Phase-contrast visualization of human tissues using superimposed wavefront imaging of diffraction-enhanced x-rays.

BACKGROUND: Phase-contrast computed tomography (CT) using high-brilliance, synchrotron-generated x-rays enable three-dimensional (3D) visualization of microanatomical structures within biological specimens, offering exceptionally high-contrast images of soft tissues. Traditional methods for phase-contrast CT; however, necessitate a gap between the subject and the x-ray camera, compromising spatial resolution due to penumbral blurring. Our newly developed technique, Superimposed Wavefront Imaging of Diffraction-enhanced x-rays (SWIDeX), leverages a Laue-case Si angle analyzer affixed to a scintillator to convert x-rays to visible light, capturing second-order differential phase contrast images and effectively eliminating the distance to the x-ray camera. This innovation achieves superior spatial resolution over conventional methods. PURPOSE: In this paper, the imaging principle and CT reconstruction algorithm based on SWIDeX are presented in detail and compared with conventional analyzer-based imaging (ABI). It also shows the physical setup of SWIDeX that provides the resolution preserving second-order differential images for reconstruction. We compare the spatial resolution and the sensitivity of SWIDeX to conventional ABI. METHODS: To demonstrate high-spatial resolution achievable by SWIDeX, the internal structures of four human tissues-ductal carcinoma in situ, normal stomach, normal pancreas, and intraductal papillary mucinous neoplasm of the pancreas-were visualized using an imaging system configured at the Photon Factory's BL14B beamline under the High Energy Accelerator Research Organization (KEK). Each tissue was thinly sliced after imaging, stained with hematoxylin and eosin (H&E) for conventional microscope-based pathology. RESULTS: A comparison of SWIDeX-CT and pathological images visually demonstrates the effectiveness of SWIDeX-CT for biological tissue imaging. SWIDeX could generate clearer 3D images than existing analyzer-based phase-contrast methods and accurately delineate tissue structures, as validated against histopathological images. CONCLUSIONS: SWIDeX can visualize important 3D structures in biological soft tissue with high spatial resolution and can be an important tool for providing information between the disparate scales of clinical and pathological imaging.

Evaluation of the usefulness of non-weight-bearing tunnel view using X-ray in the short term after medial meniscus posterior root tear onset: a retrospective study.

BACKGROUND: This study aimed to examine whether the non-weight-bearing tunnel view X-ray is effective for short-term evaluation of medial meniscus posterior root tear (MMPRT) by assessing the X-ray characteristics at the initial and follow-up visits. METHODS: This was a retrospective longitudinal study of 26 enrolled knees diagnosed with MMPRT on magnetic resonance imaging. The distance between the medial tibial eminence and medial femoral condyle (MTE-MFC distance) and medial tibiofemoral joint (MTFJ) width were measured by obtaining non-weight-bearing tunnel view and frontal view X-ray radiographs. The initial and follow-up values at a median interval of 17 days were compared. Additionally, the correlations between the MTE-MFC distance increase rate and body mass index (BMI), age, femorotibial angle (FTA), and posterior tibial slope (PTS) were evaluated using linear regression analysis. RESULTS: The tunnel view images of the initial and follow-up X-rays showed a significant increase in the MTE-MFC distance and a significant decrease in the MTFJ width. Furthermore, a moderate correlation was observed between the change in the MTE-MFC distance and the time interval between X-rays. However, no substantial correlation was observed for the change in the MTFJ width over time. Moreover, no significant correlation was observed between the change in the MTE-MFC distance in the non-weight-bearing tunnel view and BMI, age, FTA, and PTS. CONCLUSIONS: The non-weight-bearing tunnel view is highly beneficial for evaluating MMPRT progression in the short term.

On the feasibility of time-resolved X-ray powder diffraction of macromolecules using laser-driven ultrafast X-ray sources.

With the emergence of ultrafast X-ray sources, interest in following fast processes in small molecules and macromolecules has increased. Most of the current research into ultrafast structural dynamics of macromolecules uses X-ray free-electron lasers. In parallel, small-scale laboratory-based laser-driven ultrafast X-ray sources are emerging. Continuous development of these sources is underway, and as a result many exciting applications are being reported. However, because of their low flux, such sources are not commonly used to study the structural dynamics of macromolecules. This article examines the feasibility of time-resolved powder diffraction of macromolecular microcrystals using a laboratory-scale laser-driven ultrafast X-ray source.

Effect of posture on the position of the subcutaneous implantable defibrillator.

BACKGROUND: The PRAETORIAN score is developed as an alternative for defibrillation testing (DFT) post subcutaneous implantable cardioverter-defibrillator (S-ICD) implantation, and assess three aspects of implant position on a bidirectional chest X-ray. The score is validated on a standard standing chest X-ray with arms elevated in the lateral view. OBJECTIVE: We aim to evaluate the effect of different anatomical positions on the PRAETORIAN score. METHODS: Thirty S-ICD patients underwent standard posterior-anterior (PA) and lateral chest X-rays, including additional lateral views in two positions: standing with arms down and supine with arms alongside the body. PRAETORIAN score and weighted kappa coefficient were calculated for each position. RESULTS: In 8 out of 30 patients the PRAETORIAN score was ≥90 in standard position. The agreement in PRAETORIAN score was substantial (κ=0.677) for the position with the arms down and fair (κ =0.399) for the supine position. In 10 patients (33%) with the arms down the PRAETORIAN score decreased, of whom 4 changed to a lower risk category. In 16 patients (53%) the PRAETORIAN score decreased in supine position, of whom 7 changed to a lower risk category of which one patient changed from high to low risk. CONCLUSION: A supine or arms-down position during chest X-rays can result in lower PRAETORIAN scores and underestimation of associated risk on DFT failure. This emphasizes the importance of correct anatomical positioning ('arms up') during chest X-rays when using the PRAETORIAN score.

Clinical and radiological response of Maffucci related enchondromas to mutant IDH1 inhibitor Ivosidenib.

Ollier Disease (OD) and Maffucci syndrome (MS) is a rare bone disorder that affects the growth and development of the bones, with an estimated prevalence of 1 in 100,000 people. It is associated with somatic mosaicism of isocitrate dehydrogenase-1 (IDH1) or 2 (IDH2) pathogenic variants. Ivosidenib is indicated for the treatment of acute myeloid leukemia and locally advanced or metastatic cholangiocarcinoma and is currently investigated in low-grade glioma with a susceptible isocitrate dehydrogenase-1 (IDH1) pathogenic variant, but its effects in patients with OD or MS are unknown. We here report the first case of a patient with MS who was treated with Ivosidenib for recurrent IDH-1 mutated glioma. Besides the stabilization of the tumor size, the patient observed significant improvement in his enchondromas that became stiffer, with reduced pain, and significant modification of the mineralization of the enchondromas observed on X-rays. This first case report provides hope for the medical management of patients suffering because of OD or MS. Future clinical research is urgently needed to evaluate long-term benefit risk profile of IDH inhibitors in these rare diseases.

Deep learning prediction of survival in patients with heart failure using chest radiographs.

Heart failure (HF) is associated with high rates of morbidity and mortality. The value of deep learning survival prediction models using chest radiographs in patients with heart failure is currently unclear. The aim of our study is to develop and validate a deep learning survival prediction model using chest X-ray (DLSPCXR) in patients with HF. The study retrospectively enrolled a cohort of 353 patients with HF who underwent chest X-ray (CXR) at our institution between March 2012 and March 2017. The dataset was randomly divided into training (n = 247) and validation (n = 106) datasets. Univariate and multivariate Cox analysis were conducted on the training dataset to develop clinical and imaging survival prediction models. The DLSPCXR was trained and the selected clinical parameters were incorporated into DLSPCXR to establish a new model called DLSPinteg. Discrimination performance was evaluated using the time-dependent area under the receiver operating characteristic curves (TD AUC) at 1, 3, and 5-years survival. Delong's test was employed for the comparison of differences between two AUCs of different models. The risk-discrimination capability of the optimal model was evaluated by the Kaplan-Meier curve. In multivariable Cox analysis, older age, higher N-terminal pro-B-type natriuretic peptide (NT-ProBNP), systolic pulmonary artery pressure (sPAP) > 50 mmHg, New York Heart Association (NYHA) functional class III-IV and cardiothoracic ratio (CTR) ≥ 0.62 in CXR were independent predictors of poor prognosis in patients with HF. Based on the receiver operating characteristic (ROC) curve analysis, DLSPCXR had better performance at predicting 5-year survival than the imaging Cox model in the validation cohort (AUC: 0.757 vs. 0.561, P = 0.01). DLSPinteg as the optimal model outperforms the clinical Cox model (AUC: 0.826 vs. 0.633, P = 0.03), imaging Cox model (AUC: 0.826 vs. 0.555, P < 0.001), and DLSPCXR (AUC: 0.826 vs. 0.767, P = 0.06). Deep learning models using chest radiographs can predict survival in patients with heart failure with acceptable accuracy.

Deep learning pneumoconiosis staging and diagnosis system based on multi-stage joint approach.

BACKGROUND: Pneumoconiosis has a significant impact on the quality of patient survival due to its difficult staging diagnosis and poor prognosis. This study aimed to develop a computer-aided diagnostic system for the screening and staging of pneumoconiosis based on a multi-stage joint deep learning approach using X-ray chest radiographs of pneumoconiosis patients. METHODS: In this study, a total of 498 medical chest radiographs were obtained from the Department of Radiology of West China Fourth Hospital. The dataset was randomly divided into a training set and a test set at a ratio of 4:1. Following histogram equalization for image enhancement, the images were segmented using the U-Net model, and staging was predicted using a convolutional neural network classification model. We first used Efficient-Net for multi-classification staging diagnosis, but the results showed that stage I/II of pneumoconiosis was difficult to diagnose. Therefore, based on clinical practice we continued to improve the model by using the Res-Net 34 Multi-stage joint method. RESULTS: Of the 498 cases collected, the classification model using the Efficient-Net achieved an accuracy of 83% with a Quadratic Weighted Kappa (QWK) score of 0.889. The classification model using the multi-stage joint approach of Res-Net 34 achieved an accuracy of 89% with an area under the curve (AUC) of 0.98 and a high QWK score of 0.94. CONCLUSIONS: In this study, the diagnostic accuracy of pneumoconiosis staging was significantly improved by an innovative combined multi-stage approach, which provided a reference for clinical application and pneumoconiosis screening.

Revolutionizing Healthcare: Qure.AI's Innovations in Medical Diagnosis and Treatment.

Qure.AI, a leading company in artificial intelligence (AI) applied to healthcare, has developed a suite of innovative solutions to revolutionize medical diagnosis and treatment. With a plethora of FDA-approved tools for clinical use, Qure.AI continually strives for innovation in integrating AI into healthcare systems. This article delves into the efficacy of Qure.AI's chest X-ray interpretation tool, "qXR," in medicine, drawing from a comprehensive review of clinical trials conducted by various institutions. Key applications of AI in healthcare include machine learning, deep learning, and natural language processing (NLP), all of which contribute to enhanced diagnostic accuracy, efficiency, and speed. Through the analysis of vast datasets, AI algorithms assist physicians in interpreting medical data and making informed decisions, thereby improving patient care outcomes. Illustrative examples highlight AI's impact on medical imaging, particularly in the diagnosis of conditions such as breast cancer, heart failure, and pulmonary nodules. AI can significantly reduce diagnostic errors and expedite the interpretation of medical images, leading to more timely interventions and treatments. Furthermore, AI-powered predictive analytics enable early detection of diseases and facilitate personalized treatment plans, thereby reducing healthcare costs and improving patient outcomes. The efficacy of AI in healthcare is underscored by its ability to complement traditional diagnostic methods, providing physicians with valuable insights and support in clinical decision-making. As AI continues to evolve, its role in patient care and medical research is poised to expand, promising further advancements in diagnostic accuracy and treatment efficacy.

3D quantification of the lacunocanalicular network on human femoral diaphysis through synchrotron radiation-based nanoCT.

Osteocytes are the major actors in bone mechanobiology. Within bone matrix, they are trapped close together in a submicrometric interconnected network: the lacunocanalicular network (LCN). The interstitial fluid circulating within the LCN transmits the mechanical information to the osteocytes that convert it into a biochemical signal. Understanding the interstitial fluid dynamics is necessary to better understand the bone mechanobiology. Due to the submicrometric dimensions of the LCN, making it difficult to experimentally investigate fluid dynamics, numerical models appear as a relevant tool for such investigation. To develop such models, there is a need for geometrical and morphological data on the human LCN. This study aims at providing morphological data on the human LCN from measurement of 27 human femoral diaphysis bone samples using synchrotron radiation nano-computed tomography with an isotropic voxel size of 100 nm. Except from the canalicular diameter, the canalicular morphological parameters presented a high variability within one sample. Some differences in terms of both lacunar and canalicular morphology were observed between the male and female populations. But it has to be highlighted that all the canaliculi cannot be detected with a voxel size of 100 nm. Hence, in the current study, only a specific population of large canaliculi that could be characterize. Still, to the authors knowledge, this is the first time such a data set was introduced to the community. Further processing will be achieved in order to provide new insight on the LCN permeability.

Cardiomegaly: Navigating the uncharted territories of heart failure - A multimodal radiological journey through advanced imaging, pathophysiological landscapes, and innovative therapeutic frontiers.

Cardiomegaly is among the disorders categorized by a structural enlargement of the heart by any of the situations including pregnancy, resulting in damage to heart muscles and causing trouble in normal heart functioning. Cardiomegaly can be defined in terms of dilatation with an enlarged heart and decreased left or biventricular contraction. The genetic origin of cardiomegaly is becoming more evident due to extensive genomic research opening up new avenues to ensure the use of precision medicine. Cardiomegaly is usually assessed by using an array of radiological modalities, including computed tomography (CT) scans, chest X-rays, and MRIs. These imaging techniques have provided an important opportunity for the physiology and anatomy of the heart. This review aims to highlight the complexity of cardiomegaly, highlighting the contribution of both ecological and genetic variables to its progression. Moreover, we further highlight the worth of precise clinical diagnosis, which comprises blood biomarkers and electrocardiograms (EKG ECG), demonstrating the significance of distinguishing between numerous basic causes. Finally, the analysis highlights the extensive variation of treatment lines, such as lifestyle modifications, prescription drugs, surgery, and implantable devices, although highlighting the critical need for individualized and personalized care.

Development of an X-ray ionization beam position monitor for PAL-XFEL soft X-rays.

The Pohang Accelerator Laboratory X-ray Free-Electron Laser (PAL-XFEL) operates hard X-ray and soft X-ray beamlines for conducting scientific experiments providing intense ultrashort X-ray pulses based on the self-amplified spontaneous emission (SASE) process. The X-ray free-electron laser is characterized by strong pulse-to-pulse fluctuations resulting from the SASE process. Therefore, online photon diagnostics are very important for rigorous measurements. The concept of photo-absorption and emission using solid materials is seldom considered in soft X-ray beamline diagnostics. Instead, gas monitoring detectors, which utilize the photo-ionization of noble gas, are employed for monitoring the beam intensity. To track the beam position at the soft X-ray beamline in addition to those intensity monitors, an X-ray ionization beam position monitor (XIBPM) has been developed and characterized at the soft X-ray beamline of PAL-XFEL. The XIBPM utilizes ionization of either the residual gas in an ultra-high-vacuum environment or injected krypton gas, along with a microchannel plate with phosphor. The XIBPM was tested separately for monitoring horizontal and vertical beam positions, confirming the feasibility of tracking relative changes in beam position both on average and down to single-shot measurements. This paper presents the basic structure and test results of the newly developed non-invasive XIBPM.

Substantial variability in what is considered important in the radiological report for anterior shoulder instability: a Delphi study with Dutch musculoskeletal radiologists and orthopedic surgeons.

Background: Standardized consensus-based radiological reports for shoulder instability may improve clinical quality, reduce heterogeneity, and reduce workload. Therefore, the aim of this study was to determine important elements for the x-ray, magnetic resonance imaging (MRI) arthrography (MRA), and computed tomography (CT) report, the extent of variability, and important MRI views and settings. Methods: An expert panel of musculoskeletal radiologists and orthopedic surgeons was recruited in a three-round Delphi design. Important elements were identified for the x-ray, MRA, and CT report and important MRI views and setting. These were rated on a 0-9 Likert scale. High variability was defined as at least one score between 1-3 and 7-9. Consensus was reached when ≥80% scored an element 1-3 or 7-9. Results: The expert panel consisted of 21 musculoskeletal radiologists and 15 orthopedic surgeons. The number of elements identified in the first round was seventeen for the x-ray report, 52 for MRA, 21 for CT, and 23 for the MRI protocol. The number of elements that reached consensus was five for x-ray, twenty for MRA, nine for CT, and two for the MRI protocol. High variability was observed in 76.5% (n = 13) x-ray elements, 85.0% (n = 45) MRA, 76.2% (n = 16) CT, and 85.7% (n = 18) MRI protocol. Conclusion: Substantial variability was observed in the scoring of important elements in the radiological for the evaluation of anterior shoulder instability, regardless of modality. Consensus was reached for five elements in the x-ray report, twenty in the MRA report, and nine in the CT report. Finally, consensus was reached on two elements regarding MRA views and settings.

Urgent health concerns: Clinical issues associated with accidental ingestion of new metal-blade-containing sticks for heated tobacco products.

INTRODUCTION: Recently, a concerning pattern has emerged in clinical settings, drawing attention to the potential health risks associated with the accidental ingestion, mostly by children, of a new Heated Tobacco Product (HTP) stick, which contains a sharp metal blade inside. METHODS: Following a webinar of the Joint Action on Tobacco Control 2 project, where data on adverse health incidents related to novel tobacco and nicotine products from EU Member States were presented, the Milan Poison Control Center (PCC) conducted a case series study on the accidental ingestion of blade-containing HTP sticks in Italy, between July 2023 and February 2024. The data in the medical records were analyzed to identify the age distribution, clinical presentation symptoms, performed diagnostic procedures, and medical management. RESULTS: Overall, 40 cases of accidental ingestion of HTP sticks were identified and are described. A total of 33 (82.5%) children (infants and toddlers, mean age 12.3 ± 3.3 months) were hospitalized. Of these, 29 underwent abdominal X-rays, two children underwent esophagogastroduodenoscopy, and one child suffered from cut injuries to the tonsillar pillar and genian mucosa, requiring anesthesia for fibroscopy. The observed clinical cases associated with new HTP sticks containing a metal blade occurred over just eight months. This issue required the immediate implementation of corrective measures to mitigate health risks. The Ministry of Health issued an alert regarding the dangers related to the accidental ingestion of the stick and imposed more visible warnings on the package. CONCLUSIONS: It is of the utmost importance to raise awareness among both the general public and medical practitioners to prevent further cases of accidental ingestion of HTP sticks by infants and toddlers, and ensure a prompt and informed response in emergency situations.

The diagnostic accuracy of community spine radiology for adolescent idiopathic scoliosis brace candidates.

PURPOSE: The study aims to establish the diagnostic accuracy of community spine x-rays for brace candidates. METHODS: A review of adolescent idiopathic scoliosis patients seen for initial visit at a tertiary care pediatric hospital was conducted (n = 170). The index test was the pre-referral community spine x-ray interpreted by a community radiologist. Measures of diagnostic accuracy for the index test were determined against the reference standard if images were obtained within 90 days (n = 111). The reference standard was the 3-foot standing EOS spine x-ray evaluated by spine specialists. Diagnostic criterion for a brace candidate was dichotomized by Cobb angle range (25-40°) according to Scoliosis Research Society criteria. Risser stage was not included given significant missing data in index reports. To mitigate the uncertainty around true progression, sensitivity analyses were conducted on a sub-sample of data when index test was within 60 days of the reference standard (n = 67). RESULTS: Accuracy of the community spine x-ray to detect a brace candidate was 65.8% (95% CI 56.2-74.5). Sensitivity of the index test was 65.4% with a false negative rate of 34.6%. Specificity was 66.1% with a false positive rate of 33.9%. Positive and negative predictive values were 63.0% and 68.4%, respectively. Of the total number of brace candidates (n = 52), 32.7% were missed because of underestimation in Cobb angle (95% CI 21.5-46.2). The proportion of missed brace candidates because of underestimation was unchanged with 60-day data (p = 0.37). CONCLUSIONS: Inaccuracies in community spine radiology may lead to missed opportunities for non-operative treatment.

Hard X-ray imaging and tomography at the Biomedical Imaging and Therapy beamlines of Canadian Light Source.

The Biomedical Imaging and Therapy facility of the Canadian Light Source comprises two beamlines, which together cover a wide X-ray energy range from 13 keV up to 140 keV. The beamlines were designed with a focus on synchrotron applications in preclinical imaging and veterinary science as well as microbeam radiation therapy. While these remain a major part of the activities of both beamlines, a number of recent upgrades have enhanced the versatility and performance of the beamlines, particularly for high-resolution microtomography experiments. As a result, the user community has been quickly expanding to include researchers in advanced materials, batteries, fuel cells, agriculture, and environmental studies. This article summarizes the beam properties, describes the endstations together with the detector pool, and presents several application cases of the various X-ray imaging techniques available to users.

Development of Lead-Free Materials for Radiation Shielding in Medical Settings: A Review.

Radiation protection is an essential issue in diagnostic radiology to ensure the safety of patients, healthcare professionals, and the general public. Lead has traditionally been used as a shielding material due to its high atomic number, high density, and effectiveness in attenuating radiation. However, some concerns related to the long-term health effects of toxicity, environmental disease as well as heavy weight of lead have led to the search for alternative lead-free shielding materials. Leadfree multilayered polymer composites and non-lead nano-composite shields have been suggested as effective shielding materials to replace conventional lead-based and single metal shields. Using several elements with high density and atomic number, such as bismuth, barium, gadolinium, and tungsten, offer significant enhancements in the shielding ability of composites. This review focuses on the development and use of lead-free materials for radiation shielding in medical settings. It discusses the drawbacks of traditional lead shielding, such as toxicity, weight, and recycling challenges, and highlights the benefits of lead-free alternatives.

Thia- and Seleno-Michael reactions for the synthesis of Carbonic anhydrases inhibitors.

Novel chalcogen-containing amides and esters bearing the benzenesulfonamide moiety have been synthesised upon nucleophilic conjugate addition of thiols and selenols to suitable electron-deficient alkenes. The activity of the synthesised compounds as Carbonic Anhydrases inhibitors has been investigated in vitro and the inhibition mechanism has been elucidated by X-rays studies.

An advanced multisystem histiocytic sarcoma in a pregnant woman: A case report.

Histiocytic sarcoma is an extremely rare disease that's hard to diagnose and treat, often leading to a poor prognosis. Here, we present a case report detailing a rare occurrence of HS in a 37-year-old pregnant woman who first presented with left shoulder pain, palpitations, and a productive cough at 20 weeks of gestation. Her diagnostic evaluations were performed, including different imaging modalities such as chest X-rays, CT scans, and MRI. Imaging revealed a large mediastinal mass with extensive involvement of the adrenal glands, lungs, and lymph nodes. The definitive diagnosis of HS is based on pathological and morphological features, and the immunohistochemistry report plays a key role. In our case, the diagnosis of HS was confirmed through pathological evaluation and immunohistochemistry, with a positive CD68 result obtained from a supraclavicular lymph node biopsy. A hospital committee comprising medical specialists like hematologists-oncologists, pathologists, pulmonologists, and obstetricians was brought together to assess the case collectively. The patient received chemotherapy, which alleviated her symptoms and maintained her condition. Based on the committee's recommendations, despite a healthy fetus and normal obstetric sonograms, the decision was made to terminate the pregnancy with the consent of the patient and her family. Despite initial improvement postchemotherapy, the patient's condition worsened, necessitating intubation. Tragically, two months after the initial admission, the patient passed away due to severe complications. In this case report, we provide a literature review and review of the patient's imaging reports. Since the patient is pregnant and HS is uncommon, it's important to highlight that this case is unique and worth sharing.

Role of Lung Ultrasonography in Acute Respiratory Distress in Pediatric Age Group: A Prospective Single-Centre Study.

Introduction Lung diseases are the most frequently encountered form of diseases primarily affecting infants under one year of age. Although the chest X-ray is the first modality of choice, ultrasonography (USG) has emerged as an alternative. Lung ultrasound (LUS) finds its application in the evaluation of several pediatric lung diseases. Objective To assess the use of LUS in acute lower respiratory infections and assess the correlation between etiological diagnosis and radiological diagnosis. Methods This was a hospital-based prospective observational study conducted with children presenting with upper respiratory infections. Around 97 children were included in the study. Clinical diagnosis was made by the pediatrician. LUS was performed by a trained radiologist, using the two-dimensional (2D) ultrasound mode and motion mode (M mode) to assess the LUS in the respective areas of the chest, thereby assessing bilateral lung fields for these patients. Results The majority of our study participants were under one year old (87%), and more than half were male (55%). Bronchiolitis and lower respiratory tract infections (LRIs) were the most commonly seen clinical diagnoses. The distribution of USG findings was statistically significant across the clinical diagnosis (p-value < 0.05). Conclusion Our study found that LUS can serve as an important tool for diagnosing several acute respiratory diseases. It also showed that LUS can replace X-rays in cases of children diagnosed with acute respiratory diseases.

Multi-centre benchmarking of deep learning models for COVID-19 detection in chest x-rays.

Introduction: This study is a retrospective evaluation of the performance of deep learning models that were developed for the detection of COVID-19 from chest x-rays, undertaken with the goal of assessing the suitability of such systems as clinical decision support tools. Methods: Models were trained on the National COVID-19 Chest Imaging Database (NCCID), a UK-wide multi-centre dataset from 26 different NHS hospitals and evaluated on independent multi-national clinical datasets. The evaluation considers clinical and technical contributors to model error and potential model bias. Model predictions are examined for spurious feature correlations using techniques for explainable prediction. Results: Models performed adequately on NHS populations, with performance comparable to radiologists, but generalised poorly to international populations. Models performed better in males than females, and performance varied across age groups. Alarmingly, models routinely failed when applied to complex clinical cases with confounding pathologies and when applied to radiologist defined "mild" cases. Discussion: This comprehensive benchmarking study examines the pitfalls in current practices that have led to impractical model development. Key findings highlight the need for clinician involvement at all stages of model development, from data curation and label definition, to model evaluation, to ensure that all clinical factors and disease features are appropriately considered during model design. This is imperative to ensure automated approaches developed for disease detection are fit-for-purpose in a clinical setting.