Thoracic Abnormalities Research Articles

The Incidence of Body Posture Abnormalities in Relation to the Segmental Body Composition in Early School-Aged Children.

Children are exposed to multiple factors that contribute to an increase in body mass and the development of posture defects. The aim of the study is to assess the relationship between the segmental distribution of fat mass and muscle mass and the incidence of body posture abnormalities in early school-aged children. A total of 190 children aged 7–9 were included in the research project. The examined children were divided according to age (class level) into three groups. Height, weight and body composition, BMI, and body posture were determined. Thoracic and lumbar spine abnormalities occurred most frequently in the examined children (7–95%, 8–92%, 9–89.5%). During the assessment of the segmental body composition, the lowest fat–fat-free index was found in the trunk. The number of abnormalities of the cervical spine, pelvis, and lower extremities increases with age. The number of abnormalities of the thoracic and lumbar spine, as well as of upper extremities and the pectoral girdle decreases with age. Body posture abnormalities are correlated with body composition and in particular with the fat mass percentage. The segmental body com-position analyzer can be used to screen for posture defects.

Diagnostic imaging findings in a referral population of dogs diagnosed with immune-mediated haemolytic anaemia: 50 cases (2015-2018).

To describe and characterise changes documented on thoracic and abdominal imaging of dogs with confirmed immune-mediated haemolytic anaemia. Medical records from a referral hospital were searched from 2015 to 2018 for all dogs diagnosed with immune-mediated haemolytic anaemia that underwent thoracic and abdominal imaging by radiography, ultrasound or computed tomography. Fifty dogs were included. Thoracic imaging revealed abnormalities in 10 dogs (20%) of which lymphadenopathy and cardiomegaly were documented in four dogs (8%) each, and pleural effusion and pleural thickening in one dog (2%) each. Abdominal imaging revealed abnormalities in 43 dogs (86%), in which hepatomegaly and peritoneal effusion were documented in 20 (40%) and 19 dogs (38%), gallbladder wall thickening and sludge in 16 (32%) and 14 dogs (28%) and splenic nodules and splenomegaly in 13 (26%) and seven dogs (14%), respectively. Hepatic and splenic abnormalities were further investigated via fine needle aspirates in 18 dogs and revealed extramedullary haematopoiesis in 12 hepatic (66.7%) and 14 splenic (77.8%) fine needle aspirate samples. Cholecystocentesis was performed in nine dogs with gallbladder abnormalities and revealed bactibilia in three samples (33.3%). In this population of dogs with immune-mediated haemolytic anaemia, thoracic imaging abnormalities were uncommon. Hepatomegaly, peritoneal effusion and gallbladder wall thickening were the most common abdominal imaging findings with bactibilia confirmed in one third of collected bile samples. Hepatosplenomegaly and abdominal lymphadenopathy were not associated with neoplasia in any of the dogs included in this study.

Whole pulmonary assessment 1 year after paediatric acute respiratory distress syndrome: prospective multicentre study

BackgroundLong-term pulmonary sequelae, including 1-year thoracic computed tomography (CT) sequelae of paediatric acute respiratory distress syndrome (ARDS) remain unknown. The purpose of the study was to determine pulmonary abnormalities in child survivors of pulmonary (p-ARDS) and extra-pulmonary ARDS (ep-ARDS) 1 year after paediatric intensive care unit discharge (PICUD).MethodsProspective multicentre study in four paediatric academic centres between 2005 and 2014. Patients with ARDS were assessed 1 year after PICUD with respiratory symptom questionnaire, thoracic CT and pulmonary function tests (PFT).Results39 patients (31 p-ARDS) aged 1.1–16.2 years were assessed. Respiratory symptoms at rest or exercise and/or respiratory maintenance treatment were reported in 23 (74%) of children with p-ARDS but in 1 (13%) of those with ep-ARDS. Thoracic CT abnormalities were observed in 18 (60%) of children with p-ARDS and 4 (50%) of those with ep-ARDS. Diffuse and more important CT abnormalities, such as ground glass opacities or mosaic perfusion patterns, were observed in 5 (13%) of children, all with p-ARDS. PFT abnormalities were observed in 30 (86%) of patients: lung hyperinflation and/or obstructive pattern in 12 (34%) children, restrictive abnormalities in 6 (50%), mild decrease in diffusing capacity in 2 (38%) and 6-min walking distance decrease in 11 (73%). Important PFT abnormalities were observed in 7 (20%) children, all with p-ARDS. Increasing driving pressure (max plateau pressure—max positive end-expiratory pressure) was correlated with increasing CT-scan abnormalities and increasing functional residual capacity (more hyperinflation) (p < 0.005).ConclusionsChildren surviving ARDS requiring mechanical ventilation present frequent respiratory symptoms, significant CT-scan and PFT abnormalities 1 year after PICUD. This highlights the need for a systematic pulmonary assessment of these children.Trial registration The study was registered on Clinical Trials.gov PRS (ID NCT01435889)

Mitochondrial characteristics of chicken breast muscle affected by wooden breast

The growth rate of broiler chickens has increased by 400% over the past 50 years, and breast yields continue to increase. This has led to an increase in thoracic muscle abnormalities in broilers, with wooden breast becoming a major issue worldwide. The etiology and the mechanism underlying the etiology of wooden breasts have not yet been elucidated; however, it occurs due to oxidative stress. Reactive oxygen species, which cause oxidative stress, are mainly produced in mitochondria. Thus, in this study, we investigated the relationship between the severity of wooden breast in broilers and the characteristics of mitochondria as the source of reactive oxygen species. Sampling of the pectoralis major muscle at the ventral cranial position was conducted in 50-day-old broilers. The severity of wooden breast was classified into three groups based on the muscle fiber roundness and wing–wing contact test, with highest severity in severe wooden breast and lowest severity in normal breast. Nicotinamide adenine dinucleotide tetrazolium reductase staining revealed an increase in darkly stained muscle fibers, indicating high severity of wooden breast. The mitochondria were swollen in severe wooden breast cases, with highest swelling in severe wooden breast and lowest swelling in normal breast. The expression levels of the mitochondrial antioxidant enzyme genes superoxide dismutase 1 and superoxide dismutase 2 were significantly lower in wooden breast-severe tissue than in normal tissue. These results suggest that when the levels of reactive oxygen species in muscle fibers, which should be constant, are increased, mitochondrial homeostasis is not maintained and the damage levels increase in various membranes of the cell, leading to the disruption of normal physiological functions.

Imaging Findings of Thoracic Lymphatic Abnormalities

The lymphatic system plays an important role in balancing fluid compartments in the body. It is disrupted by various disease processes in the thorax, including injury to the thoracic lymphatic duct after surgery, as well as malignancy and heart failure. Because of the small size of lymphatic vessels, imaging of the lymphatics is relatively difficult, and effective imaging methods are still being optimized and developed. The standard of reference for lymphatic imaging has been conventional lymphangiography for several decades. Other modalities such as CT, noncontrast or contrast-enhanced MRI, and lymphoscintigraphy can also demonstrate lymphatic abnormalities and help in treatment planning. Imaging findings associated with lymphatic abnormalities can be seen in the pulmonary parenchyma, pleural space, and mediastinum. In the pulmonary parenchyma, common findings include interlobular septal thickening as well as reversal of lymphatic flow with intravasation of contrast material into pulmonary lymphatics. In the pleural space, findings include chylous pleural effusion and occasionally nonchylous pleural effusion. In the mediastinum, thoracic duct leak, plexiform thoracic duct, lymphatic malformations, and lymphangiectasis may occur. Management of chylothorax includes conservative or medical treatment, surgery, and interventional radiology procedures. The authors discuss thoracic lymphatic anatomy, imaging manifestations of lymphatic abnormalities in the various anatomic compartments, and interventional radiology treatment of chylothorax. Radiologists should be familiar with these imaging findings for diagnosis and to help guide appropriate management. ©RSNA, 2022.

Adjunct diagnostic value of radiological findings in mucopolysaccharidosis type IVa-related thoracic spinal abnormalities: a pilot study

BackgroundIn patients with mucopolysaccharidosis (MPS), systematic assessment and management of cervical instability, cervicomedullary and thoracolumbar junction spinal stenosis and spinal cord compression averts or arrests irreversible neurological damage, improving outcomes. However, few studies have assessed thoracic spinal involvement in MPS IVa patients. We aimed to evaluate thoracic spinal abnormalities in MPS IVa patients and identify associated image manifestations by CT and MRI study.ResultsData of patients diagnosed and/or treated for MPS IVa at MacKay Memorial Hospital from January 2010 to December 2020 were extracted from medical records and evaluated retrospectively. Computed tomography (CT), plain radiography and magnetic resonance imaging (MRI) findings of MPS IVa-related spinal abnormalities were reviewed. Spine CT and plain radiography findings of 12 patients (6 males and 6 females with median age 7.5 years, range 1–28 years) revealed two subtypes of spinal abnormalities: thoracic kyphosis apex around T2 (subtype 1, n = 8) and thoracic kyphosis apex around T5 (subtype 2, n = 4). Spine CT and plain radiography clearly identified various degrees of thoracic kyphosis with apex around T2 or T5 in MPS IVa patients. Square-shaped to mild central beaking in middle thoracic vertebral bodies was observed in subtype 1 patients, while greater degrees of central beaking in middle thoracic vertebral bodies was observed in subtype 2 patients.ConclusionsSpine CT findings clearly identify new radiological findings of thoracic kyphosis apex around T2 or T5 in MPS IVa patients. The degrees of central beaking at middle thoracic vertebral bodies may be a critical factor associated with different image presentations of thoracic kyphosis.

Feature-level ensemble approach for COVID-19 detection using chest X-ray images.

Severe acute respiratory syndrome coronavirus 2 (SARS CoV-2), also known as the coronavirus disease 2019 (COVID-19), has threatened many human beings around the world and capsized economies at unprecedented magnitudes. Therefore, the detection of this disease using chest X-ray modalities has played a pivotal role in producing fast and accurate medical diagnoses, especially in countries that are unable to afford laboratory testing kits. However, identifying and distinguishing COVID-19 from virtually similar thoracic abnormalities utilizing medical images is challenging because it is time-consuming, demanding, and susceptible to human-based errors. Therefore, artificial-intelligence-driven automated diagnoses, which excludes direct human intervention, may potentially be used to achieve consistently accurate performances. In this study, we aimed to (i) obtain a customized dataset composed of a relatively small number of images collected from publicly available datasets; (ii) present the efficient integration of the shallow handcrafted features obtained from local descriptors, radiomics features specialized for medical images, and deep features aggregated from pre-trained deep learning architectures; and (iii) distinguish COVID-19 patients from healthy controls and pneumonia patients using a collection of conventional machine learning classifiers. By conducting extensive experiments, we demonstrated that the feature-based ensemble approach provided the best classification metrics, and this approach explicitly outperformed schemes that used only either local, radiomic, or deep features. In addition, our proposed method achieved state-of-the-art multi-class classification results compared to the baseline reference for the currently available COVID-19 datasets.

Chest wall deformities and their possible associations with different genetic syndromes.

Our primary objective was to identify discrete and syndromic cases of Pectus excavatum (PE) and Pectus carinatum (PC). We also intended to highlight the significance of further genetic exploration in clinically suspected syndromic cases of PC and PE. Pectus excavatum (PE) and Pectus carinatum (PC) are the most common morphological chest wall deformities. Although various hypotheses have been put forth, the pathogenesis of both entities is largely unknown. Clinicians often refer such cases for further genetic evaluation to exclude an associated underlying connective tissue disorder or a syndrome. Additionally, a detailed anamnesis with focused family history and thorough dysmorphological physical examination was done. PE and PC are considered isolated abnormalities if there is the absence of features of other syndromes, eliminating the need for further genetic evaluations. It is believed that the pattern of inheritance of these non-syndromic isolated PE and PC cases with positive family history could be multifactorial in nature. The recurrence risk of such isolated cases is thought to be low. Further diagnostic studies are indicated as PE and PC could be a part of a syndrome. Among the many syndromes, the most common monogenic syndromes associated with PE and PC are Marfan's and Noonan's. After obtaining the consent, we compiled a database of the patients who presented with chest wall deformities during the period 2017-2019. We selected 70 cases with PC and PE deformities to identify the discrete and syndromic PC and PE cases. During the study, we perused the cytogenetic and/or molecular analyses, that had been conducted to confirm the clinically suspected syndromic cases. We also scrutinized for the presence of PC and PE cases that are associated with the rare syndrome (s). Various genetic abnormalities were identified in 28 (40%) of the 70 cases that had been diagnosed with chest wall abnormalities. Along with PE and PC, other thoracic wall abnormalities were also identified, such as the broad chest, bell-shaped thorax, and elongated or enlarged thorax. One case of a rare genetic disorder of Morquio syndrome associated with PC was also identified. Novel (previously unpublished) genomic variants are reported here. It is important to delve deeper when encountering cases of PE and PC by conducting a further genetic exploration of such cases to identify syndromic associations that cause other structural and functional disorders, diagnosis of which might be missed during the early developmental period. Early identification of such disorders may help us correcting the defects, slowing the progression of disease processes, and preparing better to deal with the potential outcome.

Bedside Chest Ultrasound in Postoperative Pediatric Cardiac Surgery Patients: Comparison With Bedside Chest Radiography

The primary objective was to study the degree of agreement between the chest ultrasound (CUS) studies and chest x-ray (CXR) studies in postoperative pediatric cardiac surgical patients regarding the diagnosis of thoracic abnormalities, and also to compare the diagnostic performance of CUS in reference to CXR for the detection of thoracic abnormalities. The secondary objective was to compare the necessity for interventions done on the basis of CUS and CXR findings in the postoperative setting. A prospective observational study. At a postoperative pediatric cardiac surgical intensive care unit in a tertiary-care center. One hundred sixty patients between the age of 2 months to 18 years undergoing elective cardiac surgery for various congenital heart diseases. After obtaining permission from the institutional ethics committee, 160 pediatric cardiac surgical patients were studied prospectively in the postoperative period. On the day of surgery (postoperative day [POD] 0), bedside CXR was done in the immediate postoperative period. After bedside CXR, CUS examination was performed and then interpreted by the principal investigator. The CXR was interpreted by the surgical team. Provisional diagnosis was made by the principal investigator and surgical team. Any intervention required was decided based on CXR or CUS findings or both. The procedure was repeated in the morning of POD 1. The degree of agreement between CUS studies and CXR studies in detecting abnormalities was evaluated by Cohen's kappa (k) statistics. The diagnostic performance of CUS was compared with that of CXR using sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and diagnostic accuracy. Overall, kappa analysis (k) showed substantial agreement between the findings of the CUS and CXR studies (k=0.749). The diagnostic performance of CUS, as compared with CXR, was found to have a sensitivity of 96.9%, specificity of 84.75%, PPV of 73.4%, NPV of 98.43%, and diagnostic accuracy of 88.44%. In 94 abnormal findings, the interventions were done based on CUS or CXR findings or both. Overall, there was a substantial agreement (k=0.787) between CUS and CXR regarding the necessity for interventions. The degree of agreement between CUS and CXR studies was substantial for atelectasis, interstitial edema, and diaphragmatic weakness. The degree of agreement between CUS and CXR studies was almost perfect for pneumothorax and fair for pleural effusion. More CUS studies detected intrathoracic pathologies than CXR studies. The CUS also detected abnormalities earlier than CXR and was found to be useful for the early institution of intervention therapy in patients with interstitial edema and atelectasis. It would be reasonable to conclude that CUS may be considered in some instances as an alternative to CXR.

An adult with left isomerism having an interrupted inferior vena cava and persistent left superior vena cava associated with partial atrioventricular canal defect and complete heart block — a case report

BackgroundPersistent left superior vena cava is a well-recognized thoracic venous abnormality, most of which do not present with any symptoms. Its opening into the left atrium is uncommonly encountered and, if present, is noted to be associated with various other complex intracardiac malformations, which further complicates its management. Herein, we highlight a case of an adult with persistent left superior vena cava with a spectrum of other cardiac anomalies rarely encountered with it, which was effectively managed by tailored surgical intervention.Case presentationA 26-year-old female on meticulous evaluation was found to have left isomerism with an interrupted inferior vena cava and hemiazygos continuing as a persistent left superior vena cava. It was also associated with common atrium, partial atrioventricular canal defect, and complete heart block. This complex array of anomalies was managed surgically. Common atrium was closed with atrial neo-septation using autologous pericardial patch tailored in a way, such that the persistent left superior vena cava drained into right atrium with left atrial appendage being on right side of neo-septum. Cleft in the left atrioventricular valve was also repaired. Despite preoperative complete heart block, the patient had an uneventful postoperative recovery and was in atrial fibrillation with controlled ventricular rate, thus precluding the need for permanent pacemaker implantation.ConclusionsA rare spectrum of adult congenital cyanotic heart disease was successfully managed with thorough preoperative evaluation and judicious intraoperative management. Surgical management should be tailored based on specific anatomy for reduction of morbidity and optimum results.

ThoraciNet: thoracic abnormality detection and disease classification using fusion DCNNs.

Chest X-rays are arguably the de facto medical imaging technique for diagnosing thoracic abnormalities. Chest X-ray analysis is complex, especially in asymptomatic diseases, and relies heavily on the expertise of radiologists. This work proposes the use of deep learning models to automate the process of thoracic abnormality detection, classification, and segmentation. The advent of large-scale, annotated and public chest X-ray databases have enabled deep learning researchers to build state-of-the-art computer-aided diagnosis systems for such tasks. In this work, a two-stage pipeline is proposed for thoracic abnormality detection and disease classification using chest X-rays. Two fusion-based models are proposed for disease classification, using two asymmetric, deep convolutional neural networks. Results are evaluated over NIH database covering multiple patients' X-rays with metrics such as accuracy and AUC scores. The proposed architecture outperforms the existing ones, achieving AUC scores of 0.99 for CXR triaging and 0.79 for CXR disease classification. Furthermore, GradCAM visualization is performed to validate the results, rendering model predictions interpretable to experts and end-users.

Performance improvement in multi-label thoracic abnormality classification of chest X-rays with noisy labels.

This study aimed at developing a deep learning-based method for multi-label thoracic abnormality classification on frontal view chest X-ray (CXR). To improve the performance of classification, issues of class imbalance, noisy labels and ensemble of networks are addressed in the paper. The experiments were performed on a public dataset called Chest X-ray 14 (CXR14), which includes 112,120 frontal view CXRs from 30,805 patients. We came up with an ensemble learning framework to improve the classification and a noisy label detection method to detect the CXRs with noisy labels. The detected CXRs were reviewed by two board-certificated radiologists in a consensus fashion to evaluate detected noisy labels. The classification was assessed on CXR14 with area under the receiver operating characteristic curve (AUC). Report from the radiologists indicated that detected noisy labels had high possibility to be true positives. A notable improvement from baseline in performance of classification was observed with the ensemble learning framework. After removing the CXRs with detected noisy labels, 8 out of 14 abnormalities improved significantly on CXR14. The suggested framework achieved AUC score of 0.827 on CXR14. The methods of this study boost the classification on CXR with awareness of the label noise. Expanded experimental results show that all of them were able to improve multi-label thoracic abnormality classification performance, respectively. A new state-of-the-art is achieved in this study.

Serial T2-Weighted Thoracic and Abdominal Lymphatic Imaging in Fontan Patients-New Insights into Dynamics of Lymphatic Abnormalities after Total Cavopulmonary Connection.

Lymphatic congestion in single-ventricle patients has been associated with increased morbidity and poor outcomes. Little is known about the dynamics of lymphatic abnormalities over time, on their association with clinical presentation or response to catheter interventions. This retrospective, single-center study describes Fontan patients who underwent at least two magnetic resonance imaging (MRI) studies. T2-weighted lymphatic imaging was used to classify thoracic and abdominal (para-aortic and portal-venous) lymphatic abnormalities. The relationship between lymphatic congestion and hemodynamic changes after cardiac catheter interventions, clinical presentation and MRI data was analyzed. A total of 33 Fontan patients underwent at least two cardiac MRI studies. Twenty-two patients had two, eight had three and three had four lymphatic imaging studies (total of 80 MRIs studies). No significant changes in lymphatic classification between MRI 1 and 2 were observed for thoracic (p = 0.400), para-aortic (0.670) and portal-venous (p = 0.822) abnormalities. No significant correlation between lymphatic classification and hemodynamic changes after intervention or MRI parameters was found. This study illustrates thoracic and abdominal lymphatic abnormalities in serial T2-weighted imaging after Fontan. Fontan patients did not demonstrate significant changes in their lymphatic perfusion, despite clinical or hemodynamic changes. We assume that lymphatic congestion might develop after total cavopulmonary connection (TCPC) and remain relatively stable, despite further intervention targeting hemodynamic parameters.

Spectrum of thoracic systemic venous abnormalities using multidetector computed tomography

BackgroundAnomalies of the thoracic systemic venous return vary widely and range from those with completely normal physiology to severe right to left shunting thus requiring surgical correction. The aim of the study is to enhance the awareness of multidetector computed tomography (MDCT) role in evaluation of systemic venous abnormalities, and be familiar with the imaging characteristics of even the extremely rare abnormalities.ResultsAmong 270 examined patients, 15.19% had systemic venous abnormalities. Inferior vena cava (IVC) congenital anomalies accounted for (24.4%) of the detected abnormalities (prevalence: 3.7% among the studied population) where IVC interruption with azygos continuation was the most common detected IVC abnormality accounting for 17.7% of the detected abnormalities (prevalence: 2.6%), while IVC thrombosis accounted for 21.9% (prevalence: 3.3%). Persistent left sided superior vena cava (SVC) accounted for 14.6% of the detected abnormalities (prevalence: 2.2%), while SVC syndrome represented 19.5% (prevalence: 2.9%) and SVC aneurysm represented 2.4% (prevalence: 0.37%). Retroaortic brachiocephalic vein (BCV) and BCV thrombosis accounted for 7.3% each (prevalence: 1.1). Finally, persistent levo-atrial cardinal vein represented 2.4% of the detected abnormalities (prevalence: 0.37%).ConclusionsMDCT is a non-invasive modality that can provide detailed information about the systemic thoracic veins before surgical or interventional procedures, especially in patients with congenital anomalies.

Mapping Pediatric Spinal Cord Development with Age.

Pediatric spinal cord morphometry has been relatively understudied because of non-optimal image quality due to the difficulty of spine imaging, rarity of post-mortem analysis, motion artifacts, and pediatric MR imaging research focus on understanding spinal injury or pathology. The pediatric brain has been comparatively well-studied with white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) differences observed with age and gender. Therefore, a greater understanding of pediatric cervical and thoracic spinal cord morphometry would be beneficial for developing clinically relevant cord growth models. We focused on retrospectively characterizing cervical and thoracic spinal cord growth and morphometry changes in a healthy pediatric population. High resolution multi-echo gradient echo (mFFE) images were acquired from pediatric spinal cord scans from 63 patients (mean: 9.24 years, range: 0.83-17.67 years). The mFFE scans were then registered to the template space for uniform viewing and analysis by using a customized semi-automatic processing pipeline involving Spinal Cord Toolbox (SCT). Jacobian control determinants were calculated, and subsequent WM, GM, dorsal column, lateral funiculi, and ventral funiculi scalar averaging was conducted. Random effects models were used to model age-related Jacobian scalar differences. Observing the growth of cord matter by patient age and vertebral level suggests that the upper cervical spinal cord, specifically C2-C3, and mid-thoracic spinal cord, T3-T8, grow faster than other cervical levels and thoracic levels, respectively. This knowledge will facilitate clinical decision making when considering spine interventions and conducting radiological analysis in children with cervical and thoracic spine abnormalities.

A Nonimmune Hydrops Case.

A Nonimmune Hydrops Case.

A classification of abdominal lymphatic perfusion patterns after Fontan surgery.

Complications after Fontan surgery have been associated with arise and classification of abnormal thoracic lymphatic perfusion pattern. This study compiles abnormal abdominal lymphatic perfusion patterns and investigates their impact on serum protein readings. We performed a retrospective analysis of patients who underwent magnetic resonance imaging with T2-weighted lymphatic imaging and serum protein measurements 6 months after having Fontan surgery. The abdominal lymphatic images were classified according to the anatomical lymphatic drainage patterns into 2 categories: (1) para-aortic (types 1-4); (2) portal-venous (types 1-3). Thoracic lymphatic images were classified (types 1-4) as described earlier. A total of 71 patients were included in the study. Para-aortic lymphatic perfusion patterns were classified as type 1 in 4, type 2 in 13, type 3 in 37 and type 4 in16 out of 71 patients. Portal-venous lymphatic perfusion patterns were classified as type 1 in 20, type 2 in 10 and type 3 in 41 patients. Thoracic lymphatic perfusion patterns were classified as type 1 in 8, type 2 in 11, type 3 in 39 and type 4 in 13 patients. The serum protein level was 66 (interquartile range: 7.5) g/l (< standard value in 37%). Higher-grade para-aortic (p = 0.0062), portal-venous (p = 0.022) and thoracic (p = 0.011) lymphatic abnormalities were correlated with lower total serum protein levels. Higher ratings of para-aortic lymphatic abnormalities were significantly associated with higher ratings of portal-venous abnormalities (p < 0.0001). Ratings of para-aortic and portal-venous classifications were correlated with the thoracic classification (p < 0.001). Abnormal abdominal lymphatic perfusion patterns can be classified according to anatomical structures with increasing severity. Higher grade abdominal and thoracic lymphatic perfusion patterns are associated with lower serum protein values.

Concordance rate of radiologists and a commercialized deep-learning solution for chest X-ray: Real-world experience with a multicenter health screening cohort.

Lunit INSIGHT CXR (Lunit) is a commercially available deep-learning algorithm-based decision support system for chest radiography (CXR). This retrospective study aimed to evaluate the concordance rate of radiologists and Lunit for thoracic abnormalities in a multicenter health screening cohort. We retrospectively evaluated the radiology reports and Lunit results for CXR at several health screening centers in August 2020. Lunit was adopted as a clinical decision support system (CDSS) in routine clinical practice. Subsequently, radiologists completed their reports after reviewing the Lunit results. The DLA result was provided as a color map with an abnormality score (%) for thoracic lesions when the score was greater than the predefined cutoff value of 15%. Concordance was achieved when (a) the radiology reports were consistent with the DLA results ("accept"), (b) the radiology reports were partially consistent with the DLA results ("edit") or had additional lesions compared with the DLA results ("add"). There was discordance when the DLA results were rejected in the radiology report. In addition, we compared the reading times before and after Lunit was introduced. Finally, we evaluated systemic usability scale questionnaire for radiologists and physicians who had experienced Lunit. Among 3,113 participants (1,157 men; mean age, 49 years), thoracic abnormalities were found in 343 (11.0%) based on the CXR radiology reports and 621 (20.1%) based on the Lunit results. The concordance rate was 86.8% (accept: 85.3%, edit: 0.9%, and add: 0.6%), and the discordance rate was 13.2%. Except for 479 cases (7.5%) for whom reading time data were unavailable (n = 5) or unreliable (n = 474), the median reading time increased after the clinical integration of Lunit (median, 19s vs. 14s, P < 0.001). The real-world multicenter health screening cohort showed a high concordance of the chest X-ray report and the Lunit result under the clinical integration of the deep-learning solution. The reading time slight increased with the Lunit assistance.

Frequency of Cervical, Thoracic and Lumber Pain and Postural Changes in Madrassa Students

Musculoskeletal pain and abnormal postural change is very common among school going students. The prevalence is also high in madrassa students. Their number increase because of bad posture, prolong sitting and repetitive movement. Objective: The objective of the study was to find the frequency of pain in cervical, thoracic, and lumbar spine and postural abnormalities occurring in madrassa students. Methods: This is a descriptive cross sectional study which was conducted from 15th February 2016 to 28th June 2016 at different madrassa’s of Rawalpindi and Islamabad. This include: Madrassa Zia-ul-Quran, Shah Khalid Colony Rawalpindi, DarulSufah Faisal Colony Rawalpindi, Madrassa Hazrat Abdullah bin Abbas(R.A) Islamabad, Madrassa Hazrat Salman Pharsi(R.A) DhokMangtal, Rawalpindi, Madrassa Abdullah bin Umar (R.A) Jinnah Garden, Phase I, Islamabad, Madrassa KhadijahtulQubra, Khayaban-e-Sirsyed, Rawalpindi, JamyaAmna Zia ulBinat, Railway scheme 7, Rawalpindi. A sample of 205 male and female madrassa students (age 10-17year) was recruited through convenient sampling. The inclusion criteria was both gender, male &amp; female, Age; 10-17, only madrassa students, exclusion criteria was, students above the age of 17 years, students under 10 year of age, children with poliomyelitis, active tuberculosis, neurological problems, congenital deformities Normal posture and pain was assessed by Adam’s bend test and Numeric pain rating scale (NRPS). Later the data was analyzed through SPSS 17. Result: A total sample size of 205 was selected in which 61% were male students and 39% were female students. The mean age of the madrassa students is 13.19±2.06 of which 12.98±2.00 male and 13.51±2.14.Out of 205(100%) madrassa students 74.6% madrassa students have pain, most of them have moderate intensity of pain 55.6% and 12.7% have severe intensity of pain and 25.4% madrassa students have no pain. 78.5% of the madrassa students were sitting with low level of desk and 21.5% with appropriate leveled height of the desk. Only 6.8% of madrassa students have activity restriction due to pain. Forward head posture is present in 37.1% of madrassa students and absent in 62.9% of the students out of 100%. 36.6% of madrassa students presents with rounded shoulders. Out of 100% of madrassa students 36.1% of madrassa students have increased thoracic kyphotic and lumber Lordotic curve.In 11.7% of the madrassa students Adams forward bending test for scoliosis came positive and negative in 88.3% of the madrassa students. Conclusion: It is concluded that the cervical and lumber pain is more prevalent in madrassa students and some of the students show increased kyphotic and lordotic curves which is correlated with long periods of sitting for recitation in forward flexion of head, neck, and back and poor posture maintenance.

Artificial Intelligence-Based Identification of Normal Chest Radiographs: A Simulation Study in a Multicenter Health Screening Cohort.

ObjectiveThis study aimed to investigate the feasibility of using artificial intelligence (AI) to identify normal chest radiography (CXR) from the worklist of radiologists in a health-screening environment.Materials and MethodsThis retrospective simulation study was conducted using the CXRs of 5887 adults (mean age ± standard deviation, 55.4 ± 11.8 years; male, 4329) from three health screening centers in South Korea using a commercial AI (Lunit INSIGHT CXR3, version 3.5.8.8). Three board-certified thoracic radiologists reviewed CXR images for referable thoracic abnormalities and grouped the images into those with visible referable abnormalities (identified as abnormal by at least one reader) and those with clearly visible referable abnormalities (identified as abnormal by at least two readers). With AI-based simulated exclusion of normal CXR images, the percentages of normal images sorted and abnormal images erroneously removed were analyzed. Additionally, in a random subsample of 480 patients, the ability to identify visible referable abnormalities was compared among AI-unassisted reading (i.e., all images read by human readers without AI), AI-assisted reading (i.e., all images read by human readers with AI assistance as concurrent readers), and reading with AI triage (i.e., human reading of only those rendered abnormal by AI).ResultsOf 5887 CXR images, 405 (6.9%) and 227 (3.9%) contained visible and clearly visible abnormalities, respectively. With AI-based triage, 42.9% (2354/5482) of normal CXR images were removed at the cost of erroneous removal of 3.5% (14/405) and 1.8% (4/227) of CXR images with visible and clearly visible abnormalities, respectively. In the diagnostic performance study, AI triage removed 41.6% (188/452) of normal images from the worklist without missing visible abnormalities and increased the specificity for some readers without decreasing sensitivity.ConclusionThis study suggests the feasibility of sorting and removing normal CXRs using AI with a tailored cut-off to increase efficiency and reduce the workload of radiologists.