Science AI Journal
Medicine · Research topic

Open research questions in Radiology practices and education

85 gap statements mined from Radiology practices and education papers in our 4.5M-paper local library, which holds 870 papers on the topic — drawn mostly from each paper's own stated research gap, future-work, challenge and limitation notes, and its abstract. The ones listed below are a selection still marked open; each names the study that raised it, with a DOI link where the paper has one.

Choosing where to publish on Radiology practices and education? See the ranked Medicine journals.

What the literature leaves open

  • The study only included radiology residents and did not evaluate the performance of more experienced radiologists. The study used a limited number of scanners and imaging protocols.

    Commercial artificial intelligence–assisted performance and interpretation time of first-on-call radiology residents using computed tomography pulmonary angiography to detect pulmonary embolism: a multireader, multicenter study · 2026 · DOI

  • The effect of AI support on the performance of radiology residents in detecting pulmonary embolism is not well established. There is a need to investigate the potential of AI assistance to improve diagnostic accuracy and reduce interpretation time.

    Commercial artificial intelligence–assisted performance and interpretation time of first-on-call radiology residents using computed tomography pulmonary angiography to detect pulmonary embolism: a multireader, multicenter study · 2026 · DOI

  • Considering the theoretical contribution and the limitation of this research, several suggestions for future research can be derived. Thematically, more in-depth insights are needed concerning the most important barriers and facilitators identified above. First of all, the application at the core of this research, BoneXpert, only presents a very small part of the day to day work of radiologists.

    Automatic Speech Recognition and Large Language Models for Multilingual Pathology Report Generation: Proof-of-Concept Study · 2026 · DOI

  • There is a gap in the literature regarding the evaluation of medical interns' proficiency in identifying critical findings on chest X-rays. The study aims to address this gap by evaluating the proficiency of medical interns in identifying critical findings on chest X-rays.

    Medical Interns' Skill Levels in Emergency Chest X-ray Interpretation · 2026 · DOI

  • Future studies could evaluate the performance of LLMs on other specialized medical board examinations. Future studies could also investigate the use of LLMs in medical education and practice.

    Performance of large language models on the radiation and cancer biology practice exam · 2026 · DOI

  • There is a need to evaluate the performance of LLMs on specialized medical board examinations. The study addresses this gap by evaluating the performance of three widely used LLMs on a domain-specific radiation and cancer biology examination.

    Performance of large language models on the radiation and cancer biology practice exam · 2026 · DOI

  • The lack of studies assessing the performance of MLLMs in Bone-RADS classification. The need to evaluate the accuracy of MLLMs in medical imaging tasks.

    Diagnostic Performance of Multimodal Large Language Models in Assigning Bone-RADS Categories on CT · 2026 · DOI

  • The absence of clinical information likely affected both human and AI performance, particularly in borderline entities where morphology alone is insufficient for confident classification.

    EXPLORING THE DIAGNOSTIC LIMITS OF CHATGPT: HOW FAR CAN A LARGE LANGUAGE MODEL GO IN HISTOPATHOLOGICAL IMAGE INTERPRETATION? · 2026 · DOI

  • The challenges facing pediatric radiology informatics are shared across specialties and institutions. Publishing solutions, participating in professional society informatics committees, and mentoring trainees in informatics principles expand the community of advocates for children’s needs within enterprise systems.

    Pediatric radiology informatics within a larger academic practice · 2026 · DOI

  • International experience suggests that technology alone is insufficient for successful adoption of eCDS systems. The study aims to address the gap in implementing eCDS systems by focusing on clinician engagement and education strategies.

    Implementation of Electronic Clinical Decision Support for Radiology Referrals: The Role of Governance, Clinician Engagement and Education · 2026 · DOI

  • There is a lack of structured, multi-phase improvement reports from high-volume publicly funded radiology departments. The gap is due to the complexity of workflow challenges and the need for data-driven approaches.

    Optimising radiology workflow in a high-volume academic medical centre: a multi-phase, data-driven quality improvement initiative · 2026 · DOI

  • The lack of standardization in interventional radiology. The occupational safety risks associated with interventional radiology.

    Why Interventional Radiology Should Consider Robotics: A Step Toward Augmented Interventional Radiology · 2026 · DOI

  • This suggests that even in many large children’s hospitals, where the demand for minimally invasive procedures should be high, PIR is not yet established as a core clinical discipline.

    Mapping Paediatric Interventional Radiology Provision: Results of a CIRSE Member Survey · 2026 · DOI

  • The performance of large language models (LLMs)-DeepSeek in the generation of in-training examination questions in radiology resident education is understudied.

    Performance of DeepSeek in the generation of in-training examination questions in radiology resident education · 2026 · DOI

  • However, the rapid increase in studies investigating these models, along with the lack of standardized LLM-specific reporting practices, affects reproducibility, reliability, and clinical applicability.

    Guidelines for Reporting Studies on Large Language Models in Radiology: An International Delphi Expert Survey · 2026 · DOI

  • Chest X-ray (CXR) radiology report generation (RRG) models have shown rapid progress on automated metrics, yet their clinical utility remains uncertain due to limited qualitative evaluation by radiologists.

    CXRMate-2: Structured multimodal temporal embeddings and tractable reinforcement learning for clinically acceptable chest X-ray radiology report generation · 2026 · DOI

  • Discrepancies between preliminary reports by on-call radiology residents and final reports of coronary computed tomography angiography (CCTA) in the emergency department (ED) have not been thoroughly investigated.

    Incidence and predictors of discrepancies in radiology resident interpretations of coronary CT in the emergency department · 2025 · DOI

  • Medical interns may have limited experience in interpreting chest X-rays. Medical interns may have varying levels of competence in identifying critical findings on chest X-rays. The study's findings may be limited by the sample size and population.

    Medical Interns' Skill Levels in Emergency Chest X-ray Interpretation · 2026 · DOI

  • Legislators, mostly without medical training, enacting laws mandating certain medical procedures undercuts the principle that every patient is unique and requires an individualized approach to treatment.

    Modality matters · 2026 · DOI

  • The traditional mentoring approach often fails to meet the diverse and evolving needs of learners in radiology. There is a shortage of qualified faculty in radiology.

    Cascade mentoring: a proposal for transforming radiology education in line with the European training curriculum · 2026 · DOI

  • Across all included studies, training and evaluation were based on retrospective datasets that were often task-specific, derived from public repositories, and frequently lacked evidence of robustness to different patient populations, imaging systems, and acquisition settings.

    AI-Based Post-processing for Artefact Mitigation in Radiography: A Systematic Review · 2026 · DOI

  • For KPI outcomes, covariate-adjusted primary analyses confirmed that these modest shifts did not account for the observed reduction in patient entry/exit time.

    Optimizing efficiency in CT services: a data-driven approach using action logs from the radiology information system · 2026 · DOI

  • Future multicenter studies with larger sample sizes and longitudinal follow-up are recommended to validate these findings, assess radiological-clinical correlations, evaluate interobserver agreement, and establish evidence-based imaging protocols for the management of non-traumatic LBP.

    Diagnostic accuracy of plain radiography compared with MRI in adults with non-traumatic low back pain · 2026 · DOI

  • Electronic health records (EHRs) capture resident clinical activities, but few studies have effectively used EHR data to characterize resident experiences.

    US Internal Medicine Residents’ Inpatient Learning Experience Variation Revealed Through Electronic Health Record Data · 2025 · DOI

  • Evaluating the performance of MLLMs in other medical imaging tasks. Assessing the potential applications of MLLMs in routine clinical practice. Developing more accurate and reliable MLLMs for medical imaging tasks.

    Diagnostic Performance of Multimodal Large Language Models in Assigning Bone-RADS Categories on CT · 2026 · DOI

Most-cited papers in Radiology practices and education

Most recent work

Find a gap in your own Radiology practices and education sub-topic

This page shows what the Radiology practices and education literature already flags as unresolved. To narrow it to your specific question, search the Research Gap Finder: the search is free with a free account and lists the papers closest to your topic first. Unlocking that topic (50 credits, charged once) fills the comparison table from our 4.5M-paper local library and writes the gaps from its rows.

Open the Research Gap Finder →

Related topics in Medicine

Artificial Intelligence in Healthcare and Education
2,304 open questions
Substance Abuse Treatment and Outcomes
1,956 open questions
Dementia and Cognitive Impairment Research
1,232 open questions
Ferroptosis and cancer prognosis
1,146 open questions
Liver Disease Diagnosis and Treatment
1,049 open questions
Smoking Behavior and Cessation
1,025 open questions
Physical Activity and Health
1,002 open questions
Attention Deficit Hyperactivity Disorder
982 open questions
Open questions raised by papers listed on this page include: (1) The effect of AI support on the performance of radiology residents in detecting pulmonary embolism is not well established (“Commercial artificial intelligence–assisted performance and interpretation time…”, 2026); (2) Thematically, more in-depth insights are needed concerning the most important barriers and facilitators identified above (“Automatic Speech Recognition and Large Language Models for Multilingual…”, 2026); (3) Future studies could evaluate the performance of LLMs on other specialized medical board examinations (“Performance of large language models on the radiation and cancer biology…”, 2026); (4) The lack of studies assessing the performance of MLLMs in Bone-RADS classification (“Diagnostic Performance of Multimodal Large Language Models in Assigning…”, 2026); (5) There is a lack of structured, multi-phase improvement reports from high-volume publicly funded radiology departments (“Optimising radiology workflow in a high-volume academic medical centre: a…”, 2026). 85 gap statements have been mined from Radiology practices and education papers in our 4.5M-paper local library, which holds 870 papers on the topic; the gaps come from whichever of those papers state one. They are mostly the research gaps the authors state and the papers' abstracts, plus future-work, limitations and challenges passages. The ones listed below are a selection still marked open; each names the study that raised it, with a DOI link where the paper has one, so you can read the original claim in context.

Tools for your next paper

Gaps & Literature SearchFind open questions in any field — 120,000+ open gaps mined from our own library.Pre-CheckIs your paper ready? Acceptance odds for top, mid and open/emerging journals, in seconds.Journal FinderA ranked shortlist of target journals from a 17,500-venue index.Duplicate Publication CheckerCheck for prior publication across 7 sources and our local library.Citation GeneratorFreeA DOI or title → APA, MLA, Vancouver, Chicago, BibTeX, RIS. No signup.Graphical Abstract MakerFreeTurn your findings into a colorblind-safe graphical abstract.

How Pre-Check worksHow AI Review works

Compare the category — Honest roundups of the AI research tools, ours listed alongside the alternatives.

Command palette

Jump anywhere, run any action.