Current problems in diagnostic radiology最新文献

Rationale and objectives: Radiology residents often receive limited feedback on preliminary reports issued during independent call. This study aimed to determine if Large Language Models (LLMs) can supplement traditional feedback by identifying missed diagnoses in radiology residents' preliminary reports.

Materials & methods: A randomly selected subset of 500 (250 train/250 validation) paired preliminary and final reports between 12/17/2022 and 5/22/2023 were extracted and de-identified from our institutional database. The prompts and report text were input into the GPT-4 language model via the GPT-4 API (gpt-4-0314 model version). Iterative prompt tuning was used on a subset of the training/validation sets to direct the model to identify important findings in the final report that were absent in preliminary reports. For testing, a subset of 10 reports with confirmed diagnostic errors were randomly selected. Fourteen residents with on-call experience assessed the LLM-generated discrepancies and completed a survey on their experience using a 5-point Likert scale.

Results: The model identified 24 unique missed diagnoses across 10 test reports with i% model prediction accuracy as rated by 14 residents. Five additional diagnoses were identified by users, resulting in a model sensitivity of 79.2 %. Post-evaluation surveys showed a mean satisfaction rating of 3.50 and perceived accuracy rating of 3.64 out of 5 for LLM-generated feedback. Most respondents (71.4 %) favored a combination of LLM-generated and traditional feedback.

Conclusion: This pilot study on the use of LLM-generated feedback for radiology resident preliminary reports demonstrated notable accuracy in identifying missed diagnoses and was positively received, highlighting LLMs' potential role in supplementing conventional feedback methods.

Objective: In January 2016, we created an Instagram page for radiology education. Numerous publications in different fields have reported that Instagram "reels," introduced in 2020 as a short-form video feature, are more popular than image posts. These findings and our familiarity with Instagram prompted us to analyze our own data to better understand how image posts compared with reels when used in the context of radiology education.

Materials and methods: For each post category, metric values were extracted from the Instagram platform and analyzed as continuous variables, reported as medians with interquartile ranges (IQR). Metrics were compared between image categories using the Kruskal-Wallis test, with resulting p-values adjusted for multiple comparisons using the Bonferroni correction. Corrected p-values of less than 0.05 were considered statistically significant.

Results: We included 128 images and 96 reels in the analysis. Images generally reached a larger audience, with a median of 18,745 [IQR: 13,478-27,243] impressions vs. 11,972 [IQR: 9,310.0-13,844.5] for reels (p < 0.01). Images also tended to be shared more frequently (median 19 vs. 20, p < 0.01), liked more often (median 480 vs. 296, p < 0.01), and saved more by users (median 138 vs. 84, p < 0.01) than reels, respectively. Both images and reels received a similar number of comments, with a median of 3 comments for both (p > 0.99). We also explored the performance differences of image post subcategories. Within images, our "You Make the Call!" (YMTC) questions (n = 23) displayed higher performance metrics across the board than the three other types of image posts combined (n = 105). When compared, the median number of impressions for YMTC images was 36,735 [IQR: 31,343-40,742] vs. 15,992 [IQR:12,774-21,873] for other types of images (p < 0.01). YMTC images were shared more often (median 25 vs. 17, p < 0.01), received more likes (median 809 vs. 445, p < 0.01) and saves (median 206 vs. 119, p < 0.01) than non-YMTC images, respectively. User engagement showed slightly different trends with YMTC reels being the most liked, while quiz reels receiving the most comments and talking clips being the most saved.

Conclusion: Our findings on the use of Instagram in radiology education suggest that static images perform much better than reels. Consequently, we recommend to radiology educators seeking to establish an Instagram presence that using static image posts is an appropriate approach for reaching a radiology audience, particularly with image posts that engage an audience with participatory opportunities such as answering quiz-like questions aimed at making a diagnosis.

Novel strategies are needed to improve low rates of lung cancer screening (LCS) in the US. Seeking to determine hospitalists' perspectives on leveraging hospitalizations to identify patients eligible for LCS, we performed qualitative interviews with eight hospitalists from two hospitals within a large integrated healthcare system. The interviews used semi-structured questions to assess (1) knowledge and practice of general screening and LCS guidelines from the United States Preventive Services Task Force (USPSTF), (2) identification of smoking history, and (3) hospitalists' views on how data obtained during hospitalization may be utilized to improve general screening and LCS post hospitalization. We ultimately reached the conclusion that hospitalists would support a dedicated program to identify hospitalized patients eligible for LCS and facilitate testing after discharge. Efforts to identify patients and arrange subsequent screening should be performed by team members outside the inpatient team.

Bronchoscopy using a flexible bronchoscope is considered a safe procedure and has been used for diagnosing and treating airway and parenchymal lung diseases. Bronchoscopic interventions in selected patients with emphysema, airway stenosis, and air leaks provide new treatment options. The application of multidetector computed tomography (MDCT) planning prior to bronchoscopy is comprehensively addressed. Using MDCT scan for pre-procedural planning, ensures precise navigation and device placement during bronchoscopy, ultimately improving patient outcomes. Radiological features can be correlated with bronchoscopy findings, linking MDCT images with direct bronchoscopy observations. This educational statement provides a comprehensive overview of the integration of computed tomography and bronchoscopy in managing different pulmonary conditions treated with endobronchial valve and airway stent placement, focusing on key aspects to enhance understanding and application in clinical practice. Emphasis is placed on their role in treating airway stenosis (AS), air leaks, and chronic obstructive pulmonary disease (COPD), highlighting the conditions under which these procedures are most beneficial. It explores how MDCT imaging contributes to the diagnosis and treatment planning of these conditions and the correct interpretation of MDCT image findings during follow-up after the procedure.

Objective: The purpose of this article is to review the staging systems for common malignant genitourinary and gynecological tumors, including renal cell carcinoma, urinary bladder carcinoma, as well as cervical, endometrial, and ovarian carcinoma, and to highlight the key imaging findings ("tipping points") that may alter patient management algorithms based on radiological staging.

Conclusion: There are identifiable imaging features for the common genitourinary and gynecological malignancies, including the size of the primary tumor, tumor extension, invasion of adjacent structures, lymph node involvement, and distant metastasis, which provide important prognostic information and determine patient management. Radiologists must be aware of these imaging findings ("tipping points") when interpreting staging examinations.

Objectives: This quality improvement project (QIP) aimed to foster radiology training at a regional tertiary cardiothoracic centre that had very low trainee satisfaction rankings.

Methods: To study the problem and intervene timely, multiple methods were applied, including a local feedback survey, placement reorganisation, consultant encouragement to train as accredited supervisors, followed by departmental education portal creation and start of externally funded Visiting Fellowships and salaried Clinical Fellowships. The regional rating was monitored. The local feedback survey was distributed and analysed using descriptive statistics. Alongside the QIP, service expansion occurred.

Results: The site regionally ranked 9/19 in 2 years. Local survey responses (53) showed continuous improvement; cardiothoracic subspecialty interest (+39%) and audit/academic involvement (+36%) increased. Multiple Fellowships were completed; internationally reputable placements were agreed upon. Most consultants trained as supervisors. Per increased demand, compulsory deanery posts were changed to motivation-based, and an additional salaried position was offered. Five fellows stayed in the region as subspecialist consultants. Unexpected challenges included space and workstation loss with service expansion, lack of regional surveys since 2019, and the global pandemic. Regardless, the results were positive with subspecialty interest and projected reputational effect increase. Local long-term survey provided sustainable data in detecting improvement areas.

Conclusions: Given the national radiologist shortage, this quality improvement project shows a possible positive impact of similar interventions, including workforce retention/recruitment and thus improving patient care.

Advances in knowledge: Continuous feedback and quality improvement maintenance are valuable to enhance training quality locally and beyond.

While there is no precise formula for a great radiology resident, certain attributes and achievements may herald success during training. We briefly review prior works exploring predictive factors and evaluation metrics of top resident performance, noting that those focusing on non-cognitive attributes are over twenty years old. As radiology practice and education has substantially evolved in the interim, we revisit this topic from a contemporary perspective. Inspired by the literature and our own personal experiences, we suggest that the following non-cognitive traits are invaluable for radiology trainees: communication expertise, workplace adaptability, self-awareness, tech savvy and genuine interest in one's individual work and greater community. These characteristics should be highlighted by applicants, sought by selection committees, cultivated by mentors, evaluated by programs and valued by colleagues.

Background: Mastitis is an inflammatory condition of the breast which represents an array of underlying etiologies encompassing both infectious and non-infectious causes. Exacerbating factors include endemic infections, lack of awareness and suboptimal breastfeeding practices. Neglected cases lead to prolonged morbidity, recurrent episodes, and complications such as abscess or sinus formation, resulting in permanent breast disfigurement. Its overlapping clinical presentation with breast cancer necessitates an integrated multidisciplinary approach for diagnosis and treatment.

Objectives: The primary aim was to investigate demographic, radiological, and histopathological characteristics of mastitis. Objectives included correlating radiological and histopathological findings, classifying mastitis by etiology, identifying the clinical and imaging patterns across diverse clinical settings to enhance the understanding of mastitis.

Material and method: This is a retrospective observational study, analysing the clinical, radiological, and histopathological data from 65 patients with mastitis between February 2023 and February 2024.

Results: The study included 65 patients, aged 18 to 65 years, with breast pain as the most prevalent clinical presentation. Cases were classified as infectious (47.6%) and non-infectious (52%). Acute puerperal mastitis (26.15%) and granulomatous mastitis (30%) were the most common subtypes. The commonest mammographic finding was focal asymmetry. On ultrasound, infectious mastitis showed oedema with other inflammatory changes, including diffuse skin thickening and collections; while non-infectious mastitis typically presented as solitary or multiple breast masses (p < 0.001). Surprisingly, idiopathic granulomatous mastitis constituted the largest percentage amongst various histopathological causes of mastitis in our study.

Conclusion: An integrated multidisciplinary approach with understanding of the pathogenesis is imperative for prompt diagnosis and optimizing treatment strategies, thereby improving patient outcome. Radiological imaging is critical for diagnosis, evaluating disease extent, conducting guided interventions, and monitoring treatment response.

This manuscript explores the application of the 5S methodology in optimizing workplace safety and efficiency within the context of biopsy training equipment. Drawing from a Quality Improvement Report presented at the 2023 RSNA annual meeting, our manuscript focuses on implementing 5S principles with a dedicated emphasis on safety (the 6th S). We demonstrate how the systematic application of 5S principles can revolutionize the functionality of biopsy training equipment, mitigate safety risks, and enhance overall workplace productivity. This manuscript offers valuable insights and practical strategies for improving healthcare training environments, with broader implications for quality improvement initiatives in the healthcare sector.

Rationale and objectives: Medical education led by peers and near-peers has been shown to benefit both teachers and learners and can be successfully incorporated into radiology education. The authors created a virtual, multi-institution pediatric radiology conference employing peer and near-peer teaching with the goals of improving radiology knowledge and enhancing the educational experience of radiology trainees.

Materials and methods: Two radiology residency programs implemented a common pediatric radiology curriculum and joint quarterly virtual peer teaching conference. Conferences featured short teaching sessions led by six to ten radiology trainees and were facilitated by attending pediatric radiologists. Knowledge assessments (KA) consisting of multiple-choice questions inspired by conference learning objectives were sent to peer educators before the conference (pre-conference), directly after the conference (immediate post-conference), and three months after the conference (delayed post-conference). Surveys were distributed to peer educators immediately after conferences to assess conference reception and solicit feedback. Quantitative data was analyzed using ANOVA, Kruskal-Wallis test, and post-hoc Tukey HSD test.

Results: Four conferences featured 33 peer educators consisting primarily of first-year (60.6 %), second-year (18.2 %), and third-year (15.2 %) radiology residents. Compared to pre-conference scores, immediate post-conference scores were significantly increased (HSD 13, p = 0.02) and delayed post-conference scores were increased without statistical significance (HSD 5.8, p = 0.29). Almost all survey respondents perceived the conferences as helpful, well-organized, and effective in teaching pediatric radiology. A majority of participants expressed interest in participating in future peer teaching radiology conferences.

Conclusion: A virtual pediatric radiology peer and near-peer teaching conference held between two radiology residencies improved short-term radiology knowledge of educators and was highly received.