Machine learning and deep learning for classifying the justification of brain CT referrals.

OBJECTIVES: To train the machine and deep learning models to automate the justification analysis of radiology referrals in accordance with iGuide categorisation, and to determine if prediction models can generalise across multiple clinical sites and outperform human experts. METHODS: Adult brain computed tomography (CT) referrals from scans performed in three CT centres in Ireland in 2020 and 2021 were retrospectively collected. Two radiographers analysed the justification of 3000 randomly selected referrals using iGuide, with two consultant radiologists analysing the referrals with disagreement. Insufficient or duplicate referrals were discarded. The inter-rater agreement among radiographers and consultants was computed. A random split (4:1) was performed to apply machine learning (ML) and deep learning (DL) techniques to unstructured clinical indications to automate retrospective justification auditing with multi-class classification. The accuracy and macro-averaged F1 score of the best-performing classifier of each type on the training set were computed on the test set. RESULTS: 42 referrals were ignored. 1909 (64.5%) referrals were justified, 811 (27.4%) were potentially justified, and 238 (8.1%) were unjustified. The agreement between radiographers (κ = 0.268) was lower than radiologists (κ = 0.460). The best-performing ML model was the bag-of-words-based gradient-boosting classifier achieving a 94.4% accuracy and a macro F1 of 0.94. DL models were inferior, with bi-directional long short-term memory achieving 92.3% accuracy, a macro F1 of 0.92, and outperforming multilayer perceptrons. CONCLUSION: Interpreting unstructured clinical indications is challenging necessitating clinical decision support. ML and DL can generalise across multiple clinical sites, outperform human experts, and be used as an artificial intelligence-based iGuide interpreter when retrospectively vetting radiology referrals. CLINICAL RELEVANCE STATEMENT: Healthcare vendors and clinical sites should consider developing and utilising artificial intelligence-enabled systems for justifying medical exposures. This would enable better implementation of imaging referral guidelines in clinical practices and reduce population dose burden, CT waiting lists, and wasteful use of resources. KEY POINTS: Significant variations exist among human experts in interpreting unstructured clinical indications/patient presentations. Machine and deep learning can automate the justification analysis of radiology referrals according to iGuide categorisation. Machine and deep learning can improve retrospective and prospective justification auditing for better implementation of imaging referral guidelines.

Validating the safety of low-dose CTPA in pregnancy: results from the OPTICA (Optimised CT Pulmonary Angiography in Pregnancy) Study.

BACKGROUND: Pulmonary embolism (PE) is a leading cause of pregnancy-related mortality. CT pulmonary angiogram (CTPA) is the first-line advanced imaging modality for suspected PE in pregnancy at institutes offering low-dose techniques; however, a protocol balancing safety with low dose remains undefined. The wide range of CTPA doses reported in pregnancy suggests a lack of confidence in implementing low-dose techniques in this group. PURPOSE: To define and validate the safety, radiation dose and image quality of a low-dose CTPA protocol optimised for pregnancy. MATERIALS AND METHODS: The OPTICA study is a prospective observational study. Pregnant study participants with suspected PE underwent the same CTPA protocol between May 2018 and February 2022. The primary outcome, CTPA safety, was judged by the reference standard; the 3-month incidence of venous thromboembolism (VTE) in study participants with a negative index CTPA. Secondary outcomes defined radiation dose and image quality. Absorbed breast, maternal effective and fetal doses were estimated by Monte-Carlo simulation on gestation-matched phantoms. Image quality was assessed by signal-to-noise and contrast-to-noise ratios and a Likert score for pulmonary arterial enhancement. RESULTS: A total of 116 CTPAs were performed in 113 pregnant women of which 16 CTPAs were excluded. PE was diagnosed on 1 CTPA and out-ruled in 99. The incidence of recurrent symptomatic VTE was 0.0% (one-sided 95% CI, 2.66%) at follow-up. The mean absorbed breast dose was 2.9 ± 2.1mGy, uterine/fetal dose was 0.1 ± 0.2mGy and maternal effective dose was 1.4 ± 0.9mSv. Signal-to-noise ratio (SNR) was 11.9 ± 3.7. Contrast-to-noise ratio (CNR) was 10.4 ± 3.5. CONCLUSION: The OPTICA CTPA protocol safely excluded PE in pregnant women across all trimesters, with low fetal and maternal radiation. CLINICAL RELEVANCE: OPTICA (Optimised CT Pulmonary Angiography in Pregnancy) is the first prospective study to define the achievable radiation dose, image-quality and safety of a low-dose CT pulmonary angiogram protocol optimised for pregnancy (NCT04179487). It provides the current benchmark for safe and achievable CT pulmonary angiogram doses in the pregnant population. KEY POINTS: • Despite the increased use of CT pulmonary angiogram in pregnancy, an optimised low-dose protocol has not been defined and reported doses in pregnancy continue to vary widely. • The OPTICA (Optimised CT Pulmonary Angiography in Pregnancy) study prospectively defines the achievable dose, image quality and safety of a low-dose CT pulmonary angiogram protocol using widely available technology. • OPTICA provides a benchmark for safe and achievable CT pulmonary angiogram doses in the pregnant population.

Development of the EVIBEC Learning Outcomes Framework to support the delivery of evidence-based practice curricula in health care professional programmes: a codesign approach.

BACKGROUND: All healthcare professional education programmes must adopt a systematic approach towards ensuring graduates achieve the competencies required to be an evidence-based practitioner. While a list of competencies for evidence-based practice exist, health care educators continue to struggle with effectively integrating the necessary competencies into existing curricula. The purpose of this project was to develop an open access cross-discipline, learning outcomes framework to support educators in integrating the teaching, learning and assessment required to ensure all graduates of health care professional programmes can achieve the necessary evidence-based practice competencies. METHODS: An interdisciplinary team of health care professional educators and a librarian completed a review of the health professions literature on the teaching and assessment of evidence-based practice. The literature, coupled with the teams' collective experiences in evidence-based education and research, were used to identify relevant teaching, learning and evidence-based competency frameworks to inform the project design. The guide and toolkit for experience-based co-design developed by the National Health Service Institute for Innovation and Improvement was adopted for this study ( Institute for Innovation and Improvement: Experience Based Design: Guide & Tools In. Leeds: NHS; 2009.). A four-step approach involving three online participatory co-design workshops and a national validation workshop was designed. Students (n = 33), faculty (n = 12), and clinical educators (n = 15) participated in formulating and mapping learning outcomes to evidence-based competencies. RESULTS: Through a rigorous, systematic co-design process the Evidenced-based Education Collaborative (EVIBEC) Learning Outcomes Framework was developed. This framework consists of a series of student-centred learning outcomes, aligned to evidence-based practice competencies, classified according to the 5 As of EBP and mapped to the cognitive levels of Bloom's taxonomy. Associated learning activities for each step of EBP are suggested. CONCLUSIONS: A consensus-based, student-centred learning outcomes framework aligned to a contemporary set of EBP core competencies has been developed. The freely accessible EVIBEC framework may support entry level health care professional EBP education, by informing EBP curriculum development and offering the potential for interdisciplinary approaches to and sharing of valuable teaching and learning resources. Co-design proved an effective method in creating and refining this framework.

Exploring the translational challenge for medical applications of ionising radiation and corresponding radiation protection research.

BACKGROUND: Medical applications of ionising radiation and associated radiation protection research often encounter long delays and inconsistent implementation when translated into clinical practice. A coordinated effort is needed to analyse the research needs for innovation transfer in radiation-based high-quality healthcare across Europe which can inform the development of an innovation transfer framework tailored for equitable implementation of radiation research at scale. METHODS: Between March and September 2021 a Delphi methodology was employed to gain consensus on key translational challenges from a range of professional stakeholders. A total of three Delphi rounds were conducted using a series of electronic surveys comprised of open-ended and closed-type questions. The surveys were disseminated via the EURAMED Rocc-n-Roll consortium network and prominent medical societies in the field. Approximately 350 professionals were invited to participate. Participants' level of agreement with each generated statement was captured using a 6-point Likert scale. Consensus was defined as median ≥ 4 with ≥ 60% of responses in the upper tertile of the scale. Additionally, the stability of responses across rounds was assessed. RESULTS: In the first Delphi round a multidisciplinary panel of 20 generated 127 unique statements. The second and third Delphi rounds recruited a broader sample of 130 individuals to rate the extent to which they agreed with each statement as a key translational challenge. A total of 60 consensus statements resulted from the iterative Delphi process of which 55 demonstrated good stability. Ten statements were identified as high priority challenges with ≥ 80% of statement ratings either 'Agree' or 'Strongly Agree'. CONCLUSION: A lack of interoperability between systems, insufficient resources, unsatisfactory education and training, and the need for greater public awareness surrounding the benefits, risks, and applications of ionising radiation were identified as principal translational challenges. These findings will help to inform a tailored innovation transfer framework for medical radiation research.

Semi-automated Tracing of Hamstring Muscle Architecture for B-mode Ultrasound Images.

Hamstring strains are the most prevalent injury sustained by field-sport athletes. Insufficiencies in the architectural characteristics of the hamstring muscles can heighten an athlete's risk of incurring a hamstring strain. To evaluate the influence of hamstring muscle architectural characteristics (i. e., fascicle length, pennation angle, muscle thickness) on injury risk, it is necessary to precisely evaluate these characteristics. Considering this, our aim was to develop and evaluate the precision of a novel semi-automated tracing software to measure the architectural characteristics of the biceps femoris long head (the most commonly injured hamstring muscle) in B-mode ultrasound images. We acquired static sonograms of the biceps femoris long head from ten healthy male field-sport athletes. The architectural characteristics (fascicle length, pennation angle, and muscle thickness) of participants' biceps femoris long head were evaluated 10 times using the tracing software, with the specific purpose of determining its measurement precision. The tracing software precisely measured the architectural characteristics of the participants' biceps femoris long head: fascicle length (% CV: 0.64-1.12), pennation angle (% CV: 2.58-10.70), muscle thickness (% CV: 0.48-2.04) Our semi-automated skeletal muscle tracing algorithm precisely measures fascicle length, pennation angles, and muscle thickness of the biceps femoris long head in static B-mode ultrasound images.

A Risk Score Including Carotid Plaque Inflammation and Stenosis Severity Improves Identification of Recurrent Stroke.

Background and Purpose- In randomized trials of symptomatic carotid endarterectomy, only modest benefit occurred in patients with moderate stenosis and important subgroups experienced no benefit. Carotid plaque 18F-fluorodeoxyglucose uptake on positron emission tomography, reflecting inflammation, independently predicts recurrent stroke. We investigated if a risk score combining stenosis and plaque 18F-fluorodeoxyglucose would improve the identification of early recurrent stroke. Methods- We derived the score in a prospective cohort study of recent (<30 days) non-severe (modified Rankin Scale score ≤3) stroke/transient ischemic attack. We derived the SCAIL (symptomatic carotid atheroma inflammation lumen-stenosis) score (range, 0-5) including 18F-fluorodeoxyglucose standardized uptake values (SUVmax <2 g/mL, 0 points; SUVmax 2-2.99 g/mL, 1 point; SUVmax 3-3.99 g/mL, 2 points; SUVmax ≥4 g/mL, 3 points) and stenosis (<50%, 0 points; 50%-69%, 1 point; ≥70%, 2 points). We validated the score in an independent pooled cohort of 2 studies. In the pooled cohorts, we investigated the SCAIL score to discriminate recurrent stroke after the index stroke/transient ischemic attack, after positron emission tomography-imaging, and in mild or moderate stenosis. Results- In the derivation cohort (109 patients), recurrent stroke risk increased with increasing SCAIL score (P=0.002, C statistic 0.71 [95% CI, 0.56-0.86]). The adjusted (age, sex, smoking, hypertension, diabetes mellitus, antiplatelets, and statins) hazard ratio per 1-point SCAIL increase was 2.4 (95% CI, 1.2-4.5, P=0.01). Findings were confirmed in the validation cohort (87 patients, adjusted hazard ratio, 2.9 [95% CI, 1.9-5], P<0.001; C statistic 0.77 [95% CI, 0.67-0.87]). The SCAIL score independently predicted recurrent stroke after positron emission tomography-imaging (adjusted hazard ratio, 4.52 [95% CI, 1.58-12.93], P=0.005). Compared with stenosis severity (C statistic, 0.63 [95% CI, 0.46-0.80]), prediction of post-positron emission tomography stroke recurrence was improved with the SCAIL score (C statistic, 0.82 [95% CI, 0.66-0.97], P=0.04). Findings were confirmed in mild or moderate stenosis (adjusted hazard ratio, 2.74 [95% CI, 1.39-5.39], P=0.004). Conclusions- The SCAIL score improved the identification of early recurrent stroke. Randomized trials are needed to test if a combined stenosis-inflammation strategy improves selection for carotid revascularization where benefit is currently uncertain.

Development of a computational tool for estimating computed tomography dose parameters.

BACKGROUND: Computed Tomographic (CT) imaging procedures have been reported as the main source of radiation in diagnostic procedures compared to other modalities. To provide the optimal quality of CT images at the minimum radiation risk to the patient, periodic inspections and calibration tests for CT equipment are required. These tests involve a series of measurements that are time consuming and may require specific skills and highly-trained personnel. OBJECTIVE: This study aims to develop a new computational tool to estimate the dose of CT radiation outputs and assist in the calibration of CT scanners. It may also provide an educational resource by which radiological practitioners can learn the influence of technique factors on both patient radiation dose and the produced image quality. METHODS: The computational tool was developed using MATLAB in order to estimate the CT radiation dose parameters for different technique factors. The CT radiation dose parameters were estimated from the calibrated energy spectrum of the x-ray tube for a CT scanner. RESULTS: The estimated dose parameters and the measured values utilising an Adult CT Head Dose Phantom showed linear correlations for different tube voltages (80 kVp, 100 kVp, 120 kVp, and 140 kVp), with R2 nearly equal to 1 (0.99). The maximum differences between the estimated and measured CTDIvol were under 5 %. For 80 kVp and low tube currents (50 mA, 100 mA), the maximum differences were under 10%. CONCLUSIONS: The prototyped computational model provides a tool for the simulation of a machine-specific spectrum and CT dose parameters using a single dose measurement.

Carotid Plaque Inflammation Imaged by 18F-Fluorodeoxyglucose Positron Emission Tomography and Risk of Early Recurrent Stroke.

Background and Purpose- Plaque inflammation contributes to stroke and coronary events. 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) identifies plaque inflammation-related metabolism. Almost no prospective data exist on the relationship of carotid 18F-FDG uptake and early recurrent stroke. Methods- We did a multicenter prospective cohort study BIOVASC (Biomarkers/Imaging Vulnerable Atherosclerosis in Symptomatic Carotid disease) of patients with carotid stenosis and recent stroke/transient ischemic attack with 90-day follow-up. On coregistered carotid 18F-FDG PET/computed tomography angiography, 18F-FDG uptake was expressed as maximum standardized uptake value (SUVmax) in the axial single hottest slice. We then conducted a systematic review of similar studies and pooled unpublished individual-patient data with 2 highly similar independent studies (Dublin and Barcelona). We analyzed the association of SUVmax with all recurrent nonprocedural stroke (before and after PET) and with recurrent stroke after PET only. Results- In BIOVASC (n=109, 14 recurrent strokes), after adjustment (for age, sex, stenosis severity, antiplatelets, statins, diabetes mellitus, hypertension, and smoking), the hazard ratio for recurrent stroke per 1 g/mL SUVmax was 2.2 (CI, 1.1-4.5; P=0.025). Findings were consistent in the independent Dublin (n=52, hazard ratio, 2.2; CI, 1.1-4.3) and Barcelona studies (n=35, hazard ratio, 2.8; CI, 0.98-5.5). In the pooled cohort (n=196), 37 recurrent strokes occurred (29 before and 8 after PET). Plaque SUVmax was higher in patients with all recurrence ( P<0.0001) and post-PET recurrence ( P=0.009). The fully adjusted hazard ratio of any recurrent stroke was 2.19 (CI, 1.41-3.39; P<0.001) and for post-PET recurrent stroke was 4.57 (CI, 1.5-13.96; P=0.008). Recurrent stroke risk increased across SUVmax quartiles (log-rank P=0.003). The area under receiver operating curve for all recurrence was 0.70 (CI, 0.59-0.78) and for post-PET recurrence was 0.80 (CI, 0.64-0.96). Conclusions- Plaque inflammation-related 18F-FDG uptake independently predicted future recurrent stroke post-PET. Although further studies are needed, 18F-FDG PET may improve patient selection for carotid revascularization and suggest that anti-inflammatory agents may have benefit for poststroke vascular prevention.

The impact of pediatric-specific dose modulation curves on radiation dose and image quality in head computed tomography.

BACKGROUND: The volume of CT examinations has increased with resultant increases in collective dose values over the last decade. OBJECTIVE: To analyze the impact of the tube current and voltage modulation for dose values and image quality of pediatric head CT examinations. MATERIALS AND METHODS: Head CT examinations were performed on anthropomorphic phantoms and four pediatric age categories before and after the introduction of dedicated pediatric curves for tube voltage and current modulation. Local diagnostic reference levels were calculated. Visual grading characteristic image quality evaluation was performed by four pediatric neuroradiologists and image noise comparisons were performed. RESULTS: Pediatric-specific modulation curves demonstrated a 49% decrease in mean radiation dose for phantom examinations. The local diagnostic reference levels (CTDIvol) for clinical examinations decreased by 52%, 41%, 46% and 40% for newborn, 5-, 10- and 15-year-old patients, respectively. Visual grading characteristic image quality was maintained for the majority of age categorizations (area under the curve = 0.5) and image noise measurements did not change (P = 0.693). CONCLUSION: Pediatric-specific dose modulation curves resulted in an overall mean dose reduction of 45% with no significant differences in subjective or objective image quality findings.

Current and potential applications of artificial intelligence in medical imaging practice: A narrative review.

BACKGROUND AND PURPOSE: Artificial intelligence (AI) is present in many areas of our lives. Much of the digital data generated in health care can be used for building automated systems to bring improvements to existing workflows and create a more personalised healthcare experience for patients. This review outlines select current and potential AI applications in medical imaging practice and provides a view of how diagnostic imaging suites will operate in the future. Challenges associated with potential applications will be discussed and healthcare staff considerations necessary to benefit from AI-enabled solutions will be outlined. METHODS: Several electronic databases, including PubMed, ScienceDirect, Google Scholar, and University College Dublin Library Database, were used to identify relevant articles with a Boolean search strategy. Textbooks, government sources and vendor websites were also considered. RESULTS/DISCUSSION: Many AI-enabled solutions in radiographic practice are available with more automation on the horizon. Traditional workflow will become faster, more effective, and more user friendly. AI can handle administrative or technical types of work, meaning it is applicable across all aspects of medical imaging practice. CONCLUSION: AI offers significant potential to automate most of the manual tasks, ensure service consistency, and improve patient care. Radiographers, radiation therapists, and clinicians should ensure they have adequate understanding of the technology to enable ethical oversight of its implementation.

Potential for Dose Reduction in CT-Derived Left Ventricular Ejection Fraction: A Simulation Study.

BACKGROUND: Measuring left ventricular ejection fraction (LVEF) is important for detecting heart failure, e.g., in treatment with potentially cardiotoxic chemotherapy. MRI is considered the reference standard for LVEF, but availability may be limited and claustrophobia or metal implants still present challenges. CT has been shown to be accurate and would be advantageous, as LVEF could be measured in conjunction with routine chest-abdomen-pelvis oncology CT. However, the use of CT is not recommended due to the excessive radiation dose. This study aimed to explore the potential for dose reduction using simulation. Using an anthropomorphic heart phantom scanned at 13 dose levels, a noise simulation algorithm was developed to introduce controlled Poisson noise. Filtered backprojection parameters were iteratively tested to minimise differences in myocardium-to-ventricle contrast/noise ratio, as well as structural similarity index (SSIM) differences between real and simulated images at all dose levels. Fifty-one clinical CT coronary angiographies, scanned with full dose through end-systolic and -diastolic phases, were located retrospectively. Using the developed algorithm, noise was introduced corresponding to 25, 10, 5 and 2% of the original dose level. LVEF was measured using clinical software (Syngo.via VB50) with papillary muscles in and excluded from the LV volume. At each dose level, LVEF was compared to the 100% dose level, using Bland-Altman analysis. The effective dose was calculated from DLP using a conversion factor of 0.026 mSv/mGycm. RESULTS: In the clinical images, mean CTDIvol and DLP were 47.1 mGy and 771.9 mGycm, respectively (effective dose 20.0 mSv). Measurements with papillary muscles excluded did not exhibit statistically significant LVEF bias to full-dose images at 25, 10 and 5% simulated dose. At 2% dose, a significant bias of 4.4% was found. With papillary muscles included, small but significant biases were found at all simulated dose levels. CONCLUSION: Provided that measurements are performed with papillary muscles excluded from the LV volume, the dose can be reduced by a factor of 20 without significantly affecting LVEF measurements. This corresponds to an effective dose of 1 mSv. CT can potentially be used for LVEF measurement with minimal excessive radiation.

The architectural characteristics of the hamstring muscles do not differ between male and female elite-level rugby union players.

Purpose: To determine whether differences exist in the architectural characteristics of the hamstring muscles of elite-level male and female rugby union players. Methods: Forty elite-level rugby union players (male n = 20, female n = 20) participated in this cross-sectional study. A sonographer acquired static ultrasound images using a 92 mm linear transducer to quantify (via a semi-automated tracing software tool) the architectural characteristics (muscle length, fascicle length, pennation angle, and muscle thickness) of the biceps femoris long head and semimembranosus muscles of participants' left limb. Muscle length and muscle thickness of the biceps femoris short head and semitendinosus muscles of participants' left limb were also quantified. Bonferroni adjusted independent samples t-tests were performed to evaluate whether differences exist in the architectural characteristics of the hamstring muscles of elite-level male and female rugby union players. Results: There were no significant differences in fascicle length or pennation angle of the hamstring muscles of elite-level male and female rugby union players. Some significant differences in muscle thickness (biceps femoris short head, and semimembranosus) and muscle length (biceps femoris short head, biceps femoris long head, semitendinosus, and semimembranosus) were observed; in all cases the male players had thicker and longer muscles. Conclusion: At a group level, hamstring muscle fascicle length and pennation angle are unlikely to be a sex-specific intrinsic risk factor for Hamstring strain injuries.

COMBINING HI-RESOLUTION SCAN MODE WITH DEEP LEARNING RECONSTRUCTION ALGORITHMS IN CARDIAC CT.

To investigate the impact of combining the high-resolution (Hi-res) scan mode with deep learning image reconstruction (DLIR) algorithm in CT. Two phantoms (Catphan600® and Lungman, small, medium, large size) were CT scanned using combinations of Hi-res/standard mode and high-definition (HD)/standard kernels. Images were reconstructed with ASiR-V and three levels of DLIR. Spatial resolution, noise and contrast-to-noise ratio (CNR) were assessed. The radiation dose was recorded. The spatial resolution increased using Hi-res & HD. Image noise in the Catphan600® (69%) and the Lungman (10-70%) significantly increased when Hi-res & HD was applied. DLIR reduced the mean noise (54%). The CNR was reduced (64%) for Hi-res & HD. The radiation dose increased for both small (+70%) and medium (+43%) Lungman phantoms but decreased slightly for the large ones (-3%) when Hi-res was applied. In conclusion, the Hi-res scan mode improved the spatial resolution. The HD kernel significantly increased the image noise. DLIR improved the image noise and CNR and did not affect the spatial resolution.

Breast Shielding Combined With an Optimized Computed Tomography Pulmonary Angiography Pregnancy Protocol: A Special Use-Case for Shielding?

OBJECTIVES: To determine the impact of breast shields on breast dose and image quality when combined with a low-dose computed tomography pulmonary angiography (CTPA) protocol for pregnancy. METHODS: A low-dose CTPA protocol, with and without breast shields, was evaluated by anthropomorphic phantom and 20 prospectively recruited pregnant participants from January to October 2019. Thermoluminescent dosimeters measured surface and absorbed breast dose in the phantom and surface breast dose in participants. The Monte-Carlo method estimated the absorbed breast dose in participants. Image quality was assessed quantitatively by regions of interest analysis and subjectively by the Likert scale. Doses and image quality for CTPA alone were compared with CTPA with breast shields. RESULTS: Mean surface and absorbed breast dose for CTPA alone were 1.3±0.4 and 2.8±1.5 mGy in participants, and 1.5±0.7 and 1.6±0.6 mGy in the phantom. Shielding reduced surface breast dose to 0.5±0.3 and 0.7±0.2 mGy in the phantom (66%) and study participants (48%), respectively. Absorbed breast dose reduced to 0.9±0.5 mGy (46%) in the phantom.Noise increased with breast shields at lower kV settings (80 to 100 kV) in the phantom; however, in study participants there was no significant difference between shield and no-shield groups for main pulmonary artery noise (no-shield: 34±9.8, shield: 36.3±7.2, P =0.56), SNR (no-shield: 11.2±3.7, shield: 10.8±2.6, P =0.74) or contrast-to-noise ratio (no-shield: 10.0±3.3, shield: 9.3±2.4, P =0.6). Median subjective image quality scores were comparable (no-shield: 4.0, interquartile range: 3.5 to 4.4, shield: 4.3, interquartile range: 4.0 to 4.5). CONCLUSION: Combining low-dose CTPA with breast shields confers additional breast-dose savings without impacting image quality and yields breast doses approaching those of low-dose scintigraphy, suggesting breast shields play a role in protocol optimization for select groups.

European survey on the use of patient contact shielding during radiological examinations.

OBJECTIVES: Contact shielding (CS) of patients during X-ray studies has been used for decades to protect radiosensitive organs. This practice has not changed much despite increasing evidence that CS is not useful in many cases. The Gonad And Patient Shielding (GAPS) group-founded by representatives of the main European bodies involved in radiology-promoted this survey to assess the current practice of CS among European radiology departments and the attitude towards a non-shielding policy. METHODS: Over a four-month period (15 May-15th September 2021) European Society of Radiology and European Society of Paediatric Radiology radiologist members were invited to respond to a web-based questionnaire consisting of 59 questions. RESULTS: 225 centres from 35 countries responded to this survey. CS was routinely applied in at least one radiological modality in 49.2% of centres performing studies in adults, 57.5% of centres performing studies in children, and 47.8% of centres performing studies on pregnant women. CS was most frequently used in conventional radiography, where the most frequently shielded organs were the gonads, followed by thyroid, female breasts, and eye lens. 83.6% respondents would follow European recommendations on the use of CS when provided by the main European bodies involved in radiology. CONCLUSIONS: This review shows that CS is still largely used across Europe. However, a non-shielding policy could be adopted in most departments if European professional societies provided recommendations. In this regard, a strong commitment by European and national professional societies to educate and inform practitioners, patients and carers is paramount. CLINICAL RELEVANCE STATEMENT: According to this survey expectations of patients and carers, and skepticism among professionals about the limited benefits of CS are the most important obstacles to the application of a no-shielding policy. A strong commitment from European and national professional societies to inform practitioners, patients and carers is fundamental.

Education and training in radiation protection in Europe: results from the EURAMED Rocc-n-Roll project survey.

PURPOSE: To analyse the existing radiation protection (RP) education and training (E&T) capabilities in the European Union and identify associated needs, problems and challenges. METHOD: An online survey was disseminated via the EURAMED Rocc-n-Roll consortium network and prominent medical societies in the field of radiological research. The survey sections analyse the RP E&T during undergraduate, residency/internship and continuous professional development; RP E&T problems and legal implementation. Differences were analysed by European geographic regions, profession, years of professional experience and main area of practice/research. RESULTS: The majority of the 550 respondents indicated that RP topics are part of undergraduate curricula in all courses for their profession and country (55%); however, hands-on practical training is not included according to 30% of the respondents. The lack of E&T, practical aspects in current E&T, and mandatory continuing E&T were considered the major problems. The legal requirement that obtained higher implementation score was the inclusion of the practical aspects of medical radiological procedures on education (86%), and lower score was obtained for the inclusion of RP E&T on medical and dental school curriculums (61%). CONCLUSIONS: A heterogeneity in RP E&T during undergraduate, residency/internship and continuous professional development is evident across Europe. Differences were noted per area of practice/research, profession, and European geographic region. A large variation in RP E&T problem rating was also obtained.

Symptomatic Carotid Atheroma Inflammation Lumen-stenosis score compared with Oxford and Essen risk scores to predict recurrent stroke in symptomatic carotid stenosis.

BACKGROUND: The Oxford Carotid Stenosis tool (OCST) and Essen Stroke Risk Score (ESRS) are validated to predict recurrent stroke in patients with and without carotid stenosis. The Symptomatic Carotid Atheroma Inflammation Lumen stenosis (SCAIL) score combines stenosis and plaque inflammation on fluorodeoxyglucose positron-emission tomography (18FDG-PET). We compared SCAIL with OCST and ESRS to predict ipsilateral stroke recurrence in symptomatic carotid stenosis. PATIENTS AND METHODS: We pooled three prospective cohort studies of patients with recent (<30 days) non-severe ischaemic stroke/TIA and internal carotid artery stenosis (>50%). All patients had carotid 18FDG-PET/CT angiography and late follow-up, with censoring at carotid revascularisation. RESULTS: Of 212 included patients, 16 post-PET ipsilateral recurrent strokes occurred in 343 patient-years follow-up (median 42 days (IQR 13-815)).Baseline SCAIL predicted recurrent stroke (unadjusted hazard ratio [HR] 1.96, CI 1.20-3.22, p = 0.007, adjusted HR 2.37, CI 1.31-4.29, p = 0.004). The HR for OCST was 0.996 (CI 0.987-1.006, p = 0.49) and for ESRS was 1.26 (CI 0.87-1.82, p = 0.23) (all per 1-point score increase). C-statistics were: SCAIL 0.66 (CI 0.51-0.80), OCST 0.52 (CI 0.40-0.64), ESRS 0.61 (CI 0.48-0.74). Compared with ESRS, addition of plaque inflammation (SUVmax) to ESRS improved risk prediction when analysed continuously (HR 1.51, CI 1.05-2.16, p = 0.03) and categorically (ptrend = 0.005 for risk increase across groups; HR 3.31, CI 1.42-7.72, p = 0.006; net reclassification improvement 10%). Findings were unchanged by further addition of carotid stenosis. CONCLUSIONS: SCAIL predicted recurrent stroke, had discrimination better than chance, and improved the prognostic utility of ESRS, suggesting that measuring plaque inflammation may improve risk stratification in carotid stenosis.

Hamstring muscle architecture assessed sonographically using wide field of view: A reliability study.

PURPOSE: To assess the intra-rater reliability of static wide field of view ultrasound to quantify the architectural characteristics of the hamstring muscles. METHODS: Twenty amateur male athletes were recruited. Their left hamstring muscles were assessed using static wide field of view ultrasound on two separate occasions. Static ultrasound images were acquired by a single sonographer using a 92mm linear transducer. The architectural characteristics (muscle length, fascicle length, pennation angle and muscle thickness) from two distinct locations of the bicep femoris long head and semimembranosus were evaluated. Muscle length and thickness of the bicep femoris short head and semitendinosus muscle were also evaluated. Intraclass correlation coefficient analyses were performed to determine the intra-rater reliability of the performed measurements. RESULTS: Both muscle (intraclass correlation coefficient = 0.99; standard error of measurement = 4.3 to 6.6mm) and fascicle (intraclass correlation coefficient = 0.92 to 0.98; standard error measurement = 1.1 to 2.4mm) length were measured with excellent intra-rater reliability. Muscle thickness was measured with excellent reliability (intraclass correlation coefficient = 0.9 to 0.96; standard error of measurement = 0.91mm to 1.4mm) for all hamstring muscles except for the proximal segments of the bicep femoris short head (intraclass correlation coefficient = 0.85; standard error of measurement = 0.84mm) and semitendinosus (intraclass correlation coefficient = 0.88; standard error of measurement = 0.82mm), which were measured with good reliability. Pennation angle was measured with good reliability (intraclass correlation coefficient = 0.77 to 0.87; standard error of measurement = 1 to 1.6°). CONCLUSION: The architectural characteristics of the hamstring muscles of male amateur athletes can be reliably quantified using static wide field of view ultrasound.

Automated vetting of radiology referrals: exploring natural language processing and traditional machine learning approaches.

BACKGROUND: With a significant increase in utilisation of computed tomography (CT), inappropriate imaging is a significant concern. Manual justification audits of radiology referrals are time-consuming and require financial resources. We aimed to retrospectively audit justification of brain CT referrals by applying natural language processing and traditional machine learning (ML) techniques to predict their justification based on the audit outcomes. METHODS: Two human experts retrospectively analysed justification of 375 adult brain CT referrals performed in a tertiary referral hospital during the 2019 calendar year, using a cloud-based platform for structured referring. Cohen's kappa was computed to measure inter-rater reliability. Referrals were represented as bag-of-words (BOW) and term frequency-inverse document frequency models. Text preprocessing techniques, including custom stop words (CSW) and spell correction (SC), were applied to the referral text. Logistic regression, random forest, and support vector machines (SVM) were used to predict the justification of referrals. A test set (300/75) was used to compute weighted accuracy, sensitivity, specificity, and the area under the curve (AUC). RESULTS: In total, 253 (67.5%) examinations were deemed justified, 75 (20.0%) as unjustified, and 47 (12.5%) as maybe justified. The agreement between the annotators was strong (κ = 0.835). The BOW + CSW + SC + SVM outperformed other binary models with a weighted accuracy of 92%, a sensitivity of 91%, a specificity of 93%, and an AUC of 0.948. CONCLUSIONS: Traditional ML models can accurately predict justification of unstructured brain CT referrals. This offers potential for automated justification analysis of CT referrals in clinical departments.

The impact of ASiR-V on abdominal CT radiation dose and image quality - A phantom study.

INTRODUCTION: To investigate how ASiR-V and kVp changes in Computed tomography (CT) affect radiation dose and image quality, when using automatic tube current modulation (ATCM) for different sized phantoms. METHODS: A liver-phantom with two different liver inserts (QRM, Moehrendorf, Germany), with extension rings, representing fat, were additionally applied to the phantom to simulate patients of different sizes (small: 30cm diameter, medium: 35cm and large: 40cm). Abdominal scans were performed on a 256 slice CT scanner (GE Healthcare, Milwaukee, WI, USA), with consistent pitch (0.992), rotation time (0.5s), slice thickness (0.625mm) and collimation (80mm), while other parameters were varied (kVp: 80/100/120/140; Noise Index: 13/22; mA interval 80-720, ASiR-V: 30/60/100%). CTDI and DLP was recorded for each scan and image quality was assessed using objective metrics in predefined anatomic areas (HU and noise). Radiation dose and image quality metrics were compared between protocols. RESULTS: CTDI decreased by 80% from ASIR-V 30% to ASiR-V 100% for prescribed NI 13, and by 79% for the prescribed NI of 22. For 100% ASiR-V and a prescribed NI of 22 the CTDI remained the same regardless of phantom size for the different kVp settings. Pairwise comparison revealed significant differences in CTDI (p < 0.0001) for all combinations of prescribed NI and ASIR-V levels, except the difference between ASIR-V levels of 30 and 60%, with a prescribed NI of 13 (p = 0.124). When data from the three phantom sizes were combined, increasing ASIR-V from 30-100%, resulted in noise decreases of 22% for NI of 13 and by 8% for NI of 22. Notably, image quality in the low contrast area of the liver insert was impaired when the large phantom was scanned with 100% ASiR-V and either 80/100kVp (NI 22), because of the large reduction in tube current applied (down to 80 mA). CONCLUSION: Substantial radiation dose reductions (up to 80%) resulted from increasing ASiR-V levels. However, image quality deteriorates when 100% ASiR-V is applied due to low applied tube current by the ATCM.