Artificial Intelligence in Emergency Radiology: Where Are We Going?

[Applications of artificial intelligence in radiology]

BACKGROUND

Artificial intelligence (AI) is increasingly finding its way into routine radiological work.

OBJECTIVE

Presentation of the current advances and applications of AI along the entire radiological patient journey.

METHODS

Systematic literature review of established AI techniques and current research projects, with reference to consensus recommendations.

RESULTS

The applications of AI in radiology cover a wide range, starting with AI-supported scheduling and indications assessment, extending to AI-enhanced image acquisition and reconstruction techniques that have the potential to reduce radiation doses in computed tomography (CT) or acquisition times in magnetic resonance imaging (MRI), while maintaining comparable image quality. These include computer-aided detection and diagnosis, such as fracture recognition or nodule detection. Additionally, methods such as worklist prioritization and structured reporting facilitated by large language models enable a rethinking of the reporting process. The use of AI promises to increase the efficiency of all steps of the radiology workflow and an improved diagnostic accuracy. To achieve this, seamless integration into technical workflows and proven evidence of AI systems are necessary.

CONCLUSION

Applications of AI have the potential to profoundly influence the role of radiologists in the future.

Assessing the Performance of Artificial Intelligence Models: Insights from the American Society of Functional Neuroradiology Artificial Intelligence Competition

BACKGROUND AND PURPOSE

Artificial intelligence models in radiology are frequently developed and validated using data sets from a single institution and are rarely tested on independent, external data sets, raising questions about their generalizability and applicability in clinical practice. The American Society of Functional Neuroradiology (ASFNR) organized a multicenter artificial intelligence competition to evaluate the proficiency of developed models in identifying various pathologies on NCCT, assessing age-based normality and estimating medical urgency.

MATERIALS AND METHODS

In total, 1201 anonymized, full-head NCCT clinical scans from 5 institutions were pooled to form the data set. The data set encompassed studies with normal findings as well as those with pathologies, including acute ischemic stroke, intracranial hemorrhage, traumatic brain injury, and mass effect (detection of these, task 1). NCCTs were also assessed to determine if findings were consistent with expected brain changes for the patient's age (task 2: age-based normality assessment) and to identify any abnormalities requiring immediate medical attention (task 3: evaluation of findings for urgent intervention). Five neuroradiologists labeled each NCCT, with consensus interpretations serving as the ground truth. The competition was announced online, inviting academic institutions and companies. Independent central analysis assessed the performance of each model. Accuracy, sensitivity, specificity, positive and negative predictive values, and receiver operating characteristic (ROC) curves were generated for each artificial intelligence model, along with the area under the ROC curve.

RESULTS

Four teams processed 1177 studies. The median age of patients was 62 years, with an interquartile range of 33 years. Nineteen teams from various academic institutions registered for the competition. Of these, 4 teams submitted their final results. No commercial entities participated in the competition. For task 1, areas under the ROC curve ranged from 0.49 to 0.59. For task 2, two teams completed the task with area under the ROC curve values of 0.57 and 0.52. For task 3, teams had little-to-no agreement with the ground truth.

CONCLUSIONS

To assess the performance of artificial intelligence models in real-world clinical scenarios, we analyzed their performance in the ASFNR Artificial Intelligence Competition. The first ASFNR Competition underscored the gap between expectation and reality; and the models largely fell short in their assessments. As the integration of artificial intelligence tools into clinical workflows increases, neuroradiologists must carefully recognize the capabilities, constraints, and consistency of these technologies. Before institutions adopt these algorithms, thorough validation is essential to ensure acceptable levels of performance in clinical settings.

Applications of artificial intelligence in computed tomography imaging for phenotyping pulmonary hypertension

PURPOSE OF REVIEW

Pulmonary hypertension is a heterogeneous condition with significant morbidity and mortality. Computer tomography (CT) plays a central role in determining the phenotype of pulmonary hypertension, informing treatment strategies. Many artificial intelligence tools have been developed in this modality for the assessment of pulmonary hypertension. This article reviews the latest CT artificial intelligence applications in pulmonary hypertension and related diseases.

RECENT FINDINGS

Multistructure segmentation tools have been developed in both pulmonary hypertension and nonpulmonary hypertension cohorts using state-of-the-art UNet architecture. These segmentations correspond well with those of trained radiologists, giving clinically valuable metrics in significantly less time. Artificial intelligence lung parenchymal assessment accurately identifies and quantifies lung disease patterns by integrating multiple radiomic techniques such as texture analysis and classification. This gives valuable information on disease burden and prognosis. There are many accurate artificial intelligence tools to detect acute pulmonary embolism. Detection of chronic pulmonary embolism proves more challenging with further research required.

SUMMARY

There are numerous artificial intelligence tools being developed to identify and quantify many clinically relevant parameters in both pulmonary hypertension and related disease cohorts. These potentially provide accurate and efficient clinical information, impacting clinical decision-making.

Diagnostic performance of an AI algorithm for the detection of appendicular bone fractures in pediatric patients

PURPOSE

To evaluate the diagnostic performance of an Artificial Intelligence (AI) algorithm, previously trained using both adult and pediatric patients, for the detection of acute appendicular fractures in the pediatric population on conventional X-ray radiography (CXR).

MATERIALS AND METHODS

In this retrospective study, anonymized extremities CXRs of pediatric patients (age <17 years), with or without fractures, were included. Six hundred CXRs (maintaining the positive-for-fracture and negative-for-fracture balance) were included, grouping them per body part (shoulder/clavicle, elbow/upper arm, hand/wrist, leg/knee, foot/ankle). Follow-up CXRs and/or second-level imaging were considered as reference standard. A deep learning algorithm interpreted CXRs for fracture detection on a per-patient, per-radiograph, and per-location level, and its diagnostic performance values were compared with the reference standard. AI diagnostic performance was computed by using cross-tables, and 95 % confidence intervals [CIs] were obtained by bootstrapping.

RESULTS

The final cohort included 312 male and 288 female with a mean age of 8.9±4.5 years. Three undred CXRs (50 %) were positive for fractures, according to the reference standard. For all fractures, the AI tool showed a per-patient 91.3% (95%CIs = 87.6-94.3) sensitivity, 76.7% (71.5-81.3) specificity, and 84% (82.1-86.0) accuracy. In the per-radiograph analysis the AI tool showed 85% (81.9-87.8) sensitivity, 88.5% (86.3-90.4) specificity, and 87.2% (85.7-89.6) accuracy. In the per-location analysis, the AI tool identified 606 bounding boxes: 472 (77.9 %) were correct, 110 (18.1 %) incorrect, and 24 (4.0 %) were not-overlapping.

CONCLUSION

The AI algorithm provides good overall diagnostic performance for detecting appendicular fractures in pediatric patients.

Emergency Radiology in the First 24 h of Two Major Earthquakes on the Same Day and Radiologic Evaluation of Trauma Cases

BACKGROUND

On 6 February 2023, two major earthquakes occurred in Turkey on the same day. More than 50,000 people died, and more than 100,000 people were injured in these earthquakes. The aim of this study is to contribute to disaster management plans by evaluating the functioning of a radiology department and the imaging examinations performed after this disaster.

METHODS

The functioning of the radiology clinic at Malatya Training and Research Hospital in the first 24 h after the earthquake was evaluated. The images of 596 patients who were admitted to Malatya Training and Research Hospital for earthquake-related trauma between 6 February 2023, at 4:17 a.m. and 7 February 2023, at 4:17 a.m., and who underwent radiography and computed tomography (CT) were retrospectively reviewed.

RESULTS

The mean age of the patients was 37.3 ± 20.1 years. A total of 313 (52.5%) patients were male. The most frequently performed imaging test was a CT scan. In total, 437 (73.3%) of 596 patients underwent a CT scan. At least one body part was affected in 160 patients (26.8%). The most commonly affected regions were the thorax, vertebrae, and extremities. Thoracic findings were observed in 52 patients (32.5%), vertebral findings in 52 patients (32.5%), and extremity findings in 46 patients (28.7%). Fractures were the most common finding in our study. Of the 160 patients with pathologic findings, 139 (86.9%) had evidence of fractures.

CONCLUSIONS

The role of radiology in disasters is important. When disaster preparedness plans are made, radiology departments should be actively involved in these plans. This will ensure the quick and efficient functioning of radiology departments.

GPT-4 Vision: Multi-Modal Evolution of ChatGPT and Potential Role in Radiology

GPT-4 Vision (GPT-4V) represents a significant advancement in multimodal artificial intelligence, enabling text generation from images without specialized training. This marks the transformation of ChatGPT as a large language model (LLM) into GPT-4's promised large multimodal model (LMM). As these AI models continue to advance, they may enhance radiology workflow and aid with decision support. This technical note explores potential GPT-4V applications in radiology and evaluates performance for sample tasks. GPT-4V capabilities were tested using images from the web, personal and institutional teaching files, and hand-drawn sketches. Prompts evaluated scientific figure analysis, radiologic image reporting, image comparison, handwriting interpretation, sketch-to-code, and artistic expression. In this limited demonstration of GPT-4V's capabilities, it showed promise in classifying images, counting entities, comparing images, and deciphering handwriting and sketches. However, it exhibited limitations in detecting some fractures, discerning a change in size of lesions, accurately interpreting complex diagrams, and consistently characterizing radiologic findings. Artistic expression responses were coherent. WhileGPT-4V may eventually assist with tasks related to radiology, current reliability gaps highlight the need for continued training and improvement before consideration for any medical use by the general public and ultimately clinical integration. Future iterations could enable a virtual assistant to discuss findings, improve reports, extract data from images, provide decision support based on guidelines, white papers, and appropriateness criteria. Human expertise remain essential for safe practice and partnerships between physicians, researchers, and technology leaders are necessary to safeguard against risks like bias and privacy concerns.

Developing a Nomogram for Predicting Surgical Intervention in Pediatric Intussusception After Pneumatic Reduction: A Multicenter Study from China

Purpose

The objective of this study was to develop and validate a nomogram for predicting the need for surgical intervention in pediatric intussusception after pneumatic reduction.

Patients and Methods

This retrospective study analyzed the clinical data of children with acute intussusception admitted to four hospitals in China from January 2019 to January 2022. Based on the results of pneumatic reduction, the patients were divided into two groups: the successful reduction group (control group) and the failed reduction group (operation group). The total sample was randomly divided into a training set and a validation set in a 7:3 ratio. Logistic regression analysis was performed to establish a predictive model for surgical risk.

Results

A total of 1041 samples were included in this study, with 852 in the control group and 189 in the operation group. Among the total sample, 728 cases were used for training and 313 cases were used for validation. Logistic regression analysis of the training set identified age, time of abdominal pain, presence or absence of hematostoecia, C-reactive protein value from blood test on admission, and nested position indicated by B-ultrasound as independent predictors of intussusception intervention. Based on the five independent risk factors identified through multivariate logistic regression, a nomogram was successfully constructed to predict the failure of resetting by air enema under X-ray.

Conclusion

A nomogram was developed to predict the need for surgical intervention after intussusception pneumatic reduction in children. The nomogram was based on clinical risk factors including age, time of abdominal pain, presence or absence of blood in stool, value of C-reactive protein in blood test on admission, and nested position indicated by B-ultrasound. Our internal validation demonstrated that this nomogram can serve as a useful tool for identifying risk factors associated with failure of air enema in children with intussusception.

The Competency of Emergency Medicine Residents in Interpreting Hand X-rays Across the Three Major Regions of Saudi Arabia

Background Interpreting hand X-rays is crucial for emergency medicine residents to accurately diagnose traumatic injuries and conditions affecting the hand. This study aimed to assess the competency of emergency medicine residents in interpreting hand X-rays across three major regions in Saudi Arabia. Methodology We conducted a cross-sectional study involving 100 emergency medicine residents from the Central, Eastern, and Western regions of Saudi Arabia. Participants were presented with 10 clinical case scenarios each accompanied by hand X-rays and were asked to provide their interpretations. Assessment scores were calculated based on the proportion of correct answers for each case. Results Half of the participants (50 residents) fell within the age range of 25 to 27 years, with 61 male and 39 female participants, respectively. Residents in the third year of training (R3) exhibited the highest mean score of 74.83% ± 20.46%. Participants using desktops to view the images achieved the highest mean score of 75% ± 10.49% compared to those using smartphones or tablets. Significant associations were found between age (F = 4.072, p = 0.020), training level (F = 3.161, p = 0.028), and choice of viewing device (F = 7.811, p = 0.001) and assessment scores. Conclusions Our study highlighted that emergency medicine residents in Saudi Arabia demonstrate competent proficiency in interpreting hand X-rays, with higher competency observed among senior residents (R3 and R4), those aged 28 to 30 years, and those using desktops for image viewing.

Combining Non-Contrast CT Signs With Onset-to-Imaging Time to Predict the Evolution of Intracerebral Hemorrhage

OBJECTIVE

This study aimed to determine the predictive performance of non-contrast CT (NCCT) signs for hemorrhagic growth after intracerebral hemorrhage (ICH) when stratified by onset-to-imaging time (OIT).

MATERIALS AND METHODS

1488 supratentorial ICH within 6 h of onset were consecutively recruited from six centers between January 2018 and August 2022. NCCT signs were classified according to density (hypodensities, swirl sign, black hole sign, blend sign, fluid level, and heterogeneous density) and shape (island sign, satellite sign, and irregular shape) features. Multivariable logistic regression was used to evaluate the association between NCCT signs and three types of hemorrhagic growth: hematoma expansion (HE), intraventricular hemorrhage growth (IVHG), and revised HE (RHE). The performance of the NCCT signs was evaluated using the positive predictive value (PPV) stratified by OIT.

RESULTS

Multivariable analysis showed that hypodensities were an independent predictor of HE (adjusted odds ratio [95% confidence interval] of 7.99 [4.87-13.40]), IVHG (3.64 [2.15-6.24]), and RHE (7.90 [4.93-12.90]). Similarly, OIT (for a 1-h increase) was an independent inverse predictor of HE (0.59 [0.52-0.66]), IVHG (0.72 [0.64-0.81]), and RHE (0.61 [0.54-0.67]). Blend and island signs were independently associated with HE and RHE (10.60 [7.36-15.30] and 10.10 [7.10-14.60], respectively, for the blend sign and 2.75 [1.64-4.67] and 2.62 [1.60-4.30], respectively, for the island sign). Hypodensities demonstrated low PPVs of 0.41 (110/269) or lower for IVHG when stratified by OIT. When OIT was ≤ 2 h, the PPVs of hypodensities, blend sign, and island sign for RHE were 0.80 (215/269), 0.90 (142/157), and 0.83 (103/124), respectively.

CONCLUSION

Hypodensities, blend sign, and island sign were the best NCCT predictors of RHE when OIT was ≤ 2 h. NCCT signs may assist in earlier recognition of the risk of hemorrhagic growth and guide early intervention to prevent neurological deterioration resulting from hemorrhagic growth.

Artificial Intelligence in Optimizing the Functioning of Emergency Departments; a Systematic Review of Current Solutions

Introduction

The burgeoning burden on emergency departments is a global challenge that we have been confronting for many years. Emerging artificial intelligence (AI)-based solutions may constitute a critical component in the optimization of these units. This systematic review was conducted to thoroughly examine and summarize the currently available AI solutions, assess potential benefits from their implementation, and identify anticipated directions of further development in this fascinating and rapidly evolving field.

Methods

This systematic review utilized data compiled from three key scientific databases: PubMed (2045 publications), Scopus (877 publications), and Web of Science (2495 publications). After meticulous removal of duplicates, we conducted a detailed analysis of 2052 articles, including 147 full-text papers. From these, we selected 51 of the most pertinent and representative publications for the review.

Results

Overall the present research indicates that due to high accuracy and sensitivity of machine learning (ML) models it's reasonable to use AI in support of doctors as it can show them the potential diagnosis, which could save time and resources. However, AI-generated diagnoses should be verified by a doctor as AI is not infallible.

Conclusions

Currently available AI algorithms are capable of analysing complex medical data with unprecedented precision and speed. Despite AI's vast potential, it is still a nascent technology that is often perceived as complicated and challenging to implement. We propose that a pivotal point in effectively harnessing this technology is the close collaboration between medical professionals and AI experts. Future research should focus on further refining AI algorithms, performing comprehensive validation, and introducing suitable legal regulations and standard procedures, thereby fully leveraging the potential of AI to enhance the quality and efficiency of healthcare delivery.

Adoption of AI in Oncological Imaging: Ethical, Regulatory, and Medical-Legal Challenges

Artificial Intelligence (AI) algorithms have shown great promise in oncological imaging, outperforming or matching radiologists in retrospective studies, signifying their potential for advanced screening capabilities. These AI tools offer valuable support to radiologists, assisting them in critical tasks such as prioritizing reporting, early cancer detection, and precise measurements, thereby bolstering clinical decision-making. With the healthcare landscape witnessing a surge in imaging requests and a decline in available radiologists, the integration of AI has become increasingly appealing. By streamlining workflow efficiency and enhancing patient care, AI presents a transformative solution to the challenges faced by oncological imaging practices. Nevertheless, successful AI integration necessitates navigating various ethical, regulatory, and medical-legal challenges. This review endeavors to provide a comprehensive overview of these obstacles, aiming to foster a responsible and effective implementation of AI in oncological imaging.

Radiomics and Artificial Intelligence in Renal Lesion Assessment

Radiomics, the extraction and analysis of quantitative features from medical images, has emerged as a promising field in radiology with the potential to revolutionize the diagnosis and management of renal lesions. This comprehensive review explores the radiomics workflow, including image acquisition, feature extraction, selection, and classification, and highlights its application in differentiating between benign and malignant renal lesions. The integration of radiomics with artificial intelligence (AI) techniques, such as machine learning and deep learning, can help patients' management and allow the planning of the appropriate treatments. AI models have shown remarkable accuracy in predicting tumor aggressiveness, treatment response, and patient outcomes. This review provides insights into the current state of radiomics and AI in renal lesion assessment and outlines future directions for research in this rapidly evolving field.

Diagnostic Accuracy and Performance Analysis of a Scanner-Integrated Artificial Intelligence Model for the Detection of Intracranial Hemorrhages in a Traumatology Emergency Department

Intracranial hemorrhages require an immediate diagnosis to optimize patient management and outcomes, and CT is the modality of choice in the emergency setting. We aimed to evaluate the performance of the first scanner-integrated artificial intelligence algorithm to detect brain hemorrhages in a routine clinical setting. This retrospective study includes 435 consecutive non-contrast head CT scans. Automatic brain hemorrhage detection was calculated as a separate reconstruction job in all cases. The radiological report (RR) was always conducted by a radiology resident and finalized by a senior radiologist. Additionally, a team of two radiologists reviewed the datasets retrospectively, taking additional information like the clinical record, course, and final diagnosis into account. This consensus reading served as a reference. Statistics were carried out for diagnostic accuracy. Brain hemorrhage detection was executed successfully in 432/435 (99%) of patient cases. The AI algorithm and reference standard were consistent in 392 (90.7%) cases. One false-negative case was identified within the 52 positive cases. However, 39 positive detections turned out to be false positives. The diagnostic performance was calculated as a sensitivity of 98.1%, specificity of 89.7%, positive predictive value of 56.7%, and negative predictive value (NPV) of 99.7%. The execution of scanner-integrated AI detection of brain hemorrhages is feasible and robust. The diagnostic accuracy has a high specificity and a very high negative predictive value and sensitivity. However, many false-positive findings resulted in a relatively moderate positive predictive value.

A Deep Learning Model Based on Capsule Networks for COVID Diagnostics through X-ray Images

X-ray diagnostics are widely used to detect various diseases, such as bone fracture, pneumonia, or intracranial hemorrhage. This method is simple and accessible in most hospitals, but requires an expert who is sometimes unavailable. Today, some diagnoses are made with the help of deep learning algorithms based on Convolutional Neural Networks (CNN), but these algorithms show limitations. Recently, Capsule Networks (CapsNet) have been proposed to overcome these problems. In our work, CapsNet is used to detect whether a chest X-ray image has disease (COVID or pneumonia) or is healthy. An improved model called DRCaps is proposed, which combines the advantage of CapsNet and the dilation rate (dr) parameter to manage images with 226 × 226 resolution. We performed experiments with 16,669 chest images, in which our model achieved an accuracy of 90%. Furthermore, the model size is 11M with a reconstruction stage, which helps to avoid overfitting. Experiments show how the reconstruction stage works and how we can avoid the max-pooling operation for networks with a stride and dilation rate to downsampling the convolution layers. In this paper, DRCaps is superior to other comparable models in terms of accuracy, parameters, and image size handling. The main idea is to keep the model as simple as possible without using data augmentation or a complex preprocessing stage.

Artificial Intelligence in Lung Cancer Screening: The Future Is Now

Lung cancer has one of the worst morbidity and fatality rates of any malignant tumour. Most lung cancers are discovered in the middle and late stages of the disease, when treatment choices are limited, and patients' survival rate is low. The aim of lung cancer screening is the identification of lung malignancies in the early stage of the disease, when more options for effective treatments are available, to improve the patients' outcomes. The desire to improve the efficacy and efficiency of clinical care continues to drive multiple innovations into practice for better patient management, and in this context, artificial intelligence (AI) plays a key role. AI may have a role in each process of the lung cancer screening workflow. First, in the acquisition of low-dose computed tomography for screening programs, AI-based reconstruction allows a further dose reduction, while still maintaining an optimal image quality. AI can help the personalization of screening programs through risk stratification based on the collection and analysis of a huge amount of imaging and clinical data. A computer-aided detection (CAD) system provides automatic detection of potential lung nodules with high sensitivity, working as a concurrent or second reader and reducing the time needed for image interpretation. Once a nodule has been detected, it should be characterized as benign or malignant. Two AI-based approaches are available to perform this task: the first one is represented by automatic segmentation with a consequent assessment of the lesion size, volume, and densitometric features; the second consists of segmentation first, followed by radiomic features extraction to characterize the whole abnormalities providing the so-called "virtual biopsy". This narrative review aims to provide an overview of all possible AI applications in lung cancer screening.

Chest X-ray in Emergency Radiology: What Artificial Intelligence Applications Are Available?

Due to its widespread availability, low cost, feasibility at the patient's bedside and accessibility even in low-resource settings, chest X-ray is one of the most requested examinations in radiology departments. Whilst it provides essential information on thoracic pathology, it can be difficult to interpret and is prone to diagnostic errors, particularly in the emergency setting. The increasing availability of large chest X-ray datasets has allowed the development of reliable Artificial Intelligence (AI) tools to help radiologists in everyday clinical practice. AI integration into the diagnostic workflow would benefit patients, radiologists, and healthcare systems in terms of improved and standardized reporting accuracy, quicker diagnosis, more efficient management, and appropriateness of the therapy. This review article aims to provide an overview of the applications of AI for chest X-rays in the emergency setting, emphasizing the detection and evaluation of pneumothorax, pneumonia, heart failure, and pleural effusion.