Radiation Dose Management Research Articles

Abdominal Applications of Photon-Counting CT.

Photon-counting computed tomography (PCCT) has shown promising advancements in abdominal imaging in clinical use. Though more peer-reviewed primary literature is needed, this commentary explores PCCT's potential applications, focusing on enhancing diagnostic accuracy, optimizing radiation dose management, and improving patient care. PCCT offers improved spatial and contrast resolution, lower image noise, and reduced radiation dose. Increased spatial resolution provides better detail in abdominal imaging, aiding in the detection of small lesions and subtle pathological changes. However, this generates more images per scan, raising concerns about "image overload" in PACS, potentially leading to longer reading times and increased stress for radiologists. PCCT's improved contrast resolution enhances tissue differentiation, reducing the need for intravenous contrast agents. The technology's advanced tissue characterization provides several advantages, such as non-invasive and opportunistic liver disease evaluation and improved differentiation of renal and adrenal masses. PCCT's optimized radiation dose management is crucial for patients requiring frequent scans. Enhanced diagnostic accuracy through spectral information aids in tissue differentiation, improving confidence in diagnoses. Streamlined workflows, particularly in emergency settings, and oncologic imaging, are potential benefits, reducing the need for additional imaging studies. Future integration of PCCT into clinical practice requires collaboration, education, and research to fully harness its potential, ensuring optimized abdominal imaging and improved patient care.

Factors affecting distribution of dose in horizontal direction during irradiation

Recording and managing the dose of x-rays in an x-ray machine is an important part of the data. In addition, recording and managing radiation dose data in x-ray devices plays an important role in providing transparency of radiation dose to medical staff and patients by quantifying the radiation dose data. Four mobile diagnostic X-ray units were used to analyze the dose by spatial location. The dose distribution by location was analyzed by identifying and analyzing the dose by angle for both image intensifier and flat panel detector types. The three-dimensional space of the radiation area consisted of 27 sides, and the structure of the space was assumed to be horizontal X, Y, and Z sides and vertical A, B, and C sides, and the dose analysis was performed at the assumed position. On the longitudinal side, the highest dose tissue (highest μSv/min) is B_Center : (R.B.M, Colon, Lung, Stomach, Breasts, Remainder of body) - 330.404 μSv/min, and the lowest dose tissue (lowest μSv/min) is 0.002 μSv/min on the (Skin, Bone surface, Salivary glands, Brain) side at C_270°. The findings from diagnostic X-ray devices have emphasized the importance of managing radiation exposure when using the devices and may raise questions about the management of radiation protection measures to protect the health of healthcare personnel and patients. This can be expected to advance the organization of the use of radiation devices in a safe healthcare environment. A system for managing data will be useful as an indicator to guide medical staff using the equipment and patients participating in procedures and surgeries where they can minimize their dose and avoid harm.

Effects of organ dose modulation applied to a part of the scan range on radiation dose in computed tomography of the body

In computed tomography (CT), organ dose modulation (ODM) reduces radiation exposure from the anterior side to reduce radiation dose received by the radiosensitive organs located anteriorly. We investigated the effects of ODM applied to a part of the scan range on radiation dose in body CT. The thorax and thoraco-abdominopelvic region of an anthropomorphic whole-body phantom were imaged with and without ODM. ODM was applied to various regions, and the tube current modulation curves were compared. Additionally, the dose indices were compared with and without ODM in thoracic and thoraco-abdominopelvic CTs in 800 patients. ODM was applied to the thyroid in male patients and to the thyroid and breast in female patients. In phantom imaging of the thorax, the application of ODM below the scan range decreased the tube current, and that to the breast showed a further decrease. Decreased tube current was also observed in phantom imaging of the thoraco-abdominopelvic regions with ODM below the scan range, and the application of ODM to the whole scan range, thyroid, breast, and both thyroid and breast further reduced the tube current in the region to which ODM was applied. In patient imaging, the dose indices were significantly lower with ODM than without ODM, regardless of the scan range or sex. The absolute reduction in dose-length product was larger for thoraco-abdominopelvic CT (male, 43.2 mGy cm; female, 59.7 mGy cm) than for thoracic CT (male, 30.8 mGy cm; female, 37.6 mGy cm) in both sexes, indicating dose reduction in the abdominopelvic region to which ODM was not applied. In conclusion, The application of ODM in body CT reduces radiation dose not only in the region to which ODM is applied but also outside the region. In radiation dose management, it should be considered that even ODM applied to a limited region affects the dose indices.

Machine learning-based estimation of patient body weight from radiation dose metrics in computed tomography.

Currently, precise patient body weight (BW) at the time of diagnostic imaging cannot always be used for radiation dose management. Various methods have been explored to address this issue, including the application of deep learning to medical imaging and BW estimation using scan parameters. This study develops and evaluates machine learning-based BW prediction models using 11 features related to radiation dose obtained from computed tomography (CT) scans. A dataset was obtained from 3996 patients who underwent positron emission tomography CT scans, and training and test sets were established. Dose metrics and descriptive data were automatically calculated from the CT images or obtained from Digital Imaging and Communications in Medicine metadata. Seven machine-learning models and three simple regression models were employed to predict BW using features such as effective diameter (ED), water equivalent diameter (WED), and mean milliampere-seconds. The mean absolute error (MAE) and correlation coefficient between the estimated BW and the actual BW obtained from each BW prediction model were calculated. Our results found that the highest accuracy was obtained using a light gradient-boosting machine model, which had an MAE of 1.99kg and a strong positive correlation between estimated and actual BW (ρ=0.972). The model demonstrated significant predictive power, with 73% of patients falling within a±5% error range. WED emerged as the most relevant dose metric for BW estimation, followed by ED and sex. The proposed machine-learning approach is superior to existing methods, with high accuracy and applicability to radiation dose management. The model's reliance on universal dose metrics that are accessible through radiation dose management software enhances its practicality. In conclusion, this study presents a robust approach for BW estimation based on CT imaging that can potentially improve radiation dose management practices in clinical settings.

Prospective dose monitoring using a manual dose management system: experience in brain computed tomography from a tertiary hospital in Nigeria.

A manual radiation dose management system was developed to track the radiation dose and scan parameters of patients for brain computed tomography (CT). Radiation dose in volume computed tomography dose index (CTDIvol) and dose length product (DLP) were monitored to identify procedures that may require optimisation using notification values. The data were analysed and compared with national and international diagnostic reference levels (DRLs). A total of 596 brain CTs were monitored and grouped as <1: 36, 1-<5: 38, 5-<10: 25, 10-<15: 31 and adult: 466. The CTDIvol notification value identified the following number of examinations having high CTDIvol in <1y: 1, 1-<5: 1, 5-<10: 0, 10-<15: 0 and adult (>15): 11. Furthermore, the DLP notification values identified the following examinations with high DLP in <1y: 1, 1-<5:1, 5-<10:1, 10-<15: 1 and adults (>15): 18. The established local paediatric DLP DRLs were 2-3 times higher than the international paediatric DLP DRLs. This calls for a total protocol review and optimisation considering the local CT practices for paediatric imaging.

Impact of implementing national diagnostic reference levels on radiation dose optimization in adult chest CT scans: a comparative analysis

The management and optimization of radiation dose in computed tomography (CT) examinations is of paramount importance, especially when the safety of patients is concerned. This study evaluated the effect of implementing national diagnostic reference levels (NDRLs) for radiation dose optimization in 1991 adult chest CT scans at a major Saudi hospital. Data was analyzed before and after NDRL implementation, with 21.5% of scans using contrast and 78.5% without. Before implementation, 11.1% used contrast and 36.7% did not; after implementation, 10.4% used contrast and 41.7% did not. The majority (83.5%) of scans passed NDRL criteria [CTDIvol and DLP are set at 12 (mGy) and 430 (mGy · cm)], with higher pass rates for contrast (91.8%) versus non-contrast (81.5%) scans. Effective dose (ED) was compared before and after NDRL implementation. For non-contrast scans, ED declined 2.43% from 12.37 ± 5.25 mSv to 12.07 ± 4.99 mSv after implementation (non-significant, p &gt; 0.05). For contrast scans, ED declined more substantially, 6.77% from 9.6 ± 4.61 mSv to 8.95 ± 4.44 mSv (non-significant, p &gt; 0.05). The findings highlight higher NDRL compliance in procedures with contrast and show areas for dose optimization improvement in procedures without contrast. Results suggest NDRLs provide guidance for optimizing radiation dose, but other factors like patient characteristics, protocol settings, and quality assurance programs should also be considered to ensure doses are as low as reasonably achievable (ALARA) without compromising diagnostic quality. Regular monitoring and review of CT protocols is recommended to avoid unintended consequences of dose reduction. Continued optimization is encouraged to reduce dose while ensuring quality.

Cone Beam Computed Tomography - An Inevitable Diagnostic Aid in Dentistry

Cone Beam Computed Tomography (CBCT) has emerged as a pivotal imaging modality across various disciplines, providing three-dimensional visualisation with significant applications in dentistry, medical diagnostics, and industrial fields. This article presents a comprehensive overview of key aspects in CBCT imaging, encompassing the critical topics of Field of View (FOV), Resolution, Dose Considerations, and Artefacts. The Field of View (FOV) is a fundamental parameter influencing the scope and application of CBCT. This article explores the impact of different FOV settings on image acquisition, highlighting considerations for selecting an optimal FOV based on the specific diagnostic requirements of diverse clinical scenarios. Resolution plays a pivotal role in defining the clarity and precision of CBCT images. The article delves into the nuances of spatial and contrast resolution in CBCT, addressing the technological advancements and challenges associated with achieving high-resolution imaging while minimizing radiation exposure. Dose considerations are paramount in any medical imaging technique, and CBCT is no exception. This article provides an analysis of radiation dose management strategies in CBCT, emphasizing the importance of balancing diagnostic efficacy with patient safety. It explores dose optimization techniques, dose monitoring, and advancements in technology aimed at minimizing radiation exposure. Artefacts are inherent challenges in CBCT imaging that can compromise diagnostic accuracy. Understanding artefacts is crucial for practitioners to enhance the reliability and interpretability of CBCT images. Key Words: CBCT, Cone Beam Computed Tomography, 3-D imaging, Diagnostic imaging, Radiation dose.

National-level Dental Radiological Dose Management

There is growing public concern about patients' radiation exposure from recent medical imaging using ion-izing radiation. While medical radiation exposure has inevitable aspects, efforts to optimize doses in line with the principles of justification and optimization are necessary to maximize diagnostic value with the minimumradiation dose. Diagnostic reference levels have been proposed as a means to achieve optimization, in accordance with ICRP (International Commission on Radiological Protection) publications 60 and 73, as well as EC (European Commission) Directive 97/43/Euratom. According to Requirement 34 of the 'InternationalBasic Safety Standards' published by the IAEA in 2014, governments are recommended to establish national diagnostic reference levels. According to ICRP Publication 135, issued in 2017, national diagnostic reference levels should be revised regularly, preferably every 3-5 years, and more frequently in the case of technologicaladvancements, such as in the case of CBCT. In South Korea, diagnostic reference levels for various imagingmodalities have been established since 2007. In the field of dentistry, diagnostic reference levels for intraoral and panoramic radiography were established in 2009, and in 2018, diagnostic reference levels for dental CBCT were introduced for the first time. The purpose of this report is to discuss the current national-level patient radia-tion dose management in South Korea and explore its applications

Body CT examinations in oncologic patients: the impact of subspecialty radiology on radiation exposure in the clinical practice. A quality care study

PurposesThe 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 methodsChest 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.ResultsA 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).ConclusionIn 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.

A Vision for Global CT Radiation Dose Optimization

The topic of CT radiation dose management is receiving renewed attention since the recent approval by CMS for new CT dose measures. Widespread variation in CT dose persists in practices across the world, suggesting that current dose optimization techniques are lacking. The author outlines a proposed strategy for facilitating global CT radiation dose optimization. CT radiation dose optimization can be defined as the routine use of CT scan parameters that consistently produce images just above the minimum threshold of acceptable image quality for a given clinical indication, accounting for relevant patient characteristics, using the most dose-efficient techniques available on the scanner. To accomplish this, an image quality–based target dose must be established for every protocol; for nonhead CT applications, these target dose values must be expressed as a function of patient size. As variation in outcomes is reduced, the dose targets can be decreased to more closely approximate the minimum image quality threshold. Maintaining CT radiation dose optimization requires a process control program, including measurement, evaluation, feedback, and control. This is best accomplished by local teams made up of radiologists, medical physicists, and technologists, supported with protected time and needed tools, including analytics and protocol management applications. Other stakeholders critical to facilitating CT radiation dose management include researchers, funding agencies, industry, regulators, accreditors, payers, and the ACR. Analogous coordinated approaches have transformed quality in other industries and can be the mechanism for achieving the universal goal of CT radiation dose optimization.

Age-Dependent Changes in Effective Dose in Pediatric Brain CT: Comparisons of Estimation Methods.

The effective dose (ED) in computed tomography (CT) may be calculated by multiplying the dose-length product (DLP) by a conversion factor. As children grow, automatic exposure control increases the DLP, while the conversion factor decreases; these two changes affect the ED in opposite ways. The aim of this study was to investigate the methods of ED estimation according to age in pediatric brain CT. We retrospectively analyzed 980 brain CT scans performed for various clinical indications in children. The conversion factor at each age, in integer years, was determined based on the values at 0, 1, 5, and 10 years provided by the International Commission on Radiological Protection (ICRP), using a curve (curve method) or lines (linear method). In the simple method, the ED was estimated using the ICRP conversion factor for the closest age. We also analyzed the ED estimated by a radiation dose management system. Although the median DLP at each age increased with age, the median ED estimated by the curve method was highest at 0 years, decreased with age, and then plateaued at 9 years. The linear method yielded mildly different results, especially at 2 and 3 years. The ED estimated by the simple method or the radiation dose management system showed inconsistent, up-and-down changes with age. In conclusion, the ED in pediatric brain CT decreases with age despite increased DLP. Determination of the conversion factor at each age using a curve is expected to contribute to estimating the ED in pediatric CT according to age.

Technical specifications of dose management systems: An international atomic energy agency survey.

Dose management systems (DMS) have been introduced in radiological services to facilitate patient radiation dose management and optimization in medical imaging. The purpose of this study was to gather as much information as possible on the technical characteristics of DMS currently available, regarding features that may be considered essential for simply ensuring regulatory compliance or desirable to fully utilize the potential role of DMS in optimization of many aspects of radiological examinations. A technical survey was carried out and all DMS developers currently available (both commercial and open source) were contacted and were asked to participate. An extensive questionnaire was prepared and uploaded in the IAEA International Research Integration System (IRIS) online platform which was used for data collection process. Most of the questions (93%) required a "Yes/No" answer, to facilitate an objective analysis of the survey results. Some free text questions and comments' slots were also included, to allow participants to give additional information and clarifications where necessary. Depending on the answer, they were considered either as "Yes" or "No." Given the way that the questions were posed, every positive response indicated that a feature was offered. Thus, the percentage of positive responses was used as a measure of adherence. The percentages of positive answers per section (and sub-section) are presented in graphs and limitations of this type of analysis are discussed in detail. The results of this survey clearly exhibit that large differences exist between the various DMS developers. Consequently, potential end users of a DMS should carefully determine which of the features available are essential for their needs, prioritize desirable features, but also consider their infrastructure, the level of support required and the budget available before selecting a DMS.

Chinese expert consensus on transradial access in percutaneous peripheral interventions

Transradial access (TRA) is a safe and comfortable approach and the preferred access for percutaneous coronary intervention. However, TRA is not widely used for peripheral interventions. Currently, there is a lack of data on patient selection, appropriate medical devices, complication prevention, and TRA adoption. Therefore, the Chinese Society of Interventional Oncology of the China Anti-Cancer Association organized nationwide experts to establish a Working Group of China Expert Consensus on TRA in percutaneous peripheral interventions in 2022, and jointly formulated this consensus to better promote the application of TRA in peripheral interventions to guide clinicians on patient selection, technical recommendations, and physician training. This consensus mainly focuses on the current situation, advantages and limitations of TRA in peripheral interventions, anatomical characteristics of the radial artery, patient selection, technical aspects, prevention and management of complications, radiation dose, and learning curve. A consensus was reached through a literature evaluation and by referring to the opinions of the expert group.

Milestones in CT: Past, Present, and Future.

In 1971, the first patient CT examination by Ambrose and Hounsfield paved the way for not only volumetric imaging of the brain but of the entire body. From the initial 5-minute scan for a 180° rotation to today's 0.24-second scan for a 360° rotation, CT technology continues to reinvent itself. This article describes key historical milestones in CT technology from the earliest days of CT to the present, with a look toward the future of this essential imaging modality. After a review of the beginnings of CT and its early adoption, the technical steps taken to decrease scan times-both per image and per examination-are reviewed. Novel geometries such as electron-beam CT and dual-source CT have also been developed in the quest for ever-faster scans and better in-plane temporal resolution. The focus of the past 2 decades on radiation dose optimization and management led to changes in how exposure parameters such as tube current and tube potential are prescribed such that today, examinations are more customized to the specific patient and diagnostic task than ever before. In the mid-2000s, CT expanded its reach from gray-scale to color with the clinical introduction of dual-energy CT. Today's most recent technical innovation-photon-counting CT-offers greater capabilities in multienergy CT as well as spatial resolution as good as 125 μm. Finally, artificial intelligence is poised to impact both the creation and processing of CT images, as well as automating many tasks to provide greater accuracy and reproducibility in quantitative applications.

Personal Dosimeters Worn by Radiation Workers in Korea: Actual Condition and Consideration of Their Proper Application for Radiation Protection

Background: Assessment of the radiation doses to which workers are exposed can differ depending on the placement of dosimeters on the body. In addition, it is affected by whether the placement is under or over a shielding apron. This study aimed to evaluate the actual positioning of personal dosimeters on the body, with or without shielding aprons, among radiation workers in Korea.Materials and Methods: We analyzed the survey data, which included demographic characteristics, such as sex, age, occupation, work history, and placement of the personal dosimeter being worn, from a cohort study of Korean radiation workers. We assessed the use of personal dosimeters among workers, stratified by sex, age, working period, starting year of work, and occupation.Results and Discussion: Overall, high compliance (89.1% to 99.0%) with the wearing of dosimeters on the chest was observed regardless of workers’ characteristics, such as age, sex, occupation, and work history. However, the placement of dosimeters, either under or over the shielding aprons, was inconsistent. Overall, 40.1% of workers wore dosimeters under their aprons, while the others wore dosimeters over their aprons. This inconsistency indicates that radiation doses are possibly measured differently under the same exposure conditions solely owing to variations in the placement of worn dosimeters.Conclusion: Although a lack of uniformity in dosimeter placement when wearing a shielding apron may not cause serious harm in radiation dose management for workers, the development of detailed guidelines for dosimeter placement may improve the accuracy of dose assessment.

Deep learning-based body weight from scout images can be an alternative to actual body weight in CT radiation dose management.

Accurate body weight measurement is essential to promote computed tomography (CT) dose optimization; however, body weight cannot always be measured prior to CT examination, especially in the emergency setting. The aim of this study was to investigate whether deep learning-based body weight from chest CT scout images can be an alternative to actual body weight in CT radiation dose management. Chest CT scout images and diagnostic images acquired for medical checkups were collected from 3601 patients. A deep learning model was developed to predict body weight from scout images. The correlation between actual and predicted body weight was analyzed. To validate the use of predicted body weight in radiation dose management, the volume CT dose index (CTDIvol ) and the dose-length product (DLP) were compared between the body weight subgroups based on actual and predicted body weight. Surrogate size-specific dose estimates (SSDEs) acquired from actual and predicted body weight were compared to the reference standard. The median actual and predicted body weight were 64.1 (interquartile range: 56.5-72.4) and 64.0 (56.3-72.2) kg, respectively. There was a strong correlation between actual and predicted body weight (ρ=0.892, p<0.001). The CTDIvol and DLP of the body weight subgroups were similar based on actual and predicted body weight (p<0.001). Both surrogate SSDEs based on actual and predicted body weight were not significantly different from the reference standard (p=0.447 and 0.410, respectively). Predicted body weight can be an alternative to actual body weight in managing dose metrics and simplifying SSDE calculation. Our proposed method can be useful for CT radiation dose management in adult patients with unknown body weight.

Radiation Dose Management in Computed Tomography: Introduction to the Practice at a Single Facility.

Although the clinical benefits of computed tomography (CT) are undoubtedly high, radiation doses received by patients are also relatively high; therefore, radiation dose management is mandatory to optimize CT radiation doses and prevent excessive radiation events. This article describes CT dose management practice at a single facility. Many imaging protocols are used in CT depending on the clinical indications, scan region, and CT scanner; thus, managing the protocols is the first step for optimization. The appropriateness of the radiation dose for each protocol and scanner is verified, while answering whether the dose is the minimum to obtain diagnostic-quality images. Moreover, examinations with exceptionally high doses are identified, and the cause and clinical validity of the high dose are assessed. Daily imaging practice should follow standardized procedures, avoiding operator-dependent errors, and information required for radiation dose management should be recorded at each examination. The imaging protocols and procedures are reviewed for continuous improvement based on regular dose analysis and multidisciplinary team collaboration. The participation of many staff members in the dose management process is expected to contribute to promoting radiation safety through increased staff awareness.

SIZE-SPECIFIC DOSE ESTIMATES IN PEDIATRIC BRAIN CT IN RELATION TO AGE AND WEIGHT.

The size-specific dose estimate (SSDE) is used for radiation dose management in computed tomography (CT) and represents patient's absorbed dose more accurately than volume CT dose index. The relationship between SSDE and age or weight was investigated using 980 pediatric brain CT scans. Monolinear, power, and bilinear functions were fitted to the plots of SSDE against age or weight, and SSDE was estimated using the obtained functions. SSDE showed a biphasic increase with increasing age and weight: a rapid initial increase and subsequent a slow increase. Bilinear and power functions were successfully fitted to the plots, and mean estimation errors were close to 0, irrespective of the age or weight group. The standard SSDE values estimated from the obtained functions agreed well with the median values for each age or weight group. The curve-fitting method is expected to aid radiation dose management for pediatric brain CT using SSDE.

RADIATION DOSE MANAGEMENT SYSTEM IN COMPUTED TOMOGRAPHY PROCEDURES: A SYSTEMATIC REVIEW.

A systematic literature review was carried out to explore articles that reported the use of radiation dose management systems (RDMSs) in computed tomography (CT). The preferred reporting items for systematic review and meta-analysis flow chart were used to screen articles in PubMed, EBSCOhost, Web of Science, SCOPUS and Cochrane Library. A total of 1041 articles were retrieved and screened. After evaluation against criteria, 38 articles were selected and synthesised narratively. The results revealed that several RDMSs have been used in CT. The review also indicated that the use of RDMSs has promoted the implementation of diagnostic reference levels for dose optimisation. A RDMS, such as DoseWatch, is associated with compatibility challenges and failure in data transmission, while manual RDMSs are cumbersome and prone to data entry errors. Thus, a robust automated RDMS that is compatible with the different CT systems would provide efficient CT dose management.

Prediction of body weight from chest radiographs using deep learning with a convolutional neural network.

Accurate body weights are not necessarily available in routine clinical practice. This study aimed to investigate whether body weight can be predicted from chest radiographs using deep learning. Deep-learning models with a convolutional neural network (CNN) were trained and tested using chest radiographs from 85,849 patients. The CNN models were evaluated by calculating the mean absolute error (MAE) and Spearman's rank correlation coefficient (ρ). The MAEs of the CNN models were 2.63kg and 3.35kg for female and male patients, respectively. The predicted body weight was significantly correlated with the actual body weight (ρ = 0.917, p < 0.001 for females; ρ = 0.915, p < 0.001 for males). The body weight was predicted using chest radiographs by applying deep learning. Our method is potentially useful for radiation dose management, determination of the contrast medium dose, and estimation of the specific absorption rate in patients with unknown body weights.