RESUMO
INTRODUCTION: Central venous catheters (CVCs) are widely used in the management and resuscitation of critically ill patients in emergency departments and intensive care units. Correct depth of insertion of the CVC line is important to ensure uninterrupted flow, avoid complications, and monitor central venous pressure. Transthoracic echocardiography, with contrast enhancement, has been proposed as an alternative to chest X-ray in detecting central venous line positioning with high accuracy. Nevertheless, this method is not widely used due to some previous conflicting results and the cumbersomeness of the procedure. MATERIAL AND METHODS: After approval by the Institutional Ethics Committee, this prospective observational study was carried out in patients for whom a central venous line was warranted. The study was conducted in the Intensive Care Unit of a tertiary care hospital among 150 adult patients to compare the "Rapid Atrial Swirl Sign" (RASS) technique by transthoracic echocardiography and the landmark-based technique for ensuring accurate depth of central venous line placement. RESULTS: In this study, we found that the mean depth of insertion of the CVC for the Echocardiography RASS group (E) was 12.84 cm, while for the Landmark technique group (L), it was 12.02 cm. There was a significant difference between these groups, with a p-value of <0.05. We found that the majority of patients (98.63%) in Group E had the catheter tip in Zones 1, 2, and 3, while only 66.6% of patients in Group L had the catheter tip in similar zones. The mean standard deviation for zones on chest X-ray was 1.8 for Group E and 2.26 for Group L, with a significant difference between these groups (p-value <0.05). CONCLUSION: The RASS technique is superior to the landmark technique in ensuring the correct depth of the tip of the CVC. When confirmed by chest X-ray, it was found that most patients had the catheter tip in Zone 1, 2, or 3 using the RASS technique. This confirms that the RASS technique can minimize the requirement of resources and hasten the initiation of patient management in a timely manner, unlike the landmark technique, which requires chest X-ray confirmation before use.
RESUMO
Background: The integration of artificial intelligence (AI) into medicine is growing, with some experts predicting its standalone use soon. However, skepticism remains due to limited positive outcomes from independent validations. This research evaluates AI software's effectiveness in analyzing chest X-rays (CXR) to identify lung nodules, a possible lung cancer indicator. Methods: This retrospective study analyzed 7,670,212 record pairs from radiological exams conducted between 2020 and 2022 during the Moscow Computer Vision Experiment, focusing on CXR and computed tomography (CT) scans. All images were acquired during clinical routine. The final dataset comprised 100 CXR images (50 with lung nodules, 50 without), selected consecutively and based on inclusion and exclusion criteria, to evaluate the performance of all five AI-based solutions, participating in the Moscow Computer Vision Experiment and analyzing CXR. The evaluation was performed in 3 stages. In the first stage, the probability of a nodule in the lung obtained from AI services was compared with the Ground Truth (1-there is a nodule, 0-there is no nodule). In the second stage, 3 radiologists evaluated the segmentation of nodules performed by the AI services (1-nodule correctly segmented, 0-nodule incorrectly segmented or not segmented at all). In the third stage, the same radiologists additionally evaluated the classification of the nodules (1-nodule correctly segmented and classified, 0-all other cases). The results obtained in stages 2 and 3 were compared with Ground Truth, which was common to all three stages. For each stage, diagnostic accuracy metrics were calculated for each AI service. Results: Three software solutions (Celsus, Lunit INSIGHT CXR, and qXR) demonstrated diagnostic metrics that matched or surpassed the vendor specifications, and achieved the highest area under the receiver operating characteristic curve (AUC) of 0.956 [95% confidence interval (CI): 0.918 to 0.994]. However, when evaluated by three radiologists for accurate nodule segmentation and classification, all solutions performed below the vendor-declared metrics, with the highest AUC reaching 0.812 (95% CI: 0.744 to 0.879). Meanwhile, all AI services demonstrated 100% specificity at stages 2 and 3 of the study. Conclusions: To ensure the reliability and applicability of AI-based software, it is crucial to validate performance metrics using high-quality datasets and engage radiologists in the evaluation process. Developers are recommended to improve the accuracy of the underlying models before allowing the standalone use of the software for lung nodule detection. The dataset created during the study may be accessed at https://mosmed.ai/datasets/mosmeddatargogksnalichiemiotsutstviemlegochnihuzlovtipvii/.
RESUMO
Urgent direct access to diagnostic services for general practitioners (GPs) is a new pathway to capture any cancer diagnoses that may have been missed due to vague symptom presentations. Hence, GPs should look out for the key symptoms mentioned by NHS England that should prompt urgent direct access referrals for chest X-ray (CXR), computed tomography (CT) chest, MRI brain, ultrasound (US) abdomen and pelvis, and CT abdomen and pelvis. By implementing this approach, we can significantly reduce the time to diagnosis, while minimizing the number of visits to GP and specialist appointments prior to initiating investigations. However, the use of this pathway can only improve if access to diagnostic scans is improved. This needs to be done by ensuring all GPs in the country have access to directly request MRI brains, CT chest, abdomen, and pelvis. Further research into the impact of the urgent direct access pathway as well as investigating the number of GPs without access to these vital diagnostic services is required to fully improve and measure the progress of this referral pathway.
RESUMO
Congenital heart disease in adult patients (ACHD) includes individuals with native anatomic deformities and those who have benefited from corrective, ameliorative, or interventional heart and vascular interventions. Congenital heart disease is the most common birth defect, although with interventions most survive into adulthood. Newborns and children with complex congenital heart diseases that feature cyanosis fail to thrive, and once this is identified, heart failure can promptly undergo diagnostic evaluations and treatment. However, patients with simple congenital heart disease and subtle clinical signs and symptoms may escape diagnosis until adulthood or experience changes in their cardiac hemodynamics and physiology in settings such as pregnancy or newly diagnosed arrhythmias. The chest X-ray (CXR) is the most common X-ray among all radiological procedures. Individual features or a constellation of features on a CXR are often present in patients who have congenital heart disease. The ability to recognize these CXR features is a valuable skill for making the diagnosis of ACHD and for following these patients as they age, and can complement echocardiographic findings. When used well to diagnose ACHD, the CXR will be the sharpest arrow in the quiver.
RESUMO
OBJECTIVE: Although there is growing evidence that ultrasonography is superior to X-ray for rib fractures' detection, X-ray is still indicated as the most appropriate method. This has partially been attributed to a lack of studies using an appropriate reference modality. We aimed to compare the diagnostic accuracy of ultrasonography and X-ray in the detection of rib fractures, considering CT as the reference standard. MATERIALS AND METHODS: Within a 2.5-year period, all consecutive patients with clinically suspected rib fracture(s) following blunt chest trauma and available posteroanterior/anteroposterior X-ray and thoracic CT were prospectively studied and planned to undergo thoracic ultrasonography, by a single operator. All imaging examinations were evaluated for cortical rib fracture(s), and their location was recorded. The cartilaginous rib portions were not assessed. CTs and X-rays were evaluated retrospectively. Concomitant thoracic/extra-thoracic injuries were assessed on CT. Comparisons were performed with the Mann-Whitney U test and Fisher's exact test. RESULTS: Fifty-nine patients (32 males, 27 females; mean age, 53.1 ± 16.6 years) were included. CT, ultrasonography, and X-ray (40 posteroanterior/19 anteroposterior views) diagnosed 136/122/42 rib fractures in 56/54/27 patients, respectively. Ultrasonography and X-ray had sensitivity of 100%/40% and specificity of 89.7%/30.9% for rib fractures' detection. Ultrasound accuracy was 94.9% compared to 35.4% for X-rays (P < .001) in detecting individual rib fractures. Most fractures involved the 4th-9th ribs. Upper rib fractures were most commonly overlooked on ultrasonography. Thoracic cage/spine fractures and haemothorax represented the most common concomitant injuries. CONCLUSION: Ultrasonography appeared to be superior to X-ray for the detection of rib fractures with regard to a reference CT.
RESUMO
Convolutional neural networks (CNNs) have been successfully applied to chest x-ray (CXR) images. Moreover, annotated bounding boxes have been shown to improve the interpretability of a CNN in terms of localizing abnormalities. However, only a few relatively small CXR datasets containing bounding boxes are available, and collecting them is very costly. Opportunely, eye-tracking (ET) data can be collected during the clinical workflow of a radiologist. We use ET data recorded from radiologists while dictating CXR reports to train CNNs. We extract snippets from the ET data by associating them with the dictation of keywords and use them to supervise the localization of specific abnormalities. We show that this method can improve a model's interpretability without impacting its image-level classification.
RESUMO
The segmentation of lungs from medical images is a critical step in the diagnosis and treatment of lung diseases. Deep learning techniques have shown great promise in automating this task, eliminating the need for manual annotation by radiologists. In this research, a convolution neural network architecture is proposed for lung segmentation using chest X-ray images. In the proposed model, concatenate block is embedded to learn a series of filters or features used to extract meaningful information from the image. Moreover, a transpose layer is employed in the concatenate block to improve the spatial resolution of feature maps generated by a prior convolutional layer. The proposed model is trained using k-fold validation as it is a powerful and flexible tool for evaluating the performance of deep learning models. The proposed model is evaluated on five different subsets of the data by taking the value of k as 5 to obtain the optimized model to obtain more accurate results. The performance of the proposed model is analyzed for different hyper-parameters such as the batch size as 32, optimizer as Adam and 40 epochs. The dataset used for the segmentation of disease is taken from the Kaggle repository. The various performance parameters such as accuracy, IoU, and dice coefficient are calculated, and the values obtained are 0.97, 0.93, and 0.96, respectively.
RESUMO
Supervised deep learning methods have been successfully applied in medical imaging. However, training deep learning systems often requires ample annotated data. Due to cost and time restrictions, not all collected medical images, e.g., chest x-rays (CXRs), can be labeled in practice. To classify these unlabeled images, a solution may involve adopting a model trained with sufficient labeled data in relevant domains (with both source and target being CXRs). However, domain shift may cause the trained model not able to generalize well on unlabeled target datasets. This work aims to develop a novel unsupervised domain adaptation (UDA) framework to improve recognition performance on unlabeled target data. We present a semantically preserving adversarial UDA network, i.e., SPA-UDA net, with the potential to bridge the domain gap, by reconstructing the images in the target domain via an adversarial encode-and-reconstruct translation architecture. To preserve the class-specific semantic information (i.e., with or without disease) of the original images when translating, a semantically consistent framework is embedded. This framework is designed to guarantee that fine-grained disease-related information on the original images can be safely transferred. Furthermore, the proposed SPA-UDA net does not require paired images from source and target domains when training, which reduces the cost of arranging data significantly and is ideal for UDA. We evaluate the proposed SPA-UDA net on two public CXR datasets for lung disease recognition. The experimental results show that the proposed framework achieves significant performance improvements compared to other state-of-the-art UDA methods.
Assuntos
Raios X , RadiografiaRESUMO
INTRODUCTION: The Radiographic Assessment of Lung Edema (RALE) score provides a semi-quantitative measure of pulmonary edema. In patients with acute respiratory distress syndrome (ARDS), the RALE score is associated with mortality. In mechanically ventilated patients in the intensive care unit (ICU) with respiratory failure not due to ARDS, a variable degree of lung edema is observed as well. We aimed to evaluate the prognostic value of RALE in mechanically ventilated ICU patients. METHODS: Secondary analysis of patients enrolled in the 'Diagnosis of Acute Respiratory Distress Syndrome' (DARTS) project with an available chest X-ray (CXR) at baseline. Where present, additional CXRs at day 1 were analysed. The primary endpoint was 30-day mortality. Outcomes were also stratified for ARDS subgroups (no ARDS, non-COVID-ARDS and COVID-ARDS). RESULTS: 422 patients were included, of which 84 had an additional CXR the following day. Baseline RALE scores were not associated with 30-day mortality in the entire cohort (OR: 1.01, 95% CI: 0.98-1.03, p = 0.66), nor in subgroups of ARDS patients. Early changes in RALE score (baseline to day 1) were only associated with mortality in a subgroup of ARDS patients (OR: 1.21, 95% CI: 1.02-1.51, p = 0.04), after correcting for other known prognostic factors. CONCLUSIONS: The prognostic value of the RALE score cannot be extended to mechanically ventilated ICU patients in general. Only in ARDS patients, early changes in RALE score were associated with mortality.
RESUMO
Chest radiographs (CXRs) are the most widely available radiographic imaging modality used to detect respiratory diseases that result in lung opacities. CXR reports often use non-standardized language that result in subjective, qualitative, and non-reproducible opacity estimates. Our goal was to develop a robust deep transfer learning framework and adapt it to estimate the degree of lung opacity from CXRs. Following CXR data selection based on exclusion criteria, segmentation schemes were used for ROI (Region Of Interest) extraction, and all combinations of segmentation, data balancing, and classification methods were tested to pick the top performing models. Multifold cross validation was used to determine the best model from the initial selected top models, based on appropriate performance metrics, as well as a novel Macro-Averaged Heatmap Concordance Score (MA HCS). Performance of the best model is compared against that of expert physician annotators, and heatmaps were produced. Finally, model performance sensitivity analysis across patient populations of interest was performed. The proposed framework was adapted to the specific use case of estimation of degree of CXR lung opacity using ordinal multiclass classification. Acquired between March 24, 2020, and May 22, 2020, 38,365 prospectively annotated CXRs from 17,418 patients were used. We tested three neural network architectures (ResNet-50, VGG-16, and ChexNet), three segmentation schemes (no segmentation, lung segmentation, and lateral segmentation based on spine detection), and three data balancing strategies (undersampling, double-stage sampling, and synthetic minority oversampling) using 38,079 CXR images for training, and validation with 286 images as the out-of-the-box dataset that underwent expert radiologist adjudication. Based on the results of these experiments, the ResNet-50 model with undersampling and no ROI segmentation is recommended for lung opacity classification, based on optimal values for the MAE metric and HCS (Heatmap Concordance Score). The degree of agreement between the opacity scores predicted by this model with respect to the two sets of radiologist scores (OR or Original Reader and OOBTR or Out Of Box Reader) in terms of performance metrics is superior to the inter-radiologist opacity score agreement.
RESUMO
Background: The coronavirus disease 2019 (COVID-19) led to a dramatic increase in the number of cases of patients with pneumonia worldwide. In this study, we aimed to develop an AI-assisted multistrategy image enhancement technique for chest X-ray (CXR) images to improve the accuracy of COVID-19 classification. Methods: Our new classification strategy consisted of 3 parts. First, the improved U-Net model with a variational encoder segmented the lung region in the CXR images processed by histogram equalization. Second, the residual net (ResNet) model with multidilated-rate convolution layers was used to suppress the bone signals in the 217 lung-only CXR images. A total of 80% of the available data were allocated for training and validation. The other 20% of the remaining data were used for testing. The enhanced CXR images containing only soft tissue information were obtained. Third, the neural network model with a residual cascade was used for the super-resolution reconstruction of low-resolution bone-suppressed CXR images. The training and testing data consisted of 1,200 and 100 CXR images, respectively. To evaluate the new strategy, improved visual geometry group (VGG)-16 and ResNet-18 models were used for the COVID-19 classification task of 2,767 CXR images. The accuracy of the multistrategy enhanced CXR images was verified through comparative experiments with various enhancement images. In terms of quantitative verification, 8-fold cross-validation was performed on the bone suppression model. In terms of evaluating the COVID-19 classification, the CXR images obtained by the improved method were used to train 2 classification models. Results: Compared with other methods, the CXR images obtained based on the proposed model had better performance in the metrics of peak signal-to-noise ratio and root mean square error. The super-resolution CXR images of bone suppression obtained based on the neural network model were also anatomically close to the real CXR images. Compared with the initial CXR images, the classification accuracy rates of the internal and external testing data on the VGG-16 model increased by 5.09% and 12.81%, respectively, while the values increased by 3.51% and 18.20%, respectively, for the ResNet-18 model. The numerical results were better than those of the single-enhancement, double-enhancement, and no-enhancement CXR images. Conclusions: The multistrategy enhanced CXR images can help to classify COVID-19 more accurately than the other existing methods.
RESUMO
Background: Respiratory distress syndrome (RDS) is a common disease that seriously endangers the life and safety of newborns, especially premature infants. Exogenous pulmonary surfactant (PS) is the specific agent for the treatment of neonatal RDS. Lung ultrasound (LUS) has been successfully used in the diagnosis of RDS, but its value in guiding the application of PS is still unclear. This paper explored whether the application of PS under LUS monitoring has some advantages, including (1) decreasing the misdiagnosis rate of RDS and decreasing probability of using PS, and (2) reducing the dose of PS without reducing the therapeutic effect. Methods: This study included two parts. Part 1: To decide whether the LUS is good to differentiate RDS from other lung diseases in the premature infants. All patients who were diagnosed with RDS and required PS treatment based on conventional criteria were routinely examined by LUS. Then, according to LUS findings, we decided whether they needed to receive PS treatment. Part 2: To see the dose reduction of surfactant is applicable. In RDS patients diagnosed based on LUS presentation and treated with Curosurf (Chiesi Pharmaceutical, Parma, Italy), the dose of Curosurf was compared with that recommended by the European RDS management guidelines. Results: (1) Since March 2017, 385 newborn infants admitted to our neonatal intensive care unit met the traditional diagnostic criteria of RDS. Of these, only 269 cases were diagnosed with RDS and needed PS treatment according to LUS manifestations. The other 116 infants who did not meet the criteria for ultrasound diagnosis of RDS did not receive PS supplementation but obtained good outcomes, that is LUS findings decreased a misdiagnosis rate of RDS by 30.1% and subsequently resulted in a 30.1% reduction in PS use. (2) Among the 269 RDS patients diagnosed based on LUS findings, 148 were treated with Curosurf (another 121 RDS infants who received domestic PS treatment were not included in the study group), and the average dose was 105.4 ± 24.3â mg/kg per time, which is significantly lower than the dose of 200â mg/kg per time recommended by the European RDS guidelines. (3) The mortality rate of RDS patients was 0%, and no patients had ventilator-associated pneumonia or bronchopulmonary dysplasia in this study. Conclusion: LUS can decrease the misdiagnosis rate of RDS, thereby decreasing the probability of using PS and decreasing the dose of PS, and can help RDS infants to achieve better outcomes.
RESUMO
OBJECTIVE: To compare the effect of managing neonatal lung disease with lung ultrasound (LUS) or chest X-ray (CXR) monitoring on health outcomes and cost-effectiveness. METHODS: The data obtained from the NICU of the Beijing Chaoyang District Maternal and Child Healthcare Hospital were used as the study group, as LUS has completely replaced CXR in managing newborn lung disease in the hospital for the past 5 years. The primary outcomes of this study were the misdiagnosis rate of respiratory distress syndrome (RDS), the using status of mechanical ventilation, the incidence rate of bronchopulmonary dysplasia (BPD) and the survival rate in hospitalized infants. The secondary outcomes included the use pulmonary surfactant (PS), and the mortality rate of severe diseases (such as pneumothorax, pulmonary hemorrhage and RDS, etc.). RESULTS: Managing neonatal lung disease with LUS monitoring may enable the following effects: The frequency of ventilator use reducing by 40.2%; the duration of mechanical ventilation reducing by 67.5%; and the frequency of ventilator weaning failure being totally avoided. A misdiagnosis rate of 30% for RDS was also avoided. The dosage of PS was significantly reduced by 50% to 75%. No BPD occurred in the LUS-based care group for 5 years. The fatality rates of RDS, pneumothorax and pulmonary hemorrhage decreased by 100%. The poor prognosis rate of VLBW infants decreased by 85%, and the total mortality rate of hospitalized infants decreased by 90%. Therefore, the cost of LUS-based care was inevitably saved. CONCLUSIONS: Diagnosing and managing neonatal lung diseases with LUS monitoring have significant benefits, and this technology should be widely promoted and applied around the world.
RESUMO
Developments in deep learning techniques have led to significant advances in automated abnormality detection in radiological images and paved the way for their potential use in computer-aided diagnosis (CAD) systems. However, the development of CAD systems for pulmonary tuberculosis (TB) diagnosis is hampered by the lack of training data that is of good visual and diagnostic quality, of sufficient size, variety, and, where relevant, containing fine region annotations. This study presents a collection of annotations/segmentations of pulmonary radiological manifestations that are consistent with TB in the publicly available and widely used Shenzhen chest X-ray (CXR) dataset made available by the U.S. National Library of Medicine and obtained via a research collaboration with No. 3. People's Hospital Shenzhen, China. The goal of releasing these annotations is to advance the state-of-the-art for image segmentation methods toward improving the performance of fine-grained segmentation of TB-consistent findings in digital Chest X-ray images. The annotation collection comprises the following: 1) annotation files in JSON (JavaScript Object Notation) format that indicate locations and shapes of 19 lung pattern abnormalities for 336 TB patients; 2) mask files saved in PNG format for each abnormality per TB patient; 3) a CSV (comma-separated values) file that summarizes lung abnormality types and numbers per TB patient. To the best of our knowledge, this is the first collection of pixel-level annotations of TB-consistent findings in CXRs. Dataset: https://data.lhncbc.nlm.nih.gov/public/Tuberculosis-Chest-X-ray-Datasets/Shenzhen-Hospital-CXR-Set/Annotations/index.html.
RESUMO
Covid-19 disease has had a disastrous effect on the health of the global population, for the last two years. Automatic early detection of Covid-19 disease from Chest X-Ray (CXR) images is a very crucial step for human survival against Covid-19. In this paper, we propose a novel data-augmentation technique, called SVD-CLAHE Boosting and a novel loss function Balanced Weighted Categorical Cross Entropy (BWCCE), in order to detect Covid 19 disease efficiently from a highly class-imbalanced Chest X-Ray image dataset. Our proposed SVD-CLAHE Boosting method is comprised of both oversampling and under-sampling methods. First, a novel Singular Value Decomposition (SVD) based contrast enhancement and Contrast Limited Adaptive Histogram Equalization (CLAHE) methods are employed for oversampling the data in minor classes. Simultaneously, a Random Under Sampling (RUS) method is incorporated in major classes, so that the number of images per class will be more balanced. Thereafter, Balanced Weighted Categorical Cross Entropy (BWCCE) loss function is proposed in order to further reduce small class imbalance after SVD-CLAHE Boosting. Experimental results reveal that ResNet-50 model on the augmented dataset (by SVD-CLAHE Boosting), along with BWCCE loss function, achieved 95% F1 score, 94% accuracy, 95% recall, 96% precision and 96% AUC, which is far better than the results by other conventional Convolutional Neural Network (CNN) models like InceptionV3, DenseNet-121, Xception etc. as well as other existing models like Covid-Lite and Covid-Net. Hence, our proposed framework outperforms other existing methods for Covid-19 detection. Furthermore, the same experiment is conducted on VGG-19 model in order to check the validity of our proposed framework. Both ResNet-50 and VGG-19 model are pre-trained on the ImageNet dataset. We publicly shared our proposed augmented dataset on Kaggle website (https://www.kaggle.com/tr1gg3rtrash/balanced-augmented-covid-cxr-dataset), so that any research community can widely utilize this dataset. Our code is available on GitHub website online (https://github.com/MrinalTyagi/SVD-CLAHE-and-BWCCE).
Assuntos
COVID-19 , Humanos , COVID-19/diagnóstico por imagem , Raios X , Entropia , Redes Neurais de Computação , RadiografiaRESUMO
Aiming at detecting COVID-19 effectively, a multiscale class residual attention (MCRA) network is proposed via chest X-ray (CXR) image classification. First, to overcome the data shortage and improve the robustness of our network, a pixel-level image mixing of local regions was introduced to achieve data augmentation and reduce noise. Secondly, multi-scale fusion strategy was adopted to extract global contextual information at different scales and enhance semantic representation. Last but not least, class residual attention was employed to generate spatial attention for each class, which can avoid inter-class interference and enhance related features to further improve the COVID-19 detection. Experimental results show that our network achieves superior diagnostic performance on COVIDx dataset, and its accuracy, PPV, sensitivity, specificity and F1-score are 97.71%, 96.76%, 96.56%, 98.96% and 96.64%, respectively; moreover, the heat maps can endow our deep model with somewhat interpretability.
Assuntos
COVID-19 , Aprendizado Profundo , Atenção , COVID-19/diagnóstico por imagem , Teste para COVID-19 , Progressão da Doença , Humanos , Raios XRESUMO
The risk of contagion and the lockdown caused by the COVID-19 pandemic forced a change in teaching methodologies in radiology. New knowledge about the disease that was being acquired on a daily basis needed to be rapidly spread worldwide, but the restrictions imposed made it difficult to share this information. This paper describes the methodology applied to design and launch a practice-based course on chest X-ray suggestive of COVID-19 right after the pandemic started, and aims to determine whether asynchronous online learning tools for radiology education are useful and acceptable to general practitioners and other medical personnel during a pandemic. The study was carried out from April to October 2020 and involved 2632 participants. Pre- and post-testing was used to assess the participants' gain of knowledge in the course content (paired t-tests and chi-squared tests of independence). A five-point Likert scale questionnaire inspired by the technological acceptance model (TAM) was provided to evaluate the e-learning methodology (ANOVA tests). The results from the pre- and post-tests showed that there were significant differences in the scores before and after completing the course (sample size = 2632, response rate = 56%, p<0.001). As for the questionnaire, all questions surpassed 4.5 out of 5, including those referring to perceived ease of use and perceived usefulness, and no significant differences were found between experienced and inexperienced participants (sample size = 2535, response rate = 53%, p=0.85). The analysis suggests that the applied methodology is flexible enough to adapt to complex situations, and is useful to improve knowledge on the subject of the course. Furthermore, a wide acceptance of the teaching methodology is confirmed for all technological profiles, pushing for and endorsing a more widespread use of online platforms in the domain of radiology continuing education.
Assuntos
COVID-19 , Educação a Distância , Radiologia , COVID-19/epidemiologia , Controle de Doenças Transmissíveis , Humanos , PandemiasRESUMO
Background: The purpose of this paper is to demonstrate a mechanism for deploying and validating an AI-based system for detecting abnormalities on chest X-ray scans at the Phu Tho General Hospital, Vietnam. We aim to investigate the performance of the system in real-world clinical settings and compare its effectiveness to the in-lab performance. Method: The AI system was directly integrated into the Hospital's Picture Archiving and Communication System (PACS) after being trained on a fixed annotated dataset from other sources. The system's performance was prospectively measured by matching and comparing the AI results with the radiology reports of 6,285 chest X-ray examinations extracted from the Hospital Information System (HIS) over the last 2 months of 2020. The normal/abnormal status of a radiology report was determined by a set of rules and served as the ground truth. Results: Our system achieves an F1 score-the harmonic average of the recall and the precision-of 0.653 (95% CI 0.635, 0.671) for detecting any abnormalities on chest X-rays. This corresponds to an accuracy of 79.6%, a sensitivity of 68.6%, and a specificity of 83.9%. Conclusions: Computer-Aided Diagnosis (CAD) systems for chest radiographs using artificial intelligence (AI) have recently shown great potential as a second opinion for radiologists. However, the performances of such systems were mostly evaluated on a fixed dataset in a retrospective manner and, thus, far from the real performances in clinical practice. Despite a significant drop from the in-lab performance, our result establishes a reasonable level of confidence in applying such a system in real-life situations.
RESUMO
Few cases of Hypervirulent Klebsiella Pneumonia (HvKP) have been described. Even fewer cases with renal abscess and metastatic pulmonary spread are reported. Typically, prompt introduction of intravenous antibiotics leads to clinical resolution and more invasive measures of source control are rarely required. To date only one other case of disseminated metastatic HvKP requiring nephrectomy for infective source control is described. Here we present a rare case of metastatic HvKP refractory to intravenous antimicrobial therapy in an immunocompromised newly diagnosed diabetic patient. Specifically, we seek to illustrate the rapid effectiveness of surgical intervention following a poor response to initial treatment.
RESUMO
Pneumonia and pulmonary edema are the most common causes of acute respiratory failure in emergency and intensive care. Airway maintenance and heart function preservation are two foundations for resuscitation. Laboratory examinations have been utilized for clinicians to early differentiate pneumonia and pulmonary edema; however, none can provide results as prompt as radiology examinations, such as portable chest X-ray (CXR), which can quickly deliver results without mobilizing patients. However, similar features between pneumonia and pulmonary edema are found in CXR. It remains challenging for Emergency Department (ED) physicians to make immediate decisions as radiologists cannot be on-site all the time and provide support. Thus, Accurate interpretation of images remains challenging in the emergency setting. References have shown that deep convolutional neural networks (CNN) have a high sensitivity in CXR readings. In this retrospective study, we collected the CXR images of patients over 65 hospitalized with pneumonia or pulmonary edema diagnosis between 2016 and 2020. After using the ICD-10 codes to select qualified patient records and removing the duplicated ones, we used keywords to label the image reports found in the electronic medical record (EMR) system. After that, we categorized their CXR images into five categories: positive correlation, negative correlation, no correlation, low correlation, and high correlation. Subcategorization was also performed to better differentiate characteristics. We applied six experiments includes the crop interference and non-interference categories by GoogLeNet and applied three times of validations. In our best model, the F1 scores for pneumonia and pulmonary edema are 0.835 and 0.829, respectively; accuracy rate: 83.2%, Recall rate: 83.2%, positive predictive value: 83.3%, and F1 Score: 0.832. After the validation, the best accuracy rate of our model can reach up to 73%. The model has a high negative predictive value of excluding pulmonary edema, meaning the CXR shows no sign of pulmonary edema. At the time, there was a high positive predictive value in pneumonia. In that way, we could use it as a clinical decision support (CDS) system to rule out pulmonary edema and rule in pneumonia contributing to the critical care of the elderly.