Radiology Quality Research Articles

Deep Learning-Based Estimation of Radiographic Position to Automatically Set Up the X-Ray Prime Factors.

Radiation dose and image quality in radiology are influenced by the X-ray prime factors: KVp, mAs, and source-detector distance. These parameters are set by the X-ray technician prior to the acquisition considering the radiographic position. A wrong setting of these parameters may result in exposure errors, forcing the test to be repeated with the increase of the radiation dose delivered to the patient. This work presents a novel approach based on deep learning that automatically estimates the radiographic position from a photograph captured prior to X-ray exposure, which can then be used to select the optimal prime factors. We created a database using 66 radiographic positions commonly used in clinical settings, prospectively obtained during 2022 from 75 volunteers in two different X-ray facilities. The architecture for radiographic position classification was a lightweight version of ConvNeXt trained with fine-tuning, discriminative learning rates, and a one-cycle policy scheduler. Our resulting model achieved an accuracy of 93.17% for radiographic position classification and increased to 95.58% when considering the correct selection of prime factors, since half of the errors involved positions with the same KVp and mAs values. Most errors occurred for radiographic positions with similar patient pose in the photograph. Results suggest the feasibility of the method to facilitate the acquisition workflow reducing the occurrence of exposure errors while preventing unnecessary radiation dose delivered to patients.

Radiographers Role in Quality and Safety in Diagnostic Radiology and Nuclear Medicine: IAEA Vision

Radiographers Role in Quality and Safety in Diagnostic Radiology and Nuclear Medicine: IAEA Vision

From Bench to Bedside With Large Language Models: AJR Expert Panel Narrative Review.

Large language models (LLMs) hold immense potential to revolutionize radiology. However, their integration into practice requires careful consideration. Artificial intelligence (AI) chatbots and general-purpose LLMs have potential pitfalls related to privacy, transparency, and accuracy, limiting their current clinical readiness. Thus, LLM-based tools must be optimized for radiology practice to overcome these limitations. Although research and validation for radiology applications remain in their infancy, commercial products incorporating LLMs are becoming available alongside promises of transforming practice. To help radiologists navigate this landscape, this AJR Expert Panel Narrative Review provides a multidimensional perspective on LLMs, encompassing considerations from bench (development and optimization) to bedside (use in practice). At present, LLMs are not autonomous entities that can replace expert decision-making, and radiologists remain responsible for the content of their reports. Patient-facing tools, particularly medical AI chatbots, require additional guardrails to ensure safety and prevent misuse. Still, if responsibly implemented, LLMs are well-positioned to transform efficiency and quality in radiology. Radiologists must be well-informed and proactively involved in guiding the implementation of LLMs in practice to mitigate risks and maximize benefits to patient care.

THE INFLUENCE OF THE QUALITY OF X-RAY IMAGES FROM TELEMEDICINE ON THE COLLECTIVE EFFECTIVE DOSE OF PATIENTS

Ensuring a quality of diagnostic radiology along with increasing efficiency is a key task for healthcare system for both municipal medical facilities and private medicine. When a defective X-ray image is obtained, there is a need to re-conduct a examination, which in turn entails reputational, temporary and economic losses for a medical facility. Repeated examination makes an additional contribution to the patient’s radiation exposure also. The paper shows that for facilities providing telemedicine services, implementation of a clinical audit for diagnostic examinations using information technology is efficient. In 2022 2059 error x-ray images were identified applying a similar system, which is 0.084% of the total number of telemedicine radiology examinations. A collective effective dose due to defective examinations was 3,613 man-Sv, which is less than 0.11% of the total collective dose.

Maintaining Radiology Quality with National Hospital Accreditation Standards

Maintaining Radiology Quality with National Hospital Accreditation Standards

A Comparative Study on Microbial Air Quality of Radiology and Patient Waiting Rooms of a Full-Equipped Hospital in Aydın Province

Every year many patients die due to hospital-acquired infections. These infections also put the lives of healthcare workers at risk. Additionally, hospitals are one of the main reservoirs of antimicrobial resistance. In this study, the effect of X-rays on species diversity and functions and antimicrobial resistance were observed. Metagenome analysis was performed on air samples taken from the x-ray room (radiation exposure) and the waiting room (non-radiation area) to examine whether the radiation affected the species present in the air. The diversity of microorganisms was analysed based on phylum, genus, and species levels. Functional profiling and resistance screening were also performed. X-ray radiation was found to have a major effect at the phylum level. It was observed that Proteobacteria species almost dominated the microbiome in the x-ray room (99%) while Actinobacteria species dominated the microbiome in the waiting room (84%). No significant differences were observed between the two areas in functional profiling. A total of thirty-eight functions were observed, twenty-four of which were overlapping. Antimicrobial resistance was not as diverse as expected. Only beta-lactam, penicillin, tetracycline, and lincomycin resistance genes were present (2364 reads belonging to four different genes). According to the results, it was observed that X-rays affected the air microbiome, as expected. A decrease in the number of microorganisms was expected, but it was also observed that the dominant microorganism types changed. On the other hand, no significant difference was found in terms of functional profiling and no significant antimicrobial resistance was observed.

Creating a Sustainable Foundation for IR Services and Training in Sub-Saharan Africa: 5-Year Update on the Road2IR Initiative

PurposeTo evaluate the growth and quality of an interventional radiology (IR) training model designed for resource-constrained settings and implemented in Tanzania as well as its overall potential to increase access to minimally invasive procedures across the region. Materials and MethodsIR training in Tanzania began in October 2018 through monthly deployment of visiting teaching teams for hands-on training combined with in-person and remote lectures. A competency-based 2-year Master of Science in IR curriculum was inaugurated at the nation’s main teaching hospital in October 2019, with the first 2 classes graduating in 2021 and 2022. Procedural data, demographics, and clinical outcomes were collected and analyzed throughout the duration of this program. ResultsFrom October 2018 to July 2022, 1,595 procedures were performed in Tanzania: 1,236 nonvascular and 359 vascular, all with local fellows as primary interventional radiologists. Of these, 97.2% were technically successful, 95.2% were without adverse events, and 28.9% were performed independently by Tanzanian fellows and faculty with no difference in adverse event and technical success rates (P = .63 and P = .90, respectively), irrespective of procedural class. Ten IR physicians graduated from this program during the study period, followed by another 3 per year going forward. Partner training programs in Uganda and Rwanda mirroring this model commenced in 2023 and 2024, respectively. ConclusionsThe reported training model offers a practical and effective solution to meet many of the challenges associated with the lack of access to IR in sub-Saharan Africa.

Lean Six Sigma Approach for Wait Time Analysis in Radiology Services at Krakatau Medika Hospital

Krakatau Medika Hospital (RSKM), an integral part of Indonesia Healthcare Corporation (IHC), grapples with challenges in radiology services and wait time standards. Amidst the surge in healthcare facilities, IHC, overseen by PT Pertamina Bina Medika, strategically plans Lean Six Sigma implementation to enhance radiology quality, efficiency, and customer satisfaction. Non-Communicable Diseases (NCDs) complexities. The research methodology adopts a qualitative approach, incorporating process flow observations, document reviews, and in-depth interviews at the Radiology Installation of Krakatau Medika Hospital. Data collection involves direct observations, in-depth interviews, and research instruments with various stakeholders. The study, encompassing January to July 2023, reveals RSKM's radiology indicators falling short, with excessive wait times jeopardizing service effectiveness. The Lean Six Sigma approach, utilizing the DMAIC methodology, aims to eliminate waste, improve processes, and enhance organizational performance. Findings emphasize the urgency for improvements, with Lean Six Sigma anticipated to play a pivotal role in reducing wait times and overall performance enhancement. Ethical considerations guide the research, ensuring informed consent and confidentiality. Collaborative efforts with RSKM management are vital for sustained positive outcomes. The study underscores Lean Six Sigma's potential benefits, emphasizing ethical healthcare research principles

ACR Appropriateness Criteria Patient-Friendly Summaries and Patient-Friendly Animations: Initiatives to Engage Patients and Promote Shared Decision Making

The American College of Radiology Appropriateness Criteria® are evidence-based guidelines for the use of diagnostic imaging tests and image-guided interventions. They are approved to provide appropriate use criteria (AUC) under the Medicare Appropriate Use Criteria program for advanced diagnostic imaging. The guidelines are created by expert panels of radiologists and other clinicians and are written in technical language intended for health care professionals. In order to make the information in the guidelines more accessible to patients, and to enable patients to participate in shared decision making about their imaging care, two patient-centered initiatives have been developed. The ACR Appropriateness Criteria® Patient-Friendly Summaries are 250-word lay language documents, written by lay persons working together with radiologists, that summarize the information in the Appropriateness Criteria®. The ACR Patient-Friendly Animations are one minute animated videos that further condense the information in the guidelines into a format that can be easily absorbed by lay persons and shared via social media. This article provides the history, development and current status of these initiatives which promote patient and family centered care, quality, and safety in radiology.

243 A missed opportunity for intervention: vertebral fracture reporting

Abstract Background Vertebral Fractures (VFs) are the most common fragility fracture—with an incidence of 1 in 5 women over 70. A Vertebral Fragility Fracture (VFF) is a powerful predictor of another VF and of future hip fractures. Yet nearly 70% of VFs do not come to medical attention. Opportunities to identify a VFF and institute secondary prevention arises when a patient is referred for imaging for any clinical reason. However, VFFs are commonly unrecognised radiologically or reported ambiguously. The aim of this audit was to retrospectively evaluate VFF reporting terminology and recommendations as per published guidelines. Methods All radiographic reports from 2021–2023 in an Irish hospital were screened for osteoporotic and VFF key-terms in patients >65 years via the PACs platform. Data was analysed for 1) comments on vertebral integrity; 2) usage of the term ‘vertebral fracture’; 3) inclusion of actionable recommendations. Results A resultant total of 250 reports were reviewed, 223/250 from plain films. Fracture was reported 50.8% (n = 127) of the time. Ambiguous terminology like ‘compression’; ‘sagging’; ‘height loss’ ‘collapse’; ‘wedging’ was used in 49.2% (n = 123). Even where vertebral height loss was reported as 20% or greater, the term ‘fracture’ was not used in 59% (29/49). No report made recommendations for further investigation. Conclusion This audit highlights that even when osteoporotic challenges to vertebral integrity are recognised, they are not reported in a standardised way that reflects the ‘red flag’ significance of a VFF. The heterogeneous and ambiguous reporting fails to alert other clinicians to their significance—resulting in a missed opportunity to intervene. A reporting template and addition of actionable recommendations is for review at the internal monthly radiology quality forum.

Refocusing the Lens: Adding Downstream Value to the Radiology Quality Equation

Refocusing the Lens: Adding Downstream Value to the Radiology Quality Equation

The radiology quality assurance process in the Yorkshire Lung Screening Trial, and findings from the baseline round of low dose CT screening for lung cancer.

As lung cancer screening is rolled-out, there is a need to develop an effective quality assurance (QA) framework around radiology reporting to ensure optimal implementation. Here, we report a structured QA process for low-dose CT (LDCT) scans performed in the Yorkshire Lung Screening Trial. Negative LDCT scans were single read after using computer-aided detection software. The radiology QA process included reviewing 5% of negative scans selected at random, and all cases with a subsequent diagnosis of extrapulmonary cancer or interval lung cancer not detected on the baseline scan. Radiologists were not informed of the reason for review and original radiology reports were scored as either "satisfactory", "satisfactory with learning points", or "unsatisfactory". From 6650 participants undergoing LDCT screening, 208 negative scans were reviewed alongside 11 cases with subsequent extrapulmonary cancer and 10 cases with interval lung cancer. Overall, only three reports were ultimately judged "unsatisfactory", 1% of randomly selected negative scans (n = 2/208) and one interval lung cancer scan (n = 1/10). Four out of a total of five cases judged "satisfactory with learning points" were related to oesophageal abnormalities where the participant was subsequently diagnosed with oesophageal cancer. The described process attempts to minimise bias in retrospective review of screening scans, and may represent a framework for future QA of national screening programmes. This study describes a structured QA process for a lung cancer screening programme, involving blinded second-read of LDCT screening scans to ensure fair, constructive audit of clinical performance.

Improving the quality and safety of radiology reporting: A prospective audit of discrepancies among consultant radiologists

AbstractObjectivesTo examine discrepancy rates over multiple annual cycles in reporting by consultant radiologists for the interpretation of acute Computerized Tomography (CT) examinations.MethodsA prospective audit with peer review and second reading of acute CT scans was implemented in one radiology department in the UK. A longitudinal audit over 5 years was performed to determine the discrepancy rate of acute and emergency CT scans conducted on weekends. The examinations comprised CT head, thorax, abdomen and pelvis, CT Kidneys, Ureters, and Bladder (CT KUB), and CT angiography scans. Discrepancies were scored as no discrepancy (zero), minor discrepancy (one), moderate discrepancy (two), or significant discrepancy (three). Seventeen consultants took part in the audit as primary reporters and second readers. All consultants were on‐call radiologists, and the allocation of cases was randomized depending on the on‐call rota. Results were reported annually to one consultant radiologist.ResultsA significant discrepancy rate of 1.2% (p = 0.026) was found for consultant radiologists, interpreting acute CT examinations based on 2951 s read CT scans.ConclusionsTo the best of our knowledge, this is the first study to establish significant discrepancy rates among consultant radiologists, interpreting acute CT examinations over time.

The role of teleradiology during COVID-19 outbreak: Saudi radiologists' perspectives.

To evaluate the role of teleradiology during the COVID-19 pandemic from Saudi radiologists' perspectives to improve the radiology quality service. A cross-sectional study was carried out in Saudi Arabia among radiologists working at local hospitals from October to November 2021. It contains 21 questions involved demographic information; general information on teleradiology services; and the impact of teleradiology during COVID-19. One-way ANOVA was used to compare demographic groups. Chi-square test was used to compare demographic groups regarding their distribution of responses. All tests were carried out <0.05 level of significance. A total of 102 radiologists participated in this study (56% males, 44% females), 58.8% of them were sub-specialized in chest radiology. Regarding the general status of teleradiology, 69.6% of participants believed that teleradiology is a helpful tool for imaging interpretation. However, 44% of them were uncertain on the impact of teleradiology on patients' confidentiality. Approximately 87% of participants agreed that there is a positive contribution of teleradiology during COVID-19, which enables decreasing risk of infection and workload. There was a significant difference between professional degrees and overall participant responses (p<0.05). Academicians agreed that it enhances radiology departments' work (mean=17.78, SD=1.86). Concerns raised on complicated cases that require physical presence of patients, cannot be performed by teleradiology. Additionally, it might provide insufficient communication with other professionals to discuss images.

SACCSG HL-2018. Barriers and enablers of a harmonized treatment protocol for childhood and adolescent Hodgkin lymphoma in South Africa

Introduction: Collaborative studies have contributed to improved survival of pediatric Hodgkin lymphoma in well-resourced settings, but few are documented in resource-constrained countries. The South Africa Children’s Cancer Study Group initiated harmonization of management protocols in 2015. This article analyzes barriers and enablers of the process. Methods: Clinician-researchers at 11 state-funded pediatric oncology units completed preparatory questionnaires in June 2018. Parameters included infrastructure, access to therapeutic modalities and clinician numbers. A reassessment of 13 sites (two new pediatric oncology unit) in February 2021 ascertained changes in resources and identified challenges to full participation. Questions investigated the presence and quality of diagnostic radiology, availability of surgeons, cytology/pathology options and hematology laboratory facilities. Results: The response rate was 11/11 to survey 1 and 13/13 to survey 2. The anticipated pre-study barriers to participation of pediatric oncology units included time constraints and understaffing. PET-CT was unavailable to two centers. The majority of pediatric oncology units met the minimum criteria to participate. The interim survey confirmed chemotherapy and radiotherapy availability nearly 100% of the time. One site reported improved access to radiotherapy while another reported improved access to PET-CT. Barriers to participation included excessive times to obtain regulatory approvals, time constraints and lack of dedicated research staff. Enablers include the simple management algorithm and communication tools. Conclusion: This study demonstrates that multicenter collaboration and harmonization of management protocols are achievable in a middle-income setting. Minimal funding is required but full participation to run high-quality studies requires more financial investment. Focused funding and increased prioritization of research may address systemic barriers to full participation.

Pemilihan Indikator Mutu Prioritas Unit “Pengulangan Foto X-Ray” Sebagai Aspek Fundamental Proteksi dan Budaya Keselamatan Radiasi di Instalasi Radiologi RS Indriati Solobaru

An essential aspect of a diagnostic radiology quality assurance program is X-ray image repeat analysis, a systematic process to record rejected or repeated images to determine the cause so we can minimize that image repetition in the future. Some of the disadvantages caused by repeated X-ray photo examinations are giving additional doses to patients (unnecessary exposure), ineffective time for radiology staff and patients (wasting time), and financial losses due to electricity for the X-ray machine and the DR system (unit costs). In January 2021, at the Radiology Installation of Indriati Hospital, repeated X-Ray photos analysis was chosen as one of the quality indicators by Decree No. 031/PER-RSIND/2021. The goal is to look for improvements to minimize repeated X-ray photos occurrence and prevent unnecessary exposure. Monitoring is carried out daily through SISMADAK V5.0.3 and is reported monthly to the KMRS committee. The step for selecting quality indicators for X-ray photo examination repetition has greatly impacted the aspects of radiation protection and safety because it can reduce the number of X-ray photo inspection repetitions by 0.6% from 2020. The continuous improvement step based on the root cause of the fishbone method is with the supervision of a radiographer intensively with OPPE assessment and credentials in the hope of minimizing the repetition of X-ray photos. It can become a fundamental aspect of radiation protection and culture safety, especially in the radiology installation of Indriati-Solobaru Hospital, Sukoharjo, Central Java. Keywords: X-ray photo repetition, quality indicators, fishbone method, radiation safety culture.

Quality of radiology in determining the dominant stricture in patients with primary sclerosing cholangitis

Quality of radiology in determining the dominant stricture in patients with primary sclerosing cholangitis

Mammography image quality evaluation in breast cancer screening: The Saudi experience

ObjectiveTo evaluate the mammographic image quality carried out within the Saudi breast cancer screening program. MethodsTwo radiologists reviewed 956 mammograms using the American College of Radiology (ACR) quality standard. Each quality criterion was rated on a 5-point ordinal scale (1 = best to 5 = severe deficiency). A score of 5 or 4 for any category or a score of 3 for multiple categories led to failure. When disagreement occurred in the overall quality or positioning score, the mammograms were further evaluated by a third radiologist. Inter-rater agreement was tested using Cohen's kappa. ResultsInter-rater agreement ranged from slight (kappa 0.18, p=<0.0001) for positioning to low (kappa = 0.02, p = 0.002) for contrast. Positioning was the most frequently reported issue that led to failure in image quality (n = 324). When the set of images sent to the third reviewers, only 25.5% were deemed deficient in positioning. Of the 324 mammograms that failed due to positioning, the most common problems reported by all three reviewers were inadequate pectoralis major muscle on a mediolateral oblique view, a posterior nipple line on craniocaudal view exceeding 1 cm, other body parts projecting over the breast and poor visualization of posterior tissue on MLO. ConclusionPositioning was the major contributor to failures associated with mammography image quality. Considerable room for improvement exists through ongoing education and training, with particular emphasis on breast positioning. Radiologists are encouraged to be actively involved in this development process.

Outcomes of Postprocedural Closeout Checklist Implementation to Prevent Adverse Events during Interventional Radiology Procedures: An Initiative to Improve Outcomes

PurposeTo assess whether adherence to a postprocedural closeout (PPC) checklist decreases adverse events during image-guided procedures. Materials and MethodsBased on the analysis of prior adverse events related to image-guided procedures, the Radiology Quality Committee developed a PPC checklist. The rates of serious reportable events related to image-guided procedures performed in the radiology department were recorded annually from 2015 to 2021. The rate of adverse events was normalized to the procedure volume in the corresponding periods. The number of patients requiring repeat procedures was recorded. The severity of impact was classified according to the Society of Interventional Radiology Adverse Event Classification System. The annual rates before (2015 and 2016) and after (2017–2021) the implementation of PPC were compared. ResultsSeventy-seven safety reports were identified in image-guided procedures over the study period, of which 43 cases were not related to the PPC, leaving 34 cases for the analysis. Radiology adverse events decreased from 0.069% (14/20,218, 7/y) before PPC implementation to 0.034% (20/58,793, 4/y) after implementation (P = .05, 43% decrease). Radiology repeat procedures decreased from 0.040% (8/20,218, 4/y) before PPC implementation to 0.007% (4/58,793, 0.8/y) after implementation (P = .0033, 80% decrease). Moreover, severity of adverse events decreased (P = .009). ConclusionsImplementation of a PPC checklist improved patient outcomes by decreasing the number of adverse events that occur from inadequate safety processes at the end of image-guided procedures by 43%, need for repeat procedures by 80%, and severity of impact of errors.

Radiology Quality Improvement: Lessons From the “Toyota Way”

A medical student applying for radiology residency was formerly employed by Toyota as an engineer. During that time, he learned that production-line employees found it difficult to install moonroofs, experiencing back pain after climbing into and out of trucks 120 times per day. He walked the production line and talked with team members, brainstorming process improvement ideas and developing a solution, which he reviewed and reflected on each day. Within months, his team rectified the ergonomic problems and designed and installed an in-line quality assessment device that improved workers’ experiences and saved the company over $8 million per year by reducing error rates.