X-ray Scan Research Articles

Effect of X-ray scan quality on the collective effective dose in patients in telemedicine

BACKGROUND: The key objective of a healthcare provider is to ensure the quality and increase the efficiency of X-ray diagnostics in both municipal and private medical facilities. A poor-quality radiologic image requires repeated procedures, which results in further reputation, time, and economic losses for the medical organization. Moreover, repeated examinations further contribute to the patient’s total radiation exposure. AIM: To assess the contribution of poor-quality X-ray examinations to patient exposure in outpatient medical organizations with telemedicine services. MATERIALS AND METHODS: This study aimed to evaluate poor-quality X-ray examinations recorded by radiologists at the Moscow Reference Center in 2022 by applying a specially developed quality control system for diagnostic examinations based on information technology. In addition, during X-ray examinations, the methods for finding effective doses received by patients were applied in compliance with current regulatory requirements. Statistical methods were also used. RESULTS: In this study, 2,059 poor-quality examinations were recorded, accounting for 0.084% of the total number of examinations interpreted with telemedicine. The collective effective dose from poor-quality examinations was 3.613 man-Sv, which was 0.11% of the total collective dose of patients in outpatient medical organizations. CONCLUSION: The implementation of a quality control system for diagnostic examinations based on information technology proved to be efficient for medical organizations rendering telemedicine services.

Limitations of using artificial intelligence services to analyze chest x-ray imaging

BACKGROUND: Chest X-ray examination is one of the first radiology areas that started applying artificial intelligence, and it is still used to the present. However, when interpreting X-ray scans using artificial intelligence, radiologists still experience several routine restrictions that should be considered in issuing a medical report and require the attention of artificial intelligence developers to further improve the algorithms and increase their efficiency. AIM: To identify restrictions of artificial intelligence services for analyzing chest X-ray images and assesses the clinical significance of these restrictions. MATERIALS AND METHODS: A retrospective analysis was performed for 155 cases of discrepancies between the conclusions of artificial intelligence services and medical reports when analyzing chest X-ray images. All cases included in the study were obtained from the Unified Radiological Information Service of the Unified Medical Information and Analytical System of Moscow. RESULTS: Of the 155 analyzed difference cases, 48 (31.0%) were false-positive and 78 (50.3%) were false-negative cases. The remaining 29 (18.7%) cases were removed from further studies because they were true positive (27) or true negative (2) in the expert review. Most (93.8%) of the 48 false-positive cases were due to the artificial intelligence service mistaking normal chest anatomy (97.8% of cases) or catheter shadow (2.2% of cases) for pneumothorax signs. Overlooked clinically significant pathologies accounted for 22.0% of false-negative scans. Nearly half of these cases (44.4%) were overlooked lung nodules. Lung calcifications (60.9%) were the most common clinically insignificant pathology. CONCLUSIONS: Artificial intelligence services demonstrate a tendency toward over diagnosis. All false-positive cases were associated with erroneous detection of clinically significant pathology: pneumothorax, lung nodules, and pulmonary consolidation. Among false-negative cases, the rate of overlooked clinically significant pathology was low, which accounted for less than one-fourth.

QCT/FEA analyses of palateless splinted and unsplinted maxillary all-on-4 systems

The goal of the presented study was to determine the viability of using splinted and unsplinted maxillary implant-supported overdentures. The main physical quantity used to evaluate their differences was compressive stress in bone and equivalent (von Mises) stress in the implant and overdenture components. We took a 3D X-ray scan of the maxilla and imported the data into a QCT/FEA (Quantitative Computed Tomography-based Finite Element Analysis) software. The loading was done in three load cases. We designed both models of the overdentures in CAD, included the polyetheretherketone (PEEK) overdenture and analyzed the whole model of the reconstructed maxilla with implants. The results show worse (more concentrated) compressive stress distributions for the unsplinted locator variant. The splinted, bar-retained variant shows lower values of stress in all load cases. These findings and their potential for real-time selection of the optimal variant are then further discussed.

RADIOLOGICAL ASSESSMENT OF SPONDYLOLISTHESIS OF LUMBOSACRAL SPINE

Introduction: One major injury or frequent minor injuries cause the vertebral body, pedicle and superior articular surfaces to slide forward. This disorder is known as spondylolisthesis and is usually accompanied by symptoms, often proportional to the degree of forward movement. Patients may complain of pain in the lower back that spreads to the thighs, and limited range of motion is possible Objectives: The aim of this study is to determine the frequency of spondylolisthesis by age and gender in the patients studied at SKB Mostar. Research methodology: The method of content analysis was used to retrospectively examine X-ray, CT and MRI examinations of patients with the clinical features of lumbar pain syndrome in the period from 1 January 2019 to 1 January 2020 in patients who underwent radiological examination of the LS spine at the Clinical Institute of Radiology of the University Clinical Hospital Mostar. Data were collected from IMPAX at the SKB Mostar Department of Radiology. The input parameters that were observed were: pain syndrome, diagnosis. The output parameters were the radiological findings from the X-ray, CT, and MRI scans. Results: During the study period, 297 spinal scans were performed, and spondylolisthesis was found in 32 patients, or 11%. The youngest respondent was 8 years old, and the oldest was 85 years old. The average age of the respondents was 64.37 years. The largest number of respondents was in the age group of over 75 years old. Of the tests performed, the most common were CT scans, followed by MRI, and the rarest were X-ray scans. The highest prevalence of spondylolisthesis was found in vertebrae L4-L5 and L5-S1 at 41%. Spondylolisthesis was found bilaterally in 9% of cases at the L3-L4 and L5 vertebrae. Conclusion: Most often, spondylolisthesis is found in L4-L5 and L5-S1 vertebrae. There was no difference according to gender, and most often subjects older than 75 years had spondylolisthesis.

Non-Destructive Wood Analysis Dataset: Comparing X-Ray and Terahertz Imaging Techniques

Wood density measurement plays a crucial role in assessing wood quality and predicting its mechanical performance. This dataset was collected to compare the accuracy and reliability of two non-destructive techniques, X-rays and terahertz waves, for measuring wood density. While X-rays have been commonly used in the industry due to their effectiveness, they pose health risks due to ionizing radiation. Terahertz waves, on the other hand, are non-ionizing and offer high spatial resolution. This article presents a database of wood samples measurements obtained using both techniques, on the same 110 samples with a fine location of the measuring points, on a wide range of wood species (tropical and temperate ones) and densities, from 111 kg·m−3 to 1086 kg·m−3. The database includes X-ray and terahertz scans, sample dimensions, moisture content, and color photographs.

A Novel Unilateral Bi/Multi-Portal Endoscopic Transforaminal Interbody Fusion Utilizing Uniaxial Spinal Endoscope Instead of Arthroscope: Technical Note and Preliminary Clinical Results.

Currently, traditional UBE surgery, which is based on arthroscope, has been increasingly employed for complex lumbar degenerative diseases. However, this approach is associated with complications such as intraoperative dural sac tears, nerve root injuries, and postoperative epidural hematomas. In response to these challenges, we propose a novel technique utilizing uniaxial spinal endoscope to replace arthroscope-Unilateral Bi/Multi-Portal Endoscopy (UME). This new method has successfully treated complex lumbar disc herniation and spinal stenosis, resulting in improved postoperative outcomes and a reduction in complications. Based on the previous findings, we utilized uniaxial spinal endoscopy as the primary operating method, with the assistance of multi-portal endoscopic techniques (UME-TLIF), to perform transforaminal lumbar interbody fusion. The feasibility and preliminary clinical results have been presented in this paper. A total of 18 patients (8 men and 10 women, aged 52.6 ± 15.29 years) diagnosed with lumbar degenerative diseases, such as giant lumbar disc herniation, severe lumbar spinal stenosis, or lumbar spondylolisthesis, were included in this study from January 2022 to March 2023. Various parameters including operation time, ambulatory time, intraoperative fluoroscopy times, hospitalization days, and complications were recorded during the perioperative period. Clinically relevant symptoms were evaluated and documented 1, 3, 6, and 12 months postoperatively. Visual analogue scale (VAS) scores for lower back pain and leg pain, as well as the Oswestry disability index (ODI), were measured. The extent of lumbar interbody fusion was assessed using lumbar X-ray and CT scans at the 12-months follow-up. MRI was performed to assess the degree of nerve decompression in patients at the same time points. The paired t-test or Wilcoxon signed-rank test were used as statistical methods. The single-segment UME-TLIF procedure had an average operation time of 211 ± 53.3 min, and the average number of X-rays taken during the operation was 11.78 ± 5.32. Patients were able to walk and perform functional exercises approximately 35.11 ± 8.41 h post-surgery, and the average duration of hospital stay was 8.5 ± 2.27 days. The VAS and ODI values at each time point post-surgery were significantly lower than the respective pre-surgery values (p < 0.05). Two patients developed postoperative sensory disturbances which significantly improved with conservative treatment. Furthermore, a follow-up CT scan conducted 12 months post-surgery showed 100% fusion rate of the surgical segments in all patients. UME-TLIF is an endoscopy-assisted fusion procedure that minimizes muscle damage in patients and allows early rehabilitation. This technique broadens the surgical applications of uniaxial spinal endoscope as a surgical tool, particularly benefitingpatients diagnosed with severe lumbar disc herniation and lumbar instability.

Classification of Pneumonia via a Hybrid ZFNet-Quantum Neural Network Using a Chest X-ray Dataset.

Deep neural networks (DNNs) have made significant contributions to diagnosing pneumonia from chest X-ray imaging. However, certain aspects of diagnosis and planning can be further enhanced through the implementation of a quantum deep neural network (QDNN). Therefore, we introduced a technique that integrates neural networks with quantum algorithms named the ZFNet-quantum neural network for detecting pneumonia using 5863 X-ray scans with binary cases. The hybrid model efficiently pre-processes complex and high-dimensional data by extracting significant features from the ZFNet model. These significant features are given to the quantum circuit algorithm and further embedded into a quantum device. The parameterized quantum circuit algorithm using qubits, superposition theorem, and entanglement phenomena generates 4 features from 4098 features extracted from images via a deep transfer learning model. Moreover, to validate the outcome measures of the proposed technique, we used various PennyLane quantum devices to detect pneumonia and normal control images. By using the Adam optimizer, which exploits an adaptive learning rate that is fixed to 10-6 and six layers of a quantum circuit composed of quantum gates, the proposed model achieves an accuracy of 96.5%, corresponding to 25 epochs. The integrated ZFNet-quantum learning network outperforms the deep transfer learning network in terms of testing accuracy, as the accuracy gained by the convolutional neural network (CNN) is 94%. Therefore, we use a hybrid classical-quantum model to detect pneumonia in which a variational quantum algorithm enhances the outcomes of a ZFNet transfer learning method. This approach is an efficient and automated method for detecting pneumonia and could significantly enhance outcome measures related to the speed and accuracy of the network in the clinical and healthcare sectors.

Ratting on wildlife crime: training African giant pouched rats to detect illegally trafficked wildlife

The illegal wildlife trade (IWT) is one of the largest global crime economies, directly threatening species and their habitats, and biodiversity, and indirectly the global climate, and countries’ economies. Syndicates operating within the IWT are often involved in trafficking of humans, weapons, and drugs. IWT takes place in large scale through international ports, with wildlife being smuggled inside shipping containers. Current methods to combat IWT and screen these shipping containers, such as X-ray scans, are expensive and time-consuming. Scent-detection animals present an innovative approach to combatting IWT, as animals may be better suited to distinguish between organic materials and less susceptible to visual concealment methods. Previous scent-detection work has largely focused on conservation dogs (Canis lupus familiaris). Here, we present a series of proof-of-principle studies training African giant pouched rats (Cricetomys ansorgei) to detect illegally trafficked wildlife. As initial proof-of-principle within a controlled laboratory environment, we trained rats (n=11) to detect the scent of pangolin scales (Manis spp.) and a threatened African hardwood (Dalbergia melanoxylon). In subsequent experiments, we trained these rats (n=10) to detect rhinoceros horn (family Rhinocerotidae), and elephant tusks (Loxodonta spp.). At the conclusion of these studies, rats (n=7) accurately identified all four target species (although ivory samples may have been cross-contaminated, and results should be interpreted with caution) while correctly rejecting non-target items commonly used by traffickers to conceal the presence of illicit material. Rats detected the presence of wildlife targets even when these were concealed in mixtures among non-target items. These results provide the foundation to train rats for scent-detection of illegally trafficked wildlife to combat IWT. The unique attributes of rats could allow them to complement existing screening technologies in the fight against IWT. Rats have low training and maintenance costs, flexibly work with multiple handlers, have a long lifespan, and a sophisticated sense of smell. Their small size also offers unique capabilities for the screening of shipping containers, such as being able to navigate densely packed areas or be lifted to assess contents of sealed containers by screening ventilation systems. Future directions include assessing operational feasibility of deploying rats at ports.

A hybrid feature fusion deep learning framework for multi-source medical image analysis

Despite the widespread adoption of deep learning to enhance image classification, significant obstacles remain. First, multisource data with diverse sizes and formats is a great challenge for most current deep learning models. Second, lacking manual labeled data for model training limits the application of deep learning. Third, the widely used CNN-based methods shows their limitations in extracting global features and yield poor performance for image topology. To address these issues, we propose a Hybrid Feature Fusion Deep Learning (HFFDL) framework for image classification. This framework consists of an automated image segmentation module, a two-stream backbone module, and a classification module. The automatic image segmentation module utilizes the U-Net model and transfer learning to detect region of interest (ROI) in multisource images; the two-stream backbone module integrates the Swin Transformer architecture with the Inception CNN, with the aim of simultaneous extracting local and global features for efficient representation learning. We evaluate the performance of HFFDL framework with two publicly available image datasets: one for identifying COVID-19 through X-ray scans of the chest (30,386 images), and another for multiclass skin cancer screening using dermoscopy images (25,331 images). The HFFDL framework exhibited greater performance in comparison to many cutting-edge models, achieving the AUC score 0.9835 and 0.8789, respectively. Furthermore, a practical application study conducted in a hospital, identifying viable embryos using medical images, revealed the HFFDL framework outperformed embryologists.

Pre-trained quantum convolutional neural network for COVID-19 disease classification using computed tomography images.

The COVID-19 pandemic has had a significant influence on economies and healthcare systems around the globe. One of the most important strategies that has proven to be effective in limiting the disease and reducing its rapid spread is early detection and quick isolation of infections. Several diagnostic tools are currently being used for COVID-19 detection using computed tomography (CT) scan and chest X-ray (CXR) images. In this study, a novel deep learning-based model is proposed for rapid detection of COVID-19 using CT-scan images. The model, called pre-trained quantum convolutional neural network (QCNN), seamlessly combines the strength of quantum computing with the feature extraction capabilities of a pre-trained convolutional neural network (CNN), particularly VGG16. By combining the robust feature learning of classical models with the complex data handling of quantum computing, the combination of QCNN and the pre-trained VGG16 model improves the accuracy of feature extraction and classification, which is the significance of the proposed model compared to classical and quantum-based models in previous works. The QCNN model was tested on a SARS-CoV-2 CT dataset, initially without any pre-trained models and then with a variety of pre-trained models, such as ResNet50, ResNet18, VGG16, VGG19, and EfficientNetV2L. The results showed the VGG16 model performs the best. The proposed model achieved 96.78% accuracy, 0.9837 precision, 0.9528 recall, 0.9835 specificity, 0.9678 F1-Score and 0.1373 loss. Our study presents pre-trained QCNN models as a viable technique for COVID-19 disease detection, showcasing their effectiveness in reaching higher accuracy and specificity. The current paper adds to the continuous efforts to utilize artificial intelligence to aid healthcare professionals in the diagnosis of COVID-19 patients.

Deep Learning Methods for Detecting Chest X-Ray and CT Scan Abnormalities

Deep learning's quick development has created new opportunities to improve medical image analysis, especially in the identification of anomalies in chest CT and X-ray scans. This work investigates several deep learning techniques designed for this particular purpose to enhance the efficiency and accuracy of diagnosis in medical settings. We explore the use of 3D CNNs, transfer learning, and convolutional neural networks, or CNNs, for the analysis of volumetric CT scan information as well as 2D chest X-ray pictures. Comparative analyses show the benefits and drawbacks of various deep learning architectures for identifying a variety of anomalies, including tumors, tumors in the lungs, pneumonia, and other diseases. We also go over the significance of preprocessing methods, assessment metrics specifically designed for medical picture analysis, and dataset preparation. The results highlight how deep learning has the potential to revolutionize chest imaging diagnostics by facilitating the quicker and more accurate identification of anomalies, which will enhance patient outcomes and the effectiveness of healthcare delivery. To spur additional developments in the deep learning-powered analysis of medical images for chest problems, future research topics, and obstacles in this area are also covered.

Evaluating Explainable Artificial Intelligence (XAI) techniques in chest radiology imaging through a human-centered Lens.

The field of radiology imaging has experienced a remarkable increase in using of deep learning (DL) algorithms to support diagnostic and treatment decisions. This rise has led to the development of Explainable AI (XAI) system to improve the transparency and trust of complex DL methods. However, XAI systems face challenges in gaining acceptance within the healthcare sector, mainly due to technical hurdles in utilizing these systems in practice and the lack of human-centered evaluation/validation. In this study, we focus on visual XAI systems applied to DL-enabled diagnostic system in chest radiography. In particular, we conduct a user study to evaluate two prominent visual XAI techniques from the human perspective. To this end, we created two clinical scenarios for diagnosing pneumonia and COVID-19 using DL techniques applied to chest X-ray and CT scans. The achieved accuracy rates were 90% for pneumonia and 98% for COVID-19. Subsequently, we employed two well-known XAI methods, Grad-CAM (Gradient-weighted Class Activation Mapping) and LIME (Local Interpretable Model-agnostic Explanations), to generate visual explanations elucidating the AI decision-making process. The visual explainability results were shared through a user study, undergoing evaluation by medical professionals in terms of clinical relevance, coherency, and user trust. In general, participants expressed a positive perception of the use of XAI systems in chest radiography. However, there was a noticeable lack of awareness regarding their value and practical aspects. Regarding preferences, Grad-CAM showed superior performance over LIME in terms of coherency and trust, although concerns were raised about its clinical usability. Our findings highlight key user-driven explainability requirements, emphasizing the importance of multi-modal explainability and the necessity to increase awareness of XAI systems among medical practitioners. Inclusive design was also identified as a crucial need to ensure better alignment of these systems with user needs.

A case of early-onset congenital syphilitic osteomyelitis of the calcaneus and literature review

BackgroundCongenital syphilis (CS) is a sexually transmitted disease caused by Treponema pallidum (TP). When the skeletal system is involved, it often results in multiple, symmetrical bone destruction at the epiphyses of long tubular bones such as the humerus and radius, rarely involving the calcaneus. This article reports a case of calcaneal osteomyelitis caused by TP in a child with no other bone damage and subtle clinical manifestations, No similar cases have been reported.Case presentationA 4-month-old male infant presented with right foot swelling without any obvious cause and no history of trauma. X-ray and CT scans showed bone loss in the calcaneus and surrounding soft tissue swelling. Review of past medical records revealed that the infant had been diagnosed with CS infection during a hospital stay for “pneumonia” at one month old. The parents refused surgery, opting for conservative treatment at an external hospital for three weeks, during which the symptoms of the affected foot showed no significant improvement. Subsequently, the child was treated at our hospital with surgery, including lesion removal and cast fixation, followed by oral antibiotic treatment. The last follow-up showed no swelling or tenderness in the affected foot, with good mobility, and X-rays indicated that the bone had essentially returned to normal.ConclusionsEarly CS rarely involves the calcaneus. When diagnosing unexplained calcaneal osteomyelitis in infants, this rare cause should be considered. A thorough medical history should be taken and a careful physical examination conducted. Once diagnosed, timely surgical debridement and appropriate antibiotic therapy targeting TP infection are required. Early identification and intervention can result in a good prognosis without related complications.

Development of a clinical risk score for the prediction of Pneumocystis jirovecii pneumonia in hospitalised patients

BackgroundThe performance and availability of invasive and non-invasive investigations for the diagnosis of Pneumocystis jirovecii pneumonia (PCP) vary across clinical settings. Estimating the pre-test probability of PCP is essential to the optimal selection and interpretation of diagnostic tests, such as the 1,3-β-D-glucan assay (BDG), for the prioritization of bronchoscopy, and to guide empiric treatment decisions. We aimed to develop a multivariable risk score to estimate the pre-test probability of PCP.MethodsThe score was developed from a cohort of 626 individuals who underwent bronchoscopy for the purposes of identifying PCP in a Canadian tertiary-care centre, between 2015 and 2018. We conducted a nested case-control study of 57 cases and 228 unmatched controls. Demographic, clinical, laboratory, and radiological data were included in a multivariable logistic regression model to estimate adjusted odds ratios for PCP diagnosis. A clinical risk score was derived from the multivariable model and discrimination was assessed by estimating the score’s receiver operating characteristic curve.ResultsParticipants had a median age of 60 years (interquartile range [IQR] 49–68) and 115 (40%) were female; 40 (14%) had HIV and 49 (17%) had a solid organ transplant (SOT). The risk score included prior SOT or HIV with CD4 ≤ 200/µL (+ 2), serum lactate dehydrogenase ≥ 265.5 IU/mL (+ 2), radiological pattern typical of PCP on chest x-ray (+ 2) or CT scan (+ 2.5), and PCP prophylaxis with trimethoprim-sulfamethoxazole (-3) or other antimicrobials (-2). The median score was 4 points (IQR, 2-4.5) corresponding to a 28% probability of PCP. The risk prediction model had good discrimination with a c-statistic of 0.79 (0.71–0.84). Given the operating characteristics of the BDG assay, scores ≤ 3 in patients without HIV, and ≤ 5.5 in those with HIV, paired with a negative BDG, would be expected to rule out PCP with 95% certainty.ConclusionWe propose the PCP Score to estimate pre-test probability of PCP. Once validated, it should help clinicians determine which patients to refer for invasive investigations, when to rely on serological testing, and in whom to consider pre-emptive treatment.

Diagnostic approach to bone metastasis of unknown origin: a systematic review

BACKGROUND Among all MBD cases, 3% have an unidentified origin and are commonly misdiagnosed. On average, nearly 75% of MBD cases with an unknown origin take four months to diagnose. This difficulty in identifying the primary cancer limits the treatment of skeletal metastases to palliative measures, negatively impacting a patient’s prognosis. The purpose of this systematic review is to evaluate the current diagnostic work-up approaches available for MBD. METHODS This systematic review was carried out according to the guidelines of the (PRISMA) 2020 Statement, including studies with a population of interest of MBD with unknown primary origin. We excluded studies with non-English language and MBD cases with known origin. The intervention of the diagnostic approach was the primary outcome. The authors searched three electronic medical databases. Individual reviewers performed quality and risk of bias assessments. RESULTS All ten articles were cohort studies, with the median age of the subjects ranging from 55.6 to 65.2 years. The most frequently recommended supporting examination was biopsy, with a detection rate of 38.2%, followed by chest X-ray and CT scan, both with a detection rate of 26.7%. Overall, the detection rate of the primary lesion from individual examinations ranged from 2.8% to 38.2%, highlighting the difficulty of diagnosis when relying solely on a single examination. CONCLUSIONS Biopsy is crucial in identifying the primary lesion of metastatic bone disease with an unknown origin, with a detection rate of 38.2%, making it the most frequently recommended examination. However, this review has several limitations. A few assumptions were made in the synthesis of numerical data.

Understanding Rhododendron intraspecific compatibility in botanic garden collections for species conservation

Context Controlled pollination is an important technique for maintaining intraspecific diversity in integrated plant conservation practices, particularly in genera such as Rhododendron, where open pollination usually produces hybrids with unknown paternal lineages. Aims This study investigated the capacity for viable seed set from self- and intraspecific cross-pollination for Rhododendron taxa in different categories of the International Union for Conservation of Nature (IUCN) Red List, to guide conservation management of threatened species in botanic garden collections. Methods The following five taxa of subsection Maddenia were studied: R. dalhousiae var. dalhousiae (Least Concern), R. dalhousiae var. rhabdotum (Vulnerable), R. lindleyi (Least Concern), R. nuttallii (Near Threatened), and R. excellens (Vulnerable). Controlled pollination was performed on selected garden accessions, and seed germination was tested at an alternating temperature regime of 15/25°C, 8 h photoperiod, and ~6 μmol m−2 s−1 photosynthetic photon flux density (PPFD). Key results Intraspecific compatibilities varied among different taxa and between self- and outcross treatments. X-ray images for Rhododendron seeds showed low capacity to predict seed germination. Neither X-ray scan nor fungicide (Ridomil) treatment showed any adverse impact on seed germination, which has positive implications for seed-banking and subsequent raising of Rhododendron seedlings. Conclusions Controlled intraspecific pollination can be used to maintain diversity of ex situ accessions for selected Rhododendron species. However, the zero or low compatibility demonstrated in some species, such as R. excellens, suggests that these species may require a different approach. Implications Intraspecific pollination should be evaluated for each Rhododendron species before a propagation program is initiated in ex situ conservation.

An automated framework for pediatric hip surveillance and severity assessment using radiographs.

Hip dysplasia is the second most common orthopedic condition in children with cerebral palsy (CP) and may result in disability and pain. The migration percentage (MP) is a widely used metric in hip surveillance, calculated based on an anterior-posterior pelvis radiograph. However, manual quantification of MP values using hip X-ray scans in current standard practice has challenges including being time-intensive, requiring expert knowledge, and not considering human bias. The purpose of this study is to develop a machine learning algorithm to automatically quantify MP values using a hip X-ray scan, and hence provide an assessment for severity, which then can be used for surveillance, treatment planning, and management. X-ray scans from 210 patients were curated, pre-processed, and manually annotated at our clinical center. Several machine learning models were trained using pre-trained weights from Inception ResNet-V2, VGG-16, and VGG-19, with different strategies (pre-processing, with and without region of interest (ROI) detection, with and without data augmentation) to find an optimal model for automatic hip landmarking. The predicted landmarks were then used by our geometric algorithm to quantify the MP value for the input hip X-ray scan. The pre-trained VGG-19 model, fine-tuned with additional custom layers, outputted the lowest mean squared error values for both train and test data, when ROI cropped images were used along with data augmentation for model training. The MP value calculated by the algorithm was compared to manual ground truth labels from our orthopedic fellows using the hip screen application for benchmarking. The results showed the feasibility of the machine learning model in automatic hip landmark detection for reliably quantifying MP value from hip X-ray scans. The algorithm could be used as an accurate and reliable tool in orthopedic care for diagnosing, severity assessment, and hence treatment and surgical planning for hip displacement.

Multi-task learning for calcaneus fracture diagnosis of X-ray images

Fracture diagnosis is critical in clinical settings, and imaging modalities like X-ray and CT scans are crucial for bone fracture diagnosis. Although X-ray scans are more convenient and affordable, they are prone to misdiagnosis and missed diagnosis due to the limited number of poses that can be observed and the uneven distribution of grayscales. Deep learning methods show great potential in improving the efficiency and accuracy of x-ray fracture diagnosis.This paper proposes MTL-DlinkNet, a multi-task learning model based on D-linkNet, that can perform both classification tasks for automatic identification of calcaneus fractures, and segmentation tasks for generation of regions of interest (RoI). The model achieves high accuracy (0.989 AUC) while annotating the data at the same time, making diagnosis more efficient and reducing the burden on doctors. The paper also presents an intelligent diagnostic tool for calcaneus fracture that assists doctors in clinical settings. The main contributions of this work include building a dataset of foot X-rays for fracture diagnosis, proposing a better-performing fracture diagnosis deep learning model, and developing an efficient diagnostic tool. Experimental results show that the MTL-DlinkNet model achieves better performance than the baseline models.Overall, this paper demonstrates the potential of deep learning methods in improving fracture diagnosis accuracy and efficiency, especially when multi-task learning is used, with practical applications in clinical settings.

An electrochemical sensor based on cobalt hydroxide/hydroxylated multiwalled carbon nanotubes for sensitively detecting 4-nitrochlorobenzene

In this work, cobalt hydroxide (Co(OH)2) is electrodeposited on glassy carbon electrode (GCE) modified by hydroxylated multiwalled carbon nanotubes (MWCNTs-OH). The obtained electrode (Co(OH)2/MWCNTs-OH/GCE) is utilized to determine 4-nitrochlorobenzene (4-NCB). The as-prepared materials are characterized through scan electron microscope, energy-dispersive spectroscopy, X-ray diffraction and X-ray photoelectron spectroscopy to analyze crystal structure, morphology, element composition and distribution. The electrochemical behaviors of 4-NCB on modified electrodes and GCE are investigated via cyclic voltammetry (CV) and AC impedance. CV curves and Nyquist plots show that the electrochemical properties of Co(OH)2/MWCNTs-OH/GCE are significantly better than the others. Differential pulse voltammetry tests demonstrate that Co(OH)2/MWCNTs-OH/GCE possesses great electrocatalytic activity for determining 4-NCB in the range of 0.01 ∼ 400 μM, and the detection limit is 6.5 nM (S/N=3). Additionally, the constructed sensor exhibits excellent reproducibility, stability and selectivity. Moreover, recovery experiment using the standard addition method is conducted on tap water, yielding satisfactory recovery rates.

Pulmonary Shunt in Critical Care: A Comprehensive Review of Pathophysiology, Diagnosis, and Management Strategies.

Pulmonary shunt, an abnormal passage of blood through the pulmonary circulation without adequate gas exchange, poses significant challenges in critical care. This comprehensive review explores the pathophysiology, diagnostic approaches, and management strategies associated with pulmonary shunt. Pulmonary shunts are classified into anatomical and physiological types, each with distinct mechanisms and implications for gas exchange. Anatomical shunts result from structural heart defects, while physiological shunts arise from ventilation-perfusion (V/Q) mismatches. Both conditions can significantly impair oxygenation and contribute to multi-organ dysfunction. This review delves into various diagnostic modalities, including clinical assessment, imaging techniques such as chest X-ray and CT scans, and advanced diagnostic methods such as V/Q scanning and echocardiography. Challenges in diagnosing pulmonary shunt are discussed, emphasizing the limitations of current tools and the need for accurate differentiation of shunt types. Management strategies are examined, covering pharmacological interventions, non-pharmacological treatments such as mechanical ventilation and prone positioning, and surgical options. Emerging therapies and innovations in treatment are also highlighted. Special considerations are given to different patient populations, including pediatric and elderly patients and those with multiple comorbidities. This review concludes with an analysis of the prognosis and outcomes associated with pulmonary shunt, focusing on short-term and long-term impacts on survival and quality of life. This review aims to enhance understanding and guide effective management practices for pulmonary shunt in critical care settings by synthesizing current knowledge and identifying areas for further research.