Measurement of Cardiothoracic Ratio on Chest X-rays Using Artificial Intelligence-A Systematic Review and Meta-Analysis.

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.

Deep Learning in Cardiothoracic Ratio Calculation and Cardiomegaly Detection.

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.

Work-Related Quality of Life among Physicians in Poland: A Cross-Sectional Study.

BACKGROUND AND OBJECTIVES: Working in a healthcare setting is associated with high levels of stress and burnout syndrome. Work-related quality of life (WRQoL) remains insufficiently evaluated among physicians. The aim of this study is to assess the WRQoL among physicians of interventional, non-interventional, and diagnostic specialties in Poland. MATERIALS AND METHODS: Standardized and anonymous WRQoL questionnaires have been filled in by 257 physicians working in Silesia, Poland. After the removal of missing data, 246 individuals were stratified in terms of specialties into the appropriate categories, including interventional, non-interventional, and diagnostics. These categories were compared using the following subscales: general well-being (GWB), home-work interface (HWI), job and career satisfaction (JCS), control at work (CAW), working conditions (WCS), and stress at work (SAW). RESULTS: Out of 246 individuals, 132 were women (53.7%) and 112 (45.5%) were men. There were no differences in terms of WRQoL scores (p = 0.220) and subscales GWB (p = 0.148), HWI (p = 0.368), JCS (p = 0.117), CAW (p = 0.224), WCS (p = 0.609), SAW (p = 0.472) between interventional, non-interventional, and diagnostic specialties. The group of young doctors (age ≤ 30 years) had higher JCS scores than the older ones (mean score [SD], 22.7 [3.98] vs. 21 [4.6]; p = 0.013). Physicians who were not working in hospital had higher WRQoL score than respondents working in hospital (p = 0.061), with significant differences in terms of GWB (mean score [SD], 20.3 [4.93] vs. 22.8 [3.2], p = 0.014), HWI (mean score [SD], 9.1 [=2.65] vs. 10.6 [2.73], p = 0.011), and WCS (mean score [SD], 9.5 [2.61] vs. 10.8 [2.54], p = 0.035). CONCLUSION: There were no differences considering overall WRQoL between analyzed groups stratified according to specialty. However, we disclosed a significant association between the respondent's WRQoL and age as well as place of work.

Evaluation of Various Methods of Liver Measurement in Comparison to Volumetric Segmentation Based on Computed Tomography.

Background: A reliable assessment of liver volume, necessary before transplantation, remains a challenge. Our work aimed to assess the differences in the evaluation and measurements of the liver between independent observers and compare different formulas calculating its volume in relation to volumetric segmentation. Methods: Eight researchers measured standard liver dimensions based on 105 abdominal computed tomography (CT) scans. Based on the results obtained, the volume of the liver was calculated using twelve different methods. An independent observer performed a volumetric segmentation of the livers based on the same CT examinations. Results: Significant differences were found between the formulas and in relation to volumetric segmentation, with the closest results obtained for the Heinemann et al. method. The measurements of individual observers differed significantly from one another. The observers also rated different numbers of livers as enlarged. Conclusions: Due to significant differences, despite its time-consuming nature, the use of volumetric liver segmentation in the daily assessment of liver volume seems to be the most accurate method.

Influence of the physical pressure of an ultrasound probe on shear-wave elastography measurements of the gastrocnemius muscle in a paediatric population: a non-interventional cohort study.

Purpose: The aim of our study is to evaluate the impact of ultrasound probe mechanical pressure on the stiffness of the gastrocnemius muscle in a healthy paediatric population. As far as we know, there has been no previous qualitative in vivo study on the impact of probe pressure on muscle shear-wave elastography results with objective evaluation of compression in the paediatric population. Material and methods: In this cohort study, a group of 22 children (mean age 8.99 years, SD 2.74, 11 males) underwent elastography of the gastrocnemius muscle of the dominant leg. A custom-made, 3-dimensional printed probe cover was used to measure the mechanical pressure of the probe on tissues. Results: The obtained results were related to the age, sex, BMI, and calf circumference of the subjects. We observed a significant difference in the stiffness parameter at a pressure of 1 N, with a further increase if force was increased (p < 0.001). A significant, very weak positive correlation of age and stiffness was observed (p < 0.001, r2 = 0.022). There was no significant correlation of stiffness, BMI, and calf circumference. Conclusions: The use of compression during muscle elastography in children causes a significant bias in results, regardless of age, sex, BMI, or calf size.

Mobile applications in radiology: own study based on polish data.

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.

Will ChatGPT pass the Polish specialty exam in radiology and diagnostic imaging? Insights into strengths and limitations.

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.

Abbreviated magnetic resonance imaging protocols in oncology: improving accessibility in precise diagnostics.

Cancer, as the second leading cause of death in the world, is one of the major public health concerns today. Accurate diagnosis and prompt initiation of adequate treatment are of key importance for prognosis. Abbreviated magnetic resonance protocols (AMRI) are promising techniques based on magnetic resonance imaging (MRI) protocols that shorten acquisition time without significant loss of examination quality. Faster protocols that focus on detection of suspicious lesions with most precise sequences, can contribute to comparable diagnostic performance of a full MRI protocol. The purpose of this article was to review the current application of AMRI protocols in several oncological diseases.

Multi-Label Classification of Chest X-ray Abnormalities Using Transfer Learning Techniques.

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).

Chest X-ray Foreign Objects Detection Using Artificial Intelligence.

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.

Reliability of inter-recti distance measurement on ultrasound images captured by novice examiners.

BACKGROUND: With the increased interest in inter-recti distance measurement using ultrasound imaging in physiotherapy, there is a question of measurement reliability, and the importance of the examiner's experience. PURPOSE: The study aimed to investigate the reliability of inter-recti distance measurement in a DICOM viewer software by an experienced radiologist. For the measurement, the radiologist used linea alba images captured by two physiotherapists who were novice examiners. METHODS: Ultrasound images were acquired by two novice examiners on repeated occasions 7 days apart (sessions A and B) in 28 nulliparous women at supraumbilical, umbilical, and infraumbilical locations along linea alba. RESULTS: Excellent intra-examiner reliability of inter-recti distance measurements was shown at the supraumbilical and umbilical levels (ICC2,k = 0.941-0.983) with minimal detectable change (MDC95) ranging from 1.31 mm to 2.29 mm. Infraumbilical measurements had good to excellent reliability (ICC2,k = 0.894-0.972) with MDC95 ranging from 0.33 mm to 0.72 mm. Session A inter-examiner reliability was excellent for the mean measurements of two, three, four, and five images taken at each location (ICC2,k = 0.913-0.954) with MDC95 ranging from 0.47 mm to 2.96 mm. Session B inter-examiner reliability was excellent for the mean measurements of two, three, four, and five images taken at the supraumbilical and umbilical (ICC2,k = 0.94-0.98), MDC95 ranging from 1.38 mm to 2.58 mm and good (ICC2,k ≥ 0.81) with MDC95 ranging from 0.72 mm to 0.80 mm at the infraumbilical locations. CONCLUSION: Novice examiners were able to capture good-quality ultrasound images of the linea alba that allowed for good to excellent intra- and inter-examiner reliability.

What Is Machine Learning, Artificial Neural Networks and Deep Learning?-Examples of Practical Applications in Medicine.

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.

A single-center, retrospective, cross-sectional study comparing the number of non-diagnostic measurements ratio in the pSWE and SSI ultrasound elastography methods.

The point shear wave elastography and supersonic shear imaging methods were compared regarding incorrect measurements during the liver examinations. A report-based, single-center, retrospective analysis of 425 liver elastography examinations was performed. A lower success ratio was observed for the point shear wave elastography method, as well as the older and obese patients pre-dominated in non-diagnostic studies. In our center experience, it is easier to obtain diagnostic data using the supersonic shear imaging method. However, further investigation of the subject is needed.

POLCOVID: a multicenter multiclass chest X-ray database (Poland, 2020-2021).

The outbreak of the SARS-CoV-2 pandemic has put healthcare systems worldwide to their limits, resulting in increased waiting time for diagnosis and required medical assistance. With chest radiographs (CXR) being one of the most common COVID-19 diagnosis methods, many artificial intelligence tools for image-based COVID-19 detection have been developed, often trained on a small number of images from COVID-19-positive patients. Thus, the need for high-quality and well-annotated CXR image databases increased. This paper introduces POLCOVID dataset, containing chest X-ray (CXR) images of patients with COVID-19 or other-type pneumonia, and healthy individuals gathered from 15 Polish hospitals. The original radiographs are accompanied by the preprocessed images limited to the lung area and the corresponding lung masks obtained with the segmentation model. Moreover, the manually created lung masks are provided for a part of POLCOVID dataset and the other four publicly available CXR image collections. POLCOVID dataset can help in pneumonia or COVID-19 diagnosis, while the set of matched images and lung masks may serve for the development of lung segmentation solutions.

Pathological changes or technical artefacts? The problem of the heterogenous databases in COVID-19 CXR image analysis.

BACKGROUND: When the COVID-19 pandemic commenced in 2020, scientists assisted medical specialists with diagnostic algorithm development. One scientific research area related to COVID-19 diagnosis was medical imaging and its potential to support molecular tests. Unfortunately, several systems reported high accuracy in development but did not fare well in clinical application. The reason was poor generalization, a long-standing issue in AI development. Researchers found many causes of this issue and decided to refer to them as confounders, meaning a set of artefacts and methodological errors associated with the method. We aim to contribute to this steed by highlighting an undiscussed confounder related to image resolution. METHODS: 20 216 chest X-ray images (CXR) from worldwide centres were analyzed. The CXRs were bijectively projected into the 2D domain by performing Uniform Manifold Approximation and Projection (UMAP) embedding on the radiomic features (rUMAP) or CNN-based neural features (nUMAP) from the pre-last layer of the pre-trained classification neural network. Additional 44 339 thorax CXRs were used for validation. The comprehensive analysis of the multimodality of the density distribution in rUMAP/nUMAP domains and its relation to the original image properties was used to identify the main confounders. RESULTS: nUMAP revealed a hidden bias of neural networks towards the image resolution, which the regular up-sampling procedure cannot compensate for. The issue appears regardless of the network architecture and is not observed in a high-resolution dataset. The impact of the resolution heterogeneity can be partially diminished by applying advanced deep-learning-based super-resolution networks. CONCLUSIONS: rUMAP and nUMAP are great tools for image homogeneity analysis and bias discovery, as demonstrated by applying them to COVID-19 image data. Nonetheless, nUMAP could be applied to any type of data for which a deep neural network could be constructed. Advanced image super-resolution solutions are needed to reduce the impact of the resolution diversity on the classification network decision.

The application of abbreviated MRI protocols in malignant liver lesions surveillance.

Cancer is one of the leading public health problems globally. Since time is of the essence in oncology, the sooner an accurate diagnosis is made, the better the prognosis for patients. There is a growing need to find a flawless and fast imaging method for cancer detection, but also for its evaluation during treatment. In this respect, the possibilities and novelties of magnetic resonance imaging are particularly promising. Abbreviated magnetic resonance imaging (AMRI) protocols have aroused universal interest as a compromise between scanning time reduction and preservation of image quality. Shorter protocols focused on the detection of suspicious lesions with the most sensitive sequences could provide a diagnostic performance similar to the one of the standard protocol. The purpose of this article is to review the ongoing accomplishments in the use of AMRI protocols in liver metastases and HCC detection.

Technical aspects of inter-recti distance measurement with ultrasonographic imaging for physiotherapy purposes: the scoping review.

BACKGROUND: Inter-recti distance (IRD) measurement using musculoskeletal USI has been used in physiotherapy research, in particular, to investigate pregnancy-related diastasis recti abdominis (DRA) and to seek its effective treatment methods. Severe and untreated diastasis may result in the formation of umbilical or epigastric hernias. OBJECTIVE: This study aimed to systematically map physiotherapy-related research articles that included descriptions of IRD measurement procedures using USI to present their similarities and differences, and formulate recommendations on the procedure. DESIGN: A scoping review was conducted according to PRISMA-ScR guidelines, including 49 of 511 publications from three major databases. Publications were selected and screened by two independent reviewers whose decisions were consulted with a third reviewer. The main synthesized data items were: the examinees' body position, breathing phase, measurement sites, and DRA screening methods. The final conclusions and recommendations were the result of a consensus between seven reviewers from four research centers. RESULTS: Studies used 1-5 measurement sites that were differently determined. IRD was measured at the umbilicus (n = 3), at its superior (n = 16) and/or inferior border (n = 9), and at different levels: between 2 and 12 cm above the umbilicus, or a third of the distance and halfway between the umbilicus and xiphoid (n = 37); between 2 and 4.5 cm below the umbilicus or halfway between the umbilicus and pubis (n = 27). Different approaches were used to screen subjects for DRA. CONCLUSIONS: The discrepancies between the measurement procedures prevent between-study comparisons. The DRA screening method should be standardized. IRD measurement protocol standardization has been proposed. CRITICAL RELEVANCE STATEMENT: This scoping review indicates that the inter-recti distance measurement procedures using ultrasound imaging differ between studies, preventing between-study comparisons. Based on the results synthesis, the measurement protocol standardization has been proposed. KEY POINTS: The inter-recti distance measurement procedures using USI differ between studies. Proposed standardization concerns body position, breathing phase, measurements number per location. Determination of measurement locations considering individual linea alba length is suggested. Recommended locations: umbilical top, ½ of umbilical top-xiphoid, » of umbilical top-xiphoid/pubis distances. Diastasis recti abdominis diagnostic criteria are needed for proposed measurement locations.

Encephalocraniocutaneous Lipomatosis, a Radiological Challenge: Two Atypical Case Reports and Literature Review.

Encephalocraniocutaneous lipomatosis (ECCL; Haberland syndrome, #613001) is an extremely rare congenital disorder that is manifested by the involvement of the skin, eyes and central nervous system (CNS). We report two cases of children with ECCL diagnosis. First was an 8-year-old girl who presented with symptomatic epilepsy, cerebral palsy and developmental delay. In 2020, she was admitted to the hospital due to the exacerbation of paresis and intensified prolonged epileptic seizures, provoked by infection of the middle ear. Diagnostic imaging revealed radiological changes suggestive of ECCL, providing a reason for the diagnosis, despite the lack of skin and eye anomalies. The second child, a 14-year-old girl, was consulted for subtle clinical signs and epilepsy suspicion. Diagnostic imaging findings were similar, though less pronounced. Based on neuroradiological abnormalities typical for Haberland syndrome, the authors discuss possible ECCL diagnosis.

The Assessment of the Rationale for Urgent Head CT-Comparative Analysis of Referrals and Results of Examinations without and with Contrast Enhancement.

The study analyzes the correlation between the indications and results of head CT examinations in search of evidence of the excessive use of this diagnostic method. In total, 1160 referrals for urgent head CT were analyzed retrospectively, including the following parameters: patients' sex and age, type of scan (C-, C+, angio-CT), description of symptoms and presence of diagnostic target. Pathologies identified by the radiologist were assigned to four classes, regarding the severity of diagnosed conditions. The analysis of the CT results has shown that over half (55.22%) of the examinations revealed no deviations or showed chronic, asymptomatic lesions. As many as 73.71% referrals constituted group 0 in terms of the lack of a diagnostic target of a specific pathology. The presence of specific clinical targeting in a referral correlated significantly with a higher frequency of acute diagnosis. Contrast-enhanced follow-up examinations allowed the unequivocal classification of patients into extreme classes (I or IV) and accurate identification of patients requiring urgent or chronic treatment. Excessive use of diagnostic imaging is harmful, not only to patients, who often are unnecessarily exposed to radiation, but also to the quality of healthcare, since it increases the costs and radiologists' workload.

Usability of Mobile Solutions Intended for Diagnostic Images-A Systematic Review.

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.