Characterizing Sentinel Lymph Node Status in Breast Cancer Patients Using a Deep-Learning Model Compared With Radiologists' Analysis of Grayscale Ultrasound and Lymphosonography.

ABSTRACT: The objective of the study was to use a deep learning model to differentiate between benign and malignant sentinel lymph nodes (SLNs) in patients with breast cancer compared to radiologists' assessments.Seventy-nine women with breast cancer were enrolled and underwent lymphosonography and contrast-enhanced ultrasound (CEUS) examination after subcutaneous injection of ultrasound contrast agent around their tumor to identify SLNs. Google AutoML was used to develop image classification model. Grayscale and CEUS images acquired during the ultrasound examination were uploaded with a data distribution of 80% for training/20% for testing. The performance metric used was area under precision/recall curve (AuPRC). In addition, 3 radiologists assessed SLNs as normal or abnormal based on a clinical established classification. Two-hundred seventeen SLNs were divided in 2 for model development; model 1 included all SLNs and model 2 had an equal number of benign and malignant SLNs. Validation results model 1 AuPRC 0.84 (grayscale)/0.91 (CEUS) and model 2 AuPRC 0.91 (grayscale)/0.87 (CEUS). The comparison between artificial intelligence (AI) and readers' showed statistical significant differences between all models and ultrasound modes; model 1 grayscale AI versus readers, P = 0.047, and model 1 CEUS AI versus readers, P < 0.001. Model 2 r grayscale AI versus readers, P = 0.032, and model 2 CEUS AI versus readers, P = 0.041.The interreader agreement overall result showed κ values of 0.20 for grayscale and 0.17 for CEUS.In conclusion, AutoML showed improved diagnostic performance in balance volume datasets. Radiologist performance was not influenced by the dataset's distribution.

Network analysis of occupational stress and job satisfaction among radiologists.

Background: Occupational stress and job satisfaction significantly impact the well-being and performance of healthcare professionals, including radiologists. Understanding the complex interplay between these factors through network analysis can provide valuable insights into intervention strategies to enhance workplace satisfaction and productivity. Method: In this study, a convenience sampling method was used to recruit 312 radiologists for participation. Data on socio-demographic characteristics, job satisfaction measured by the Minnesota job satisfaction questionnaire revised short version (MJSQ-RSV), and occupational stress assessed using the occupational stress scale. Network analysis was employed to analyze the data in this study. Results: The network analysis revealed intricate patterns of associations between occupational stress and job satisfaction symptoms among radiologists. Organizational management and occupational interests emerged as crucial nodes in the network, indicating strong relationships within these domains. Additionally, intrinsic satisfaction was identified as a central symptom with high connectivity in the network structure. The stability analysis demonstrated robustness in the network edges and centrality metrics, supporting the reliability of the findings. Conclusion: This study sheds light on the complex relationships between occupational stress and job satisfaction in radiologists, offering valuable insights for targeted interventions and support strategies to promote well-being and job satisfaction in healthcare settings.

The clinical value of artificial intelligence in assisting junior radiologists in thyroid ultrasound: a multicenter prospective study from real clinical practice.

BACKGROUND: This study is to propose a clinically applicable 2-echelon (2e) diagnostic criteria for the analysis of thyroid nodules such that low-risk nodules are screened off while only suspicious or indeterminate ones are further examined by histopathology, and to explore whether artificial intelligence (AI) can provide precise assistance for clinical decision-making in the real-world prospective scenario. METHODS: In this prospective study, we enrolled 1036 patients with a total of 2296 thyroid nodules from three medical centers. The diagnostic performance of the AI system, radiologists with different levels of experience, and AI-assisted radiologists with different levels of experience in diagnosing thyroid nodules were evaluated against our proposed 2e diagnostic criteria, with the first being an arbitration committee consisting of 3 senior specialists and the second being cyto- or histopathology. RESULTS: According to the 2e diagnostic criteria, 1543 nodules were classified by the arbitration committee, and the benign and malignant nature of 753 nodules was determined by pathological examinations. Taking pathological results as the evaluation standard, the sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) of the AI systems were 0.826, 0.815, 0.821, and 0.821. For those cases where diagnosis by the Arbitration Committee were taken as the evaluation standard, the sensitivity, specificity, accuracy, and AUC of the AI system were 0.946, 0.966, 0.964, and 0.956. Taking the global 2e diagnostic criteria as the gold standard, the sensitivity, specificity, accuracy, and AUC of the AI system were 0.868, 0.934, 0.917, and 0.901, respectively. Under different criteria, AI was comparable to the diagnostic performance of senior radiologists and outperformed junior radiologists (all P < 0.05). Furthermore, AI assistance significantly improved the performance of junior radiologists in the diagnosis of thyroid nodules, and their diagnostic performance was comparable to that of senior radiologists when pathological results were taken as the gold standard (all p > 0.05). CONCLUSIONS: The proposed 2e diagnostic criteria are consistent with real-world clinical evaluations and affirm the applicability of the AI system. Under the 2e criteria, the diagnostic performance of the AI system is comparable to that of senior radiologists and significantly improves the diagnostic capabilities of junior radiologists. This has the potential to reduce unnecessary invasive diagnostic procedures in real-world clinical practice.

Interventional radiologists and OBLs: An excellent match.

While office-based laboratories (OBLs) have been increasing in popularity, only a small proportion of the current interventional radiology (IR) workforce works in an OBL. With the relative lack of an IR presence in OBLs compared to other endovascular specialists, combined with the growth of the OBL space, the presence of IR within OBLs will likely increase in the coming years. This article addresses the value interventional radiologists (IRs) can bring to the OBL, with primary impacts being the ability to impact a larger proportion of the population than is traditionally cared for in most hospital settings, the ability to positively influence multidisciplinary care teams and the financial leverage inherent in procedural diversification not readily afforded by other specialists working in the OBL space. IR-specific pitfalls in the OBL space are also addressed, including difficulties in obtaining patient referrals, investor relationships, and group practice arrangements. Despite potential challenges, IRs have a lot to offer within the OBL space, and conversely, the OBL space provides a mechanism for IRs to increase their reach and improve career longevity.

Sole operator: Owning and Operating an Independent Office-Based Lab.

Owning and operating an Office-Based Lab (OBL) creates a unique career, combining the privilege of practicing Interventional Radiology (IR) with the creativity and excitement of running a complex business. No business is more complicated than the American Healthcare system, with a combination of necessary operational systems, government and commercial reimbursement, local and national regulations, an ever-changing landscape, and various patient populations; the business is always shifting. No field is as complex and exciting as Interventional Radiology, with advanced clinical and technical expertise, device development, rocedural ingenuity, and the ability to solve complex medical problems with elegant solutions. A sole owner and operator in an OBL has full autotomy, and thus full responsibility for the medical and business aspects of the practice.

Transitioning from Hospital-based to Office-Based Practice.

The decision to change your career path from a hospital-based practice, whether it's from being a hospital employee or a member of a private practice, can be an emotionally draining choice that is complex and overwhelming to say the least. There are many factors to consider before making this switch, but most importantly, one must realize it may be the hardest but most rewarding work in your career. While the physical, emotional and financial stresses placed on you while developing a practice can be rather demanding, on the flip side, if done correctly and the practice thrives, it can be a change that will bring you great pride and satisfaction, as well as personal reward and freedom.

Radiologists' perceptions on AI integration: An in-depth survey study.

PURPOSE: To assess the perceptions and attitudes of radiologists toward the adoption of artificial intelligence (AI) in clinical practice. METHODS: A survey was conducted among members of the SIRM Lombardy. Radiologists' attitudes were assessed comprehensively, covering satisfaction with AI-based tools, propensity for innovation, and optimism for the future. The questionnaire consisted of two sections: the first gathered demographic and professional information using categorical responses, while the second evaluated radiologists' attitudes toward AI through Likert-type responses ranging from 1 to 5 (with 1 representing extremely negative attitudes, 3 indicating a neutral stance, and 5 reflecting extremely positive attitudes). Questionnaire refinement involved an iterative process with expert panels and a pilot phase to enhance consistency and eliminate redundancy. Exploratory data analysis employed descriptive statistics and visual assessment of Likert plots, supported by non-parametric tests for subgroup comparisons for a thorough analysis of specific emerging patterns. RESULTS: The survey yielded 232 valid responses. The findings reveal a generally optimistic outlook on AI adoption, especially among young radiologist (<30) and seasoned professionals (>60, p<0.01). However, while 36.2 % (84 out 232) of subjects reported daily use of AI-based tools, only a third considered their contribution decisive (30 %, 25 out of 84). AI literacy varied, with a notable proportion feeling inadequately informed (36 %, 84 out of 232), particularly among younger radiologists (46 %, p < 0.01). Positive attitudes towards the potential of AI to improve detection, characterization of anomalies and reduce workload (positive answers > 80 %) and were consistent across subgroups. Radiologists' opinions were more skeptical about the role of AI in enhancing decision-making processes, including the choice of further investigation, and in personalized medicine in general. Overall, respondents recognized AI's significant impact on the radiology profession, viewing it as an opportunity (61 %, 141 out of 232) rather than a threat (18 %, 42 out of 232), with a majority expressing belief in AI's relevance to future radiologists' career choices (60 %, 139 out of 232). However, there were some concerns, particularly among breast radiologists (20 of 232 responders), regarding the potential impact of AI on the profession. Eighty-four percent of the respondents consider the final assessment by the radiologist still to be essential. CONCLUSION: Our results indicate an overall positive attitude towards the adoption of AI in radiology, though this is moderated by concerns regarding training and practical efficacy. Addressing AI literacy gaps, especially among younger radiologists, is essential. Furthermore, proactively adapting to technological advancements is crucial to fully leverage AI's potential benefits. Despite the generally positive outlook among radiologists, there remains significant work to be done to enhance the integration and widespread use of AI tools in clinical practice.

Comparing Diagnostic Accuracy of Radiologists versus GPT-4V and Gemini Pro Vision Using Image Inputs from Diagnosis Please Cases.

Background The diagnostic abilities of multimodal large language models (LLMs) using direct image inputs and the impact of the temperature parameter of LLMs remain unexplored. Purpose To investigate the ability of GPT-4V and Gemini Pro Vision in generating differential diagnoses at different temperatures compared with radiologists using Radiology Diagnosis Please cases. Materials and Methods This retrospective study included Diagnosis Please cases published from January 2008 to October 2023. Input images included original images and captures of the textual patient history and figure legends (without imaging findings) from PDF files of each case. The LLMs were tasked with providing three differential diagnoses, repeated five times at temperatures 0, 0.5, and 1. Eight subspecialty-trained radiologists solved cases. An experienced radiologist compared generated and final diagnoses, considering the result correct if the generated diagnoses included the final diagnosis after five repetitions. Accuracy was assessed across models, temperatures, and radiology subspecialties, with statistical significance set at P < .007 after Bonferroni correction for multiple comparisons across the LLMs at the three temperatures and with radiologists. Results A total of 190 cases were included in neuroradiology (n = 53), multisystem (n = 27), gastrointestinal (n = 25), genitourinary (n = 23), musculoskeletal (n = 17), chest (n = 16), cardiovascular (n = 12), pediatric (n = 12), and breast (n = 5) subspecialties. Overall accuracy improved with increasing temperature settings (0, 0.5, 1) for both GPT-4V (41% [78 of 190 cases], 45% [86 of 190 cases], 49% [93 of 190 cases], respectively) and Gemini Pro Vision (29% [55 of 190 cases], 36% [69 of 190 cases], 39% [74 of 190 cases], respectively), although there was no evidence of a statistically significant difference after Bonferroni adjustment (GPT-4V, P = .12; Gemini Pro Vision, P = .04). The overall accuracy of radiologists (61% [115 of 190 cases]) was higher than that of Gemini Pro Vision at temperature 1 (T1) (P < .001), while no statistically significant difference was observed between radiologists and GPT-4V at T1 after Bonferroni adjustment (P = .02). Radiologists (range, 45%-88%) outperformed the LLMs at T1 (range, 24%-75%) in most subspecialties. Conclusion Using direct radiologic image inputs, GPT-4V and Gemini Pro Vision showed improved diagnostic accuracy with increasing temperature settings. Although GPT-4V slightly underperformed compared with radiologists, it nonetheless demonstrated promising potential as a supportive tool in diagnostic decision-making. © RSNA, 2024 See also the editorial by Nishino and Ballard in this issue.

Comparative analysis of carotid artery stenting practice and outcomes across operator specialties: insights from a prespecified subanalysis of a large real-world patient cohort (ROADSAVER Study).

BACKGROUND: In contemporary clinical practice, carotid artery stenting (CAS) is increasingly becoming a multispecialty field, joining operators of various training backgrounds, which bring forth their unique expertise, patient management philosophies, and procedural preferences. The best practices and approaches, however, are still debated. Therefore, real-world insights on different operator preferences and related outcomes are of utmost value, yet still rather scarce in the available literature. METHODS: Using the data collected in the ROADSAVER observational, European multicenter CAS study, a prespecified comparative analysis evaluating the impact of the operator's specialization was performed. We used major adverse event (MAE) rate at 30-day follow-up, defined as the cumulative incidence of any death or stroke, and its components as outcome measures. RESULTS: A total of 1965 procedures were analyzed; almost half 878 (44.7%) were performed by radiologists (interventional/neuro), 717 (36.5%) by cardiologists or angiologists, and 370 (18.8%) by surgeons (vascular/neuro). Patients treated by surgeons were the oldest (72.9±8.5), while radiologists treated most symptomatic patients (58.1%) and more often used radial access (37.2%). The 30-day MAE incidence achieved by cardiologists/angiologists was 2.0%, radiologists 2.5%, and surgeons 1.9%; the observed differences in rates were statistically not-significant (P=0.7027), even when adjusted for baseline patient/lesion and procedural disparities across groups. The corresponding incidence rates for death from any cause were 1.0%, 0.8%, and 0.3%, P=0.4880, and for any stroke: 1.4%, 2.3%, and 1.9%, P=0.4477, respectively. CONCLUSIONS: Despite the disparities in patient selection and procedural preferences, the outcomes achieved by different specialties in real-world, contemporary CAS practice remain similar when using modern devices and techniques.

Violencia y maltrato infantil. El aporte del médico radiólogo al abordaje integral multidisciplinario / Child maltreatment and violence. Contributions from radiologists to a comprehensive multidisciplinary approach

El maltrato infantil es definido por la Organización Mundial de la Salud (OMS) como "el abuso y la desatención que sufren los niños menores de 18 años. Incluye todo tipo de maltrato físico y/o emocional […] que resulte en un daño real o potencial para la salud, la supervivencia, el desarrollo o la dignidad del niño". Al examinar los rastros corporales del maltrato físico, siguiendo los mecanismos de lesión más frecuentemente implicados, es posible detectar patrones radiológicos típicos. La evaluación imagenológica del hueso en reparación permite inferir cronologías para correlacionar con los datos obtenidos en la anamnesis. Los profesionales de la salud deben detectar oportunamente lesiones radiológicas sospechosas y activar de forma temprana el resguardo del menor. Nuestro propósito es realizar una revisión sobre las publicaciones recientes referidas al estudio imagenológico en niños de quienes se sospeche que puedan ser víctimas de violencia física.

The World Health Organization (WHO) defines child maltreatment as "the abuse and neglect that occurs to children under 18 years of age. It includes all types of physical and/or emotional ill-treatment [...], which results in actual or potential harm to the child's health, survival, development or dignity." By examining the bodily traces of physical abuse, following the most frequently involved mechanisms of injury, it is possible to identify typical radiological patterns. The imaging studies of the bone under repair allows inferring a timeline that may be correlated to the data obtained during history taking. Health care providers should detect suspicious radiological lesions in a timely manner and promptly activate the safeguarding of the child. Our objective was to review recent publications on the imaging studies of children suspected of being victims of physical violence.

Artificial intelligence and radiologists in prostate cancer detection on MRI (PI-CAI): an international, paired, non-inferiority, confirmatory study.

BACKGROUND: Artificial intelligence (AI) systems can potentially aid the diagnostic pathway of prostate cancer by alleviating the increasing workload, preventing overdiagnosis, and reducing the dependence on experienced radiologists. We aimed to investigate the performance of AI systems at detecting clinically significant prostate cancer on MRI in comparison with radiologists using the Prostate Imaging-Reporting and Data System version 2.1 (PI-RADS 2.1) and the standard of care in multidisciplinary routine practice at scale. METHODS: In this international, paired, non-inferiority, confirmatory study, we trained and externally validated an AI system (developed within an international consortium) for detecting Gleason grade group 2 or greater cancers using a retrospective cohort of 10 207 MRI examinations from 9129 patients. Of these examinations, 9207 cases from three centres (11 sites) based in the Netherlands were used for training and tuning, and 1000 cases from four centres (12 sites) based in the Netherlands and Norway were used for testing. In parallel, we facilitated a multireader, multicase observer study with 62 radiologists (45 centres in 20 countries; median 7 [IQR 5-10] years of experience in reading prostate MRI) using PI-RADS (2.1) on 400 paired MRI examinations from the testing cohort. Primary endpoints were the sensitivity, specificity, and the area under the receiver operating characteristic curve (AUROC) of the AI system in comparison with that of all readers using PI-RADS (2.1) and in comparison with that of the historical radiology readings made during multidisciplinary routine practice (ie, the standard of care with the aid of patient history and peer consultation). Histopathology and at least 3 years (median 5 [IQR 4-6] years) of follow-up were used to establish the reference standard. The statistical analysis plan was prespecified with a primary hypothesis of non-inferiority (considering a margin of 0·05) and a secondary hypothesis of superiority towards the AI system, if non-inferiority was confirmed. This study was registered at ClinicalTrials.gov, NCT05489341. FINDINGS: Of the 10 207 examinations included from Jan 1, 2012, through Dec 31, 2021, 2440 cases had histologically confirmed Gleason grade group 2 or greater prostate cancer. In the subset of 400 testing cases in which the AI system was compared with the radiologists participating in the reader study, the AI system showed a statistically superior and non-inferior AUROC of 0·91 (95% CI 0·87-0·94; p<0·0001), in comparison to the pool of 62 radiologists with an AUROC of 0·86 (0·83-0·89), with a lower boundary of the two-sided 95% Wald CI for the difference in AUROC of 0·02. At the mean PI-RADS 3 or greater operating point of all readers, the AI system detected 6·8% more cases with Gleason grade group 2 or greater cancers at the same specificity (57·7%, 95% CI 51·6-63·3), or 50·4% fewer false-positive results and 20·0% fewer cases with Gleason grade group 1 cancers at the same sensitivity (89·4%, 95% CI 85·3-92·9). In all 1000 testing cases where the AI system was compared with the radiology readings made during multidisciplinary practice, non-inferiority was not confirmed, as the AI system showed lower specificity (68·9% [95% CI 65·3-72·4] vs 69·0% [65·5-72·5]) at the same sensitivity (96·1%, 94·0-98·2) as the PI-RADS 3 or greater operating point. The lower boundary of the two-sided 95% Wald CI for the difference in specificity (-0·04) was greater than the non-inferiority margin (-0·05) and a p value below the significance threshold was reached (p<0·001). INTERPRETATION: An AI system was superior to radiologists using PI-RADS (2.1), on average, at detecting clinically significant prostate cancer and comparable to the standard of care. Such a system shows the potential to be a supportive tool within a primary diagnostic setting, with several associated benefits for patients and radiologists. Prospective validation is needed to test clinical applicability of this system. FUNDING: Health~Holland and EU Horizon 2020.

Integrating intratumoral and peritumoral radiomics with deep transfer learning for DCE-MRI breast lesion differentiation: A multicenter study comparing performance with radiologists.

PURPOSE: To conduct the fusion of radiomics and deep transfer learning features from the intratumoral and peritumoral areas in breast DCE-MRI images to differentiate between benign and malignant breast tumors, and to compare the diagnostic accuracy of this fusion model against the assessments made by experienced radiologists. MATERIALS AND METHODS: This multi-center study conducted a retrospective analysis of DCE-MRI images from 330 women diagnosed with breast cancer, with 138 cases categorized as benign and 192 as malignant. The training and internal testing sets comprised 270 patients from center 1, while the external testing cohort consisted of 60 patients from center 2. A fusion feature set consisting of radiomics features and deep transfer learning features was constructed from both intratumoral (ITR) and peritumoral (PTR) areas. The Least absolute shrinkage and selection operator (LASSO) based support vector machine was chosen as the classifier by comparing its performance with five other machine learning models. The diagnostic performance and clinical usefulness of fusion model were verified and assessed through the area under the receiver operating characteristics (ROC) and decision curve analysis. Additionally, the performance of the fusion model was compared with the diagnostic assessments of two experienced radiologists to evaluate its relative accuracy. The study strictly adhered to CLEAR and METRICS guidelines for standardization to ensure rigorous and reproducible methods. RESULTS: The findings show that the fusion model, utilizing radiomics and deep transfer learning features from the ITR and PTR, exhibited exceptional performance in classifying breast tumors, achieving AUCs of 0.950 in the internal testing set and 0.921 in the external testing set. This performance significantly surpasses that of models relying on singular regional radiomics or deep transfer learning features alone. Moreover, the fusion model demonstrated superior diagnostic accuracy compared to the evaluations conducted by two experienced radiologists, thereby highlighting its potential to support and enhance clinical decision-making in the differentiation of benign and malignant breast tumors. CONCLUSION: The fusion model, combining multi-regional radiomics with deep transfer learning features, not only accurately differentiates between benign and malignant breast tumors but also outperforms the diagnostic assessments made by experienced radiologists. This underscores the model's potential as a valuable tool for improving the accuracy and reliability of breast tumor diagnosis.

Spectrum of Cognitive Biases in Diagnostic Radiology.

Cognitive biases are systematic thought processes involving the use of a filter of personal experiences and preferences arising from the tendency of the human brain to simplify information processing, especially when taking in vast amounts of data such as from imaging studies. These biases encompass a wide spectrum of thought processes and frequently overlap in their concepts, with multiple biases usually in operation when interpretive and perceptual errors occur in radiology. The authors review the gamut of cognitive biases that occur in radiology. These biases are organized according to their expected stage of occurrence while the radiologist reads and interprets an imaging study. In addition, the authors propose several additional cognitive biases that have not yet, to their knowledge, been defined in the radiologic literature but are applicable to diagnostic radiology. Case examples are used to illustrate potential biases and their impact, with emergency radiology serving as the clinical paradigm, given the associated high imaging volumes, wide diversity of imaging examinations, and rapid pace, which can further increase a radiologist's reliance on biases and heuristics. Potential strategies to recognize and overcome one's personal biases at each stage of image interpretation are also discussed. Awareness of such biases and their unintended effects on imaging interpretations and patient outcomes may help make radiologists cognizant of their own biases that can result in diagnostic errors. Identification of cognitive bias in departmental and systematic quality improvement practices may represent another tool to prevent diagnostic errors in radiology. ©RSNA, 2024 See the invited commentary by Larson in this issue.

Gartland classification concordance of supracondylar fractures among pediatric emergency medicine physicians, radiologists, and orthopedic surgeons.

BACKGROUND: The modified Gartland classification is the most widely accepted grading method of supracondylar humeral fractures among orthopedic surgeons and is relevant to identifying fractures that may require surgery. OBJECTIVE: To assess the interobserver reliability of the modified Gartland classification among pediatric radiologists, pediatric orthopedic surgeons, and pediatric emergency medicine physicians. MATERIALS AND METHODS: Elbow radiographs for 100 children with supracondylar humeral fractures were retrospectively independently graded by two pediatric radiologists, two pediatric orthopedic surgeons, and two pediatric emergency medicine physicians using the modified Gartland classification. A third grader of the same subspecialty served as a tie-breaker as needed to reach consensus. Readers were blinded to one another and to the medical record. The modified Gartland grade documented in the medical record by the treating orthopedic provider was used as the reference standard. Interobserver agreement was assessed using kappa statistics. RESULTS: There was substantial interobserver agreement (kappa = 0.77 [95% CI, 0.69-0.85]) on consensus fracture grade between the three subspecialties. Similarly, when discriminating between Gartland type I and higher fracture grades, there was substantial interobserver agreement between specialties (kappa = 0.77 [95% CI, 0.66-0.89]). The grade assigned by pediatric radiologists differed from the reference standard on 15 occasions, pediatric emergency medicine differed on 19 occasions, and pediatric orthopedics differed on 9 occasions. CONCLUSION: The modified Gartland classification for supracondylar humeral fractures is reproducible among pediatric emergency medicine physicians, radiologists, and orthopedic surgeons.

Radiographers' insights on the impact of their potential role in image interpretation within a low resource setting.

INTRODUCTION: The global shortage of radiologists has led to a growing concern in medical imaging, prompting the exploration of strategies, such as including radiographers in image interpretation, to mitigate this challenge. However, in low-resource settings, progress in adopting similar approaches has been limited. This study aimed to explore radiographers' perceptions regarding the impact of their potential role in image interpretation within a low-resource setting. METHODS: The study used a qualitative descriptive design and was conducted at two public referral hospitals. Radiographers with at least one year of experience were purposively sampled and interviewed using a semi-structured interview guide after consenting. Data saturation determined the sample size, and content analysis was applied for data analysis. RESULTS: Two themes emerged from fourteen interviews conducted with two male and twelve female radiographers. Theme one revealed the potential for enhanced healthcare delivery through improved diagnostic support, bridging radiologist shortages, career development and fulfilment as positive outcomes of role extension. Theme two revealed possible implementation hurdles including radiographer resistance and reluctance, limited training, lack of professional trust, and legal and ethical challenges. CONCLUSION: Radiographers perceived their potential participation positively, envisioning enhanced healthcare delivery, however, possible challenges like resistance and reluctance of radiographers, limited training, and legal/ethical issues pose hurdles. Addressing these challenges through tailored interventions, including formal education could facilitate successful implementation. Further studies are recommended to explore radiographers' competencies, providing empirical evidence for sustaining and expanding this role extension. IMPLICATION FOR PRACTICE: The study further supports the integration of radiographers into image interpretation with the potential to enhance healthcare delivery, however, implementation challenges in low-resource settings require careful consideration.