Clinical Radiology Research Articles

Large Language Models Take on Cardiothoracic Surgery: A Comparative Analysis of the Performance of Four Models on American Board of Thoracic Surgery Exam Questions in 2023.

Objectives Large language models (LLMs), for example, ChatGPT, have performed exceptionally well in various fields. Of note, their success in answering postgraduate medical examination questions has been previously reported, indicating their possible utility in surgical education and training. This study evaluated the performance of four different LLMs on the American Board of Thoracic Surgery's(ABTS) Self-Education and Self-Assessment in Thoracic Surgery (SESATS) XIII question bank to investigate the potential applications of these LLMs in the education and training of future surgeons. Methods The dataset in this study comprised 400 best-of-four questions from the SESATS XIII exam. This included 220 adult cardiac surgery questions, 140 general thoracic surgery questions, 20 congenital cardiac surgery questions, and 20 cardiothoracic critical care questions. The GPT-3.5 (OpenAI, San Francisco, CA) and GPT-4 (OpenAI) models were evaluated, as well as Med-PaLM 2 (Google Inc., Mountain View, CA) and Claude 2 (Anthropic Inc., San Francisco, CA), and their respective performances were compared. The subspecialties included were adult cardiac, general thoracic, congenital cardiac, and critical care. Questions requiring visual information, such as clinical images or radiology, were excluded. Results GPT-4 demonstrated a significant improvement over GPT-3.5 overall (87.0% vs. 51.8% of questions answered correctly, p < 0.0001). GPT-4 also exhibited consistently improved performance across all subspecialties, with accuracy rates ranging from 70.0% to 90.0%, compared to 35.0% to 60.0% for GPT-3.5. When using the GPT-4 model, ChatGPT performed significantly better on the adult cardiac and general thoracic subspecialties (p < 0.0001). Conclusions Large language models, such as ChatGPT with the GPT-4 model, demonstrate impressive skill in understanding complex cardiothoracic surgical clinical information, achieving an overall accuracy rate of nearly 90.0% on the SESATS question bank. Our study shows significant improvement between successive GPT iterations. As LLM technology continues to evolve, its potential use in surgical education, training, and continuous medical education is anticipated to enhance patient outcomes and safety in the future.

Prostate cancer risk assessment and avoidance of prostate biopsies using fully automatic deep learning in prostate MRI: comparison to PI-RADS and integration with clinical data in nomograms.

Risk calculators (RCs) improve patient selection for prostate biopsy with clinical/demographic information, recently with prostate MRI using the prostate imaging reporting and data system (PI-RADS). Fully-automated deep learning (DL) analyzes MRI data independently, and has been shown to be on par with clinical radiologists, but has yet to be incorporated into RCs. The goal of this study is to re-assess the diagnostic quality of RCs, the impact of replacing PI-RADS with DL predictions, and potential performance gains by adding DL besides PI-RADS. One thousand six hundred twenty-seven consecutive examinations from 2014 to 2021 were included in this retrospective single-center study, including 517 exams withheld for RC testing. Board-certified radiologists assessed PI-RADS during clinical routine, then systematic and MRI/Ultrasound-fusion biopsies provided histopathological ground truth for significant prostate cancer (sPC). nnUNet-based DL ensembles were trained on biparametric MRI predicting the presence of sPC lesions (UNet-probability) and a PI-RADS-analogous five-point scale (UNet-Likert). Previously published RCs were validated as is; with PI-RADS substituted by UNet-Likert (UNet-Likert-substituted RC); and with both UNet-probability and PI-RADS (UNet-probability-extended RC). Together with a newly fitted RC using clinical data, PI-RADS and UNet-probability, existing RCs were compared by receiver-operating characteristics, calibration, and decision-curve analysis. Diagnostic performance remained stable for UNet-Likert-substituted RCs. DL contained complementary diagnostic information to PI-RADS. The newly-fitted RC spared 49% [252/517] of biopsies while maintaining the negative predictive value (94%), compared to PI-RADS ≥ 4 cut-off which spared 37% [190/517] (p < 0.001). Incorporating DL as an independent diagnostic marker for RCs can improve patient stratification before biopsy, as there is complementary information in DL features and clinical PI-RADS assessment. For patients with positive prostate screening results, a comprehensive diagnostic workup, including prostate MRI, DL analysis, and individual classification using nomograms can identify patients with minimal prostate cancer risk, as they benefit less from the more invasive biopsy procedure. The current MRI-based nomograms result in many negative prostate biopsies. The addition of DL to nomograms with clinical data and PI-RADS improves patient stratification before biopsy. Fully automatic DL can be substituted for PI-RADS without sacrificing the quality of nomogram predictions. Prostate nomograms show cancer detection ability comparable to previous validation studies while being suitable for the addition of DL analysis.

Standardizing radiologic reporting of response to improve the patient experience: Comparing response categories of RECIST 1.1 and a novel, real-world, standardized, oncologic response lexicon derived from clinical radiology reports.

e13810 Background: With the 21st Century Cures Act of 2016, rapid and complete access to medical records including radiology reports is mandated. Patients have expressed that an unmet need is improving clarity in radiology results with more structured information that avoids technical jargon. RECIST is routinely applied in clinical trials to assess treatment response but is challenging to apply in routine practice. A standardized Oncologic Response (OR) lexicon was developed to categorize response and progression directly from clinical reports, using an ordinal scale. This study aims to compare the rates of response from OR categories to RECIST categories in the setting of three phase 2 trials. Methods: Patients from three phase 2 trials were retrospectively reviewed for real world response using OR categories by a radiologist blinded to RECIST data. Clinical radiology reports generated during the trial period were reviewed and response was categorized from the report impression text according to OR categories (OR-0: no evidence of disease, OR-1: unequivocal decrease, OR-2: slight decrease, OR-3: unchanged, OR-4: slight increase, and OR-5: unequivocal increase). Best RECIST response categories of complete response (CR) or partial response (PR), stable disease (SD), and progression of disease (PD) were compared to best OR response categories (OR-0/1, OR-2/3/4, and OR-5, respectively). Time to treatment failure (TTF) and overall survival (OS) for each category was calculated using Kaplan-Meier methodology. Results: Ninety-one patients were reviewed. Best response based on RECIST v1.1 was CR for 4 patients (4%), PR for 38 patients (42%), SD for 44 patients (48%), and PD for 5 patients (6%). Using OR-categories, 1 patient (1%) was categorized as OR-0, 46 (51%) as OR-1, 34 (37%) OR-2/3/4, and 10 (11%) OR-5. Concordance between the three response categories across RECIST (CR or PR; SD; PD) and OR-RADS (0-1; 2/3/4; 5) was 73.6%. The majority of discordant cases (50%, n=12/24) were patients with SD by RECIST but OR-1 using OR categories. Median TTF was similar between RECIST and OR categories: RECIST CR/PR: 21.8, SD: 6.9, and PD: 1.0 months (p&lt;0.0001) and OR-0/1: 21.5, OR-2/3/4: 7.0, and OR-5 1.1 (p&lt;0.0001). Median OS was similar between RECIST and OR-categories: RECIST CR/PR: 42.6, SD: 9.9, and PD: 8.2 months (p=0.005) and OR-0/1: 42.6, OR-2/3/4: 13.6, and OR-5 7.1 (p&lt;0.0001). Conclusions: There was high concordance between RECIST and OR-categories. This study provides preliminary evidence for the use of standardized OR categories to identify real world responses, with outcomes similar to RECIST response categories. Use of OR can improve communication with patients and oncologists and allow for standardized data extraction of radiologic response for real-world studies.

Diagnostic value of imaging in patients with clear cell papillary renal cell carcinoma: A case series and literature review.

Clear cell papillary renal cell carcinoma (CCPRCC) is a newly classified renal cell carcinoma with a low degree of malignancy. Its imaging features have not been studied deeply. Therefore, we reviewed the imaging features of CCPRCC. Solid CCPRCC shows high echo or isoecho mass on conventional ultrasound. Contrast enhanced ultrasound shows "fast forward and slow backward, uneven high enhancement". Computed tomography shows high enhancement and maximum enhancement in the cortical-medullary phase. Magnetic resonance imaging shows slightly low T1WI and high T2WI. This article aims to improve the understanding of CCPRCC by clinical radiologists and promote the accurate.

Lumbar spine MRI annotation with intervertebral disc height and Pfirrmann grade predictions.

Many lumbar spine diseases are caused by defects or degeneration of lumbar intervertebral discs (IVD) and are usually diagnosed through inspection of the patient's lumbar spine MRI. Efficient and accurate assessments of the lumbar spine are essential but a challenge due to the size of the clinical radiologist workforce not keeping pace with the demand for radiology services. In this paper, we present a methodology to automatically annotate lumbar spine IVDs with their height and degenerative state which is quantified using the Pfirrmann grading system. The method starts with semantic segmentation of a mid-sagittal MRI image into six distinct non-overlapping regions, including the IVD and vertebrae regions. Each IVD region is then located and assigned with its label. Using geometry, a line segment bisecting the IVD is determined and its Euclidean distance is used as the IVD height. We then extract an image feature, called self-similar color correlogram, from the nucleus of the IVD region as a representation of the region's spatial pixel intensity distribution. We then use the IVD height data and machine learning classification process to predict the Pfirrmann grade of the IVD. We considered five different deep learning networks and six different machine learning algorithms in our experiment and found the ResNet-50 model and Ensemble of Decision Trees classifier to be the combination that gives the best results. When tested using a dataset containing 515 MRI studies, we achieved a mean accuracy of 88.1%.

On the relationship between viscoelasticity and water diffusion in soft biological tissues

Magnetic resonance elastography (MRE) and diffusion-weighted imaging (DWI) are complementary imaging techniques that detect disease based on viscoelasticity and water mobility, respectively. However, the relationship between viscoelasticity and water diffusion is still poorly understood, hindering the clinical translation of combined DWI-MRE markers.We used DWI-MRE to study 129 biomaterial samples including native and cross-linked collagen, glycosaminoglycans (GAGs) with different sulfation levels, and decellularized specimens of pancreas and liver, all with different proportions of solid tissue, or solid fractions. We developed a theoretical framework of the relationship between mechanical loss and tissue-water mobility based on two parameters, solid and fluid viscosity. These parameters revealed distinct DWI-MRE property clusters characterizing weak, moderate, and strong water-network interactions. Sparse networks interacting weakly with water, such as collagen or diluted decellularized tissue, resulted in marginal changes in water diffusion over increasing solid viscosity. In contrast, dense networks with larger solid fractions exhibited both free and hindered water diffusion depending on the polarity of the solid components. For example, polar and highly sulfated GAGs as well as native soft tissues hindered water diffusion despite relatively low solid viscosity.Our results suggest that two fundamental properties of tissue networks, solid fraction and network polarity, critically influence solid and fluid viscosity in biological tissues. Since clinical DWI and MRE are sensitive to these viscosity parameters, the framework we present here can be used to detect tissue remodeling and architectural changes in the setting of diagnostic imaging. Statement of significanceThe viscoelastic properties of biological tissues provide a wealth of information on the vital state of cells and host matrix. Combined measurement of viscoelasticity and water diffusion by medical imaging is sensitive to tissue microarchitecture. However, the relationship between viscoelasticity and water diffusion is still poorly understood, hindering full exploitation of these properties as a combined clinical biomarker. Therefore, we analyzed the parameter space accessible by diffusion-weighted imaging (DWI) and magnetic resonance elastography (MRE) and developed a theoretical framework for the relationship between water mobility and mechanical parameters in biomaterials. Our theory of solid material properties related to particle motion can be translated to clinical radiology using clinically established MRE and DWI.

Ethical challenges in the bioanthropological and biomedical investigation of Sicilian mummies-Past experience and future pathways.

This article presents a multidisciplinary approach adopted in the Sicily mummy project, highlighting unique challenges and major ethical concerns inherent to the scientific study, conservation, and presentation of these mummies. Recognizing mummies as a distinct category of human remains, this paper argues for the development and application of specialized guidelines that address the intricate balance between scientific inquiry and respect for the cultural, religious, and mortuary practices that characterize the cultural context, in this case of Sicily. Through a transparent and collaborative dialogue among all stakeholders-including curators, clergy, scientists, and government officials-the project ensures the preservation of the mummies' dignity within their sacred spaces. The critical role of biological anthropologists is emphasized, alongside the contributions of clinical radiologists, pathologists, and qualified restorers, in constructing a comprehensive understanding of the mummies' biocultural significance. The paper advocates for a bioarchaeological strategy that advances scientific knowledge while safeguarding the mummies and respecting living communities. Additionally, we call for ethical rigor in scholarly publications and suggest future actions to protect this invaluable heritage. This approach not only preserves the dignity and integrity of the mummified remains but also enriches our understanding of past human societies.

Two for One-Combined Morphologic and Quantitative Knee Joint MRI Using a Versatile Turbo Spin-Echo Platform.

Quantitative MRI techniques such as T2 and T1ρ mapping are beneficial in evaluating knee joint pathologies; however, long acquisition times limit their clinical adoption. MIXTURE (Multi-Interleaved X-prepared Turbo Spin-Echo with IntUitive RElaxometry) provides a versatile turbo spin-echo (TSE) platform for simultaneous morphologic and quantitative joint imaging. Two MIXTURE sequences were designed along clinical requirements: "MIX1", combining proton density (PD)-weighted fat-saturated (FS) images and T2 mapping (acquisition time: 4:59 min), and "MIX2", combining T1-weighted images and T1ρ mapping (6:38 min). MIXTURE sequences and their reference 2D and 3D TSE counterparts were acquired from ten human cadaveric knee joints at 3.0 T. Contrast, contrast-to-noise ratios, and coefficients of variation were comparatively evaluated using parametric tests. Clinical radiologists (n = 3) assessed diagnostic quality as a function of sequence and anatomic structure using five-point Likert scales and ordinal regression, with a significance level of α = 0.01. MIX1 and MIX2 had at least equal diagnostic quality compared to reference sequences of the same image weighting. Contrast, contrast-to-noise ratios, and coefficients of variation were largely similar for the PD-weighted FS and T1-weighted images. In clinically feasible scan times, MIXTURE sequences yield morphologic, TSE-based images of diagnostic quality and quantitative parameter maps with additional insights on soft tissue composition and ultrastructure.

From Morphology to Molecules: Advances in the Distinction of Multiple Primary Lung Cancers From Intrapulmonary Metastases in Non-Small Cell Lung Cancer.

The increasing incidence of multiple lung nodules underscores the need for precise differentiation between multiple primary lung cancers (MPLCs) and intrapulmonary metastases (IPMs). This distinction impacts patient prognosis and treatment strategies. The prevalence of multiple lung nodules, ranging from 19.7% to 55.5%, highlights the clinical significance of this challenge. Historically, the role of histopathology, particularly comprehensive histology assessment (CHA), has been pivotal in differentiating MPLCs and IPMs. However, CHA has significant limitations, resulting in a constant search for a better way to distinguish those lesions. The best strategy for delineating MPLCs from IPMs is a multidisciplinary approach combining clinical data, radiology, histology, and molecular methods. Histology provides architectural and cellular characteristics, radiology contributes anatomic context and lesion characterization, and molecular methods reveal molecular features critical for accurate differentiation. Incorporating clinical data further enhances diagnostic precision. This review presents current knowledge and current approaches to multiple lung tumors. It is clear that even with a combination of pathology, radiology, and molecular data, definitive classification of multifocal lung tumors is not always possible.

Virtopsy concept around the world: Institute-based survey of worldwide forensic postmortem imaging

Introduction: Forensic routine postmortem imaging in excess of photography and conventional X-ray has been pushed since a few years, in some instances under the name ”Virtopsy”. It constitutes a pivotal innovation in forensic medicine as it allows for the non-invasive exploration of the deceased through diverse imaging techniques. This study offers an analysis of a survey with focus on the worldwide adoption and application of postmortem imaging. Our goal is to uncover and understand regional variances in its deployment application. Methods: A survey comprising 18 questions, both closed-ended and open-ended, was designed collaboratively and distributed globally via email and social network. The survey addressed topics such as autopsy rates, imaging modalities, indications for postmortem imaging, personnel involved, evaluation methods, and communication of findings. The survey was initially sent to institutes with published postmortem imaging research, and later, it was distributed through international forensic radiology and radiographer associations. Statistical analysis was conducted to interpret the results. Results: Responses were obtained from 29 countries, representing 6 continents, with a total of 100 participating institutions. European institutions were predominant (69%), followed by Australia (9), North America (8), Asia (7), Africa (6) and South America (1). The majority of institutions reported 100-500 autopsies annually (31). Among the institutes that reported that they perform post mortem imaging (PMI), most listed postmortem computed tomography (PMCT) as modality (89%). The request to perform PMI was issued by institutes of forensic medicine (51%), researchers (42%), police (43%) or public prosecutor’s office (54%). 48% of the respondents stated that an autopsy must always be performed, even if the cause and manner of death can be ascertained by postmortem imaging. radiographers were primarily responsible for technically performing PMCT (65%) whereas physicians were listed in 28%, autopsy technicians in 18%. The majority of the institutions (32%) identified clinical radiologists as the primary individuals responsible for reading, evaluating radiological images, and writing reports. Many respondents (64%) reported that their image readers had attended specialized postmortem imaging courses. Communication of findings typically involved written reports (28%) or a combination of written reports and illustrated images (31%). Membership of survey respondents was indicated in 38% for the International Society of Forensic Radiology and Imaging (ISFRI) and 5% for the International Association of Forensic Radiographers (IAFR). The question was how many of the responders are members of a PMI focused radiological society or work group. 52% (44 out of 85) respondents indicated they were not a member of a postmortem imaging society. The memberships listed are ISFRI (38%), IAFR (5%) and AGFB (Arbeitsgruppe Forensische Bildgebung, 4%). Conclusion: This study provides a global perspective on the utilization of postmortem imaging in forensic medicine, revealing regional variations in practices and technology adoption. It offers insights into the personnel, techniques, and procedures involved in this field in different countries.

Pott's puffy tumor: An unusual complication of rhino-orbito-cerebral mucormycosis

ObjectiveTo describe clinicoradiological features and surgical outcomes in a series of nine patients with rhino-orbito-cerebral mucormycosis (ROCM) who presented with Pott's puffy tumor (ROCM-PPT) MethodsThe records of nine patients with ROCM-PPT seen between March 2020 and December 2021 were analysed. Clinical features, radiology, histopathology, operative findings, management and outcome were noted. Frontal sinus pneumatisation and outflow tract configuration was compared between patients and controls with ROCM and no PPT. ResultsROCM-PPT was diagnosed in 9 of 284 (3.2 %) patients with ROCM seen during the study period. There were six (66.7 %) males and the median age was 54 (IQR 46–60) years. Eight (88.9 %) patients had diabetes mellitus and seven (77.8 %) had been COVID-19 positive. Radiological features of osteomyelitis, subperiosteal abscess formation and dural enhancement were seen in all patients. No significant differences in pneumatisation or frontal sinus outflow tract configuration were noted between patients and controls. All patients underwent a craniectomy with frontal bone debridement and frontal sinus exteriorisation. All patients were treated with anti-fungal agents for several months. All patients had symptomatic improvement at a median follow-up of 21 (IQR 18–23) months. Repeat CT/MRI scans showed disease regression/resolution in six out of eight (75 %) patients with follow-up imaging, and stable disease in two others. ConclusionsROCM-PPT is a rare, delayed complication of mucormycosis that was seen in larger numbers during the recent COVID-19 pandemic. Aggressive debridement of osteomyelitic bone and antifungal therapy results in a good outcome.

Clinical Characteristics and Prognoses of Mucormycosis in Four Children.

Mucormycosis is a fatal invasive fungal infection that commonly affects immunocompromised children. The aim of our study was to investigate the clinical manifestations, treatments, and prognosis of pediatric patients with mucormycosis. We conducted a retrospective search in Shenzhen Children's Hospital from July 2013 to July 2023 for all patients with mucormycosis. The clinical manifestation, pathogen detection, radiology, treatments, and prognosis were analyzed. Four cases were identified. Underlying conditions included acute myeloid leukemia with myeloid sarcoma (n = 1), thalassemia (post-allogeneic hematopoietic stem cell transplantation; n = 1), systemic lupus erythematosus (n = 1), and bilateral nephroblastoma (post-bilateral nephrectomy; n = 1). Two patients were disseminated mucormycosis, one case was pulmonary mucormycosis, and one case was cerebral mucormycosis. Fever, cough, and dyspnea were the main clinical symptoms of pulmonary mucormycosis, headache was the main clinical symptom of cerebral mucormycosis. Lung CT findings included consolidation, multiple nodules, halo sign, air crescent sign, and pleural effusion. The contrast-enhanced CT showed pulmonary artery and pulmonary vein occlusions in two patients and pseudoaneurysm in two patients. Amphotericin B formulations were administered as first-line therapy in all cases; in three cases, Triazole was administered in combination with amphotericin B. Mucormycosis is a life-threatening disease involving multiple systems. Aorta pseudoaneurysm is a rare and fatal complication, enhanced CT can assist in diagnosis. Early diagnosis and appropriate therapeutic strategies are needed.

ChatGPT may free time needed by the interventional radiologist for administration / documentation

Motive: Documentation and administration, unpleasant necessities, take a substantial part of the working time in the subspecialty of interventional radiology. With increasing future demand for clinical radiology predicted, time savings from use of text drafting technologies could be a valuable contribution towards our field. Method: Three cases of peripherally inserted central catheter (PICC) line insertion were defined for the present study. The current version of ChatGPT was tasked with drafting reports, following the Radiological Society of North America (RSNA) template. Key results: Score card evaluation by human radiologists indicates that time savings in documentation / administration can be expected without loss of quality from using ChatGPT. Further, automatically generated texts were not assessed to be clearly identifiable as AI-produced. Conclusions: Patients, doctors, and hospital administrators would welcome a reduction of the time that interventional radiologists need for documentation and administration these days. If AI-tools as tested in the present study are brought into clinical application, questions about trust into those systems eg with regard to medical complications will have to be addressed.

Unravelling pituitary tumours in medically treated patients with acromegaly: the impact of systematic MRI reassessment.

In acromegaly, the primary tumor is usually found during magnetic resonance imaging (MRI) of the pituitary gland. A remnant tumor after surgery is, however, harder to depict. When a tumor is missed, the remaining option is usually lifelong pharmacological treatment. To identify tumors by reassessment of all available MRI scans in pharmacologically treated patients, operated or not, and to compare our results with the routine MRI reports. Adult patients diagnosed with acromegaly and managed at a tertiary care center between 2005 and 2021 and currently on pharmacological treatment were included. MRI scans were evaluated in a standardized manner and classified independently by a radiologist and an endocrinologist into "certain," "suspected," or "no tumor." In case of disagreement, consensus was achieved with a senior neuroradiologist. The results were compared using the clinical radiologists' routine MRI reports. We identified certain and suspected tumors in 29/74 and 36/74 patients, respectively. No tumor was identified in nine patients. In five of these, no MRI contrast agent was given. Discrepancy between our results and the routine MRI reports was found in 31/74 patients (P = 0.01). In 22 patients, the routine reports described no tumor while we identified certain tumors in 2/22 patients and suspected tumors in 13/22 patients. In most patients with pharmacologically treated acromegaly, we identified a certain or suspected pituitary tumor. These findings were more frequent compared to the routine MRI reports. Based on our results, patients will be considered for a change in long-term treatment modality.

Gender diversity in radiology: Shedding light on the 256 shades of grey.

Despite medical school cohorts being composed of approximately 50% men and women, trainee positions in Clinical Radiology remain predominantly occupied by men. This study aims to identify reasons behind the gender gap, explore why more women are not pursuing a career in Clinical Radiology and to assess if there are gender differences in these reasons. Prospective multi-centre study using a voluntary, anonymous questionnaire aimed at senior Medical Students and Junior Doctors. A total of 318 participants responded to the questionnaire - 197 women (61.9%), 114 men (35.8%), 4 non-binary (1.3%), 2 preferred not to answer gender (0.6%), 1 I/they (0.3%). The most common reasons for not considering Clinical Radiology as a specialty include 'perceived limited patient contact' (62%), 'never/rarely exposed to it' (59%) and 'too lonely' (49%). Reasons with the largest gender discrepancies were 'too technology heavy' and 'limited patient contact', both cited more frequently by women. Most respondents indicated that their opinions of Clinical Radiology may change with more exposure during medical school, more patient contact and more mentorship. This study has revealed multiple reasons why women may not pursue specialty training in Clinical Radiology. Notable differences were found in the reasonings provided by men and women. Limited Clinical Radiology exposure and mentorship in medical school result in a lack of interest in this specialty as a career option. A proposed solution is to offer more medical school lectures and more junior doctor rotations to debunk stereotypes that may be negatively impacting opinions on Clinical Radiology. More mentorship of Medical Students and Junior Doctors, particularly from women, may also help decrease the gender gap.

Clinical utility, reproducibility, and radiologist acceptance of ILD-RADS

PurposeTo investigate the clinical utility, reproducibility, and radiologists’ acceptance of the Interstitial Lung Disease Imaging-Reporting and Data System (ILD-RADS). MethodIn this single-institutional retrospective study, three radiologists independently reviewed the chest high-resolution CT (HRCT) scans of 111 consecutive patients diagnosed with ILDs. They assessed the HRCT pulmonary features using the ILD-RADS template and assigned an ILD-RADS category (1–4) to each scan based on the identified imaging pattern. Patients were classified into idiopathic pulmonary fibrosis (IPF) (n = 14) and non-IPF ILD (n = 97) groups based on clinical diagnoses determined by multidisciplinary discussion. Association between ILD-RADS categories and clinical diagnoses was assessed using the Chi-square test for trend. Reproducibility was evaluated using kappa (k) scores, and radiologists’ acceptance of the ILD-RADS was evaluated with a questionnaire. ResultsWe found a significant association between the ILD-RADS categories and patients’ clinical diagnoses (P ≤ 0.0001) for the three readers, with a trend toward increased assignment of ILD-RADS-1 to IPF patients (50 %-57.1 %), and ILD-RADS-4 to non-IPF patients (46.4 %-49.5 %). The ILD-RADS categories showed excellent intra-reader agreement (k = 0.873) and moderate inter-reader agreement (k = 0.440). ILD-RADS-1 and −4 categories showed the highest inter-reader agreement (k = 0.681 and 0.481, respectively). Radiologists gave a positive response to using the ILD-RADS in daily practice. ConclusionsThe clinical utility of the ILD-RADS was demonstrated by the significant association between the ILD-RADS categories and patients’ clinical diagnoses, particularly the ILD-RADS-1 and −4 categories. Excellent intra-reader and moderate inter-reader reproducibility was observed. ILD-RADS has the potential to be widely accepted for standardized HRCT reporting among radiologists.

Implementing supplementary breast cancer screening in women with dense breasts: Insights from European radiographers and radiologists

IntroductionIn response to the critical need for enhancing breast cancer screening for women with dense breasts, this study explored the understanding of challenges and requirements for implementing supplementary breast cancer screening for such women among clinical radiographers and radiologists in Europe. MethodFourteen (14) semi-structured online interviews were conducted with European clinical radiologists (n = 5) and radiographers (n = 9) specializing in breast cancer screening from 8 different countries: Denmark, Finland, Greece, Italy, Malta, the Netherlands, Switzerland, United Kingdom. The interview schedule comprised questions regarding professional background and demographics and 13 key questions divided into six subgroups, namely Supplementary Imaging, Training, Resources and Guidelines, Challenges, Implementing supplementary screening and Women's Perspective. Data analysis followed the six phases of reflexive thematic analysis. ResultsSix significant themes emerged from the data analysis: Understanding and experiences of supplementary imaging for women with dense breasts; Challenges and requirements related to training among clinical radiographers and radiologists; Awareness among radiographers and radiologists of guidelines on imaging women with dense breasts; Challenges to implement supplementary screening; Predictors of Implementing Supplementary screening; Views of radiologists and radiographers on women's perception towards supplementary screening. ConclusionThe interviews with radiographers and radiologists provided valuable insights into the challenges and potential strategies for implementing supplementary breast cancer screening. These challenges included patient and staff related challenges. Implementing multifaceted solutions such as Artificial Intelligence integration, specialized training and resource investment can address these challenges and promote the successful implementation of supplementary screening. Further research and collaboration are needed to refine and implement these strategies effectively. Implications for practiceThis study highlights the urgent need for specialized training programs and dedicated resources to enhance supplementary breast cancer screening for women with dense breasts in Europe. These resources include advanced imaging technologies, such as MRI or ultrasound, and specialized software for image analysis. Moreover, further research is imperative to refine screening protocols and evaluate their efficacy and cost-effectiveness, based on the findings of this study.

Assessing the agreement of chronic lung disease of prematurity diagnosis between radiologists and clinical criteria

BackgroundChronic lung disease of prematurity (CLD) is the most prevalent complication of preterm birth and indicates an increased likelihood of long-term pulmonary complications. The accurate diagnosis of this condition is critical for long-term health management. Numerous definitions define CLD with different clinical parameters and radiology findings, making diagnosis of the disease ambiguous and potentially inaccurate.Methods95 patients were identified for this study, as determined by the diagnosis or confirmation of CLD in the impression of the radiologist’s report on chest x-ray. Pulmonary function and complications were recorded at multiple benchmark timeframes within each patient’s first few months of life and used for determining eligibility under each definition.ResultsEach clinical definition of CLD had a high sensitivity for patients identified to have CLD by radiologists, correctly fitting over 90% of patients. Most patients included required invasive mechanical ventilation or positive pressure ventilation at 36 weeks postmenstrual age, indicating patients with radiographically confirmed CLD tended to have more severe disease. Radiologists tended to diagnose CLD before 36 weeks postmenstrual age, a timepoint used by multiple standard clinical definitions, with cases called earlier fitting under a larger percentage of definitions than those called later.ConclusionsRadiologists tend to diagnose CLD in young patients with severe respiratory compromise, and can accurately diagnose the condition before developmental milestones for clinical definitions are met.

Efficiency, accuracy, and health professional's perspectives regarding artificial intelligence in radiology practice: A scoping review

AbstractIn this scoping review, we evaluated the performance of artificial intelligence (AI) in clinical radiology practice and examined health professionals' perspectives regarding AI use in radiology. This review followed the Joanna Briggs Institute (JBI) methodological guidelines. We searched multiple databases and the gray literature from March 15, 2016 to December 31, 2023. Of 49 articles reviewed, 13 assessed the performance of AI in radiology clinical practice, and 36 examined the attitudes of health professionals toward the use of AI in radiology. In four separate studies, AI significantly improved the diagnostic sensitivity or detection rate. Furthermore, six articles emphasized a significant reduction in case reading times with AI use. Although three studies suggested an increase in specificity with the assistance of AI, these findings did not reach statistical significance. Health professionals expressed the belief that AI would have a significant impact on radiology but would not replace radiologists in the near future. Limited knowledge of AI was observed among health professionals, who supported increased education and explicit regulations and guidelines related to AI. Overall, AI can enhance diagnostic efficiency and accuracy in clinical radiology practice. However, knowledge gaps and the concerns of health professionals should be addressed by prioritizing education and reinforcing ethical and legal regulations to facilitate the advancement of AI use in radiology. This scoping review provides evidence toward a comprehensive understanding of AI's potential in clinical radiology practice, promoting its use and stimulating further discussion on related challenges and implications.

Examining the clinical and radiological landscape of rhupus: navigating the challenges in disease classification.

Rhupus, in the broad sense,refers to an overlap between rheumatoid arthritis (RA) and lupus. However, there is a paucity of data on the appropriate diagnostic/classification criteria that should be used to define rhupus. Hence, we undertook this narrative review to analyze the clinical characteristics, radiology, and treatment with a focus on diagnostic challenges and defining features of rhupus. The databases of Medline/PubMed, Scopus, and DOAJ were searched for relevant articles using the following keywords: ("Rhupus"), ("lupus" AND "erosive" AND "arthritis"), and ("lupus" AND "rheumatoid arthritis" AND "overlap").Studies have used a variety of classification criteria for rhupus of which a combination of the latest classification criteria for RA and lupus along with positive anti-cyclic citrullinated peptide, anti-Smith, and anti-dsDNA antibodies seem most relevant. The majority of rhupus cohorts report the onset of the disease asRA (two-thirds of rhupus patients) followed by the development of features of lupusat an average interval of 3-11.3years. The radiographic features and distribution of erosions are similar to RA. However, ultrasonography and MRI reveal erosions in pure lupus relatedarthritis as well. This makes the reliability of radiologic tools for the evaluation of rhupus supportive at the most. Extra-articularfeatures in rhupus are mild with majororgan involvement in the form of neuropsychiatriclupus and lupus nephritis beingrare. We have further discussed the fallacies of the variousclassification criteria and proposed a theme for classifying rhupus which needs to be tested and validated in future studies. Our current state of understanding supports rhupus as an overlap of SLE and RA with articular disease similar to RA with the extra-articular disease being milder than SLE. Developing standardized classification criteria for rhupus will help in the early diagnosis and prevention of articular damagein patients with rhupus.