang
- Department of Radiology, Peking University Third Hospital, 49 Huayuan N Rd, Haidian District, Beijing, China (Y.L., S.L., Y.Z., CC.J., M.N., D.J., J.W., X.P., H.Y.)
| | - Ming Ni
- Department of Radiology, Peking University Third Hospital, 49 Huayuan N Rd, Haidian District, Beijing, China (Y.L., S.L., Y.Z., CC.J., M.N., D.J., J.W., X.P., H.Y.)
| | - Dan Jin
- Department of Radiology, Peking University Third Hospital, 49 Huayuan N Rd, Haidian District, Beijing, China (Y.L., S.L., Y.Z., CC.J., M.N., D.J., J.W., X.P., H.Y.)
| | - Zhen Qian
- The Institute of Intelligent Diagnostics, Beijing United-Imaging Research Institute of Intelligent Imaging, Building 3-4F, 9 Yongteng N. Road, Beijing, China (M.Z., Z.Q.)
| | - Jiangxuan Wang
- Department of Radiology, Peking University Third Hospital, 49 Huayuan N Rd, Haidian District, Beijing, China (Y.L., S.L., Y.Z., CC.J., M.N., D.J., J.W., X.P., H.Y.)
| | - Xuemin Pan
- Department of Radiology, Peking University Third Hospital, 49 Huayuan N Rd, Haidian District, Beijing, China (Y.L., S.L., Y.Z., CC.J., M.N., D.J., J.W., X.P., H.Y.)
| | - Huishu Yuan
- Department of Radiology, Peking University Third Hospital, 49 Huayuan N Rd, Haidian District, Beijing, China (Y.L., S.L., Y.Z., CC.J., M.N., D.J., J.W., X.P., H.Y.).
| |
Collapse
|
2
|
Szarmach A, Sabiniewicz-Ziajka D, Grzywińska M, Gać P, Piskunowicz M, Wszędybył-Winklewska M. Computed Tomography Doses Calculation: Do We Really Need a New Dose Assessment Tool? J Clin Med 2025; 14:1348. [PMID: 40004878 PMCID: PMC11856821 DOI: 10.3390/jcm14041348] [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: 01/22/2025] [Revised: 02/14/2025] [Accepted: 02/15/2025] [Indexed: 02/27/2025] Open
Abstract
Background/Objectives: The increasing use of computed tomography (CT) scans significantly contributes to population exposure to ionizing radiation. Traditional dose metrics, such as dose-length product (DLP) and effective dose (ED), lack precision in reflecting individual radiation exposure. This study introduces a novel parameters such as size-specific effective dose (EDss) and the size-specific dose-length product (DLPss), to improve patient-specific dose estimation. The aim of this study is to enhance dose calculation accuracy, optimize CT protocols, and guide the development of next-generation CT technologies. Methods: A retrospective analysis of 247 abdominal and pelvic CT scans (113 women, 134 men) was conducted. Anthropometric parameters, including body mass index (BMI), cross-sectional dimensions, and dose indices, were measured. EDss and DLPss were calculated using size-specific correction factors, and statistical correlations between these parameters were assessed. Results: The mean BMI was 25.92 ± 5.34. DLPss values ranged from 261.63 to 1217.70 mGy·cm (mean: 627.83 ± 145.32) and were roughly 21% higher than traditional DLP values, with men showing slightly higher mean values than women. EDss values ranged from 6.65 to 15.45 mSv (mean: 9.42 ± 2.18 mSv), approximately 22% higher than traditional ED values, demonstrating improved individualization. Significant correlations were observed between BMI and effective diameter (r = 0.78), with stronger correlations in men (r = 0.85). The mean CTDIvol was 11.37 ± 3.50 mGy, and SSDE averaged 13.91 ± 2.39 mGy. Scan length reductions were observed in 53.8% of cases, with statistically significant differences by gender. Conclusions: EDss and DLPss offer improved accuracy in radiation dose estimation, addressing the limitations of traditional methods. Their adoption into clinical protocols, supported by AI-driven automation, could optimize diagnostic safety and significantly reduce radiation risk for patients. Further multicenter studies and technological advancements are recommended to validate these metrics and facilitate their integration into daily practice.
Collapse
Affiliation(s)
- Arkadiusz Szarmach
- 2nd Department of Radiology, Medical University of Gdansk, 80-210 Gdansk, Poland;
| | | | - Małgorzata Grzywińska
- Neuroinformatics and Artificial Intelligence Laboratory, Department of Neurophysiology, Neuropsychology and Neuroinformatics, Medical University of Gdansk, 80-210 Gdansk, Poland; (M.G.); (M.W.-W.)
| | - Paweł Gać
- Centre for Diagnostic Imaging, 4th Military Hospital, Weigla 5, 50-981 Wroclaw, Poland;
- Department of Population Health, Division of Environmental Health and Occupational Medicine, Wroclaw Medical University, Mikulicza-Radeckiego 7, 50-368 Wroclaw, Poland
| | - Maciej Piskunowicz
- 1st Department of Radiology, Medical University of Gdansk, 80-210 Gdansk, Poland;
| | - Magdalena Wszędybył-Winklewska
- Neuroinformatics and Artificial Intelligence Laboratory, Department of Neurophysiology, Neuropsychology and Neuroinformatics, Medical University of Gdansk, 80-210 Gdansk, Poland; (M.G.); (M.W.-W.)
- Institute of Health Sciences, Pomeranian University in Slupsk, 76-200 Slupsk, Poland
| |
Collapse
|
3
|
Açıkgöz G. Investigating the Effects of Tube Current and Tube Voltage on Patient Dose in Computed Tomography Examinations with Principial Component Analysis and Cluster Analysis: Phantom Study. HEALTH PHYSICS 2024; 127:513-519. [PMID: 38787573 DOI: 10.1097/hp.0000000000001830] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/25/2024]
Abstract
ABSTRACT The aim of this study was to investigate the effects of tube current and tube voltage choices on patient dose in adult and pediatric CT protocols by qualitative analysis using Principal Component Analysis (PCA), cluster analysis, and statistical analysis.Dose length product (DLP), Effective mAs (Eff. mAs), and volume-weighted CT dose index (CTDIvol) dose descriptors were obtained from 16 adult and pediatric head phantom CT examinations. Different tube voltage and tube current values were selected in both pediatric head and adult head CT imaging protocols, and PCA and cluster analysis were applied to the data obtained for qualitative analysis of the relationship between CTDIvol, Eff. mAs and Total DLP values. The two principial components (PC) with the highest values among those obtained as a result of the PCA method were used. PC1 was 70.97%, and PC2 was 28.03%. In the cluster analysis, it was observed that the values obtained from pediatric and adult phantom CT scans were classified into two different clusters. The correlation coefficient for adult patients was r = 0.998, and for pediatric patients, the correlation coefficient was r = 0.947. When the obtained clusters were examined, the degree of closeness or distance of the variables could be observed. In the study, as a result of the analysis of CTDIvol, Eff. mAs and Total DLP data based on manufacturer data at different kV and mA values with PCA and cluster analysis, it was shown that pediatric patients could be exposed to more radiation than the adult patients.
Collapse
Affiliation(s)
- Güneş Açıkgöz
- Hatay Mustafa Kemal University Vocational School of Health Services, Hatay/Turkey. Güneş Açıkgöz, Hatay MKÜ: Hatay Mustafa Kemal Universitesi, Serinyol HMKU campus, Hatay 31100 (ORCID: 0000-0001-9118-3153 )
| |
Collapse
|
4
|
Zhao A, Resnick S, Burton CS, Fadhel M. Deciphering the Radiation Dose Summary Page in Interventional Fluoroscopy. Radiographics 2024; 44:e230197. [PMID: 39088363 DOI: 10.1148/rg.230197] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/03/2024]
Abstract
Fluoroscopy is an advanced medical imaging modality that utilizes x-rays to acquire real-time images throughout a medical examination. It is commonly used in various procedures such as in interventional radiology, cardiac catheterization, and gastrointestinal and genitourinary studies. While fluoroscopy is a valuable diagnostic and therapeutic tool, it exposes patients and medical staff to ionizing radiation, which carries health risks. A radiation dose summary page is a report generated by the fluoroscope that displays important information about the procedure. It provides an overview of the radiation doses administered during a fluoroscopic procedure, as well as certain technical parameters used during the irradiation events. The contents of a radiation dose summary page may vary depending on the make and model of the fluoroscope but some common elements include the cumulative reference air kerma, which serves as a surrogate of radiation dose delivered to the patient, and the dose-area product, which takes account of the x-ray beam area and is a measure of the total amount of energy imparted on the patient. Other imaging acquisition parameters may be also included in the dose summary page, including tube voltage, tube current, pulse width, pulse rate, spectral filters, primary and secondary angles, and source-to-image distance. The radiation dose summary page for fluoroscopy is a useful tool for physicians, technologists, and medical physicists, allowing them to comprehend the technical details of a fluoroscopically guided procedure. ©RSNA, 2024.
Collapse
Affiliation(s)
- Anzi Zhao
- From the Department of Radiation Safety (A.Z., C.S.B., M.F.), Northwestern Memorial Hospital and the Department of Radiology (S.R.), Northwestern University Feinberg School of Medicine, 676 N St. Clair St, Ste 401, Chicago, IL 60611
| | - Scott Resnick
- From the Department of Radiation Safety (A.Z., C.S.B., M.F.), Northwestern Memorial Hospital and the Department of Radiology (S.R.), Northwestern University Feinberg School of Medicine, 676 N St. Clair St, Ste 401, Chicago, IL 60611
| | - Christiane Sarah Burton
- From the Department of Radiation Safety (A.Z., C.S.B., M.F.), Northwestern Memorial Hospital and the Department of Radiology (S.R.), Northwestern University Feinberg School of Medicine, 676 N St. Clair St, Ste 401, Chicago, IL 60611
| | - Muhannad Fadhel
- From the Department of Radiation Safety (A.Z., C.S.B., M.F.), Northwestern Memorial Hospital and the Department of Radiology (S.R.), Northwestern University Feinberg School of Medicine, 676 N St. Clair St, Ste 401, Chicago, IL 60611
| |
Collapse
|
5
|
Rizzo S, Bellesi L, D'Ermo A, Bonomo L, D'Ecclesiis O, Magoga F, Presilla S, Spanò A, Minzolini V, Lo Piccolo F, Heinkel J, Rezzonico E, Del Grande M, Merli M, Del Grande F. Body CT examinations in oncologic patients: the impact of subspecialty radiology on radiation exposure in the clinical practice. A quality care study. LA RADIOLOGIA MEDICA 2024; 129:429-438. [PMID: 38341817 PMCID: PMC10943144 DOI: 10.1007/s11547-024-01790-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/08/2023] [Accepted: 01/15/2024] [Indexed: 02/13/2024]
Abstract
PURPOSES The primary objective of this retrospective study was to assess whether the CT dose delivered to oncologic patients was different in a subspecialty radiology department, compared to a general radiology department. The secondary explorative objective was to assess whether the objective image quality of CT examinations was different in the two settings. MATERIALS AND METHODS Chest and abdomen CT scans performed for oncologic indications were selected from a general radiology department and a subspecialty radiology department. By using a radiation dose management platform, we extracted and compared CT dose index (CTDIvol) and dose length product (DLP) both for each phase and for the entire CT exams. For objective image quality evaluation, we calculated the signal-to-noise ratio (SNR) and the contrast-to-noise ratio (CNR) at the level of the liver and of the aorta. A P-value < 0.05 was considered significant. RESULTS A total of 7098 CT examinations were included. CTDIvol was evaluated in 12,804 phases; DLP in 10,713 phases and in 6714 examinations. The CTDIvol and DLP overall were significantly lower in the subspecialty radiology department compared to the general radiology department CTDI median (IQR) 5.19 (3.91-7.00) and 5.51 (4.17-7.72), DLP median and IQR of 490.0 (342.4-710.6) and 503.4 (359.9-728.8), p < 0.001 and p = 0.01, respectively. The objective image quality showed no significant difference in the general and subspecialty radiology departments, with median and IQR of 4.03 (2.82-5.51) and 3.84 (3.09-4.94) for SNRLiv (p = 0.58); 4.81 (2.70-7.62) and 4.34 (3.05-6.25) for SNRAo (p = 0.30); 0.83 (0.20-1.89) and 1.00 (0.35-1.57) for CNRLiv (p = 0.99); 2.23 (0.09-3.83) and 1.01 (0.15-2.84) for CNRAo (p = 0.24) with SNRLiv (p = 0.58), SNRAo (p = 0.30), CNRLiv (p = 0.99) and CNRAo (p = 0.24). CONCLUSION In a subspecialty radiology department, CT protocols are optimized compared to a general radiology department leading to lower doses to oncologic patients without significant objective image quality degradation.
Collapse
Affiliation(s)
- Stefania Rizzo
- Clinic of Radiology, Imaging Institute of Southern Switzerland (IIMSI), Ente Ospedaliero Cantonale (EOC), Via Tesserete 46, 6900, Lugano, Switzerland.
- Faculty of Biomedical Sciences, Università Della Svizzera Italiana (USI), Via G. Buffi 13, 6904, Lugano, Switzerland.
| | - Luca Bellesi
- Service of Medical Physics, Maging Institute of Southern Switzerland (IIMSI), Ente Ospedaliero Cantonale (EOC), Bellinzona, Switzerland
| | - Andrea D'Ermo
- Service of Process Organization and Information, EOC, Support Area, Via Lugano 4D, 6500, Bellinzona, Switzerland
| | - Luca Bonomo
- Clinic of Radiology, Imaging Institute of Southern Switzerland (IIMSI), Ente Ospedaliero Cantonale (EOC), Via Tesserete 46, 6900, Lugano, Switzerland
| | - Oriana D'Ecclesiis
- Department of Experimental Oncology, IEO, European Institute of Oncology IRCCS, Milan, Italy
| | - Francesco Magoga
- Clinic of Radiology, Imaging Institute of Southern Switzerland (IIMSI), Ente Ospedaliero Cantonale (EOC), Via Tesserete 46, 6900, Lugano, Switzerland
| | - Stefano Presilla
- Service of Medical Physics, Maging Institute of Southern Switzerland (IIMSI), Ente Ospedaliero Cantonale (EOC), Bellinzona, Switzerland
| | - Arturo Spanò
- Clinic of Radiology, Imaging Institute of Southern Switzerland (IIMSI), Ente Ospedaliero Cantonale (EOC), Via Tesserete 46, 6900, Lugano, Switzerland
| | - Veronica Minzolini
- Clinic of Radiology, Imaging Institute of Southern Switzerland (IIMSI), Ente Ospedaliero Cantonale (EOC), Via Tesserete 46, 6900, Lugano, Switzerland
| | - Francesca Lo Piccolo
- Clinic of Radiology, Imaging Institute of Southern Switzerland (IIMSI), Ente Ospedaliero Cantonale (EOC), Via Tesserete 46, 6900, Lugano, Switzerland
| | - Jurgen Heinkel
- Clinic of Radiology, Imaging Institute of Southern Switzerland (IIMSI), Ente Ospedaliero Cantonale (EOC), Via Tesserete 46, 6900, Lugano, Switzerland
| | - Ermidio Rezzonico
- Clinic of Radiology, Imaging Institute of Southern Switzerland (IIMSI), Ente Ospedaliero Cantonale (EOC), Via Tesserete 46, 6900, Lugano, Switzerland
| | - Maria Del Grande
- Oncology Institute of Southern Switzerland, EOC, Bellinzona, Switzerland
| | - Matteo Merli
- Clinic of Radiology, Imaging Institute of Southern Switzerland (IIMSI), Ente Ospedaliero Cantonale (EOC), Via Tesserete 46, 6900, Lugano, Switzerland
| | - Filippo Del Grande
- Clinic of Radiology, Imaging Institute of Southern Switzerland (IIMSI), Ente Ospedaliero Cantonale (EOC), Via Tesserete 46, 6900, Lugano, Switzerland
- Faculty of Biomedical Sciences, Università Della Svizzera Italiana (USI), Via G. Buffi 13, 6904, Lugano, Switzerland
| |
Collapse
|