Image Interpretation Research Articles

Knowledge and Confidence Among Five Cohorts of Faculty Learners in a Point of Care Ultrasound (POCUS) Program: Factors Defining Learner Success

Background: The availability of faculty proficient in point of care ultrasound (POCUS) has emerged as a barrier to the ongoing expansion of POCUS across the field of internal medicine. We sought to examine the faculty graduates of our institutional POCUS program to identify characteristics associated with long-term proficiency to inform curricula and guide institutional support. Methods: We emailed a test and survey to the 89 faculty graduates of the annual POCUS course we have run from 2018-2023. Results: Of the 46 participants (52%) who completed the test and survey, the overall median test score was 72%. Graduates were most confident with image acquisition of the lung, and were most likely to use ultrasound to evaluate ascites and dyspnea. All 11 participants reporting completion of an image portfolio were actively teaching POCUS, whereas only 54% of non-completers were teaching. Portfolio completers scored higher on the test compared to non-completers (median 92% and 68%, respectively, p <0.01) and were more confident in image acquisition and interpretation (p<0.001). Conclusions: In this long-term, single-institutional study of faculty graduates of an annual POCUS program, those who reported completing an image portfolio scored significantly higher on a knowledge test, reported higher confidence with image acquisition and interpretation, and reported using and teaching POCUS more frequently compared to graduates who did not complete the portfolio. POCUS education programs should be designed to foster continuous scanning practice and image portfolio completion.

Urban expansion and agricultural land loss: a GIS-Based analysis and policy implications in Hawassa city, Ethiopia

This study investigated the historical and future trends of urban expansion and its subsequent impact on agricultural land-use in Hawassa city, Ethiopia. A time-series of remote-sensing imageries from Landsat Thematic Mapper for the years 1984, 1990, 2000, and 2010 and Operational Land Imager for 2021 were used to extract the LULC information from the study area. Seven major land-cover classes’ waterbody, built-up, agricultural land, wetland, grassland, woody vegetation, and agroforestry were identified with visual image interpretation along with supervised image classification techniques using the maximum-likelihood algorithm for the study years. The urban and agricultural lands were then extracted from the original LULC data to quantify the extent, rates, and number of area conversion between the two. The Land Change Modeler module of TerrSet software was used to predict the spatial extents of built-up and agricultural lands in 2030 and 2050. The results showed that there have been significant changes between the LULC types in Hawassa city within the past 37 years, from which built-up and agricultural land have shown the most prevalent changes. It showed that built-up land has increased from 584.73 ha in 1,984–3,939.03 ha in 2021, representing a 573.65% increase at an annual growth rate of 15.50%. However, agricultural land decreased from 8,324.64 ha to 3,595.68 ha in the respective years, with a 56.81% decrease at a rate of −1.54% each year. A total of 3,148.74 ha (37.82%) of agricultural land was converted into built-up land within the past 37 years (85.10 ha per year, a rate of 1.02%. The built-up land is projected to increase to 5,009.85 ha and 6,794.73 ha from 2021 to 2030 and 2050, with annual growth rates of 3.02% and 2.50%, respectively. In the same years, agricultural land will decrease to 2,849.58 ha and 2033.46 ha by 2.31% and 1.50% annually, respectively, from which 64.76 ha (1.80%) and 48.41 ha (1.35%) will be converted into built-up land, respectively. Future planning and development in the city should consider the rapid increase in built-up land toward agricultural land areas and develop appropriate adaptation mechanisms for the local community, which is highly dependent on agriculture.

Precision Oncology in Melanoma: Changing Practices.

Over the last 2 decades, significant progress has been made in our understanding of the genomics, tumor immune microenvironment, and immunogenicity of malignant melanoma. Historically, the prognosis for metastatic melanoma was poor because of limited treatment options. However, after multiple landmark clinical trials displaying the efficacy of combined BRAF/MEK inhibition for BRAF-mutant melanoma and the application of immune checkpoint inhibitors targeting the programmed death-1, cytotoxic T-lymphocyte antigen-4, and lymphocyte activation gene-3 molecules, overall survival rates have dramatically improved. The role of immune checkpoint inhibition has since expanded to the neoadjuvant and adjuvant settings with multiple regimens in routine use. Personalized therapies, including tumor-infiltrating lymphocytes that are extracted from a patient's melanoma and eventually reinfused into the patient, and messenger RNA vaccines used to target neoantigens unique to a patient's tumor, show promise. Improvements in accompanying imaging modalities, particularly within the field of nuclear medicine, have allowed for more accurate staging of disease and assessment of treatment response. Continued growth in the role of nuclear medicine in the evaluation of melanoma, including the incorporation of artificial intelligence into image interpretation and use of radiolabeled tracers allowing for intricate imaging of the tumor immune microenvironment, is expected in the coming years.

Accuracy of interpretation of nasogastric tube position on chest radiographs by diagnostic radiographers: A multi-case, multi-reader study.

Feeding via a misplaced nasogastric tube (NGT) is a common but preventable cause of patient harm. The aim of this study was to determine the accuracy of diagnostic radiographers' assessment of NGT position on chest radiographs (CXRs) and safe-to-feed decisions. A multi-case, multi-reader study was conducted using an online image interpretation platform. A test bank consisting of 15 CXRs with an NGT in-situ was created. Diagnostic radiographers without formal qualifications in CXR interpretation were recruited via two international conferences. Participants placed an electronic marker on each CXR to identify the location of the tip of the NGT and indicated whether or not they believed that the tube was safely positioned. 68 participants were recruited. Each participant reviewed 15 CXRs, providing 1020 unique image assessments. 76% (n=778/1020) image assessments were completely correct (both the position of the tip of the NGT was accurately located and an appropriate safe-to-use decision made). In 5% (n=56/1020) of cases the NGT was safely positioned and the location of the tip was correctly identified by the participant but the tube was erroneously determined to be unsafe for feeding. In a further 6% (n=59/1020) of cases the participant correctly located the tip of an NGT in an unsafe position but indicated that the tube was safe to use. Participants failed to correctly identify the tip of the NGT in the remaining 12% (n=127/1020) of cases. Consistent with previous studies involving other staff groups, diagnostic radiographers without formal qualification in CXR interpretation can assess NGT positioning on radiographs with moderate accuracy but require further training, including strategies for the identification of poorly-visualised tube tips, to achieve the 100% accuracy necessary for this safety-critical task. A bespoke training programme which includes teaching on image quality, tube tip identification and assessment of tube positioning using the National Patient Safety Agency (NPSA) four criteria, should be delivered prior to implementation of a radiographer-led NGT CXR evaluation service.

A call for objectivity: Radiologists' proposed wishlist for response evaluation in solid tumors (RECIST 1.1).

The Response Evaluation in Solid Tumors (RECIST) 1.1 provides key guidance for performing imaging response assessment and defines image-based outcome metrics in oncology clinical trials, including progression free survival. In this framework, tumors identified on imaging are designated as either target lesions, non-target disease or new lesions and a structured categorical response is assigned at each imaging time point. While RECIST provides definitions for these categories, it specifically and objectively defines only the target disease. Predefined thresholds of size change provide unbiased metrics for determining objective response and disease progression of the target lesions. However, worsening of non-target disease or emergence of new lesions is given the same importance in determining disease progression despite these being qualitatively assessed and less rigorously defined. The subjective assessment of non-target and new disease contributes to reader variability, which can impact the quality of image interpretation and even the determination of progression free survival. The RECIST Working Group has made significant efforts in developing RECIST 1.1 beyond its initial publication, particularly in its application to targeted agents and immunotherapy. A review of the literature highlights that the Working Group has occasionally employed or adopted objective measures for assessing non-target and new lesions in their evaluation of RECIST-based outcome measures. Perhaps a prospective evaluation of these more objective definitions for non-target and new lesions within the framework of RECIST 1.1 might improve reader interpretation. Ideally, these changes could also better align with clinically meaningful outcome measures of patient survival or quality of life.

Performance of a Deep Learning System and Performance of Optometrists for the Detection of Glaucomatous Optic Neuropathy Using Colour Retinal Photographs

Background/Objectives: Glaucoma is the leading cause of irreversible blindness, with a significant proportion of cases remaining undiagnosed globally. The interpretation of optic disc and retinal nerve fibre layer images poses challenges for optometrists and ophthalmologists, often leading to misdiagnosis. AI has the potential to improve diagnosis. This study aims to validate an AI system (a convolutional neural network based on the Inception-v3 architecture) for detecting glaucomatous optic neuropathy (GON) using colour fundus photographs from a UK population and to compare its performance against Australian optometrists. Methods: A retrospective external validation study was conducted, comparing AI’s performance with that of 11 AHPRA-registered optometrists in Australia on colour retinal photographs, evaluated against a reference (gold) standard established by a panel of glaucoma specialists. Statistical analyses were performed using sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC). Results: For referable GON, the sensitivity of the AI (33.3% [95%CI: 32.4–34.3) was significantly lower than that of optometrists (65.1% [95%CI: 64.1–66.0]), p < 0.0001, although with significantly higher specificity (AI: 97.4% [95%CI: 97.0–97.7]; optometrists: 85.5% [95%CI: 84.8–86.2], p < 0.0001). The optometrists demonstrated significantly higher AUROC (0.753 [95%CI: 0.744–0.762]) compared to AI (0.654 [95%CI: 0.645–0.662], p < 0.0001). Conclusion: The AI system exhibited lower performance than optometrists in detecting referable glaucoma. Our findings suggest that while AI can serve as a screening tool, both AI and optometrists have suboptimal performance for the nuanced diagnosis of glaucoma using fundus photographs alone. Enhanced training with diverse populations for AI is essential for improving GON detection and addressing the significant challenge of undiagnosed cases.

Abstract 4138722: Large Language Model based multi-agent Transcatheter Aortic Valve Implantation team to augment multidisciplinary meetings - proof of concept.

Introduction: Multidisciplinary team (MDT) discussions are integral to Transcatheter Aortic Valve Implantation (TAVI) decision making. Large language model (LLM) ubiquity and low-code no-code platforms have enabled clinician lead solution development. Specialised chatbots or ‘agents’ have evolved into multi-agent systems that can personify human collaboration. We assess the performance of an artificial intelligence (AI) multi-agent TAVI MDT. Methods: Four de-identified TAVI cases from two metropolitan Australian hospitals were assessed by a mock human TAVI MDT (h-MDT) and an AI multi-agent TAVI MDT (ai-MDT). The ai-MDT was created with Agentflow within Flowise AITM and had a hierarchical multi-agent architecture suited to complex reasoning required for TAVI MDT simulation (figure). LLM limitations necessitated the ai-MDT rely on imaging reports rather than clinical images. The h-MDT and ai-MDT consisted of similar team members. Outputs from the h-MDT and ai-MDT was adjudicated by a panel of four blinded TAVI doctors that determined if output was human vs AI and assigned a SMIC score (4-12, 4=good, 12=poor) that assessed structure, missing information, incorrect information and clinical utility. Time durations for h-MDT and ai-MDT were recorded. Results: Adjudicators differentiated human vs. AI output 100% of the time and ai-MDT output had better SMIC scores than h-MDT (U-stat 213, p=0.0011). ai-MDT outperformed h-MDT in the domains of structure, missing information and clinical utility but was not statistically different in the incorrect information domain (U-stat 132, p=0.88). The average time for each case in h-MDT was 15 minutes and 45 seconds compared to 97 seconds for ai-MDT. Conclusion: This demonstrates the potential of using LLM based multi-agent systems as a clinical adjunct in highly specialized multidisciplinary clinical meetings. AI responses were superior for structure, clinical utility and missing information and non-inferior for incorrect information compared to humans, which highlights that hallucinations remain an issue with generative AI. Time was saved but image interpretation still requires human input, for now. Cognitive AI continues to require human supervision for implementation.

A Radio Frequency Interference Screening Framework—From Quick-Look Detection Using Statistics-Assisted Network to Raw Echo Tracing

Synthetic aperture radar (SAR) is often affected by other high-power electromagnetic devices during ground observation, which causes unintentional radio frequency interference (RFI) with the acquired echo, bringing adverse effects into data processing and image interpretation. When faced with the task of screening massive SAR data, there is an urgent need for the global perception and detection of interference. The existing RFI detection method usually only uses a single type of data for detection, ignoring the information association between the data at all levels of the real SAR product, resulting in some computational redundancy. Meanwhile, current deep learning-based algorithms are often unable to locate the range of RFI coverage in the azimuth direction. Therefore, a novel RFI processing framework from quick-looks to single-look complex (SLC) data and then to raw echo is proposed. We take the data of Sentinel-1 terrain observation with progressive scan (TOPS) mode as an example. By combining the statistics-assisted network with the sliding-window algorithm and the error-tolerant training strategy, it is possible to accurately detect and locate RFI in the quick looks of an SLC product. Then, through the analysis of the TOPSAR imaging principle, the position of the RFI in the SLC image is preliminarily confirmed. The possible distribution of the RFI in the corresponding raw echo is further inferred, which is one of the first attempts to use spaceborne SAR data to ‌elucidate the RFI location mapping relationship between image data and raw echo. Compared with directly detecting all of the SLC data, the time for the proposed framework to determine the RFI distribution in the SLC data can be shortened by 53.526%. All the research in this paper is conducted on Sentinel-1 real data, which verify the feasibility and effectiveness of the proposed framework for radio frequency signals monitoring in advanced spaceborne SAR systems.

Emerging technologies and applications in multimodality imaging for ischemic heart disease: current state and future of artificial intelligence

Ischemic heart disease (IHD) is a major global health issue, frequently resulting in myocardial infarction and ischemic cardiomyopathy. Prompt and precise diagnosis is essential to avert complications such as heart failure and sudden cardiac death. Although invasive coronary angiography remains the gold standard for high-risk patients, noninvasive multimodality imaging is becoming more prevalent for those at low-to-intermediate risk. This review evaluated the current state of multimodality imaging in IHD, including echocardiography, nuclear cardiology, cardiac magnetic resonance imaging (MRI), computed tomography (CT) angiography, and invasive coronary angiography. Each modality has distinct strengths and limitations, and their complementary use provides a comprehensive assessment of cardiac health. Integrating artificial intelligence (AI) into imaging workflows holds promise for enhancing diagnostic accuracy and efficiency. AI algorithms can optimize image acquisition, processing, and interpretation of complex imaging data. Emerging technologies like 4D flow MRI, molecular imaging, and hybrid systems [e.g., positron emission tomography (PET)/MRI, PET/CT] integrate anatomical, functional, and molecular data, providing comprehensive insights into cardiac pathology and potentially revolutionizing the management of IHD. This review also explored the clinical applications and impact of multimodality imaging on patient outcomes, emphasizing its role in improving diagnostic precision and guiding therapeutic decisions. Future directions include AI-driven decision support systems and personalized medicine approaches. Addressing regulatory and ethical challenges, such as data privacy and algorithm transparency, is crucial for the broader adoption of these advanced technologies. This review highlighted the transformative potential of AI-enhanced multimodality imaging in improving the diagnosis and management of IHD.

The Seismic Surface Rupture Zone in the Western Segment of the Northern Margin Fault of the Hami Basin and Its Causal Interpretation, Eastern Tianshan

The Eastern Tianshan region, influenced by the far-field effect of northward compression and expansion of the Qinghai-Xizang block, features highly developed Late Quaternary active faults that exhibit significant neotectonic activity. Historically, the Barkol-Yiwu Basin, located to the north of the Eastern Tianshan, experienced two major earthquakes in 1842 and 1914, each with a magnitude of M71/2. In contrast, the Hami Basin on the southern margin of the Eastern Tianshan has no historical records of any major earthquakes, and its seismic potential, mechanisms, and future earthquake hazards remain unclear. Based on satellite image interpretation and field surveys, this study identified a relatively recent and well-preserved seismic surface rupture zone with good continuity in the Liushugou area of the western segment of the Northern Margin Fault of the Hami Basin (HMNF), which is the seismogenic structure responsible for the rupture. The surface rupture zone originates at Kekejin in the east, extends intermittently westward through Daipuseke Bulake and Liushugou, and terminates at Wuzun Bulake, with a total length of approximately 21 km. The rupture zone traverses the youngest geomorphic surface units, such as river beds or floodplains and first-order terraces (platforms), and is characterized by a series of single or multiple reverse fault scarps. The morphology of fault scarps is clear, presenting a light soil color with heights ranging from 0.15 m to 2.13 m and an average displacement of 0.56 m, suggesting that this surface rupture zone likely represents the most recent seismic event. Comparison with historical earthquake records in the Eastern Tianshan region suggests that the rupture zone may have been formed simultaneously with the Xiongkuer rupture zone by the 1842 M71/2 earthquake along the boundary faults on both sides of the Barkol Mountains, exhibiting a flower-like structural pattern. Alternatively, it might represent a separate, unrecorded seismic event occurring shortly after the 1842 earthquake. The estimated magnitude of the associated earthquake is about 6.6~6.9. Given that surface-rupturing earthquakes have already occurred in the western segment, the study indicates that the Erdaogou–Nanshankou section of the HMNF has surpassed the average recurrence interval for major earthquakes, indicating a potential future earthquake hazard.

FET PET to differentiate between post-treatment changes and recurrence in high-grade gliomas: a single center multidisciplinary clinic controlled study.

The clinico-radiological dilemma in post-treatment high-grade gliomas, between disease recurrence (TR) and treatment-related changes (TRC), still persists. FET (Fluoro-ethyl-tyrosine) PET has been extensively used as problem-solving modality for cases where MR imaging is inconclusive. We incorporated a systematic imaging and clinical follow-up algorithm in a multi-disciplinary clinic (MDC) setting to analyse our cohort of FET PET in post-treatment gliomas. We retrospectively analyzed 171 patients of post-treatment grade III and IV glioma with equivocal findings on MRI. 185-222 MBq of 18F-FET was injected and dedicated static imaging of brain was performed at 20min. TBR (Tumor to background ratio) was used as semi-quantitative parameter. Cutoff of 2.5 was used for image interpretation. Imaging findings were confirmed with histopathological diagnosis, wherever available or in a multidisciplinary joint clinic based on serial imaging. 121 of 171 patients showed recurrent disease on FET PET, on follow up, 109 were confirmed with recurrence; 7 patients showed TRC, whereas 5 were treated with bevacizumab, with no further clinico-radiological deterioration, thus confirming TRC. 50 patients showed TRC on FET PET, on follow up on follow up, 40 were confirmed as true-negative. 10 patients who showed TBR less than 2.5 had confirmed TR on subsequent MR imaging. The overall sensitivity and specificity was 91.6 and 76.9% respectively, with a diagnostic accuracy of 87.13%. There is potential for FET PET to be used along with MRI in the post treatment algorithm of high-grade glial tumors.

Precision of artificial intelligence in paediatric cardiology multimodal image interpretation.

Multimodal imaging is crucial for diagnosis and treatment in paediatric cardiology. However, the proficiency of artificial intelligence chatbots, like ChatGPT-4, in interpreting these images has not been assessed. This cross-sectional study evaluates the precision of ChatGPT-4 in interpreting multimodal images for paediatric cardiology knowledge assessment, including echocardiograms, angiograms, X-rays, and electrocardiograms. One hundred multiple-choice questions with accompanying images from the textbook Pediatric Cardiology Board Review were randomly selected. The chatbot was prompted to answer these questions with and without the accompanying images. Statistical analysis was done using X2, Fisher's exact, and McNemar tests. Results showed that ChatGPT-4 answered 41% of questions with images correctly, performing best on those with electrocardiograms (54%) and worst on those with angiograms (29%). Without the images, ChatGPT-4's performance was similar at 37% (difference = 4%, 95% confidence interval (CI) -9.4% to 17.2%, p = 0.56). The chatbot performed significantly better when provided the image of an electrocardiogram than without (difference = 18, 95% CI 4.0% to 31.9%, p < 0.04). In cases of incorrect answers, ChatGPT-4 was more inconsistent with an image than without (difference = 21%, 95% CI 3.5% to 36.9%, p < 0.02). In conclusion, ChatGPT-4 performed poorly in answering image-based multiple-choice questions in paediatric cardiology. Its accuracy in answering questions with images was similar to without, indicating limited multimodal image interpretation capabilities. Substantial training is required before clinical integration can be considered. Further research is needed to assess the clinical reasoning skills and progression of ChatGPT in paediatric cardiology for clinical and academic utility.

Evidence of late quaternary activity of the Weining-Shuicheng Fault in Guizhou, China

Abstract The Weining-Shuicheng Fault (WSF) is a northwest-southeast trending fault in the southwest of the South China Block (SCB), which is an important component of the Yadu-Ziyun Fault Zone. The study of its activity is of great significance for analyzing the boundary role of the Daliangshan secondary block on the SCB. This paper derived the following results through field investigations, high-precision remote sensing image interpretation, UAV photogrammetry, trenching technique, and AMS 14C age. The WSF is northwest-trending with a sinistral strike-slip. It has a total displacement of about 2.5–3.2 km, which is equivalent to that of the southern section of the Daliangshan Fault. There are visible landforms such as fault scarps and fault valleys along the WSF, which control the development of the Caohai Basin. The gully near Weining Airport was caused by left lateral dislocations with a displacement of about 4 m. The Tashan trench revealed two branching faults, cutting the latest strata formed during about 13,000 BC. The Wangjiachong trench revealed five branching faults, cutting the latest strata formed during about 20,000 BC. The northern section of the WSF is flower-shaped tectonic features near the plane and activated in the Late Pleistocene.

Patterns of natural vegetation removal in the Caatinga biome in Prodes Project scope

Abstract. The native vegetation removal (NVR) of Caatinga Brazilian biome has been mapped by Prodes Project coordinated by National Institute for Spatial Research (INPE) between 2000 to 2023 year. Prodes is considered an official government product for achieving Brazilian and international targets for the conservation of natural vegetation. Therefore, Prodes is committed to achieving the highest possible accuracy associated with the history of mapping already carried out, by visual interpretation of satellite images and the use of past mapping masks techniques. Mapping NVR in Caatinga biome is a major challenge compared to biomes where the tree canopy with native vegetation prevails. Caatinga is one of the least protected of Brazilian biomes and is in one of the most pressured semi-arid regions on the planet. This work aims to present the NVR in Caatinga biome from Prodes data, in terms of its trajectory and main geographical patterns, concerning the municipalities, and areas that are the focus of monitoring, conservation or restoration. According to Prodes results, by 2023, the cumulative NVR in the entire Caatinga reached 43,05%; in 2000, this figure was 29,54%. The major NVR occurred in the easternmost areas of Caatinga and regions of Serrinha and Feira de Santana in Bahia State. Also, there are areas with considerable NVR further inside the biome, such as, Irecê and Guanambi region in Bahia, west of Pernambuco and Paraíba States and South and North of Ceará State. Areas prioritized for conservation actions showed high NVR values, indicating the urgent need for implementation of such actions. The fact that Desertification Cores showed low NVR values is important, and these regions should be closely monitored to prevent uncontrolled NVR rates. The two regions with high anthropic pressure or speculation showed contrasting behaviors; while the Araripe Gypsum Pole exhibited higher NVR levels compared to the control area, the São Francisco River integration project (PISF) so far does not appear significantly different from the rest of the biome. Overall, this study clearly demonstrates the potential of monitoring the Caatinga through Prodes in understanding and integrating the various factors influencing changes in the biome's native vegetation cover. Future approaches should move beyond descriptive studies to increasingly contribute to the territorial management of this important Brazilian region.

Accuracy of the Image Interpretation Capability of ChatGPT-4 Vision in Analysis of Hess Screen and Visual Field Abnormalities.

OpenAI, the owner of ChatGPT, publicly released the GPT-4 Vision in September 2023. This multimedia chatbot has the capability to receive and analyze various images presented to it by the user. We assessed the accuracy of its interpretation of 2 of the images commonly used in neuro-ophthalmology, namely Hess screen and automated visual field images. We separately uploaded typical images of 5 abnormal Hess screen charts related to third, fourth, and sixth cranial nerve palsy, Brown syndrome, and inferior orbital wall fracture with entrapment of the inferior rectus muscle. Likewise, 5 classic images of automated visual field grayscale maps related to lesions of the optic nerve, the chiasma, the optic tract, the optic radiations, and the occipital lobe were presented. The chatbot was instructed to select the best option among the 5 choices presented in each question. The GPT-4 Vision was able to select the right choice in 2/5 questions on Hess screens and 3/5 of the visual field questions. Despite selection of the correct option, qualitative evaluation of GPT-4 responses revealed flawed analysis of certain aspects of some image findings, such as the side of involvement or the misinterpretation of the physiologic blind spot as a central scotoma. The performance of GPT-4 Vision in the interpretation of abnormalities of Hess screen and visual field involvement was highly variable, even with simple typical cases of classic disorders. As the chatbot's image recognition is currently evolving, its capacity to accurately interpret ophthalmologic images is still limited at this time.

Spatiotemporal trends and drivers of forest cover change in Metekel Zone forest areas, Northwest Ethiopia.

The spatiotemporal dynamics of forest cover are essential for understanding the patterns and processes of forest change over time and space. This research focused on the spatiotemporal trends and drivers of forest cover change in the Metekel Zone of Northwest Ethiopia. Landsat 5, Landsat 7, and Landsat 8 imagery, covering the period from 1986 to 2019, were used for land use/cover classification. Land use/cover classification was performed using random forest (RF) and support vector machine (SVM) algorithms in the Google Earth Engine (GEE) platform, with training samples obtained through visual image interpretation. Spectral indices, such as the normalized difference vegetation index, soil-adjusted vegetation index, leaf area index, and normalized difference water index, were analyzed to examine forest cover dynamics over time. In addition, key informant interviews (KIIs) and focus group discussions (FGDs) were conducted. Findings revealed that forest cover decreased significantly from 51.37% in 1986 to 17.20% in 2019, driven largely by human activities such as agricultural expansion, increased demand for firewood, and urban expansion. Findings from spectral indices further corroborated the finding that forest cover in the study region (mainly in the southwestern part) substantially decreased from 1986 to 2019. Concerning forest depletion, the lack of local community awareness has become a key challenge. This problem is attributed to communities prioritizing immediate needs such as fuel and land for agriculture over long-term forest conservation. To combat ongoing deforestation, the Metekel Zone Administration, in collaboration with the land administration office and other stakeholders, revisited and strengthened existing forest policies and control systems. It is also suggested that community awareness, chiefly among youth, should be enhanced through the strategic expansion of formal and nonformal educational initiatives, which empower the youth as agents of change and promote the dissemination of knowledge throughout the community.

A quantitative needs assessment for a tele-ultrasound consult program in a tertiary care Emergency Department.

Point-of-care ultrasound (POCUS) has been shown to be beneficial in facilitating patient care, but its adoption is variable among emergency medicine (EM) clinicians. We identified the patterns of POCUS use and gaps in POCUS integration in a tertiary care emergency department (ED). These data provide a user-centered platform for subsequent development of a tele-ultrasound (tele-US) consultation program. We developed a 25-item needs assessment survey and used a 5-point Likert scale to assess current patterns of POCUS use and potential needs for POCUS among EM clinicians. Data were analyzed descriptively, and a chi-square analysis was used to assess for differences in POCUS use and comfort levels among clinicians. Overall, 48% (91/190) of eligible providers responded to the survey. Clinician responders included 38% (35/91) attendings (including fellows), 29% (26/91) residents, and 33% (30/91) advance practice providers (APPs). In assessing needs, 70% (58/83) of clinicians noted they would use POCUS more if they had more training. 76% (63/83) of clinicians felt comfortable with image acquisition and 68% (56/83) with image interpretation. APPs were less comfortable with POCUS image interpretation and clinical integration of POCUS findings compared to residents (χ2: 16.3, p < 0.0001 and χ2: 5.1, p = 0.02, respectively). 65% (54/83) of clinicians would use POCUS more if real-time supervision via tele-US was available for image acquisition and image interpretation. EM clinicians indicated a substantial need for further real-time POCUS training and supervision, especially for image interpretation. A clinician-centered strategy, such as tele-US, has potential to increase proficient use of POCUS.

Remote Sensing Data Quality in the Era of AI

Abstract. The era of Artificial Intelligence ‘AI’ with all the benefits brought along, has raised new and additional challenges to the ongoing efforts of assessing, defining, formulating, and implementing the quality aspects of geospatial remote sensing data. Developed practices using artificial intelligence leveraged techniques such as image interpretation, classification, thematic mapping, and even image quality enhancement, necessitating by that the reassessment and redevelopment of some of the related emerging quality aspects. Moreover, technology also made the generation of false images and false data possible, this matter constrained and increased precaution and doubtfulness, altogether making some practices based on that data almost halt to further notice. This paper presents the collaborative research work to assess and clarify the quality aspects that arose with the advent and implementation of AI and associated technologies; the concerns and issues that can accompany the generation of false satellite and aerial images including the generated geospatial data out of which, how the new emerged quality aspects fit into the currently existing methods through the lifecycle of remote sensing data production and usage, and consequently how the quality dimensions are affected and should be further developed and improved to tackle the changes and innovations. Also, lame a bit on investigating how to accommodate the new challenges in standards, and practical procedures and raise the awareness to users, the level of dependency on improved and enhanced satellite images when it comes to data collection interpretation and classification, and finally define the research gaps, future expected challenges and thus enclose suggestions and recommendations in that respect.

Diagnostic Performance of a Next-Generation Virtual/Augmented Reality Headset: A Pilot Study of Diverticulitis on CT.

Next-generation virtual/augmented reality (VR/AR) headsets may rival the desktop computer systems that are approved for clinical interpretation of radiologic images, but require validation for high-resolution low-luminance diagnoses like diverticulitis. The primary aim of this study is to compare diagnostic performance for detecting diverticulitis on CT between radiologists using a headset versus a desktop. The secondary aim is to survey participating radiologists about the usage of both devices. This pilot study retrospectively included 110 patients (mean age 64 ± 14 years, 62 women) who had abdomen/pelvis CT scans for which the report mentioned the presence or absence of diverticulitis. Scans were dichotomized and matched by time, for a total of 55 cases with diverticulitis and 55 controls with no diverticulitis. Six radiologists were oriented to the VR/AR headset (Apple Vision Pro) and viewer app (Visage Ease VP) using ten scans. They each scored 100 unknown scans on a 6-level scale for diverticulitis (1 = no diverticulitis, 6 = diverticulitis) on the headset and then on a desktop. Timepercase was recorded. Finally, they completed a survey using 5-level scales about the ease of use of the headset and viewer app (1 = difficult, 5 = easy), about their experience with the headset (1 = bad, 5 = good), and about their preference between devices (1 = desktop, 5 = headset). Summary statistics and multi-reader multi-case ROC curves were calculated. The AUC (and 95% confidence interval) for diverticulitis was 0.93 (0.88-0.97) with the headset and 0.94 (0.91-0.98) with the desktop (p = 0.40). The median (and first-third quartiles) of timepercase was 57 (41-76) seconds for the headset and 31 (22-64) seconds for the desktop (p < 0.001). Average survey scores ranged from 3.3 to 5 for ease of use, from 3 to 4.7 for experience, and from 2.2 to 3.3 for preference. Diagnostic performance for detecting diverticulitis on CT was similar between the next-generation VR/AR headset and desktop. Ease of use, experience, and preference varied across different aspects of the devices and among radiologists.

TopoSense: agent driven topological graph extraction from remote sensing image

Abstract. Automatic topological graph extraction is critical for intelligent remote sensing image interpretation and cartographic representation. However, existing approaches neither adopt segmentation-based post-processing nor directly predict the graph, thereby suffering from limited scalability and poor adaptability to complex spatial structures. To address these issues, we introduce TopoSense, an innovative framework for extracting topological graphs from remote sensing images through an agent-driven approach. By employing a novel combination of reinforcement learning and neural network architectures, TopoSense autonomously navigates through pixel-level data, efficiently constructing topological representations. It not only enhances the accuracy of spatial feature detection, but also significantly reduces processing time. Experiments on the TOP-BOUNDARY and REALSCENE demonstrate its superiority in capturing intricate spatial relationships compared to traditional methods.