RESUMEN

Background: Chest X-rays (CXRs) are pivotal in clinical diagnostics, particularly in assessing cardiomegaly through the cardiothoracic ratio (CTR). This systematic review and meta-analysis evaluate the efficacy of artificial intelligence (AI) in automating CTR determination to enhance patient care and streamline diagnostic processes. They are concentrated on comparing the performance of AI models in determining the CTR against human assessments, identifying the most effective models for potential clinical implementation. This study was registered with PROSPERO (no. CRD42023437459). No funding was received. Methods: A comprehensive search of medical databases was conducted in June 2023. The search strategy adhered to the PICO framework. Inclusion criteria encompassed original articles from the last decade focusing on AI-assisted CTR assessment from standing-position CXRs. Exclusion criteria included systematic reviews, meta-analyses, conference abstracts, paediatric studies, non-original articles, and studies using imaging techniques other than X-rays. After initial screening, 117 articles were reviewed, with 14 studies meeting the final inclusion criteria. Data extraction was performed by three independent investigators, and quality assessment followed PRISMA 2020 guidelines, using tools such as the JBI Checklist, AMSTAR 2, and CASP Diagnostic Study Checklist. Risk of bias was assessed according to the Cochrane Handbook guidelines. Results: Fourteen studies, comprising a total of 70,472 CXR images, met the inclusion criteria. Various AI models were evaluated, with differences in dataset characteristics and AI technology used. Common preprocessing techniques included resizing and normalization. The pooled AUC for cardiomegaly detection was 0.959 (95% CI 0.944-0.975). The pooled standardized mean difference for CTR measurement was 0.0353 (95% CI 0.147-0.0760). Significant heterogeneity was found between studies (I2 89.97%, p < 0.0001), with no publication bias detected. Conclusions: Standardizing methodologies is crucial to avoid interpretational errors and advance AI in medical imaging diagnostics. Uniform reporting standards are essential for the further development of AI in CTR measurement and broader medical imaging applications.

RESUMEN

Cerebral vascular angiography, or digital subtraction angiography (DSA), is essential for diagnosing neurological conditions but poses radiation risks. This study aims to analyze the impact of examination parameters and patient characteristics on the radiation dose received during DSA to optimize safety and minimize exposure. A retrospective analysis of 251 DSA procedures using the GE Innova IGS 630 dual-plane instrument was conducted. Data on dose area product (DAP) and air kerma (KERMA), along with patient and examination details, were collected. Statistical analyses, including Mann-Whitney, Kruskal-Wallis, and Spearman rank correlation tests, assessed the relationships between variables and radiation dose outcomes. Significant correlations were found between the sides examined (left, right, or both) and DAP (p < 0.0001) and KERMA (p < 0.0001) values, with bilateral studies showing the highest values. The post hoc Dunn tests showed that the 'L + P' group significantly differs from both the right group (p < 0.0001 and the left group (p < 0.0001). There is no significant difference between the 'P' group and the 'L' group (p-value = 0.53). These results suggest that the right and left (both) group have unique KERMA mGy values compared to the other two groups. A strong correlation (rS = 0.87) existed between DAP and KERMA. The number of projections significantly impacted radiation dose (rS = 0.61). Tube parameters (kV and mA) and skull size had low correlations with DAP and KERMA. Optimizing imaging protocols and individualizing parameters can significantly enhance patient safety and diagnostic efficacy while also reducing occupational exposure for medical staff.

RESUMEN

Objectives: The purpose of this study is to evaluate the performance of our deep learning algorithm in calculating cardiothoracic ratio (CTR) and thus in the assessment of cardiomegaly or pericardial effusion occurrences on chest radiography (CXR). Methods: From a database of 8000 CXRs, 13 folders with a comparable number of images were created. Then, 1020 images were chosen randomly, in proportion to the number of images in each folder. Afterward, CTR was calculated using RadiAnt Digital Imaging and Communications in Medicine (DICOM) Viewer software (2023.1). Next, heart and lung anatomical areas were marked in 3D Slicer. From these data, we trained an AI model which segmented heart and lung anatomy and determined the CTR value. Results: Our model achieved an Intersection over Union metric of 88.28% for the augmented training subset and 83.06% for the validation subset. F1-score for subsets were accordingly 90.22% and 90.67%. In the comparative analysis of artificial intelligence (AI) vs. humans, significantly lower transverse thoracic diameter (TTD) (p < 0.001), transverse cardiac diameter (TCD) (p < 0.001), and CTR (p < 0.001) values obtained using the neural network were observed. Conclusions: Results confirm that there is a significant correlation between the measurements made by human observers and the neural network. After validation in clinical conditions, our method may be used as a screening test or advisory tool when a specialist is not available, especially on Intensive Care Units (ICUs) or Emergency Departments (ERs) where time plays a key role.

RESUMEN

(1) Background. Digital subtraction angiography (DSA) is indispensable for diagnosing cerebral aneurysms due to its superior imaging precision. However, optimizing X-ray parameters is crucial for accurate diagnosis, with X-ray tube settings significantly influencing image quality. Understanding the relationship between skull dimensions and X-ray parameters is pivotal for tailoring imaging protocols to individual patients. (2) Methods. A retrospective analysis of DSA data from a single center was conducted, involving 251 patients. Cephalometric measurements and statistical analyses were performed to assess correlations between skull dimensions and X-ray tube parameters (voltage and current). (3) Results. The study revealed significant correlations between skull dimensions and X-ray tube parameters, highlighting the importance of considering individual anatomical variations. Gender-based differences in X-ray parameters were observed, emphasizing the need for personalized imaging protocols. (4) Conclusions. Personalized approaches to DSA imaging, integrating individual anatomical variations and gender-specific differences, are essential for optimizing diagnostic outcomes. While this study provides valuable insights, further research across multiple centers and diverse imaging equipment is warranted to validate these findings.

RESUMEN

As the number of smartphones increases, so does the number of medical apps. Medical mobile applications are widely used in many medical fields by both patients and doctors. However, there are still few approved mobile applications that can be used in the diagnostic-therapeutic process and radiological apps are affected as well. We conducted our research by classifying radiological applications from the Google Play® store into appropriate categories, according to our own qualification system developed by researchers for the purposes of this study. In addition, we also evaluated apps from the App Store®. The radiology application rating system we created has not been previously used in other articles. Out of 228 applications from the Google Play store, only 6 of them were classified as "A" category with the highest standard. Apps from the App Store (157) were not categorized due to the lack of download counts, which was necessary in our app-rating system. The vast majority of applications are for educational purposes and are not used in clinical practice. This is due to the need of obtaining special permits and certificates from relevant institutions in order to use them in medical practice. We recommend applications from the Google Play store that have been classified in the "A" category, evaluating them as the most valuable. App Store apps data is described and presented in the form of diagrams and tables.

Asunto(s)

RESUMEN

Purpose: Rapid development of artificial intelligence has aroused curiosity regarding its potential applications in medical field. The purpose of this article was to present the performance of ChatGPT, a state-of-the-art language model in relation to pass rate of national specialty examination (PES) in radiology and imaging diagnostics within Polish education system. Additionally, the study aimed to identify the strengths and limitations of the model through a detailed analysis of issues raised by exam questions. Material and methods: The present study utilized a PES exam consisting of 120 questions, provided by Medical Exami-nations Center in Lodz. Questions were administered using openai.com platform that grants free access to GPT-3.5 model. All questions were categorized according to Bloom's taxonomy to assess their complexity and difficulty. Following the answer to each exam question, ChatGPT was asked to rate its confidence on a scale of 1 to 5 to evaluate the accuracy of its response. Results: ChatGPT did not reach the pass rate threshold of PES exam (52%); however, it was close in certain question categories. No significant differences were observed in the percentage of correct answers across question types and sub-types. Conclusions: The performance of the ChatGPT model in the pass rate of PES exam in radiology and imaging diagnostics in Poland is yet to be determined, which requires further research on improved versions of ChatGPT.

RESUMEN

In recent years, deep neural networks have enabled countless innovations in the field of image classification. Encouraged by success in this field, researchers worldwide have demonstrated how to use Convolutional Neural Network techniques in medical imaging problems. In this article, the results were obtained through the use of the EfficientNet in the task of classifying 14 different diseases based on chest X-ray images coming from the NIH (National Institutes of Health) ChestX-ray14 dataset. The approach addresses dataset imbalances by introducing a custom split to ensure fair representation. Binary cross entropy loss is utilized to handle the multi-label difficulty. The model architecture comprises an EfficientNet backbone for feature extraction, succeeded by sequential layers including GlobalAveragePooling, Dense, and BatchNormalization. The main contribution of this paper is a proposed solution that outperforms previous state-of-the-art deep learning models average area under the receiver operating characteristic curve-AUC-ROC (score: 84.28%). The usage of the transfer-learning technique and traditional deep learning engineering techniques was shown to enable us to obtain such results on consumer-class GPUs (graphics processing units).

RESUMEN

Diagnostic imaging has become an integral part of the healthcare system. In recent years, scientists around the world have been working on artificial intelligence-based tools that help in achieving better and faster diagnoses. Their accuracy is crucial for successful treatment, especially for imaging diagnostics. This study used a deep convolutional neural network to detect four categories of objects on digital chest X-ray images. The data were obtained from the publicly available National Institutes of Health (NIH) Chest X-ray (CXR) Dataset. In total, 112,120 CXRs from 30,805 patients were manually checked for foreign objects: vascular port, shoulder endoprosthesis, necklace, and implantable cardioverter-defibrillator (ICD). Then, they were annotated with the use of a computer program, and the necessary image preprocessing was performed, such as resizing, normalization, and cropping. The object detection model was trained using the You Only Look Once v8 architecture and the Ultralytics framework. The results showed not only that the obtained average precision of foreign object detection on the CXR was 0.815 but also that the model can be useful in detecting foreign objects on the CXR images. Models of this type may be used as a tool for specialists, in particular, with the growing popularity of radiology comes an increasing workload. We are optimistic that it could accelerate and facilitate the work to provide a faster diagnosis.

RESUMEN

Machine learning (ML), artificial neural networks (ANNs), and deep learning (DL) are all topics that fall under the heading of artificial intelligence (AI) and have gained popularity in recent years. ML involves the application of algorithms to automate decision-making processes using models that have not been manually programmed but have been trained on data. ANNs that are a part of ML aim to simulate the structure and function of the human brain. DL, on the other hand, uses multiple layers of interconnected neurons. This enables the processing and analysis of large and complex databases. In medicine, these techniques are being introduced to improve the speed and efficiency of disease diagnosis and treatment. Each of the AI techniques presented in the paper is supported with an example of a possible medical application. Given the rapid development of technology, the use of AI in medicine shows promising results in the context of patient care. It is particularly important to keep a close eye on this issue and conduct further research in order to fully explore the potential of ML, ANNs, and DL, and bring further applications into clinical use in the future.

RESUMEN

Despite the growing popularity of mobile devices, they still have not found widespread use in medicine. This is due to the procedures in a given place, differences in the availability of mobile devices between individual institutions or lack of appropriate legal regulations and accreditation by relevant institutions. Numerous studies have been conducted and compared the usability of mobile solutions designed for diagnostic images evaluation on various mobile devices and applications with classic stationary descriptive stations. This study is an attempt to compare the usefulness of currently available mobile applications which are used in the medical industry, focusing on imaging diagnostics. As a consequence of the healthcare sector's diversity, it is also not possible to design a universal mobile application, which results in a multitude of software available on the market and makes it difficult to reliably compile and compare studies included in this systematic review. Despite these differences, it was possible to identify both positive and negative features of portable methods analyzing radiological images. The mobile application of the golden mean in hospital infrastructure should be widely available, with convenient and simple usage. Our future research will focus on development in the use of mobile devices and applications in the medical sector.

RESUMEN

This systematic review focuses on using artificial intelligence (AI) to detect COVID-19 infection with the help of X-ray images. Methodology: In January 2022, the authors searched PubMed, Embase and Scopus using specific medical subject headings terms and filters. All articles were independently reviewed by two reviewers. All conflicts resulting from a misunderstanding were resolved by a third independent researcher. After assessing abstracts and article usefulness, eliminating repetitions and applying inclusion and exclusion criteria, six studies were found to be qualified for this study. Results: The findings from individual studies differed due to the various approaches of the authors. Sensitivity was 72.59%-100%, specificity was 79%-99.9%, precision was 74.74%-98.7%, accuracy was 76.18%-99.81%, and the area under the curve was 95.24%-97.7%. Conclusion: AI computational models used to assess chest X-rays in the process of diagnosing COVID-19 should achieve sufficiently high sensitivity and specificity. Their results and performance should be repeatable to make them dependable for clinicians. Moreover, these additional diagnostic tools should be more affordable and faster than the currently available procedures. The performance and calculations of AI-based systems should take clinical data into account.

Asunto(s)