Image Interpretation Research Articles

Diabetic Retinopathy Detection with Deep Learning Techniques on Fundus Photographs: A Review

Diabetic retinopathy (DR) is an ocular condition that can affect individuals with diabetes mellitus (DM) and may lead to reduced vision or even blindness if not detected on time. Delay in diagnosis and disagreement in interpretation of retinal images by different health experts are some of the challenges that can occur during screening for DR. Deep learning (DL) techniques are currently used for classification of images across various domains including the ophthalmic imaging field. The implementation of this cutting edge technology for detection of DR could lead to improvement of existing eye care services for diabetic individuals. This paper discussed the publicly available datasets of retinal images of diabetic individuals used for training DL models. The efficiency of several convolutional neural networks (CNNs) created for the detection of different classes of DR was also reviewed. Furthermore, the achievements and the challenges faced in the application of DL techniques for the DR detection were discussed. Finally, future works that can be performed in this research area has been suggested.

Phototherapy as the tool of emotional identification development of adolescents

The results of the empirical stage statistically proved that phototherapy is one of the effective tools of psycho-pedagogical assistance to adolescents who experience difficulties associated with emotional identification. We diagnosed the level of formation of this phenomenon within the sample of 240 respondents who are university and school students aged 17 to 20 years female and male. A number of psycho-diagnostic methods were used in the study: the method 'Toron to alexithymia scale (TAS-26)” and the questionnaire “self-attitude.” Summarizing the results, we state that most of the studied sample is in a state of emotional well-being but emotional discomfort occurs among some respondents with certain levels of propensity for alexithymia (22.5%). The research proves the positive impact of phototherapy on adolescents' emotional identification development through photographing and creating visual pictures or direct perception and interpretation of images.

Magnetic resonance classification proposal for medial gastrocnemius muscle injuries.

Calf muscle injuries are common among athletes and occupational populations, with highly variable recovery times that are challenging to be predicted at the initial clinical evaluation. Specifically, in distal gastrocnemius muscle injuries, an ultrasound-based severity classification has shown to be useful for estimating the recovery time. According to the location of lesions and the recognition of some US signs, four types of injuries of the distal gastrocnemius muscle were described. Since magnetic resonance imaging (MRI) has proven to be useful in diagnosing and prognosticating muscle injuries by assessing the extent of affected connective tissue, a specific MRI protocol involving T1-weighted and fluid-sensitive static and dynamic acquisitions has been developed aimed to characterize the four types of injuries. We here describe the characteristics of this new MRI protocol and the interpretation of images, which will be useful to improve the recognition of acute and delayed distal gastrocnemius muscle injuries. The proposed classification includes: myoaponeurotic muscle injury without aponeurotic discontinuities (type 1), myoaponeurotic muscle injury with aponeurotic discontinuities (type 2), isolated free aponeurosis discontinuity (type 3), and a mixed myoaponeurotic-aponeurotic injury pattern (type 4). A comprehensive understanding of the MRI features associated with each injury type, in conjunction with multidisciplinary team collaboration, is essential for optimizing the athlete's recovery and return to play.

Évaluation en TEP 18F-FDG de la réponse au traitement par CAR T-Cells et anticorps bispécifiques des lymphomes non hodgkiniens agressifs

Refractory or relapsing aggressive non-Hodgkin lymphomas have improved prognosis in the last few years thanks to innovative therapies such as CAR T-cells and bispecific antibodies. During these therapeutic strategies, tumoral response assessment with FDG PET remains of paramount importance. However, due to their mode of action, these treatments can result in delayed responses or in inflammatory events that may hamper interpretation of metabolic imaging. Lugano criteria, relying on the Deauville score, are useful, but it is crucial to be aware of the interpretation pitfalls and to consider all the clinical and biological background of the patient, ideally in a multidisciplinary approach.

Lumbar Spinal Stenosis Grading in Multiple Level Magnetic Resonance Imaging Using Deep Convolutional Neural Networks.

Retrospective magnetic resonance imaging grading with comparison between experts and deep convolutional neural networks (CNNs). The application of deep learning to clinical diagnosis has gained popularity. This approach can accelerate image interpretation and serve as a screening tool to help doctors. A comparison was conducted between retrospective magnetic resonance imaging (MRI) grading performed by experts and grading obtained using CNN classifiers. Data were collected from the lumbar axial dataset in the DICOM format. Two experts labeled the sampled images using the same diagnostic tools: localization of patches near the spinal canal, rootlet leveling, and stenosis grading. Comprehensive comparisons were presented for both rootlet cord classification and stenosis grading. Rootlet-cord classification for the two analyzers was 90.3% and the F1 score was 86.6%. The agreement of Analyzers-Classifiers was 92.7% and 96.8% for data with 90.6% and 95.6% F1 scores, respectively. For stenosis grading, there was an agreement of 89.2% between the two analyzers, resulting in an F1 score of 76.5%. The grades of the Analyzers-Classifiers agreed on 91.5/89.4% of the data, with an F1 score of 78.4/75.7%. Analyzer1 and Analyzer2 classified >74% as grade A (78.8% and 74.4%, respectively), 15.4% and 18.6% as grade B, 4.2% and 6.0% as grade C, and 1.6% and 2.0% as grade D, respectively. The fully automated deep learning model showed competitive results in stenosis grade diagnosis and rootlet cord classification under similar anatomical conditions. However, abrupt anatomical changes can lead to a puzzle diagnosis based only on images.

Growth Increase of Gelam (Melaleuca Leucadendron) Burnt Peatland Through the Provision of Soil Conditioner (Study in Londerang Peat Protection Forest)

The protected forest of Londerang Jambi is an area of hydrological unity with a surface area of 12.484 ha that is located in the district of Tanjung Timur and Muaro Jambi, which is surrounded by palm plantations and forest of industrial crops and 10 villages in the Districts of Tanjung Jabung Timur and Jambi. Based on the results of the Landsat 8 OLI image analysis and the SPOT 7 image interpretation by WWF Indonesia in 2015 that the Londerang Forest Protection Area (HLG) has an area of 12.848 Ha, currently the steep vegetation cover that canopies closely on the HLG Londerang remains only less than 10% of the area of HLG londerang due to forest fires in 2015. An attempt to overcome the situation has been made, one of them in the HLG Londerang being made an of the Hydrological Union of Mendahara-Sungai Batanghari which has been intervened by the Badan Restorasi Gambut (BRG). This effort was also carried out by the KIFC (Korea Indonesia Forest Center) by revegetating the blocks of land that had been burned in HLG Londerang. The planting has been carried out from the beginning of 2022 to December 2022. The species of plants planted among them are Pulai Rawa (Alstonia scholaris), Balangeran (Shorea balangeran), Gelam (Melaleuca leucadendron). In order to support the success of the revegetation, intensive maintenance is required, including the provision of soil fertilizers such as dolomite and NPK fertilizer. The research was conducted for seven months from May to December 2023 at HLG Londerang. Measuring fields are made with group random designs (RAK). The clustering is based on the difference in the height of the groundwater surface

High-Resolution SAR-to-Multispectral Image Translation Based on S2MS-GAN

Synthetic aperture radar (SAR) has been extensively applied in remote sensing applications. Nevertheless, it is a challenge to process and interpret SAR images. The key to interpreting SAR images lies in transforming them into other forms of remote sensing images to extract valuable hidden remote sensing information. Currently, the conversion of SAR images to optical images produces low-quality results and incomplete spectral information. To address these problems, an end-to-end network model, S2MS-GAN, is proposed for converting SAR images into multispectral images. In this process, to tackle the issues of noise and image generation quality, a TV-BM3D module is introduced into the generator model. Through TV regularization, block-matching, and 3D filtering, these two modules can preserve the edges and reduce the speckle noise in SAR images. In addition, spectral attention is added to improve the spectral features of the generated MS images. Furthermore, we construct a very high-resolution SAR-to-MS image dataset, S2MS-HR, with a spatial resolution of 0.3 m, which is currently the most comprehensive dataset available for high-resolution SAR-to-MS image interpretation. Finally, a series of experiments are conducted on the relevant dataset. Both quantitative and qualitative evaluations demonstrate that our method outperforms several state-of-the-art models in translation performance. The solution effectively facilitates high-quality transitions of SAR images across different types.

Current State and Outlook in Medical 3D Printing and the Role of Radiology.

Medical three-dimensional (3D) printing is playing an increasingly important role in clinical practice. The use of 3D printed models in patient care offers a wide range of possibilities in terms of personalized medicine, training and education of medical professionals, and communication with patients. DICOM files from imaging modalities such as CT and MRI provide the basis for the majority of the 3D models in medicine. The image acquisition, processing, and interpretation of these lies within the responsibility of radiology, which can therefore play a key role in the application and further development of 3D printing.The purpose of this review article is to provide an overview of the principles of 3D printing in medicine and summarize its most important clinical applications. It highlights the role of radiology as central to developing and administering 3D models in everyday clinical practice.This is a narrative review article on medical 3D printing that incorporates expert opinions based on the current literature and practices from our own medical centers.While the use of 3D printing is becoming increasingly established in many medical specialties in Germany and is finding its way into everyday clinical practice, centralized "3D printing labs" are a rarity in Germany but can be found internationally. These labs are usually managed by radiology departments, as radiology is a connecting discipline that - thanks to the imaging technology used to produce data for 3D printing - can play a leading role in the application of medical 3D printing. Copying this approach should be discussed in Germany in order to efficiently use the necessary resources and promote research and development in the future. · 3D printing in medicine is a rapidly growing field.. · Image acquisition and processing provides an important basis for high-quality 3D models.. · Radiology, as the specialist discipline responsible for imaging, has a crucial role to play.. · Radiology should play a leading role in the introduction of 3D printing in everyday clinical practice. . · Streckenbach A, Schubert N, Streckenbach F et al. Current State and Outlook in Medical 3 D Printing and the Role of Radiology. Fortschr Röntgenstr 2024; DOI 10.1055/a-2436-7185.

AFA–Mamba: Adaptive Feature Alignment with Global–Local Mamba for Hyperspectral and LiDAR Data Classification

The joint classification of hyperspectral imagery (HSI) and LiDAR data is an important task in the field of remote sensing image interpretation. Traditional classification methods, such as support vector machine (SVM) and random forest (RF), have difficulty capturing the complex spectral–spatial–elevation correlation information. Recently, important progress has been made in HSI-LiDAR classification using Convolutional Neural Networks (CNNs) and Transformers. However, due to the large spatial extent of remote sensing images, the vanilla Transformer and CNNs struggle to effectively capture global context. Moreover, the weak misalignment between multi-source data poses challenges for their effective fusion. In this paper, we introduce AFA–Mamba, an Adaptive Feature Alignment Network with a Global–Local Mamba design that achieves accurate land cover classification. It contains two main core designs: (1) We first propose a Global–Local Mamba encoder, which effectively models context through a 2D selective scanning mechanism while introducing local bias to enhance the spatial features of local objects. (2) We also propose an SSE Adaptive Alignment and Fusion (A2F) module to adaptively adjust the relative positions between multi-source features. This module establishes a guided subspace to accurately estimate feature-level offsets, enabling optimal fusion. As a result, our AFA–Mamba consistently outperforms state-of-the-art multi-source fusion classification approaches across multiple datasets.

Analysis of natural and man-made factors of landslide development in the Carpathian region using GIS

Purpose. Determination of the dependencies of spatial relationships between landslides in the Carpathian region of Ukraine and the factors causing them, taking into account the differences in geomorphological, geological, climatic conditions and natural and geographical zoning according to the landscape principle. Methodology. The morphometric analysis of the territory was carried out using QGIS tools to determine the slope angles and exposure; linear characteristics were calculated: distances to the river, road, and houses. Based on the image interpretation data, we calculated the total annual rainfall and average annual air temperature. The impact of the factors considered on landslide formation was assessed using multivariate statistical analysis: factor analysis and linear multiple regression. Findings. Studies on the impact of natural and topographical conditions and anthropogenic activity on the development of landslide processes have been conducted. Orographic and climatic factors play the most important role. Construction of business facilities results in a decrease in the slope stability in 14–19 % of cases. The analysed independed factors showed good consistency between the distribution of existing landslides and the parameters under consideration: the share of the total variance of the factors under consideration is 71–76 %, the coefficient of determination of the regression model is 0.7. Based on the results of geoinformation and statistical analyses, it is proved that differences in geomorphological conditions and human activity (construction of roads, economic facilities) are dominant in the formation of landslides in different landscape zones. Originality. It is established that there is a dynamic coherence between the spatial change in natural conditions and human settlement and activity, which interact with each other to create prerequisites for the development of landslides. Practical value. This study is important from the point of view of understanding and mitigating the cause-and-effect relationship of landslide development for certain territories, and the results obtained can be useful in developing land use planning strategies, infrastructure development, and planning new construction works.

Land Use Change in a Typical Transect in Northern China and Its Impact on the Ecological Environment

This paper uses seven periods of land use/cover data from 1990 to 2020 to investigate the spatio-temporal features of land use change in a typical transect in northern China. By using the land use transfer matrix, transect analysis, and ecological contribution rate, image interpretation data obtained from the Chinese Academy of Sciences Resource and Environmental Science Data Platform were analyzed using a spatial overlay to quantitatively examine the transect’s land use changes and their impact on the eco-environment. The results indicate that (1) the transect’s land use is dominated by cropland and grassland. (2) Cropland, forest land, and waters experienced significant transitions in 1995 and 2000, which was linked to socio-economic development and policy factors. (3) The total dynamic percentage of land use change is 4.52%, with built-up land and cropland showing the highest change. (4) The transect’s eco-environmental quality (EQ) has significantly declined, with the quality index dropping from 0.3839 to 0.3773. The transformation of cropland to forest land improves the eco-environment, while the transformation to built-up land has negative impacts. Human activities adversely affect the EQ. The findings are promising for leading the development of conserving the eco-environment and supporting the formation of regionally differentiated paths of ecological civilization construction in the transect.

Unmet Needs in Spondyloarthritis: Imaging in Axial Spondyloarthritis.

Imaging biomarkers in axial spondyloarthritis (axSpA) are currently the most specific biomarkers for the diagnosis of this condition. Despite advances in imaging, from plain radiographs-which detect only damage-to magnetic resonance imaging (MRI)-which identifies disease activity and structural change-there are still many challenges that remain. Imaging in sacroiliitis is characterized by active and structural changes. Current classification criteria stress the importance of bone marrow edema (BME); however, BME can occur in various diseases, mechanical conditions, and healthy individuals. Thus, the identification of structural lesions such as erosion, subchondral fat, backfill, and ankylosis is important to distinguish from mimics on differential diagnosis. Various imaging modalities are available to examine structural lesions, but computed tomography (CT) is considered the current reference standard. Nonetheless, recent advances in MRI allow for direct bone imaging and the reconstruction of CT-like images that can provide similar information. Therefore, the ability of MRI to detect and measure structural lesions is strengthened. Here, we present an overview of the spectrum of current and cutting-edge techniques for SpA imaging in clinical practice; namely, we discuss the advantages, disadvantages, and usefulness of imaging in SpA through radiography, low-dose and dual-energy CT, and MRI. Cutting-edge MRI sequences including volumetric interpolated breath-hold examination, ultrashort echo time, zero echo time, and deep learning-based synthetic CT that creates CT-like images without ionizing radiation, are discussed. Imaging techniques allow for quantification of inflammatory and structural lesions, which is important in the assessment of treatment response and disease progression. Radiographic damage is poorly sensitive to change. Artificial intelligence has already revolutionized radiology practice, including protocolization, image quality, and image interpretation.

Effect of isotropy and anisotropy: toward understanding the fracture behavior of magnetoactive elastomers

Magnetoactive elastomers (MAEs) exhibit magneto-mechanical coupling and typically contain micron-sized spherical ferromagnetic particles embedded in an elastomeric matrix. Anisotropic particle arrangement in MAEs, achieved by curing the material in a magnetic field, offers tailored and enhanced magneto-mechanical coupling compared to isotropic configurations. While tunable MAE properties such as the effective modulus and vibrational response have been relatively well studied, a thorough understanding of their fracture mechanisms, particularly in MAEs with microstructural anisotropy or composites with similar structures remains almost completely unexplored. Here, we characterize the fracture mechanisms of anisotropic and isotropic unmagnetized MAEs using experiments and simulations, focusing on the effects of spherical particles in anisotropic chain-like configurations. Specifically, we experimentally measure the fracture toughness of MAEs containing different volume fractions of particles, and with particles arranged both randomly and aligned at 0°, 45°, and 90° to the loading direction. Results show that anisotropic MAEs with particle chains aligned with the load direction can improve fracture toughness by up to almost 600%, whereas isotropic MAEs increase the fracture toughness by only 420%, compared to the pure elastomer. Scanning electron microscopy of the post-fractured surface reveals toughening mechanisms at micro-scale, such as chain waviness, particle agglomeration, and particle distribution. Simulations using a finite element method-based decoupled phase field-cohesive zone model on simplified geometries qualitatively support imaging interpretations. Overall, this work explains how internal geometry, including waviness in particle chains, chain alignment, and particle agglomerations affects fracture of MAEs and generally soft composites with chain-like geometries of spherical particles. These results have engineering applications in improving fracture properties of smart soft composites relevant to soft robotics, tunable vibration absorbers, and noise attenuators.

Advancing Digital Education Technologies by Empowering Nurses With Point-of-Care Ultrasound: Protocol for a Mixed Methods Study.

Bedside ultrasonography, also known as point-of-care ultrasound (PoCUS), is a promising technological tool that enhances clinical assessment, enriching diagnostic capabilities and clinical reasoning. Its use in nursing spans various patient populations and health care settings, providing nurses with a valuable health assessment tool to improve care quality and patient safety. Despite its growing integration into clinical practice, PoCUS training has mainly focused on physicians, leaving a gap for trained nurses who demonstrate similar proficiency in conducting scans and interpreting images. Previous research highlights the value of digital tools in PoCUS training, showing their role in improving professionals' and students' knowledge, image interpretation skills, and clinical acumen. This study aimed to (1) establish an assessment instrument gauging nurses' competency milestones in PoCUS and evaluate its content and appearance validity, (2) develop a series of 5 educational videos focused on PoCUS and assess their content and appearance validity, and (3) construct an online learning environment tailored to nurses' PoCUS training needs and evaluate its content and appearance validity. We will conduct a methodological study of technological production guided by Rogers' diffusion of innovations theory. Subproject 1 will design and validate a comprehensive assessment tool for evaluating nurses' competency milestones in PoCUS use. For this purpose, a scoping review will be conducted. The review will be based on JBI Collaboration guidelines and reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extended for Scoping Reviews (PRISMA-ScR) checklist. Subproject 2 involves an evaluation of content and appearance validity for a series of 5 educational videos on PoCUS, designed specifically for nurses about applying peripherally inserted central catheter lines, inserting nasogastric feeding tubes, assessing gastric residual volume, assessing pressure injuries and soft tissue conditions, and assessing muscle mass to monitor patient nutritional status. In subproject 3, a comprehensive online learning environment dedicated to PoCUS training for nurses will be developed and validated. The launch of an online learning environment represents a cornerstone of our dissemination strategy, scheduled to coincide with the inaugural Brazilian PoCUS symposium for nurses, an event organized by the project members. This platform will serve as a pivotal resource for continuous learning and professional development. Subproject 1 will start in the second half of 2024 and is expected to be completed by mid-2025. Subproject 2 is currently ongoing and is expected to be completed in early 2026. Subproject 3 is set to begin in early 2025 and is planned to be completed by 2026. Through these concerted efforts, the project aims to bridge the existing gap in PoCUS training for nurses, thereby fostering their proficiency and enhancing patient care outcomes. PRR1-10.2196/58030.

Malignancy predictors and treatment strategies for adult intestinal intussusception.

Intussusception in adult patients is a rare medical finding, which is accompanied by an underlying tumor in some cases. However, no accepted method has been established to identify patients at risk for tumor-related intussusception. This study aimed to identify imaging features as predictors for tumor-related intussusception.CT images of patients with confirmed intussusception were retrospectively acquired between 01/2008 and 12/2022. Available follow-up images and medical health records were evaluated to identify various imaging features, the cause of intussusception, and treatment strategies. Imaging interpretation was conducted by two blinded radiologists. A third radiologist was consulted in cases of disagreement.A total of 71 consecutive patients were included in this study (42 males, 29 females) with a median age of 56 years (interquartile range: 40.5-73.8 years). Enteroenteric intussusceptions in the small bowel were the most common type observed in adult patients. In contrast, colocolic intussusception was more frequently associated with malignancy, and this association was statistically significant (p < 0.05). Among the malignant tumors, adenocarcinoma was the most common, followed by metastases and lymphoma. Additionally, bowel obstruction and wall thickening were significantly correlated with malignancy (p < 0.05). The high negative predictive values (NPVs) and high specificities for ileus (NPV 88.5%, specificity 82.1%), bowel wall thickening (NPV 90.9%, specificity 71.4%), and acute abdomen (NPV 84.6%, specificity 78.8%) suggest that the absence of these features strongly predicts a low probability of malignancy in cases of adult intussusception.Active surveillance with follow-up exams is suitable for asymptomatic and transient intussusception when imaging features suggest a low likelihood of a neoplasm. Additionally, malignancy predictors such as ileus and thickening of the bowel wall in the affected segment could guide tailored treatment. Surgical interventions are essential for symptomatic cases, with adenocarcinoma being the most common malignancy found in colocolic intussusceptions.Intussusception in adults is rare and is often associated with underlying tumors, particularly in colocolic intussusceptions. Key imaging predictors for malignancy include bowel obstruction, wall thickening in the affected segment, and the presence of acute abdomen, with high NPVs and specificities indicating low malignancy risk when these features are absent. Active surveillance is recommended for asymptomatic cases with low neoplasm probability, while surgical intervention is the method of choice for symptomatic patients. · Reschke P, Le Hong QA, Gruenewald LD et al. Malignancy predictors and treatment strategies for adult intestinal intussusception. Fortschr Röntgenstr 2024; DOI 10.1055/a-2434-7932.

Nomogram based on multimodal ultrasound features for evaluating breast nonmass lesions: a single center study

BackgroundIt is challenging to correctly identify and diagnose breast nonmass lesions. This study aimed to explore the multimodal ultrasound features associated with malignant breast nonmass lesions (NMLs), and evaluate their combined diagnostic performance.MethodsThis retrospective analysis was conducted on 573 breast NMLs, including 309 were benign and 264 were malignant, their multimodal ultrasound features (B-mode, color Doppler and strain elastography) were assessed by two experienced radiologists. Univariate and multivariate logistic regression analysises were used to explore multimodal ultrasound features associated with malignancy, and a nomogram was developed. Diagnostic performance and clinical utility were evaluated and validated by the receiver operating characteristic (ROC) curve, calibration curve and decision curve in the training and validation cohorts.ResultsMultimodal ultrasound features including linear (odds ratio [OR] = 4.69) or segmental distribution (OR = 7.67), posterior shadowing (OR = 3.14), calcification (OR = 7.40), hypovascularity (OR = 0.38), elasticity scored 4 (OR = 7.00) and 5 (OR = 15.77) were independent factors associated with malignant breast NMLs. The nomogram based on these features exhibited diagnostic performance in the training and validation cohorts were comparable to that of experienced radiologists, with superior specificity (89.4%, 89.5% vs. 81.2%) and positive predictive value (PPV) (89.2%, 90.4% vs. 82.4%). The nomogram also demonstrated good calibration in both training and validation cohorts (all P > 0.05). Decision curve analysis indicated that interventions guided by the nomogram would be beneficial across a wide range of threshold probabilities (0.05-1 in the training cohort and 0.05–0.93 in the validation cohort).ConclusionsThe combined use of linear or segmental distribution, posterior shadowing, calcification, hypervascularity and high elasticity score, displayed as a nomogram, demonstrated satisfied diagnostic performance for malignant breast NMLs, which may contribute to the imaging interpretation and clinical management of tumors.

Performance of Chat Generative Pre-trained Transformer-4o in the Adult Clinical Cardiology Self-Assessment Program

Abstract Aims This study evaluates the performance of OpenAI’s latest large language model (LLM), Chat Generative Pre-trained Transformer-4o, on the Adult Clinical Cardiology Self-Assessment Program (ACCSAP). Methods and results Chat Generative Pre-trained Transformer-4o was tested on 639 ACCSAP questions, excluding 45 questions containing video clips, resulting in 594 questions for analysis. The questions included a mix of text-based and static image-based [electrocardiogram (ECG), angiogram, computed tomography (CT) scan, and echocardiogram] formats. The model was allowed one attempt per question. Further evaluation of image-only questions was performed on 25 questions from the database. Chat Generative Pre-trained Transformer-4o correctly answered 69.2% (411/594) of the questions. The performance was higher for text-only questions (73.9%) compared with those requiring image interpretation (55.3%, P &amp;lt; 0.001). The model performed worse on questions involving ECGs, with a correct rate of 56.5% compared with 73.3% for non-ECG questions (P &amp;lt; 0.001). Despite its capability to interpret medical images in the context of a text-based question, the model’s accuracy varied, demonstrating strengths and notable gaps in diagnostic accuracy. It lacked accuracy in reading images (ECGs, echocardiography, and angiograms) with no context. Conclusion Chat Generative Pre-trained Transformer-4o performed moderately well on ACCSAP questions. However, the model’s performance remains inconsistent, especially in interpreting ECGs. These findings highlight the potential and current limitations of using LLMs in medical education and clinical decision-making.

Amputation and limb-sparing surgery in childhood sarcoma: Post-operative imaging appearances and complications.

Limb-sparing surgery and amputation are common surgical techniques used to achieve local tumour control in childhood primary bone and soft tissue malignancy of the limbs. The interpretation of post-operative limb imaging in these frequently complex cases is assisted by knowledge of the surgical techniques employed. This review discusses the rationale underpinning the most common surgical techniques used for these patients as well as their expected post-operative imaging appearance and complications. Amputation, long bone resection, endoprosthetic reconstruction, allograft reconstruction, the use of fibular autografts, allograft-prosthetic composite reconstruction and arthrodesis are discussed.

Use of neonatal lung ultrasound in European neonatal units: a survey by the European Society of Paediatric Research

ObjectiveRegarding the use of lung ultrasound (LU) in neonatal intensive care units (NICUs) across Europe, to assess how widely it is used, for what indications and how its implementation might...

DCV2I$\text{DCV}^2\text{I}$: Leveraging deep vision models to support geographers' visual interpretation in dune segmentation

AbstractVisual interpretation is extremely important in human geography as the primary technique for geographers to use photograph data in identifying, classifying, and quantifying geographic and topological objects or regions. However, it is also time‐consuming and requires overwhelming manual effort from professional geographers. This paper describes our interdisciplinary team's efforts in integrating computer vision models with geographers' visual image interpretation process to reduce their workload in interpreting images. Focusing on the dune segmentation task, we proposed an approach called featuring a deep dune segmentation model to identify dunes and label their ranges in an automated way. By developing a tool to connect our model with ArcGIS—one of the most popular workbenches for visual interpretation, geographers can further refine the automatically generated dune segmentation on images without learning any CV or deep learning techniques. Our approach thus realized a noninvasive change to geographers' visual interpretation routines, reducing their manual efforts while incurring minimal interruptions to their work routines and tools they are familiar with. Deployment with a leading Chinese geography research institution demonstrated the potential of in supporting geographers in researching and solving drylands desertification.