ABSTRACT
The effect of mammography measurement conditions was investigated to evaluate their impact on measurement uncertainties in clinical practice. The most prominent physical X-ray beam quantities i.e., - air kerma, half-value layer, and X-ray tube voltage - were examined by measuring the response of two ionization chambers and six X-ray multimeters (XMMs) of different models. Measurements were performed using several anode/filter combinations and both with and without the compression paddle in the X-ray beam. Maximum differences of higher than 6 % were found for all quantities when the dosimeter displayed value was compared with the reference value or the variation within the clinical anode/filter combinations Mo/Mo and Mo/Rh were considered. The study showed that the calibration procedure with the W/Al anode/filter combination was reliable only for ionization chambers, and the response of XMMs varies in such a way that the calibration coefficient cannot be predicted between various measurement conditions used in calibration and clinical practices. XMM calibrations are typically performed without a compression paddle in the beam, and the response of the XMM changes when radiation quality is slightly altered. If XMM specific data is not available, based on this study, an additional uncertainty of 2 % (k = 1) could be used as a typical estimate, at least for air kerma measurements. XMMs should be used for clinical measurements in mammography only with correct settings. If the correct settings are not available, the XMMs should not be used or used only with extreme caution.
Subject(s)
Mammography , Mammography/instrumentation , Calibration , Uncertainty , Radiometry/instrumentation , Radiation DosimetersABSTRACT
PURPOSE: This study aimed to develop a deep learning (DL) method for noise quantification for clinical chest computed tomography (CT) images without the need for repeated scanning or homogeneous tissue regions. METHODS: A comprehensive phantom CT dataset (three dose levels, six reconstruction methods, amounting to 9240 slices) was acquired and used to train a convolutional neural network (CNN) to output an estimate of local image noise standard deviations (SD) from a single CT scan input. The CNN model consisting of seven convolutional layers was trained on the phantom image dataset representing a range of scan parameters and was tested with phantom images acquired in a variety of different scan conditions, as well as publicly available chest CT images to produce clinical noise SD maps. RESULTS: Noise SD maps predicted by the CNN agreed well with the ground truth both visually and numerically in the phantom dataset (errors of < 5 HU for most scan parameter combinations). In addition, the noise SD estimates obtained from clinical chest CT images were similar to running-average based reference estimates in areas without prominent tissue interfaces. CONCLUSIONS: Predicting local noise magnitudes without the need for repeated scans is feasible using DL. Our implementation trained with phantom data was successfully applied to open-source clinical data with heterogeneous tissue borders and textures. We suggest that automatic DL noise mapping from clinical patient images could be used as a tool for objective CT image quality estimation and protocol optimization.
Subject(s)
Deep Learning , Humans , Tomography, X-Ray Computed/methods , Neural Networks, Computer , Phantoms, Imaging , Image Processing, Computer-Assisted/methodsABSTRACT
OBJECTIVE: Indication-specific optimum field-of-views (FOVs) have been assessed for CBCT scans of impacted maxillary canines and mandibular third molars, as 40∅ × 35 mm and 35∅ × 35 mm, respectively. The objective was to investigate possible changes in absorbed organs and effective doses, for these two imaging indications, performing CBCT examinations with optimum FOV sizes instead of commonly used FOVs. Additionally, radiation exposure-induced cancer risk was calculated for both imaging indications with optimum FOVs. METHODS: An adult female head phantom (ATOM 702-D, CIRS, Norfolk, VA, USA) was scanned using Planmeca Viso G7 CBCT-device (Planmeca, Helsinki, Finland). Scanning factors, different FOV sizes, dose-area product (DAP) values and anatomical FOV locations were used for Monte Carlo PCXMC-simulation and ImpactMC software. In the PCXMC- simulation, 10-year-old child and 30-year-old adult phantoms were used to estimating effective and absorbed organ doses. RESULTS: The effective dose varied from 58 µSv to 284 µSv for impacted maxillary canines, and from 38 µSv to 122 µSv for mandibular third molars, the lowest dose value for each corresponding to optimum FOV. Effective dose reduction between the optimum FOV and the smallest common FOV of 50∅ × 50 mm, maintaining other scanning factors constant, was 33% for impacted maxillary canines, and 45% for mandibular third molars. At all examinations, the highest absorbed organ doses were in salivary glands or in oral mucosa. CONCLUSIONS: Optimum FOVs, 40∅ × 35 mm for impacted maxillary canine and 35∅ × 35 mm for mandibular third molar, could decrease effective doses received by young patients, and improve radiation safety in these common CBCT imaging procedures.
Subject(s)
Radiation Exposure , Spiral Cone-Beam Computed Tomography , Tooth, Impacted , Child , Adult , Humans , Female , Radiation Dosage , Molar, Third/diagnostic imaging , Cone-Beam Computed Tomography/methods , Phantoms, Imaging , Tooth, Impacted/diagnostic imagingABSTRACT
PURPOSE: Automatic image analysis algorithms have an increasing role in clinical quality assurance (QA) in medical imaging. Although the implementation of QA calculation algorithms may be straightforward at the development level, actual deployment of a new method to clinical routine may require substantial additional effort from supporting services. We sought to develop a multimodal system that enables rapid implementation of new QA analysis methods in clinical practice. METHODS: The QA system was built using freely available open-source software libraries. The included features were results database, database interface, interactive user interface, e-mail error dispatcher, data processing backend, and DICOM server. An in-house database interface was built, providing the developers of analyses with simple access to the results database. An open-source DICOM server was used for image traffic and automatic initiation of modality-specific QA image analyses. RESULTS: The QA framework enabled rapid adaptation of new analysis methods to automatic image processing workflows. The system provided online data review via an easily accessible user interface. In case of deviations, the system supported simultaneous review of the results for the user and QA expert to trigger corrective actions. In particular, embedded error thresholds, trend analyses, and error-feedback channels were provided to facilitate continuous monitoring and to enable pre-emptive corrective actions. CONCLUSION: An effective and novel QA framework incorporating easy adaptation and scalability to automated image analysis methods was developed. The framework provides an efficient and responsive web-based tool to manage the normal operation, trends, errors, and abnormalities in medical image quality.
Subject(s)
Diagnostic Imaging , Software , Radiography , Algorithms , Image Processing, Computer-Assisted , Quality Assurance, Health Care/methodsABSTRACT
BACKGROUND: The purpose of this study was to determine whether radiological measurements of radial fracture position made in cone beam computed tomography (CBCT) projection images are comparable to those made on traditional radiographs and could potentially substitute them. METHODS: Sixteen patients with fractures of the distal radius referred for radiographs were recruited for an additional CBCT scan which was performed immediately afterwards. Projection images and volumetric data were saved from the CBCT scans. Measurements of ulnar variance, radial inclination and volar tilt were made from all three sets of images. RESULTS: Agreement of projection image based measurements with radiographs was nearly as good as as the agreement of cross sectional image measurements with radiographs. The average difference between the results for projection images and radiographs were -1.2 mm (SD 1.9 mm), for radial inclination 0.7° (SD 2.9°) and for volar tilt 1.9° (SD 5.6°). CONCLUSION: Differences between radiological measurements between the modalities studied are small and projection images could be used for the assessment of distal radial fractures.
Subject(s)
Radiology , Radius Fractures , Wrist Fractures , Humans , Radiography , Cone-Beam Computed Tomography , Radius Fractures/diagnostic imagingABSTRACT
Cone beam computed tomography (CBCT) may provide essential additional image guidance to endovascular abdominal aneurysm repair (EVAR) operations but also significant radiation exposure to patients if scans are not carefully optimized. The purpose of our study was to define the image quality requirements for intraoperative EVAR CBCT imaging and to optimize the CBCT exposure parameters accordingly. A Multi-Energy CT phantom simulating a large patient was used by replacing the central phantom cylinder with a custom water-filled insert including an EVAR stent. Different exposure parameters covering a range of radiation qualities and dose levels were used to define the optimal image quality level regarding stent graft evaluation (compressed, bent, or collapsed). The radiation dose was measured with a calibrated air kerma-area product (KAP) meter and organ doses were calculated based on Monte Carlo simulations and a mathematical patient model. Based on the results, updated exposure parameters with the highest mean energy and lowest dose level available were recommended. With the updated protocol, the radiation exposure could be significantly decreased. The KAP value decreased from 9720 µGy·m2 to 440 µGy·m2 and reference point air kerma from 351 mGy to 16 mGy (a reduction of 96%) and organ doses of the organs in the irradiated region decreased on an average 91%. The new protocol resulted in acceptable clinical image quality based on testing with clinical cases.
ABSTRACT
Lead shields are commonly used in X-ray imaging to protect radiosensitive organs and to minimise patient's radiation dose. However, they might also complicate or interfere with the examination, and even decrease the diagnostic value if they are positioned incorrectly. In this study, the radiation dose effect of waist half-apron lead shield was examined via Monte Carlo simulations of postero-anterior (PA) chest radiography examinations using a female anthropomorphic phantom. Relevant organs for dose determination were lungs, breasts, liver, kidneys and uterus. The organ dose reductions varied depending on shield position and organ but were negligible for properly positioned shields. The shield that had the largest effective dose reduction (9%) was partly positioned inside the field of view, which should not be done in practice. Dose reduction was practically 0% for properly positioned shields. Therefore, the use of lead shield in the pelvic region during chest PA examinations should be discontinued.
Subject(s)
Breast , Radiography, Thoracic , Humans , Female , Radiography, Thoracic/methods , Radiation Dosage , Radiography , Breast/diagnostic imaging , Breast/radiation effects , Phantoms, Imaging , Pelvis/diagnostic imaging , Monte Carlo MethodABSTRACT
OBJECTIVES: Patients with univentricular heart defects require lifelong imaging surveillance. Recent advances in non-invasive imaging have enabled replacing these patients' routine catheterisation. Our objective was to describe the safety and cost savings of transition of a tertiary care children's hospital from routine invasive to routine non-invasive imaging of low-risk patients with univentricular heart defects. METHODS: This single-centre cohort study consists of 1) a retrospective analysis of the transition from cardiac catheterisation (n = 21) to CT angiography (n = 20) before bidirectional Glenn operation and 2) a prospective study (n = 89) describing cardiac magnetic resonance before and after the total cavopulmonary connection in low-risk patients with univentricular heart defects. RESULTS: Pre-Glenn: The total length of CT angiography was markedly shorter compared to the catheterisation: 30 min (range: 20-60) and 125 min (range: 70-220), respectively (p < 0.001). Catheterisation used more iodine contrast agents than CT angiography, 19 ± 3.9 ml, and 10 ± 2.4 ml, respectively (p < 0.001). Controlled ventilation was used for all catheterised and 3 (15%) CT angiography patients (p < 0.001). No complications occurred during CT angiography, while they emerged in 19% (4/21) catheterisation cases (p < 0.001). CT angiography and catheterisation showed no significant difference in the radiation exposure. Pre-/post-total cavopulmonary connection: All cardiac magnetic resonance studies were successful, and no complications occurred. In 60% of the cardiac magnetic resonance (53/89), no sedation was performed, and peripheral venous pressure was measured in all cases. Cost analysis suggests that moving to non-invasive imaging yielded cost savings of at least 2500-4000 per patient. CONCLUSION: Transition from routine invasive to routine non-invasive pre-and post-operative imaging is safely achievable with cost savings.
ABSTRACT
PURPOSE: To determine the effects of patient vertical off-centering when using organ-based tube current modulation (OBTCM) in chest computed tomography (CT) with focus on breast dose. MATERIALS AND METHODS: An anthropomorphic adult female phantom with two different breast attachment sizes was scanned on GE Revolution EVO and Siemens Definition Edge CT systems using clinical chest CT protocols and anterior-to-posterior scouts. Scans with and without OBTCM were performed at different table heights (GE: centered, ±6 cm, and ± 3 cm; Siemens: centered, -6 cm, and ± 3 cm). The dose effects were studied with metal-oxidesemiconductor field-effect transistor dosimeters with complementary Monte Carlo simulations to determine full dose maps. Changes in image noise were studied using standard deviations of subtraction images from repeated acquisitions without dosimeters. RESULTS: Patient off-centering affected both the behavior of the normal tube current modulation as well as the extent of the OBTCM. Generally, both OBTCM techniques provided a substantial decrease in the breast doses (up to 30% local decrease). Lateral breast regions may, however, in some cases receive higher doses when OBTCM is enabled. This effect becomes more prominent when the patient is centered too low in the CT gantry. Changes in noise roughly followed the expected inverse of the change in dose. CONCLUSIONS: Patient off-centering was shown to affect the outcome of OBTCM in chest CT examination, and on some occasions, resulting in higher exposure. The use of modern dose optimization tools such as OBTCM emphasizes the importance of proper centering when preparing patients to CT scans.
Subject(s)
Radiography, Thoracic , Tomography, X-Ray Computed , Adult , Female , Humans , Phantoms, Imaging , Radiation Dosage , Radiography, Thoracic/methods , Thorax , Tomography, X-Ray Computed/methodsABSTRACT
PURPOSE: Computed tomography (CT) image noise is usually determined by standard deviation (SD) of pixel values from uniform image regions. This study investigates how deep learning (DL) could be applied in head CT image noise estimation. METHODS: Two approaches were investigated for noise image estimation of a single acquisition image: direct noise image estimation using supervised DnCNN convolutional neural network (CNN) architecture, and subtraction of a denoised image estimated with denoising UNet-CNN experimented with supervised and unsupervised noise2noise training approaches. Noise was assessed with local SD maps using 3D- and 2D-CNN architectures. Anthropomorphic phantom CT image dataset (N = 9 scans, 3 repetitions) was used for DL-model comparisons. Mean square error (MSE) and mean absolute percentage errors (MAPE) of SD values were determined using the SD values of subtraction images as ground truth. Open-source clinical head CT low-dose dataset (Ntrain = 37, Ntest = 10 subjects) were used to demonstrate DL applicability in noise estimation from manually labeled uniform regions and in automated noise and contrast assessment. RESULTS: The direct SD estimation using 3D-CNN was the most accurate assessment method when comparing in phantom dataset (MAPE = 15.5%, MSE = 6.3HU). Unsupervised noise2noise approach provided only slightly inferior results (MAPE = 20.2%, MSE = 13.7HU). 2DCNN and unsupervised UNet models provided the smallest MSE on clinical labeled uniform regions. CONCLUSIONS: DL-based clinical image assessment is feasible and provides acceptable accuracy as compared to true image noise. Noise2noise approach may be feasible in clinical use where no ground truth data is available. Noise estimation combined with tissue segmentation may enable more comprehensive image quality characterization.
Subject(s)
Deep Learning , Head/diagnostic imaging , Humans , Image Processing, Computer-Assisted/methods , Neural Networks, Computer , Tomography, X-Ray Computed/methodsABSTRACT
PURPOSE: The aim of this study was to investigate the eye lens and whole-body radiation doses to interventional radiology and cardiology staff in two Finnish hospitals. METHODS: Simultaneous measurements of personal dose equivalent quantities Hp(3) and Hp(10) were conducted in clinical conditions during different radiological and cardiological interventional procedures. In order to study the feasibility to estimate eye lens dose with Hp(10) measured over the protective apron or thyroid shield, the ratio between measured Hp(3) and Hp(10) was investigated. RESULTS AND CONCLUSIONS: Applying the obtained ratio on Hp(10) records from national dose register showed that only a small number of interventional radiologists and cardiologists in Finland may exceed eye lens equivalent dose levels of 20 mSv per year or 100 mSv in five consecutive years, but likely do not exceed 50 mSv in a single year. For the most Finnish interventionalists, the eye lens dose is well below 10 mSv per year. Nurses and radiographers assisting in interventions are, on average, less exposed than interventionalists, and will not exceed 20 mSv per year. Based on our results, Hp(10) measured over the protective apron or thyroid shield provides a conservative estimate of the eye lens dose for interventional radiologists and cardiologists, provided that appropriate protective glasses are used.
Subject(s)
Cardiology , Lens, Crystalline , Occupational Exposure , Radiation Exposure , Finland , Humans , Occupational Exposure/analysis , Radiation Dosage , Radiation Exposure/analysis , Radiation Exposure/prevention & control , Radiology, Interventional/methodsABSTRACT
Cone beam computed tomography (CBCT) is a diverse 3D x-ray imaging technique that has gained significant popularity in dental radiology in the last two decades. CBCT overcomes the limitations of traditional two-dimensional dental imaging and enables accurate depiction of multiplanar details of maxillofacial bony structures and surrounding soft tissues. In this review article, we provide an updated status on dental CBCT imaging and summarise the technical features of currently used CBCT scanner models, extending to recent developments in scanner technology, clinical aspects, and regulatory perspectives on dose optimisation, dosimetry, and diagnostic reference levels. We also consider the outlook of potential techniques along with issues that should be resolved in providing clinically more effective CBCT examinations that are optimised for the benefit of the patient.
Subject(s)
Cone-Beam Computed Tomography , Radiometry , Humans , Imaging, Three-Dimensional , Radiation Dosage , X-RaysABSTRACT
Cone beam computed tomography (CBCT) has been available since the late 1990s for use in dentistry. European legislation requires optimisation of protection and the use of diagnostic reference levels (DRLs) as well as regular quality control (QC) of the imaging devices, which is well outlined in existing international recommendations. Nevertheless, the level of application is not known. Earlier studies have indicated that few European countries have established DRLs and that patient doses (exposure parameters) have not been properly optimised. The EURADOS Working Group 12-Dosimetry in Medical Imaging undertook a survey to identify existing practices in Member States. Questionnaires were developed to identify equipment types, clinical procedures performed, and exposure settings used. The surveys were circulated to 22 countries resulting in 28 responses from 13 countries. Variations were identified in the exposure factors and in the doses delivered to patients for similar clinical indicators. Results confirm that patient doses are still not properly optimised and DRLs are largely not established. There is a need to promote the importance of performing QC testing of dental CBCT equipment and to further optimise patient exposure by establishment and use of DRLs as a part of a continuous optimisation process.
Subject(s)
Cone-Beam Computed Tomography , Diagnostic Reference Levels , Humans , Quality Control , Radiation Dosage , RadiometryABSTRACT
BACKGROUND: Cone-beam computed tomography (CBCT) has become an increasingly important medical imaging modality in orthopedic operating rooms. Metal implants and related image artifacts create challenges for image quality optimization in CBCT. The purpose of this study was to develop a robust and quantitative method for the comprehensive determination of metal artifacts in novel CBCT applications. METHODS: The image quality of an O-arm CBCT device was assessed with an anthropomorphic pelvis phantom in the presence of metal implants. Three different kilovoltage and two different exposure settings were used to scan the phantom both with and without the presence of metal rods. RESULTS: The amount of metal artifact was related to the applied CBCT imaging protocol parameters. The size of the artifact was moderate with all imaging settings. The highest applied kilovoltage and exposure level distinctly increased artifact severity. CONCLUSIONS: The developed method offers a practical and robust way to quantify metal artifacts in CBCT. Changes in imaging parameters may have nonlinear effects on image quality which are not anticipated based on physics.
Subject(s)
Artifacts , Metals , Monitoring, Intraoperative/methods , Orthopedic Procedures , Prostheses and Implants , Spiral Cone-Beam Computed Tomography , Humans , Phantoms, ImagingABSTRACT
PURPOSE: Occupational radiation exposure for medical workers in radiology and cardiology was analyzed in nine hospitals in the UAE between 2002 and 2016. The purpose of the study was to determine the time trend and the differences in occupational radiation exposure among worker groups and hospitals in the country. METHODS: Readings of 5700 thermoluminescence dosimeters (TLDs) were obtained from 1011 medical workers and grouped into 5 worker groups (radiographers, diagnostic radiologists, nurses, cardiologists and physicians). RESULTS: The mean annual effective dose was from 0.38 to 0.62 mSv per worker. Even though an increase in the collective effective dose has been noticed during the study period, no significant time trend was observed in the mean effective dose. Furthermore, cardiologists received higher mean and maximum effective doses than the other worker groups. CONCLUSION: The annual effective doses were below the limits set by national legislation and international standards, and for the average worker, the likelihood of high exposure is small. However, improvements in radiation protection practices could be implemented to reduce occupational radiation dose to cardiologists, who were the most exposed worker group in this study.
Subject(s)
Cardiology , Occupational Exposure , Radiation Injuries , Radiation Monitoring , Radiology , Hospitals , Humans , Occupational Exposure/analysis , Radiation Dosage , United Arab EmiratesABSTRACT
PURPOSE: To determine the effect of patient's vertical off-centering and scout direction on the function of automatic tube voltage selection (ATVS) and tube current modulation (TCM) in chest computed tomography (CT). METHODS: Chest phantom was scanned with Siemens and GE CT systems using three clinical chest CT protocols exploiting ATVS and a fixed 120 kVp chest protocol. The scans were performed at five vertical positions of the phantom (-6 to +6 cm from the scanner isocenter). The effects of scout direction (posterior-to-anterior, anterior-to-posterior, and lateral) and vertical off-centering on the function of ATVS and TCM were studied by examining changes in selected voltage, radiation dose (volume CT dose index, CTDIvol), and image noise and contrast. RESULTS: Both scout direction and vertical off-centering affected ATVS. The effect differed between the vendors for the studied geometry, demonstrating differences in technical approaches. The greatest observed increase in CTDIvol due to off-centering was 91%. Anterior-to-posterior scout produced highest doses at the uppermost table position, whereas posterior-to-anterior scout produced highest doses at the lowermost table position. Dose varied least using lateral scouts. Vertical off-centering impacted image noise and contrast due to the combined effect of ATVS, TCM, structural noise, and bowtie filters. CONCLUSIONS: Patient vertical off-centering and scout direction affected substantially the CTDIvol and image quality in chest CT examinations. Vertical off-centering caused variation also in the selected tube voltage. The function of ATVS and TCM methods differ significantly between the CT vendors, resulting in differences in CTDIvol and image noise characteristics.
ABSTRACT
BACKGROUND: Radiation worker categorization and exposure monitoring practices must be proportional to the current working environment. PURPOSE: To analyze exposure data of Finnish radiological workers and to estimate the magnitude and frequency of their potential occupational radiation exposure, and to propose appropriate radiation worker categorization. MATERIAL AND METHODS: Estimates of the probabilities of annual effective doses exceeding certain levels were obtained by calculating the survival function of a lognormal probability density function (PDF) fitted in the measured occupational exposure data. RESULTS: The estimated probabilities of exceeding annual effective dose limits of 1 mSv, 6 mSv, and 20 mSv were in the order of 1:200, 1:10,000, and 1:500,000 per person, respectively. CONCLUSION: It is very unlikely that the Category B annual effective dose limit of 6 mSv could even potentially be exceeded using modern equipment and appropriate working methods. Therefore, in terms of estimated effective dose, workers in diagnostic and interventional radiology could be placed into Category B in Finland. Current national personal monitoring practice could be replaced or supplemented using active personal dosimeters, which offer more effective means for optimizing working methods.
Subject(s)
Health Personnel/statistics & numerical data , Models, Statistical , Occupational Exposure/statistics & numerical data , Radiation Dosage , Radiology, Interventional/statistics & numerical data , Registries/statistics & numerical data , Finland , Humans , Radiation ProtectionABSTRACT
RATIONALE AND OBJECTIVES: This phantom study aimed to evaluate low-dose (LD) chest computed tomography (CT) protocols using model-based iterative reconstruction (MBIR) for diagnosing lung metastases in patients with sarcoma. MATERIALS AND METHODS: An adult female anthropomorphic phantom was scanned with a 64-slice CT using four LD protocols and a standard-dose protocol. Absorbed organ doses were measured with 10 metal-oxide-semiconductor field-effect transistor dosimeters. Furthermore, Monte Carlo simulations were performed to estimate organ and effective doses. Image quality in terms of image noise, contrast, and resolution was measured from the CT images reconstructed with conventional filtered back projection, adaptive statistical iterative reconstruction, and MBIR algorithms. All the results were compared to the performance of the standard-dose protocol. RESULTS: Mean absorbed organ and effective doses were reduced by approximately 95% with the LD protocol (100-kVp tube voltage and a fixed 10-mA tube current) compared to the standard-dose protocol (120-kVp tube voltage and tube current modulation) while yielding an acceptable image quality for diagnosing round-shaped lung metastases. The effective doses ranged from 0.16 to 2.83 mSv in the studied protocols. The image noise, contrast, and resolution were maintained or improved when comparing the image quality of LD protocols using MBIR to the performance of the standard-dose chest CT protocol using filtered back projection. The small round-shaped lung metastases were delineated at levels comparable to the used protocols. CONCLUSIONS: Radiation exposure in patients can be reduced significantly by using LD chest CT protocols and MBIR algorithm while maintaining image quality for detecting round-shaped lung metastases.
Subject(s)
Image Processing, Computer-Assisted/methods , Lung Neoplasms/diagnostic imaging , Multidetector Computed Tomography/methods , Sarcoma/diagnostic imaging , Adult , Algorithms , Female , Humans , Lung Neoplasms/secondary , Phantoms, Imaging , Radiation Dosage , Radiographic Image Interpretation, Computer-Assisted , Radiography, Thoracic/methods , Sarcoma/secondaryABSTRACT
Big data and deep learning will profoundly change various areas of professions and research in the future. This will also happen in medicine and medical imaging in particular. As medical physicists, we should pursue beyond the concept of technical quality to extend our methodology and competence towards measuring and optimising the diagnostic value in terms of how it is connected to care outcome. Functional implementation of such methodology requires data processing utilities starting from data collection and management and culminating in the data analysis methods. Data quality control and validation are prerequisites for the deep learning application in order to provide reliable further analysis, classification, interpretation, probabilistic and predictive modelling from the vast heterogeneous big data. Challenges in practical data analytics relate to both horizontal and longitudinal analysis aspects. Quantitative aspects of data validation, quality control, physically meaningful measures, parameter connections and system modelling for the future artificial intelligence (AI) methods are positioned firmly in the field of Medical Physics profession. It is our interest to ensure that our professional education, continuous training and competence will follow this significant global development.