Artificial Intelligence-Assisted Detection of Osteoporotic Vertebral Fractures on Lateral Chest Radiographs in Post-Menopausal Women.

Osteoporotic vertebral fractures (OVFs) are often not reported by radiologists on routine chest radiographs. This study aims to investigate the clinical value of a newly developed artificial intelligence (AI) tool, Ofeye 1.0, for automated detection of OVFs on lateral chest radiographs in post-menopausal women (>60 years) who were referred to undergo chest x-rays for other reasons. A total of 510 de-identified lateral chest radiographs from three clinical sites were retrieved and analysed using the Ofeye 1.0 tool. These images were then reviewed by a consultant radiologist with findings serving as the reference standard for determining the diagnostic performance of the AI tool for the detection of OVFs. Of all the original radiologist reports, missed OVFs were found in 28.8% of images but were detected using the AI tool. The AI tool demonstrated high specificity of 92.8% (95% CI: 89.6, 95.2%), moderate accuracy of 80.3% (95% CI: 76.3, 80.4%), positive predictive value (PPV) of 73.7% (95% CI: 65.2, 80.8%), and negative predictive value (NPV) of 81.5% (95% CI: 79, 83.8%), but low sensitivity of 49% (95% CI: 40.7, 57.3%). The AI tool showed improved sensitivity compared with the original radiologist reports, which was 20.8% (95% CI: 14.5, 28.4). The new AI tool can be used as a complementary tool in routine diagnostic reports for the reduction in missed OVFs in elderly women.

Responsible AI practice and AI education are central to AI implementation: a rapid review for all medical imaging professionals in Europe.

Artificial intelligence (AI) has transitioned from the lab to the bedside, and it is increasingly being used in healthcare. Radiology and Radiography are on the frontline of AI implementation, because of the use of big data for medical imaging and diagnosis for different patient groups. Safe and effective AI implementation requires that responsible and ethical practices are upheld by all key stakeholders, that there is harmonious collaboration between different professional groups, and customised educational provisions for all involved. This paper outlines key principles of ethical and responsible AI, highlights recent educational initiatives for clinical practitioners and discusses the synergies between all medical imaging professionals as they prepare for the digital future in Europe. Responsible and ethical AI is vital to enhance a culture of safety and trust for healthcare professionals and patients alike. Educational and training provisions for medical imaging professionals on AI is central to the understanding of basic AI principles and applications and there are many offerings currently in Europe. Education can facilitate the transparency of AI tools, but more formalised, university-led training is needed to ensure the academic scrutiny, appropriate pedagogy, multidisciplinarity and customisation to the learners' unique needs are being adhered to. As radiographers and radiologists work together and with other professionals to understand and harness the benefits of AI in medical imaging, it becomes clear that they are faced with the same challenges and that they have the same needs. The digital future belongs to multidisciplinary teams that work seamlessly together, learn together, manage risk collectively and collaborate for the benefit of the patients they serve.

Plain radiography has a role to play in current clinical practice in Western Switzerland.

AIM: The aim of the study was to investigate the current role of conventional radiography examinations in Western Switzerland and the main clinical indications required to justify the use of this imaging examination. METHODS: Ethical approval was obtained from Vaud Ethics committee (Ref 2020-00311). An online questionnaire was specifically designed and implemented on the data collection tool LimeSurvey composed of two parts: a) to characterise the participants' profile and their institutions and b) 169 projections for the different anatomical area (upper and lower limbs, pelvis, skull, spine, thorax, abdomen) were presented to collect data about the frequency and main clinical indications. Statistical analysis was performed using the software IBM SPSS® (Statistical Package for the Social Sciences) version 26. RESULTS: Radiographers from 60% (26/43) of the invited institutions participated in this survey, mainly from Vaud region. The upper and lower limbs were the most commonly examined by using conventional radiography mainly for trauma and degenerative disorders. The thorax was also an anatomical area commonly explored by X-rays, so were the spine (cervical and lumbar lateral). The skull radiographs were rarely performed in clinical practice and some of the projections were not being used, namely Hirtz, Tangential Nose Bones, Worms and Caldwell's views. CONCLUSIONS: Plain radiography is being used in clinical practice mainly for appendicular skeleton studies and for trauma and degenerative pathologies. Adaptations in radiographers' education and training and other healthcare professionals are needed to provide the judicious use of data that radiographs can give to better manage the patients' imaging pathway.

Artificial intelligence to support person-centred care in breast imaging - A scoping review.

AIM: To overview Artificial Intelligence (AI) developments and applications in breast imaging (BI) focused on providing person-centred care in diagnosis and treatment for breast pathologies. METHODS: The scoping review was conducted in accordance with the Joanna Briggs Institute methodology. The search was conducted on MEDLINE, Embase, CINAHL, Web of science, IEEE explore and arxiv during July 2022 and included only studies published after 2016, in French and English. Combination of keywords and Medical Subject Headings terms (MeSH) related to breast imaging and AI were used. No keywords or MeSH terms related to patients, or the person-centred care (PCC) concept were included. Three independent reviewers screened all abstracts and titles, and all eligible full-text publications during a second stage. RESULTS: 3417 results were identified by the search and 106 studies were included for meeting all criteria. Six themes relating to the AI-enabled PCC in BI were identified: individualised risk prediction/growth and prediction/false negative reduction (44.3%), treatment assessment (32.1%), tumour type prediction (11.3%), unnecessary biopsies reduction (5.7%), patients' preferences (2.8%) and other issues (3.8%). The main BI modalities explored in the included studies were magnetic resonance imaging (MRI) (31.1%), mammography (27.4%) and ultrasound (23.6%). The studies were predominantly retrospective, and some variations (age range, data source, race, medical imaging) were present in the datasets used. CONCLUSIONS: The AI tools for person-centred care are mainly designed for risk and cancer prediction and disease management to identify the most suitable treatment. However, further studies are needed for image acquisition optimisation for different patient groups, improvement and customisation of patient experience and for communicating to patients the options and pathways of disease management.

Radiographers' musculoskeletal health in Western Switzerland: WRMSDs symptoms prevalence and risk factors.

BACKGROUND: Work-related musculoskeletal disorders (WRMSDs) are a significant occupational health concern in radiographers. OBJECTIVE: This study aimed to describe radiographers' WRMSDs symptoms prevalence and severity, exploring associations with occupational risk factors. METHODS: A cross-sectional study was conducted to explore WRMSDs symptoms and occupational risk factors in radiographers of Western Switzerland using an online survey, based on the Nordic Musculoskeletal Questionnaire (NMQ). Descriptive statistics were conducted to analyze the collected data, and associative statistics to identify the risk factors related to symptoms. RESULTS: Participants (n = 359) presented a high prevalence of WRMSDs symptoms in the last 12 months (94.7%), with a related absenteeism rate of 15.6%. In the last 7 days, symptoms prevalence was 67.7%. The most affected anatomical regions, over both time periods, were the neck (73.0%, 36.8%) and low back (67.4%, 35.7%). Associative statistics underlined risk factors affecting significantly radiographers' health (OR >2) were the "awkward postures" (OR = 2.86; 95% CI 1.78-4.58) and "feeling anxiety/stress at work" both for low back (OR = 2.38; 95% CI 1.39-4.08), and being a woman for the neck (OR = 2.64; 95% CI 1.51-4.61). CONCLUSIONS: There is a high WRMSDs symptoms prevalence in Western Switzerland radiographers. Radiographers' work demands namely for awkward postures increases the odds for WRMSDs symptoms presence, affecting predominantly neck, upper and lower back. Our data suggest that further research is needed to implement adapted prevention to this specific context.

Strategies, challenges and enabling factors when imaging autistic individuals in Swiss medical imaging departments.

INTRODUCTION: Autistic individuals may require medical imaging but they can face barriers that are related to lack of adjustments in their care. This study aims to explore and understand strategies currently used by Swiss radiographers to image autistic patients and to propose recommendations for clinical practice. METHODS: The Swiss Ethics of the canton of Vaud committee approved the study. Data collection was gathered using a mixed method approach by an online survey and followed by selected interviews. Descriptive statistics and thematic analysis were used to analyse the data. RESULTS: A hundred completed responses to the survey were obtained and five individual interviews were conducted. Sixty participants reported having managed autistic patients. The main enablers identified were: the support from carers, adapting the behaviour of staff and customising communication. The main challenges were a lack of communication and the lack of knowledge about autism to appropriately manage the patient. Only five radiographers had received prior training in autism. CONCLUSION: Medical imaging departments must develop protocols to overcome the lack of communication between services, radiographers, and autistic service users. The lack of radiographer knowledge about autism can impact autistic patient management, resulting in carers playing an important role during the examination. Customised education for radiographers about autism is needed. IMPLICATION FOR PRACTICE: The development of a scheduling protocol for each imaging modality could improve communication with the patient. The organisation of the physical environment and the patient's preparation for the examination are critical to provide adequate imaging care. It is suggested that medical imaging professionals, autistic service users, and autism organisations collaborate to develop autism related guidelines for medical imaging examinations.

Consensus about image quality assessment criteria of breast implants mammography using Delphi method with radiographers and radiologists.

AIMS: To identify image quality criteria that can be applied to assess breast implant (BI) mammograms according to radiologists and radiographers' perspectives and to explore the level of agreement about criteria priority. METHODS: A two-round Delphi method using a questionnaire was applied to identify the level of agreement between experts, asking them to rank each image criteria available for mammography according to 4 possible answers (1 = need to have, 2 = nice to have, 3 = not pertinent/appropriate, 4 = do not know). Criteria for craniocaudal (CC), mediolateral-oblique (MLO) and lateral (ML), with and without Eklund manoeuvre, were included. This process was repeated after removing the less relevant criteria. RESULTS: Between first and second rounds, different results were obtained regarding the criteria to assess CC and MLO images. Details for anatomic areas were considered the most relevant by radiographers during the first round, while general criteria were prioritised during the second round. Radiologists focused more on analysis of the spread of the breast tissue, if the breast was aligned with detector's centre and level of contrast. The analysis of implant flow, the BI anterior edge and the maximum retropulsion of BI when Eklund manoeuvre is performed were the specific aspects of BI imaging considered as relevant for assessment. CONCLUSIONS: The importance of each criterion used to assess BI mammograms was not the same between radiographers and radiologists, suggesting the two groups of experts are looking for different requirements from the image. Further education and training is necessary to align strategies for assessing BI mammograms, and some criteria need to be adapted to reduce subjectivity.

Effective dose and image optimisation of lateral lumbar spine radiography: a phantom study.

BACKGROUND: To investigate lateral lumbar spine radiography technical parameters for reduction of effective dose whilst maintaining image quality (IQ). METHODS: Thirty-six radiograms of an anthropomorphic phantom were acquired using different exposure parameters: source-to-detector distance (SDD) (100, 130 or 150 cm), tube potential (75, 85 or 95 kVp), tube current × exposure time product (4.5, 9, 18 mAs) and additional copper (Cu) filter (no filter, 0.1-, 0.2-, or 0.3-mm thickness. IQ was assessed using an objective approach (contrast-to-noise-ratio [CNR] calculation and magnification measurement) and a perceptual approach (six observers); ED was estimated using the PCXMC 2.0 software. Descriptive statistics, paired t test, and intraclass correlation coefficient (ICC) were used. RESULTS: The highest ED (0.022 mSv) was found with 100 cm SSD, 75 kVp, 18 mAs, and without Cu filter, whilst the highest CNR (7.23) was achieved at 130 cm SSD, 75 kVp, 18 mAs, and without Cu filter. The lowest ED and CNR were generated at 150 cm SDD, 95 kVp, 4.5 mAs, and 0.3-mm Cu filter. All observers identified the relevant anatomical structures on all images with the lowest ED and IQ. The intra-observer (0.61-0.79) and inter-observer (0.55-0.82) ICC ranged from moderate to excellent. CONCLUSION: All relevant anatomical structures were identified on the lateral lumbar spine radiographs despite using low-dose protocols. The lowest ED (0.002 mSv) was obtained with 150 cm SDD, 95 kVp, 4.5 mAs, and 0.3-mm Cu filter. Further technical and clinical studies are needed to verify these preliminary findings.

Study of breast implants mammography examinations for identification of suitable image quality criteria.

PURPOSE: To characterise the mammography technique used in breast cancer screening programmes for breast implants (BI) and to identify if the image quality (IQ) criteria available in literature are applicable to BI imaging. METHODS: The study was conducted in two phases: literature review to find IQ criteria used in mammography combining keywords in several sources; and assessment of 1207 BI mammograms using the criteria that was identified previously to see if they were achieved or not. An observation grid was used to collect information about positioning, beam energy, compression force, and exposure mode. Descriptive statistics and Student's t test and χ2 test were performed according to the nature of the variables. RESULTS: Forty-seven out of 2188 documents were included in the analysis, with 13 items identified to assess the quality of positioning, 4 for sharpness, 3 for artefacts, and 2 for exposure parameters. After applying the criteria to BI mammograms, retroglandular fat was not included in 37.3% of the images. The "Pectoral-Nipple-Line" criterion was achieved in 35% of MLO/ML images. The placement of the implant (subpectoral/subglandular) or performing the Eklund had significant influence on the visible anatomy (p = < 0.005), alongside whether the breast was aligned to the detector's centre. CONCLUSIONS: Some of the criteria used to assess standard mammograms were not applicable to BI due to implant overlap. The alignment of the image with the detector's centre seems to have an impact on the amount of visible tissue. Further studies are necessary to define the appropriate protocol, technique, and suitable quality criteria to assess BI mammograms.

Quantitative Measurements of Breast Density Using Magnetic Resonance Imaging: A Systematic Review and Meta-Analysis.

Breast density, a measure of dense fibroglandular tissue relative to non-dense fatty tissue, is confirmed as an independent risk factor of breast cancer. Although there has been an increasing interest in the quantitative assessment of breast density, no research has investigated the optimal technical approach of breast MRI in this aspect. Therefore, we performed a systematic review and meta-analysis to analyze the current studies on quantitative assessment of breast density using MRI and to determine the most appropriate technical/operational protocol. Databases (PubMed, EMBASE, ScienceDirect, and Web of Science) were searched systematically for eligible studies. Single arm meta-analysis was conducted to determine quantitative values of MRI in breast density assessments. Combined means with their 95% confidence interval (CI) were calculated using a fixed-effect model. In addition, subgroup meta-analyses were performed with stratification by breast density segmentation/measurement method. Furthermore, alternative groupings based on statistical similarities were identified via a cluster analysis employing study means and standard deviations in a Nearest Neighbor/Single Linkage. A total of 38 studies matched the inclusion criteria for this systematic review. Twenty-one of these studies were judged to be eligible for meta-analysis. The results indicated, generally, high levels of heterogeneity between study means within groups and high levels of heterogeneity between study variances within groups. The studies in two main clusters identified by the cluster analysis were also subjected to meta-analyses. The review confirmed high levels of heterogeneity within the breast density studies, considered to be due mainly to the applications of MR breast-imaging protocols and the use of breast density segmentation/measurement methods. Further research should be performed to determine the most appropriate protocol and method for quantifying breast density using MRI.

Characterization of radiographers' mammography practice in five European countries: a pilot study.

OBJECTIVES: This pilot study aimed to characterize and compare radiographers' mammography practice, including quality control and continuous professional development in five European countries. METHODS: Online survey was performed to collect data regarding participants' profile, institution's profile, mammography practice, quality control and continuous professional development. The questionnaire was sent to clinical radiographers working in Estonia, Finland, Norway, Portugal and Switzerland. Descriptive statistical and subgroup analyzes were performed. RESULTS: The amount of returned questionnaires was 140. Most respondents were female (92%), having radiography bachelor. The majority (89%) of radiographers was working with full-field digital mammography. The majority (97%) of mammography images were acquired using AEC, and half of the radiographers were using dose saving programmes suggested by the manufacturers. The most typical (50%) compression force ranged from 8 to 11 kg. Part of the radiographers (44%) did not know if their practice followed specific guidelines. The most challenging tasks in mammography identified by radiographers were patient positioning (86%), coping with pain (88%), managing anxiety (83%) and imaging breast implants (71%). The majority (88%) of the respondents undertook continuous professional development activities. CONCLUSIONS: The mammography practice varies across the five countries. We found country-specific traits related to mammography image acquisition, patient-centered care and quality management procedures. The lack of evidence-based knowledge suggests the importance of well-designed studies on these topics. The variability found in this pilot study encourages radiographers to question their own practice and teachers to review and revise the training programmes. Validation in larger studies including more countries is needed.

Education and training as a strategy to improve justification of medical imaging referrals in emergency departments.

Diagnostic imaging pathways are developed to ensure that medical imaging examinations are appropriately selected and referred by clinicians with the aim of justifying the use of imaging modalities for clinical diagnosis. Failing to comply with the imaging pathways or guidelines results in exposing patients to unnecessary ionising radiation due to malpractice of imaging referrals. This editorial provides a comment on a recent study reporting very high percentage of general x-ray imaging referrals which did not or partially met the imaging pathways in an emergency department.

Synchrotron radiation computed tomography versus conventional computed tomography for assessment of four types of stent grafts used for endovascular treatment of thoracic and abdominal aortic aneurysms.

BACKGROUND: To determine the accuracy of synchrotron radiation computed tomography (CT) for measurement of stent wire diameters for in vitro simulation of endovascular aneurysm repair by four different types of stent grafts when compared to conventional CT images. METHODS: This study was performed using an aorta model with implantation of four aortic stent grafts for endovascular treatment of thoracoabdominal and abdominal aortic aneurysms. The aorta model was scanned using synchrotron radiation CT with beam energies ranging from 60 to 90 keV with 10 keV increment at each scan and spatial resolution of 41.6 µm per pixel. Stent wire diameters were measured at the top and body regions of each stent graft based on 2-dimensional (2D) axial and 3-dimensional (3D) reconstruction images, with measurements compared to those obtained from 128-slice CT images which were acquired with slice thickness of 0.5 mm. RESULTS: Synchrotron radiation CT images clearly demonstrated stent graft details with accurate assessment of stent wire diameters, with measurements at the top of stent grafts (between 0.32±0.02 and 0.47±0.02 mm) similar to the actual diameters (between 0.32±0.01 and 0.48±0.01 mm) when the beam energies of 70 and 80 keV were used, regardless of the types of stent grafts assessed. A beam energy of 60 keV resulted in stent wires thicker than the actual sizes, although this did not reach statistical significance (P=0.07-0.29), while the beam energy of 90 keV led to stent wires smaller than the actual sizes at the top (P=0.16) and body region (P=0.02) of stent grafts on 2D axial images. The stent wire sizes measured at the body region of stent grafts on 3D synchrotron radiation images (between 0.19±0.02 and 0.43±0.02 mm) were significantly smaller than the actual diameters (P=0.02-0.04). Stent wires were overestimated on conventional CT images with diameters more than 2-fold larger than the actual sizes (P=0.007-0.03) at both top and body regions of all four stent grafts. CONCLUSIONS: This study further confirms the accuracy of high-resolution synchrotron radiation CT in image visualization and size measurement of different aortic stent grafts with measured wire diameters similar to the actual ones, thus allowing for more accurate assessment of stent wire details for endovascular repair of aortic aneurysms.

Correction to: European radiographers' challenges from mammography education and clinical practice-an integrative review.

Affiliation number 2 was rendered incorrectly.

PORTUGUESE STUDY OF MEAN GLANDULAR DOSE IN MAMMOGRAPHY AND COMPARISON WITH EUROPEAN REFERENCES.

To characterise the mean glandular dose (MGD) in a sample of healthcare providers for digital mammography in Portugal. To compare the achieved values with European references. The MGD was measured on a poly-methyl-methacrylate phantom (45 mm) for each system using dosimeters. In addition, MGD was estimated using exposure settings collected from mammography exams in clinical context. Data were collected from 25 computed-radiography systems (CR) and 13 integrated digital (DR). For both measurements (phantom and clinical exposures), the average MGD for CR was higher compared to the DR. For CR the mean MGD was 1.85 mGy (CC projection) and 2.10 mGy (MLO projection). For DR systems the corresponding values were 1.54 mGy (CC) and 1.68 mGy (MLO). The average MGD obtained using both methods and for both technologies is within the acceptable reference range proposed by European guidelines (<2.5 mGy). Dose Reference Levels implementation should be the next step to optimise mammography practice in Portugal.

Ergonomic strategies to improve radiographers' posture during mammography activities.

OBJECTIVES: To identify alternatives for radiographers' postures while performing mammography that can contribute to reduce the risk of work-related musculoskeletal disorders (WRMSDs). METHODS: Radiographers' postures to positioning craniocaudal (CC) and mediolateral oblique (MLO) views were simulated without any intervention for three scenarios: radiographer/patient with similar statures, radiographer smaller than patient and radiographer taller than patient. Actions were taken to modify the postures: seated radiographer; patient on a step; seated patient; radiographer on a step. All the postures were analysed using kinovea 0.8.15 software and the angles were measured twice and classified according to European standard EN1005-4: 2005. RESULTS: The non-acceptable angles were measured mainly during MLO positioning when radiographer was taller than the patient: 139° and 120° for arm-flexion and abduction, 72° for trunk and -24° for head/neck-flexion. The introduction of alternative postures (radiographer seated), allowed improvements in posture (60° and 99° for arm flexion and abduction, 14° for trunk and 0° for head/neck flexion), being classified as acceptable. CONCLUSIONS: The alternative postures simulated have the potential to reduce the risk of developing WRMSDs when radiographers and patients have different statures. MAIN MESSAGES: • Radiographers' postures in mammography can contribute to work-related musculoskeletal disorders • Non-acceptable posture was identified for MLO breast positioning (radiographer taller than patient) • Adapting posture to patient biotype reduces the WRMSD risk for radiographers.

European radiographers' challenges from mammography education and clinical practice - an integrative review.

OBJECTIVES: This study aims to identify European radiographers' challenges in clinical performance in mammography and the main areas of mammography that require more and better training. METHODS: An extensive search was performed to identify relevant studies focused on clinical practice, education and training in mammography published between January 2010 and December 2015 in the English language. The data were analysed by using deductive thematic analysis. RESULTS: A total of 27 full text articles were read, evaluating their quality. Sixteen articles out of 27 were finally selected for this integrative review. The main challenges of radiographers' mammography education/training can be divided into three groups: training needs, challenges related to radiographers, and challenges related to the organization of education. The most common challenges of clinical performance in mammography among European radiographers involved technical performance, the quality of practices, and patient-centeredness. CONCLUSIONS: The introduction of harmonized mammography guidelines across Europe may serve as an evidence-based tool to be implemented in practice and education. However, the variability in human and material resources as well as the different cultural contexts should be considered during this process. TEACHING POINTS: • Radiographers' awareness of their professional identity and enhancing multiprofessional cooperation in mammography. • Radiographers' responsibilities regarding image quality (IQ) and optimal breast imaging performance. • Patient-centred mammography services focusing on the psychosocial needs of the patient. • Challenges: positioning, QC-testing, IQ-assessment, optimization of breast compression, communication, teamwork, and patient-centred care. • Introduction of evidence-based guidelines in Europe to harmonize mammography practice and education.

Overview of the radiographers' practice in 65 healthcare centers using digital mammography systems in Portugal.

PURPOSE: To assess current practices in digital mammography (DM) in Portuguese healthcare providers using digital systems. To investigate compliance with European standards regarding mean glandular dose and quality control practice and to identify optimisation needs. METHODS: Two questionnaires, targeted at breast radiographers and chief radiographers, were designed and applied in 65 imaging departments offering DM. Questions fielded were focused on the staff profile and technical/clinical practice. RESULTS: Prior to starting their activity in DM, 70% (82 out of 118) of the respondents received training in DM. The practice in 29 out of 59 providers was established by the manufacturers' recommendations for image acquisition. Variations were observed between radiographers who belong to the same provider namely the selection of exposure parameters such as the target-filter combination and automatic mode. The use of the manual exposure mode was reported for imaging breast implants (44%) and surgical specimens (22%). The main causes of repeat examinations were skin folding (21%) and absence of pectoral muscle (PM) (20%). CONCLUSIONS: The study revealed opportunities to optimise radiographers' practice in DM regarding the selection of exposure parameters. A robust and consistent training programme in DM and established local protocols can help to reduce the variations observed and improve clinical practice. MAIN MESSAGES: • Radiographers adopted different practices selecting AEC modes and T/F combinations. • Radiographer practice is more consistent using DR than using CR systems. • The main causes for rejecting images were the visibility of skin folding and PM absence. • Radiographers were partly unaware of the dose indicator. • Radiographers' training needs: QC, interventional procedures and breast dose optimisation.