Clinical Radiology Research Articles

Rogue AI: Cautionary Cases in Neuroradiology and What We Can Learn From Them.

Introduction In recent years, artificial intelligence (AI) in medical imaging has undergone unprecedented innovation and advancement, sparking a revolutionary transformation in healthcare. The field of radiology is particularly implicated, as clinical radiologists are expected to interpret an ever-increasing number of complex cases in record time. Machine learning software purchased by our institution is expected to help our radiologists come to a more prompt diagnosis by delivering point-of-care quantitative analysis of suspicious findings and streamlining clinical workflow. This paper explores AI's impact on neuroradiology, an area accounting for a substantial portion of recent radiology studies. We present a case series evaluating an AI software's performance in detecting neurovascular findings, highlighting five cases where AI interpretations differed from radiologists' assessments. Our study underscores common pitfalls of AI in the context of CT head angiograms, aiming to guide future AI algorithms. Methods We conducted a retrospective case series study at Stony Brook University Hospital, a large medical center in Stony Brook, New York, spanning from October 1, 2021 to December 31, 2021, analyzing 140 randomly sampled CT angiograms using AI software. This software assessed various neurovascular parameters, and AI findings were compared with neuroradiologists' interpretations. Five cases with divergent interpretations were selected for detailed analysis. Results Five representative cases in which AI findings were discordant with radiologists' interpretations are presented with diagnoses including diffuse anoxic ischemic injury, cortical laminar necrosis, colloid cyst, right superficial temporal artery-to-middle cerebral artery(STA-MCA) bypass, and subacute bilateral subdural hematomas. Discussion The errors identified in our case series expose AI's limitations in radiology. Our case series reveals that AI's incorrect interpretations can stem from complexities in pathology, challenges in distinguishing densities, inability to identify artifacts, identifying post-surgical changes in normal anatomy, sensitivity limitations, and insufficient pattern recognition. AI's potential for improvement lies in refining its algorithms to effectively recognize and differentiate pathologies. Incorporating more diverse training datasets, multimodal data, deep-reinforcement learning, clinical context, and real-time learning capabilities are some ways to improve AI's performance in the field of radiology. Conclusion Overall, it is apparent that AI applications in radiology have much room for improvement before becoming more widely integrated into clinical workflows. While AI demonstrates remarkable potential to aid in diagnosis and streamline workflows, our case series highlights common pitfalls that underscore the need for continuous improvement. By refining algorithms, incorporating diverse datasets, embracing multimodal information, and leveraging innovative machine learning strategies, AI's diagnostic accuracy can be significantly improved.

ConTEXTual Net: A Multimodal Vision-Language Model for Segmentation of Pneumothorax.

Radiology narrative reports often describe characteristics of a patient's disease, including its location, size, and shape. Motivated by the recent success of multimodal learning, we hypothesized that this descriptive text could guide medical image analysis algorithms. We proposed a novel vision-language model, ConTEXTual Net, for the task of pneumothorax segmentation on chest radiographs. ConTEXTual Net extracts language features from physician-generated free-form radiology reports using a pre-trained language model. We then introduced cross-attention between the language features and the intermediate embeddings of an encoder-decoder convolutional neural network to enable language guidance for image analysis. ConTEXTual Net was trained on the CANDID-PTX dataset consisting of 3196 positive cases of pneumothorax with segmentation annotations from 6 different physicians as well as clinical radiology reports. Using cross-validation, ConTEXTual Net achieved a Dice score of 0.716±0.016, which was similar to the degree of inter-reader variability (0.712±0.044) computed on a subset of the data. It outperformed vision-only models (Swin UNETR: 0.670±0.015, ResNet50 U-Net: 0.677±0.015, GLoRIA: 0.686±0.014, and nnUNet 0.694±0.016) and a competing vision-language model (LAVT: 0.706±0.009). Ablation studies confirmed that it was the text information that led to the performance gains. Additionally, we show that certain augmentation methods degraded ConTEXTual Net's segmentation performance by breaking the image-text concordance. We also evaluated the effects of using different language models and activation functions in the cross-attention module, highlighting the efficacy of our chosen architectural design.

Clinical Radiology: Past, Present, and Future—Whither are We Going?

Clinical Radiology: Past, Present, and Future—Whither are We Going?

Detection of Brain Tumour in MRI Images using Deep Belief Network (DBN)

One of the world's deadliest illnesses is brain cancer. It is a cancer that often affects adults as much as children. It is the least likely species to survive, and its diversity is determined by its location, sweetness and structure. The negative effects will stem from the incorrect classification of the tumour brain. Therefore, determining the specific type and rank of the tumour in its early stages is required to select a specific treatment plan. A major concern is the elimination, segmentation and detection of tumour areas infected by magnetic resonance imaging (MRI). Despite the fact that it is a laborious and tedious task done by clinical experts or radiologists whose precision depends entirely on their experience. Computer-aided technology is becoming more and more important for circumventing these limitations. This study investigates a multi-layer Deep Belief Network (DBN) technique for MRI tumour detection. The proposed model is named as Brain Tumour Deep Belief Network (BT-DBN). The BT-DBN was tested with two datasets. The results demonstrate the importance of accuracy parameters relative to the most recent approaches. The results exhibit that the BT-DBN was effective in identifying different types of tumour tissue in MR images of the brain. The precision is 99.51%, the specificity is 94.28%, and the sensitivity is 98.72%.

Impact of Work Environment on Job Satisfaction among Interventional Radiologists in Japan: A Cross-sectional Study.

This study aims to measure job satisfaction among interventional radiology physicians in Japan and analyze the factors affecting job satisfaction. A web-based survey was conducted among the members of the Japanese Society of Interventional Radiology between October and December 2021. Participants were questioned regarding their job satisfaction, workplace, work status, and demographic information. Principal component analysis was applied to 15 reasons related to job satisfaction, and the factors affecting job satisfaction were analyzed. Valid responses were obtained from 901 (31.9%) of the 2,824 interventional radiology physicians invited to participate. Job satisfaction was reported as "very satisfied" in 79 (8.8%), "moderately satisfied" in 426 (47.3%), "neither satisfied nor dissatisfied" in 230 (25.5%), "moderately dissatisfied" in 133 (14.8%), and "very dissatisfied" in 33 (3.7%) respondents. Thus, there were 505 (56.0%) satisfied physicians. Three principal components were extracted from the reasons for job satisfaction. Job satisfaction tended to be higher among those who reported performing a higher number of interventional radiology procedures and was positively associated with a higher rate of work time dedicated to interventional radiology and the first principal component (the environment of clinical practice, research, and interventional radiology education). The third principal component (salary and work environment) and the absence of an "IkuBoss" [a boss who takes initiative in creating a work environment supportive of the work-life balance of colleagues] were associated with lower job satisfaction. More than half the participants reported high job satisfaction. Job satisfaction of interventional radiology physicians in Japan was positively associated with a favorable clinical, research, and educational environment and negatively associated with the absence of an "IkuBoss," noninterventional radiology work, overtime work, and salary.

The use of PET/MRI in radiotherapy.

Positron emission tomography/magnetic resonance imaging (PET/MRI) is a hybrid imaging technique that quantitatively combines the metabolic and functional data from positron emission tomography (PET) with anatomical and physiological information from MRI. As PET/MRI technology has advanced, its applications in cancer care have expanded. Recent studies have demonstrated that PET/MRI provides unique advantages in the field of radiotherapy and has become invaluable in guiding precision radiotherapy techniques. This review discusses the rationale and clinical evidence supporting the use of PET/MRI for radiation positioning, target delineation, efficacy evaluation, and patient surveillance.Critical relevance statement This article critically assesses the transformative role of PET/MRI in advancing precision radiotherapy, providing essential insights into improved radiation positioning, target delineation, efficacy evaluation, and patient surveillance in clinical radiology practice.Key points• The emergence of PET/MRI will be a key bridge for precise radiotherapy.• PET/MRI has unique advantages in the whole process of radiotherapy.• New tracers and nanoparticle probes will broaden the use of PET/MRI in radiation.• PET/MRI will be utilized more frequently for radiotherapy.

Development and Preliminary Validation of a Novel Convolutional Neural Network Model for Predicting Treatment Response in Patients with Unresectable Hepatocellular Carcinoma Receiving Hepatic Arterial Infusion Chemotherapy.

The goal of this study was to evaluate the performance of a convolutional neural network (CNN) with preoperative MRI and clinical factors in predicting the treatment response of unresectable hepatocellular carcinoma (HCC) patients receiving hepatic arterial infusion chemotherapy (HAIC). A total of 191 patients with unresectable HCC who underwent HAIC in our hospital between May 2019 and March 2022 were retrospectively recruited. We selected InceptionV4 from three representative CNN models, AlexNet, ResNet, and InceptionV4, according to the cross-entropy loss (CEL). We subsequently developed InceptionV4 to fuse the information from qualified pretreatment MRI data and patient clinical factors. Radiomic information was evaluated based on several constant sequences, including enhanced T1-weighted sequences (with arterial, portal, and delayed phases), T2 FSE sequences, and dual-echo sequences. The performance of InceptionV4 was cross-validated in the training cohort (n = 127) and internally validated in an independent cohort (n = 64), with comparisons against single important clinical factors and radiologists in terms of receiver operating characteristic (ROC) curves. Class activation mapping was used to visualize the InceptionV4 model. The InceptionV4 model achieved an AUC of 0.871 (95% confidence interval [CI] 0.761-0.981) in the cross-validation cohort and an AUC of 0.826 (95% CI 0.682-0.970) in the internal validation cohort; these two models performed better than did the other methods (AUC ranges 0.783-0.873 and 0.708-0.806 for cross- and internal validations, respectively; P < 0.01). The present InceptionV4 model, which integrates radiomic information and clinical factors, helps predict the treatment response of unresectable HCC patients receiving HAIC treatment.

Deep learning algorithm applied to plain CT images to identify superior mesenteric artery abnormalities

ObjectivesAtypical presentations, lack of biomarkers, and low sensitivity of plain CT can delay the diagnosis of superior mesenteric artery (SMA) abnormalities, resulting in poor clinical outcomes. Our study aims to develop a deep learning (DL) model for detecting SMA abnormalities in plain CT and evaluate its performance in comparison with a clinical model and radiologist assessment. Materials and MethodsA total of 1048 patients comprised the internal (474 patients with SMA abnormalities, 474 controls) and external testing (50 patients with SMA abnormalities, 50 controls) cohorts. The internal cohort was divided into the training cohort (n = 776), validation cohort (n = 86), and internal testing cohort (n = 86). A total of 5 You Only Look Once version 8 (YOLOv8)–based DL submodels were developed, and the performance of the optimal submodel was compared with that of a clinical model and of experienced radiologists. ResultsOf the submodels, YOLOv8x had the best performance. The area under the curve (AUC) of the YOLOv8x submodel was higher than that of the clinical model (internal test set: 0.990 vs 0.878, P =.002; external test set: 0.967 vs 0.912, P =.140) and that of all radiologists (P <.001). The YOLOv8x submodel, when compared with radiologist assessment, demonstrated higher sensitivity (internal test set: 100.0 % vs 70.7 %, P =.002; external test set: 96.0 % vs 68.8 %, P <.001) and specificity (internal test set: 90.7 % vs 66.0 %, P =.025; external test set: = 88.0 % vs 66.0 %, P <.001). ConclusionUsing plain CT images, YOLOv8x was able to efficiently identify cases of SMA abnormalities. This could potentially improve early diagnosis accuracy and thus improve clinical outcomes.

CT and MR Appearance of Teeth: Analysis of Anatomy and Embryology and Implications for Disease.

Abnormalities of dental development and anatomy may suggest the presence of congenital or acquired anomalies. The detection of abnormalities, therefore, is an important skill for radiologists to achieve. Knowledge of dental embryology and an understanding of the radiologic appearances of teeth at various stages of maturation are required for the appreciation of abnormal dental development. While many tooth abnormalities are well-depicted on dedicated dental radiographs, the first encounter with a dental anomaly may be by a radiologist on a computed tomographic (CT) or magnetic resonance (MR) exam performed for other reasons. This article depicts normal dental anatomy and development, describing the appearance of the neonatal dentition on CT and MRI, the modalities most often encountered by clinical radiologists. The radiology and dental literature are reviewed, and key concepts are illustrated with supplemental cases from our institution. The value of knowledge of dental development is investigated using the analysis of consecutive MR brain examinations. Finally, the anatomical principles are applied to the diagnosis of odontogenic infection on CT. Through analysis of the literature and case data, the contrast of dental pathology with normal anatomy and development facilitates the detection and characterization of both congenital and acquired dental disease.

Automated Detection of Cervical Spinal Stenosis and Cord Compression via Vision Transformer and Rules-Based Classification.

Cervical spinal cord compression, defined as spinal cord deformity and severe narrowing of the spinal canal in the cervical region, can lead to severe clinical consequences, including intractable pain, sensory disturbance, paralysis, and even death, and may require emergent intervention to prevent negative outcomes. Despite the critical nature of cord compression, no automated tool is available to alert clinical radiologists to the presence of such findings. This study aims to demonstrate the ability of a vision transformer (ViT) model for the accurate detection of cervical cord compression. A clinically diverse cohort of 142 cervical spine MRIs was identified, 34% of which were normal or had mild stenosis, 31% with moderate stenosis, and 35% with cord compression. Utilizing gradient-echo images, slices were labeled as no cord compression/mild stenosis, moderate stenosis, or severe stenosis/cord compression. Segmentation of the spinal canal was performed and confirmed by neuroradiology faculty. A pretrained ViT model was fine-tuned to predict section-level severity by using a train:validation:test split of 60:20:20. Each examination was assigned an overall severity based on the highest level of section severity, with an examination labeled as positive for cord compression if ≥1 section was predicted in the severe category. Additionally, 2 convolutional neural network (CNN) models (ResNet50, DenseNet121) were tested in the same manner. The ViT model outperformed both CNN models at the section level, achieving section-level accuracy of 82%, compared with 72% and 78% for ResNet and DenseNet121, respectively. ViT patient-level classification achieved accuracy of 93%, sensitivity of 0.90, positive predictive value of 0.90, specificity of 0.95, and negative predictive value of 0.95. Receiver operating characteristic area under the curve was greater for ViT than either CNN. This classification approach using a ViT model and rules-based classification accurately detects the presence of cervical spinal cord compression at the patient level. In this study, the ViT model outperformed both conventional CNN approaches at the section and patient levels. If implemented into the clinical setting, such a tool may streamline neuroradiology workflow, improving efficiency and consistency.

Radiation reduction for interventional radiology imaging: a video frame interpolation solution

PurposeThe aim of this study was to diminish radiation exposure in interventional radiology (IR) imaging while maintaining image quality. This was achieved by decreasing the acquisition frame rate and employing a deep neural network to interpolate the reduced frames.MethodsThis retrospective study involved the analysis of 1634 IR sequences from 167 pediatric patients (March 2014 to January 2022). The dataset underwent a random split into training and validation subsets (at a 9:1 ratio) for model training and evaluation. Our approach proficiently synthesized absent frames in simulated low-frame-rate sequences by excluding intermediate frames from the validation subset. Accuracy assessments encompassed both objective experiments and subjective evaluations conducted by nine radiologists.ResultsThe deep learning model adeptly interpolated the eliminated frames within IR sequences, demonstrating encouraging peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) results. The average PSNR values for angiographic, subtraction, and fluoroscopic modes were 44.94 dB, 34.84 dB, and 33.82 dB, respectively, while the corresponding SSIM values were 0.9840, 0.9194, and 0.7752. Subjective experiments conducted with experienced interventional radiologists revealed minimal discernible differences between interpolated and authentic sequences.ConclusionOur method, which interpolates low-frame-rate IR sequences, has shown the capability to produce high-quality IR images. Additionally, the model exhibits potential for reducing the frame rate during IR image acquisition, consequently mitigating radiation exposure.Critical relevance statementThis study presents a critical advancement in clinical radiology by demonstrating the effectiveness of a deep neural network in reducing radiation exposure during pediatric interventional radiology while maintaining image quality, offering a potential solution to enhance patient safety.Key points• Reducing radiation: cutting IR image to reduce radiation.• Accurate frame interpolation: our model effectively interpolates missing frames.• High visual quality in terms of PSNR and SSIM, making IR procedures safer without sacrificing quality.Graphical

Evaluation of clinical and imaging features for differentiating rhabdomyosarcoma from neuroblastoma in pediatric soft tissue.

In this study, we developed a nomogram predictive model based on clinical, CT, and MRI parameters to differentiate soft tissue rhabdomyosarcoma (RMS) from neuroblastoma (NB) in children preoperatively. A total of 103 children with RMS (n=37) and NB (n=66) were enrolled in the study from December 2012 to July 2023. The clinical and imaging data (assessed by two experienced radiologists) were analyzed using univariate analysis, and significant factors were further analyzed by multivariable logistic regression using the forward LR method to develop the clinical model, radiological model, and integrated nomogram model, respectively. The diagnostic performances, goodness of fit, and clinical utility of the integrated nomogram model were assessed using the area under the curve (AUC) of the receiver operator characteristics curve (ROC) with a 95% confidence interval (95% CI), calibration curve, and decision curve analysis (DCA) curves, respectively. Diagnostic efficacy between the model and radiologists' interpretations was examined. The median age at diagnosis in the RMS group was significantly older than the NB group (36.0 months vs. 14.5 months; P=0.003); the fever rates in RMS patients were significantly lower than in patients with NB (0.0% vs.16.7%; P=0.022), and the incidence of palpable mass was higher in patients with RMS compared with the NB patients (89.2% vs. 34.8%; P<0.001). Compare NB on image features: RMS occurred more frequently in the head and neck and displayed homogeneous density on non-enhanced CT than NB (48.6% vs. 9.1%; 35.3% vs. 13.8%, respectively; all P<0.05), and the occurrence of characteristics such as calcification, encasing vessels, and intraspinal tumor extension was significantly less frequent in RMS children compared to children with NB (18.9% vs. 84.8%; 13.5% vs. 34.8%; 2.7% vs. 50.0%, respectively; all P <0.05). Two, three, and four features were identified as independent parameters by multivariate logistic regression analysis to develop the clinical, radiological, and integrated nomogram models, respectively. The AUC value (0.962), calibration curve, and DCA showed that the integrated nomogram model may provide better diagnostic performance, good agreement, and greater clinical net benefits than the clinical model, radiological model, and radiologists' subjective diagnosis. The clinical and imaging features-based nomogram has potential for helping radiologists distinguish between pediatric soft tissue RMS and NB patients preoperatively, and reduce unnecessary interventions.

Vision-Language Model for Generating Textual Descriptions From Clinical Images: Model Development and Validation Study.

The automatic generation of radiology reports, which seeks to create a free-text description from a clinical radiograph, is emerging as a pivotal intersection between clinical medicine and artificial intelligence. Leveraging natural language processing technologies can accelerate report creation, enhancing health care quality and standardization. However, most existing studies have not yet fully tapped into the combined potential of advanced language and vision models. The purpose of this study was to explore the integration of pretrained vision-language models into radiology report generation. This would enable the vision-language model to automatically convert clinical images into high-quality textual reports. In our research, we introduced a radiology report generation model named ClinicalBLIP, building upon the foundational InstructBLIP model and refining it using clinical image-to-text data sets. A multistage fine-tuning approach via low-rank adaptation was proposed to deepen the semantic comprehension of the visual encoder and the large language model for clinical imagery. Furthermore, prior knowledge was integrated through prompt learning to enhance the precision of the reports generated. Experiments were conducted on both the IU X-RAY and MIMIC-CXR data sets, with ClinicalBLIP compared to several leading methods. Experimental results revealed that ClinicalBLIP obtained superior scores of 0.570/0.365 and 0.534/0.313 on the IU X-RAY/MIMIC-CXR test sets for the Metric for Evaluation of Translation with Explicit Ordering (METEOR) and the Recall-Oriented Understudy for Gisting Evaluation (ROUGE) evaluations, respectively. This performance notably surpasses that of existing state-of-the-art methods. Further evaluations confirmed the effectiveness of the multistage fine-tuning and the integration of prior information, leading to substantial improvements. The proposed ClinicalBLIP model demonstrated robustness and effectiveness in enhancing clinical radiology report generation, suggesting significant promise for real-world clinical applications.

Gallbladder tuberculosis: A rare case report with review of literature

Gallbladder tuberculosis (TB) is a rare disease, and it might be challenging to distinguish it from gallbladder cancer on clinical history and radiology. It frequently mimics carcinoma in patients who initially appear with a gallbladder mass. Gallbladder TB is only identified after histology of the resected specimen since radiography lacks pathognomic characteristics. Here, we describe a unique case of gallbladder TB that was incidentally identified when a 49-year-old lady was being evaluated for suspected gallbladder cancer. Histology of the gallbladder exhibits necrotizing granulomatous inflammation with the presence of numerous pink-colored, curved, and beaded acid-fast bacilli that were recognized on the Ziehl-Neelsen stain.

Abstract B074: Clinical inference of location and trajectory of pancreatic cancer from radiology reports using zero-shot LLM

Abstract Importance: Recent breakthroughs in Large Language models (LLM) have shown impressive reasoning capabilities. Inferring disease trajectory from radiology reports is a central task in clinical oncology, and radiographic interpretation of disease state and treatment benefits in pancreas cancer can be particularly challenging. We assess the performance of LLMs (GPT3.5-turbo and GPT4) to infer disease status, response to treatment, and location of disease for patients with pancreatic adenocarcinoma from clinical radiology reports. We also assess the ability of LLMs to extrapolate from objective findings, vs. their reliance on radiologist’s summaries. Experimental Design: We used 200 deidentified radiology reports from pancreatic cancer patients at different stages of treatment and submitted these reports to the GPT3.5 and GPT4 models via an Microsoft Azure HIPAA compliant instance. We assess the reasoning capabilities of these two models in the three independent tasks in pancreatic cancer imaging. 1) disease status/response to treatment, 2) disease location, and 3) presence of indeterminate nodules requiring further follow up. Evaluation of response was compared to a medical oncologist’s interpretation of each report. A second medical oncologist served as adjudicator for discrepancies between human and GPT models and rates of data fabrication. We also assessed importance of Radiologists summaries vs Objective finding sections, as well as different prompt engineering approaches. Results: We found a maximum performance of 71% and 85% of GPT3.5 and GPT4 respectively when asked to classify radiology reports into seven categories of malignancy presence and trajectory, as compared to a medical oncologist’s interpretation. This accuracy was strongly dependent on requesting the model demonstrate its reasoning process before providing an answer; though this dependency was abrogated by providing the Radiologist’s impression section. We also found the main source of mis-classification was incongruence between reasoning and the final classification (as opposed to incorrect medical reasoning). Finally, we showed that GPT4 performs strongly on identifying specific organ sites of disease, as well as presence of indeterminate findings requiring further follow up. Conclusion: GPT algorithms accurately interpret multiple clinically relevant features in radiology reports for Pancreatic adenocarcinoma patients. Precision improved markedly with GPT 4 compared to GPT-3.5. This suggests GPT-based tools are potential valuable clinical allies in interpreting radiologist-produced text and could be valuable aids in cohort identification for large scale real-world data research and eventually clinical management support. Citation Format: Travis Ian Zack, Madhumita Sushil, Brenda Miao, Arda Demirci, Corynn Kasap, Margaret Tempero, Atul Butte, Eric Collisson. Clinical inference of location and trajectory of pancreatic cancer from radiology reports using zero-shot LLM [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Pancreatic Cancer; 2023 Sep 27-30; Boston, Massachusetts. Philadelphia (PA): AACR; Cancer Res 2024;84(2 Suppl):Abstract nr B074.

Crop filling: A pipeline for repairing memory clinic MRI corrupted by partial brain coverage

Data-driven solutions offer great promise for improving healthcare. However, standard clinical neuroimaging data is subject to real-world imaging artefacts that can render the data unusable for computational research and quantitative neuroradiology. T1 weighted structural MRI is used in dementia research to obtain volumetric measurements from cortical and subcortical brain regions. However, clinical radiologists often prioritise T2 weighted or FLAIR scans for visual assessment. As such, T1 weighted scans are often acquired but may not be a priority, resulting in artefacts such as partial brain coverage being systematically present in memory clinic data.Here we present “MRI Crop Filling”, a pipeline to replace the missing T1 data with synthetic data generated from the T2 scan, making real-world clinical T1 data usable for computational research including the latest AI innovations. Our method consists of the following steps:•Register scans: T2 and (cropped) T1.•Synthesise a new T1 using an open source deep learning tool.•Replace missing (cropped) T1 data in original T1 scan and super-resolve to improve image quality.

Pediatric intracranial empyema complicating otogenic and sinogenic infection

ObjectiveTo describe and compare clinical and microbiological features, surgical and medical management, and outcomes of children with otogenic and sinogenic intracranial empyema (IE) in an institution with an established multidisciplinary protocol. To use the study findings to inform and update the institutional algorithm. MethodsRetrospective analysis was carried out on the electronic healthcare records of all children with oto-sinogenic IE admitted in a 5-year period. ResultsA total of 76 patients were identified and treated according to an institutional protocol. Two distinct groups were identified: intracranial empyema related to otogenic infection (OI-IE, n = 36) or sinogenic infection (SI-IE, n = 40). SI-IE was seen in older children and had a significantly higher morbidity. Sub-dural IE was seen in a minority (n = 16) and only in SI-IE and required urgent collaborative ENT-neurosurgery. Extra-dural IE occurred more frequently and was seen in both SI-IE and OI-IE. No death and overall low morbidity were observed. Particularities found in SI-IE and OI-IE groups (as thrombosis, microbiology, antibiotic treatment, duration and outcome) permitted the delineation of these groups in our updated algorithm. ConclusionThe presence of a collaborative multidisciplinary protocol permits the step-wise co-ordination of care for these complex patients in our institution. All patients received prompt imaging, urgent surgical intervention, and antibiotic treatment. Microbiological identification was possible for each patient and antibiotic rationalization was permitted through use of Polymerase chain reaction (PCR) testing in cases of sterile cultures. Of note, intracranial empyema related to sinogenic infection is shown to have significantly more severe clinical presentation, a higher morbidity, and a longer duration of antibiotic therapy than that related to otogenic infection. Study findings allowed for the update and clarification of the institutional protocol, which now clearly demarcates the clinical presentation, biological evidence, radiology, surgical and medical treatments in children with oto-sinogenic IE.

Position Statements of the Emerging Trends Committee of the Asian Oceanian Society of Radiology on the Adoption and Implementation of Artificial Intelligence for Radiology.

Artificial intelligence (AI) is rapidly gaining recognition in the radiology domain as a greater number of radiologists are becoming AI-literate. However, the adoption and implementation of AI solutions in clinical settings have been slow, with points of contention. A group of AI users comprising mainly clinical radiologists across various Asian countries, including India, Japan, Malaysia, Singapore, Taiwan, Thailand, and Uzbekistan, formed the working group. This study aimed to draft position statements regarding the application and clinical deployment of AI in radiology. The primary aim is to raise awareness among the general public, promote professional interest and discussion, clarify ethical considerations when implementing AI technology, and engage the radiology profession in the ever-changing clinical practice. These position statements highlight pertinent issues that need to be addressed between care providers and care recipients. More importantly, this will help legalize the use of non-human instruments in clinical deployment without compromising ethical considerations, decision-making precision, and clinical professional standards. We base our study on four main principles of medical care-respect for patient autonomy, beneficence, non-maleficence, and justice.

How AI May Transform Musculoskeletal Imaging.

While musculoskeletal imaging volumes are increasing, there is a relative shortage of subspecialized musculoskeletal radiologists to interpret the studies. Will artificial intelligence (AI) be the solution? For AI to be the solution, the wide implementation of AI-supported data acquisition methods in clinical practice requires establishing trusted and reliable results. This implementation will demand close collaboration between core AI researchers and clinical radiologists. Upon successful clinical implementation, a wide variety of AI-based tools can improve the musculoskeletal radiologist's workflow by triaging imaging examinations, helping with image interpretation, and decreasing the reporting time. Additional AI applications may also be helpful for business, education, and research purposes if successfully integrated into the daily practice of musculoskeletal radiology. The question is not whether AI will replace radiologists, but rather how musculoskeletal radiologists can take advantage of AI to enhance their expert capabilities.

Could ChatGPT Pass the UK Radiology Fellowship Examinations?

Chat Generative Pre-trained Transformer (ChatGPT) is an artificial intelligence (AI) tool which utilises machine learning to generate original text resembling human language. AI models have recently demonstrated remarkable ability at analysing and solving problems, including passing professional examinations. We investigate the performance of ChatGPT on some of the UK radiology fellowship equivalent examination questions. ChatGPT was asked to answer questions from question banks resembling the Fellowship of the Royal College of Radiologists (FRCR) examination. The entire physics part 1 question bank (203 5-part true/false questions) was answered by the GPT-4 model and answers recorded. 240 single best answer questions (SBAs) (representing the true length of the FRCR 2A examination) were answered by both GPT-3.5 and GPT-4 models. ChatGPT 4 answered 74.8% of part 1 true/false statements correctly. The spring 2023 passing mark of the part 1 examination was 75.5% and ChatGPT thus narrowly failed. In the 2A examination, ChatGPT 3.5 answered 50.8% SBAs correctly, while GPT-4 answered 74.2% correctly. The winter 2022 2A pass mark was 63.3% and thus GPT-4 clearly passed. AI models such as ChatGPT are able to answer the majority of questions in an FRCR style examination. It is reasonable to assume that further developments in AI will be more likely to succeed in comprehending and solving questions related to medicine, specifically clinical radiology. Our findings outline the unprecedented capabilities of AI, adding to the current relatively small body of literature on the subject, which in turn can play a role medical training, evaluation and practice. This can undoubtedly have implications for radiology.