The use of deep learning towards dose optimization in low-dose computed tomography: A scoping review.

INTRODUCTION: Low-dose computed tomography tends to produce lower image quality than normal dose computed tomography (CT) although it can help to reduce radiation hazards of CT scanning. Research has shown that Artificial Intelligence (AI) technologies, especially deep learning can help enhance the image quality of low-dose CT by denoising images. This scoping review aims to create an overview on how AI technologies, especially deep learning, can be used in dose optimisation for low-dose CT. METHODS: Literature searches of ProQuest, PubMed, Cinahl, ScienceDirect, EbscoHost Ebook Collection and Ovid were carried out to find research articles published between the years 2015 and 2020. In addition, manual search was conducted in SweMed+, SwePub, NORA, Taylor & Francis Online and Medic. RESULTS: Following a systematic search process, the review comprised of 16 articles. Articles were organised according to the effects of the deep learning networks, e.g. image noise reduction, image restoration. Deep learning can be used in multiple ways to facilitate dose optimisation in low-dose CT. Most articles discuss image noise reduction in low-dose CT. CONCLUSION: Deep learning can be used in the optimisation of patients' radiation dose. Nevertheless, the image quality is normally lower in low-dose CT (LDCT) than in regular-dose CT scans because of smaller radiation doses. With the help of deep learning, the image quality can be improved to equate the regular-dose computed tomography image quality. IMPLICATIONS TO PRACTICE: Lower dose may decrease patients' radiation risk but may affect the image quality of CT scans. Artificial intelligence technologies can be used to improve image quality in low-dose CT scans. Radiologists and radiographers should have proper education and knowledge about the techniques used.

Initial data from an experiment to implement a safe procedure to perform PA erect chest radiographs for COVID-19 patients with a mobile radiographic system in a "clean" zone of the hospital ward.

INTRODUCTION: With the current Covid-19 pandemic, general wards have been converted into cohort wards for Covid-19 patients who are stable and ambulant. A 2-radiographer mobile radiography team is required to perform bedside Chest X-rays (CXR) for these patients. Hospital guidelines require both radiographers to be in full Personal Protective Equipment (PPE) throughout the image acquisition process and the mobile radiographic unit needs to be disinfected twice after each case. This affects the efficiency of the procedure and an increase usage of limited PPE resources. This study aims to explore the feasibility of performing mobile chest radiography with the mobile radiographic unit in a "clean" zone of the hospital ward. METHODS: An anthropomorphic body phantom was used during the test. With the mobile radiographic unit placed in a "clean" zone, the phantom and the mobile radiographic unit was segregated by the room door with a clear glass panel. The test was carried out with the room door open and closed. Integrated radiation level and patient dose were measured. A consultant radiologist was invited to review and score all the images acquired using a Barco Medical Grade workstation. The Absolute Visual Grading Analysis (VGA) scoring system was used to score these images. RESULTS: A VGA score of 4 was given to all the 40 test images, suggesting that there is no significant differences in the image quality of the images acquired using the 2 different methods. Radiation exposure received by the patient at the highest kV setting through the glass is comparable to the regular CXR on patient without glass panel at 90 kV, suggesting that there is no significant increase in patient dose. CONCLUSION: The result suggests that acquiring CXR with the X-ray beam attenuating through a glass panel is a safe and feasible way of performing CXR for COVID-19 patients in the newly converted COVID wards. This will allow the mobile radiographic unit as well as one radiographer to be completely segregated from the patient. IMPLICATIONS FOR PRACTICE: This new method of acquiring CXR in an isolation facility set up requires a 2-Radiographer mobile radiography team, and is applicable only for patients who are generally well and not presented with any mobility issues. It is also important to note that a clear glass panel must be present in the barriers set up for segregation between the "clean" zone and patient zone in order to use this new method of acquiring CXR.

The impact of COVID-19 upon student radiographers and clinical training.

INTRODUCTION: To investigate student clinical placement concerns and opinions, during the initial COVID-19 pandemic outbreak and to inform educational institution support planning. METHODS: Between mid-June to mid-July 2020, educational institutions from 12 countries were invited to participate in an online survey designed to gain student radiographer opinion from a wide geographical spread and countries with varying levels of COVID-19 cases. RESULTS: 1277 respondents participated, of these 592 had completed clinical placements during January to June 2020. Accommodation and cohabiting risks were identified as challenging, as was isolation from family, travel to clinical placements, and to a lesser extent childcare. Students stated they had been affected by the feeling of isolation and concerns about the virus whilst on placement. Overall 35.4% of all respondents were 'Not at all worried' about being a radiographer, however, 64.6% expressed varying levels of concern and individual domestic or health situations significantly impacted responses (p ≤ 0.05). Year 4 students and recent graduates were significantly more likely to be 'Not worried at all' compared to Year 2 and 3 students (p ≤ 0.05). The need for improved communication regarding clinical placements scheduling was identified as almost 50% of students on clinical placements between January to June 2020 identified the completion of assessments as challenging. Furthermore, only 66% of respondents with COVID-19 imaging experience stated being confident with personal protective equipment (PPE) use. CONCLUSION: Student radiographers identified key challenges which require consideration to ensure appropriate measures are in place to support their ongoing needs. Importantly PPE training is required before placement regardless of prior COVID-19 imaging experience. IMPLICATIONS FOR PRACTICE: As the next academic year commences, the study findings identify important matters to be considered by education institutions with responsibility for Radiography training and as students commence clinical placements during the on-going global COVID-19 pandemic.

Can the anode heel effect be used to optimise radiation dose and image quality for AP pelvis radiography?

INTRODUCTION: A study was conducted to determine whether the anode heel effect can be used to influence optimisation of radiation dose and image quality (IQ) for AP pelvis radiography. METHODS: ATOM dosimetry phantom and an anthropomorphic phantom were positioned for AP pelvis. Using a CR system, images were acquired and doses were measured with phantom feet toward anode and then feet toward cathode. Exposure factors (kVp, mAs and SID) were systematically generated using a factorial design. Images were scored visually for quality using relative visual grading together with a 3 point Likert scale. Signal to noise ratio was also calculated as a physical measure of image quality. Dosimetry data were collected for the ovaries and testes. RESULTS: The optimum technique for male, which resulted in lower dose and suitable image quality, was with feet positioned toward the anode (0.80 ± 0.03 mGy; SNR of 38 ± 2.9; visual IQ score 3.13 ± 0.35). The optimum technique for female was with feet toward anode (0.23 ± 0.02 mGy; SNR of 34.7 ± 2.6; visual IQ score 3.15 ± 0.26). kVp had the biggest effect on both visual and physical image quality metrics (p < 0.001) for both tube orientations, whereas SID had the lowest effect on both visual and physical image quality metrics compared with mAs and kVp (p < 0.001). The effect of SID on the SNR was not significant (p > 0.05) with feet toward anode. CONCLUSION: Positioning the patient with feet toward the anode, as opposed to the cathode, has no adverse effect on visual image quality assessment but it does have an effect on physical image quality. IMPLICATIONS FOR PRACTICE: This study would add a new clinical concept in positioning of AP pelvis radiography especially for male positioning.

A multi institutional comparison of imaging dose and technique protocols for neonatal chest radiography.

INTRODUCTION: The focus on paediatric radiation dose reduction supports reevaluation of paediatric imaging protocols. This is particularly important in the neonates where chest radiographs are frequently requested to assess respiratory illness and line placement. This study aims to assess the impact of neonatal chest radiographic protocols on patient dose in four hospitals in different countries. METHODS: Exposure parameters, collimation, focus to skin distance (FSD) and radiation dose from 200 neonatal chest radiographs were registered prospectively. Inclusion criteria consisted of both premature and full-term neonates weighing between 1000 and 5000 g. Only data from the examinations meeting diagnostic criteria and approved for the clinical use were included. Radiation dose was assessed using dose area product (DAP). RESULTS: The lowest DAP value (4.58 mGy cm2) was recorded in the Norwegian hospital, employing a high kVp, low mAs protocol using a DR system. The Canadian hospital recorded the highest DAP (9.48), using lower kVp and higher mAs with a CR system, including the addition of a lateral projection. The difference in the mean DAP, weight, field of view (FOV) and kVp between the hospitals is statistically significant (p < 0.001). CONCLUSION: Use of non-standardised imaging protocols in neonatal chest radiography results in differences in patient dose across hospitals included in the study. Using higher kVp, lower mAs and reducing the number of lateral projections to clinically relevant indications result in a lower DAP measured in the infant sample studied. Further studies to examine image quality based on exposure factors and added filtration are recommended. IMPLICATIONS FOR PRACTICE: Reevaluation of paediatric imaging protocols presents an opportunity to reduce patient dose in a population with increased sensitivity to ionising radiation.

A method to determine the impact of reduced visual function on nodule detection performance.

PURPOSE: In this study we aim to validate a method to assess the impact of reduced visual function and observer performance concurrently with a nodule detection task. MATERIALS AND METHODS: Three consultant radiologists completed a nodule detection task under three conditions: without visual defocus (0.00 Dioptres; D), and with two different magnitudes of visual defocus (-1.00 D and -2.00 D). Defocus was applied with lenses and visual function was assessed prior to each image evaluation. Observers evaluated the same cases on each occasion; this comprised of 50 abnormal cases containing 1-4 simulated nodules (5, 8, 10 and 12 mm spherical diameter, 100 HU) placed within a phantom, and 25 normal cases (images containing no nodules). Data was collected under the free-response paradigm and analysed using Rjafroc. A difference in nodule detection performance would be considered significant at p < 0.05. RESULTS: All observers had acceptable visual function prior to beginning the nodule detection task. Visual acuity was reduced to an unacceptable level for two observers when defocussed to -1.00 D and for one observer when defocussed to -2.00 D. Stereoacuity was unacceptable for one observer when defocussed to -2.00 D. Despite unsatisfactory visual function in the presence of defocus we were unable to find a statistically significant difference in nodule detection performance (F(2,4) = 3.55, p = 0.130). CONCLUSION: A method to assess visual function and observer performance is proposed. In this pilot evaluation we were unable to detect any difference in nodule detection performance when using lenses to reduce visual function.

Evaluation of exposure parameters in plain radiography: a comparative study with European guidelines.

Typical distribution of exposure parameters in plain radiography is unknown in Portugal. This study aims to identify exposure parameters that are being used in plain radiography in the Lisbon area and to compare the collected data with European references [Commission of European Communities (CEC) guidelines]. The results show that in four examinations (skull, chest, lumbar spine and pelvis), there is a strong tendency of using exposure times above the European recommendation. The X-ray tube potential values (in kV) are below the recommended values from CEC guidelines. This study shows that at a local level (Lisbon region), radiographic practice does not comply with CEC guidelines concerning exposure techniques. Further national/local studies are recommended with the objective to improve exposure optimisation and technical procedures in plain radiography. This study also suggests the need to establish national/local diagnostic reference levels and to proceed to effective measurements for exposure optimisation.

Evaluation of exposure index (IgM) in orthopaedic radiography.

The exposure index (lgM) obtained from a radiographic image may be a useful feedback indicator to the radiographer about the appropriate exposure level in routine clinical practice. This study aims to evaluate lgM in orthopaedic radiography performed in the standard clinical environment. We analysed the lgM of 267 exposures performed with an AGFA CR system. The mean value of lgM in our sample is 2.14. A significant difference (P = 0.000 < or =0.05) from 1.96 lgM reference is shown. Data show that 72% of exposures are above the 1.96 lgM and 42% are above the limit of 2.26. Median values of lgM are above 1.96 and below 2.26 for Speed class (SC) 200 (2.16) and SC400 (2.13). The interquartile range is lower in SC400 than in SC200. Data seem to indicate that lgM values are above the manufacturer's reference of 1.96. Departmental exposure charts should be optimised to reduce the dose given to patients.