Point-of-care AI-assisted stepwise ultrasound pneumothorax diagnosis

Objective. Ultrasound is extensively utilized as a convenient and cost-effective method in emergency situations. Unfortunately, the limited availability of skilled clinicians in emergency hinders the wider adoption of point-of-care ultrasound. To overcome this challenge, this paper aims to aid less experienced healthcare providers in emergency lung ultrasound scans.Approach. To assist healthcare providers, it is important to have a comprehensive model that can automatically guide the entire process of lung ultrasound based on the clinician's workflow. In this paper, we propose a framework for diagnosing pneumothorax using artificial intelligence (AI) assistance. Specifically, the proposed framework for lung ultrasound scan follows the steps taken by skilled physicians. It begins with finding the appropriate transducer position on the chest to locate the pleural line accurately in B-mode. The next step involves acquiring temporal M-mode data to determine the presence of lung sliding, a crucial indicator for pneumothorax. To mimic the sequential process of clinicians, two DL models were developed. The first model focuses on quality assurance (QA) and regression of the pleural line region-of-interest, while the second model classifies lung sliding. To achieve the inference on a mobile device, a size of EfficientNet-Lite0 model was further reduced to have fewer than 3 million parameters.Main results. The results showed that both the QA and lung sliding classification models achieved over 95% in area under the receiver operating characteristic (AUC), while the ROI performance reached 89% in the dice similarity coefficient. The entire stepwise pipeline was simulated using retrospective data, yielding an AUC of 89%.Significance. The step-wise AI framework for the pneumothorax diagnosis with QA offers an intelligible guide for each clinical workflow, which achieved significantly high precision and real-time inferences.

Quantification of the Thoracic Aorta and Detection of Aneurysm at CT: Development and Validation of a Fully Automatic Methodology

Purpose

To develop and validate a deep learning-based system that predicts the largest ascending and descending aortic diameters at chest CT through automatic thoracic aortic segmentation and identifies aneurysms in each segment.

Materials and Methods

In this retrospective study conducted from July 2019 to February 2021, a U-Net and a postprocessing algorithm for thoracic aortic segmentation and measurement were developed by using a dataset (dataset A) that included 315 CT studies split into training, hyperparameter-tuning, and testing sets. The U-Net and postprocessing algorithm were associated with a Digital Imaging and Communications in Medicine series filter and visualization interface and were further validated by using a dataset (dataset B) that included 1400 routine CT studies. In dataset B, system-predicted measurements were compared with annotations made by two independent readers as well as radiology reports to evaluate system performance.

Results

In dataset B, the mean absolute error between the automatic and reader-measured diameters was equal to or less than 0.27 cm for both the ascending aorta and the descending aorta. The intraclass correlation coefficients (ICCs) were greater than 0.80 for the ascending aorta and equal to or greater than 0.70 for the descending aorta, and the ICCs between readers were 0.91 (95% CI: 0.90, 0.92) and 0.82 (95% CI: 0.80, 0.84), respectively. Aneurysm detection accuracy was 88% (95% CI: 86, 90) and 81% (95% CI: 79, 83) compared with reader 1 and 90% (95% CI: 88, 91) and 82% (95% CI: 80, 84) compared with reader 2 for the ascending aorta and descending aorta, respectively.

Conclusion

Thoracic aortic aneurysms were accurately predicted at CT by using deep learning.Keywords: Aorta, Convolutional Neural Network, Machine Learning, CT, Thorax, AneurysmsSupplemental material is available for this article.© RSNA, 2022.

Federated learning for predicting clinical outcomes in patients with COVID-19

Federated learning (FL) is a method used for training artificial intelligence models with data from multiple sources while maintaining data anonymity, thus removing many barriers to data sharing. Here we used data from 20 institutes across the globe to train a FL model, called EXAM (electronic medical record (EMR) chest X-ray AI model), that predicts the future oxygen requirements of symptomatic patients with COVID-19 using inputs of vital signs, laboratory data and chest X-rays. EXAM achieved an average area under the curve (AUC) >0.92 for predicting outcomes at 24 and 72 h from the time of initial presentation to the emergency room, and it provided 16% improvement in average AUC measured across all participating sites and an average increase in generalizability of 38% when compared with models trained at a single site using that site's data. For prediction of mechanical ventilation treatment or death at 24 h at the largest independent test site, EXAM achieved a sensitivity of 0.950 and specificity of 0.882. In this study, FL facilitated rapid data science collaboration without data exchange and generated a model that generalized across heterogeneous, unharmonized datasets for prediction of clinical outcomes in patients with COVID-19, setting the stage for the broader use of FL in healthcare.

A multi-center study of COVID-19 patient prognosis using deep learning-based CT image analysis and electronic health records

PURPOSE

As of August 30th, there were in total 25.1 million confirmed cases and 845 thousand deaths caused by coronavirus disease of 2019 (COVID-19) worldwide. With overwhelming demands on medical resources, patient stratification based on their risks is essential. In this multi-center study, we built prognosis models to predict severity outcomes, combining patients' electronic health records (EHR), which included vital signs and laboratory data, with deep learning- and CT-based severity prediction.

METHOD

We first developed a CT segmentation network using datasets from multiple institutions worldwide. Two biomarkers were extracted from the CT images: total opacity ratio (TOR) and consolidation ratio (CR). After obtaining TOR and CR, further prognosis analysis was conducted on datasets from INSTITUTE-1, INSTITUTE-2 and INSTITUTE-3. For each data cohort, generalized linear model (GLM) was applied for prognosis prediction.

RESULTS

For the deep learning model, the correlation coefficient of the network prediction and manual segmentation was 0.755, 0.919, and 0.824 for the three cohorts, respectively. The AUC (95 % CI) of the final prognosis models was 0.85(0.77,0.92), 0.93(0.87,0.98), and 0.86(0.75,0.94) for INSTITUTE-1, INSTITUTE-2 and INSTITUTE-3 cohorts, respectively. Either TOR or CR exist in all three final prognosis models. Age, white blood cell (WBC), and platelet (PLT) were chosen predictors in two cohorts. Oxygen saturation (SpO2) was a chosen predictor in one cohort.

CONCLUSION

The developed deep learning method can segment lung infection regions. Prognosis results indicated that age, SpO2, CT biomarkers, PLT, and WBC were the most important prognostic predictors of COVID-19 in our prognosis model.

Multicenter Assessment of CT Pneumonia Analysis Prototype for Predicting Disease Severity and Patient Outcome

To perform a multicenter assessment of the CT Pneumonia Analysis prototype for predicting disease severity and patient outcome in COVID-19 pneumonia both without and with integration of clinical information. Our IRB-approved observational study included consecutive 241 adult patients (> 18 years; 105 females; 136 males) with RT-PCR-positive COVID-19 pneumonia who underwent non-contrast chest CT at one of the two tertiary care hospitals (site A: Massachusetts General Hospital, USA; site B: Firoozgar Hospital Iran). We recorded patient age, gender, comorbid conditions, laboratory values, intensive care unit (ICU) admission, mechanical ventilation, and final outcome (recovery or death). Two thoracic radiologists reviewed all chest CTs to record type, extent of pulmonary opacities based on the percentage of lobe involved, and severity of respiratory motion artifacts. Thin-section CT images were processed with the prototype (Siemens Healthineers) to obtain quantitative features including lung volumes, volume and percentage of all-type and high-attenuation opacities (≥ -200 HU), and mean HU and standard deviation of opacities within a given lung region. These values are estimated for the total combined lung volume, and separately for each lung and each lung lobe. Multivariable analyses of variance (MANOVA) and multiple logistic regression were performed for data analyses. About 26% of chest CTs (62/241) had moderate to severe motion artifacts. There were no significant differences in the AUCs of quantitative features for predicting disease severity with and without motion artifacts (AUC 0.94-0.97) as well as for predicting patient outcome (AUC 0.7-0.77) (p > 0.5). Combination of the volume of all-attenuation opacities and the percentage of high-attenuation opacities (AUC 0.76-0.82, 95% confidence interval (CI) 0.73-0.82) had higher AUC for predicting ICU admission than the subjective severity scores (AUC 0.69-0.77, 95% CI 0.69-0.81). Despite a high frequency of motion artifacts, quantitative features of pulmonary opacities from chest CT can help differentiate patients with favorable and adverse outcomes.

Deep metric learning-based image retrieval system for chest radiograph and its clinical applications in COVID-19

In recent years, deep learning-based image analysis methods have been widely applied in computer-aided detection, diagnosis and prognosis, and has shown its value during the public health crisis of the novel coronavirus disease 2019 (COVID-19) pandemic. Chest radiograph (CXR) has been playing a crucial role in COVID-19 patient triaging, diagnosing and monitoring, particularly in the United States. Considering the mixed and unspecific signals in CXR, an image retrieval model of CXR that provides both similar images and associated clinical information can be more clinically meaningful than a direct image diagnostic model. In this work we develop a novel CXR image retrieval model based on deep metric learning. Unlike traditional diagnostic models which aim at learning the direct mapping from images to labels, the proposed model aims at learning the optimized embedding space of images, where images with the same labels and similar contents are pulled together. The proposed model utilizes multi-similarity loss with hard-mining sampling strategy and attention mechanism to learn the optimized embedding space, and provides similar images, the visualizations of disease-related attention maps and useful clinical information to assist clinical decisions. The model is trained and validated on an international multi-site COVID-19 dataset collected from 3 different sources. Experimental results of COVID-19 image retrieval and diagnosis tasks show that the proposed model can serve as a robust solution for CXR analysis and patient management for COVID-19. The model is also tested on its transferability on a different clinical decision support task for COVID-19, where the pre-trained model is applied to extract image features from a new dataset without any further training. The extracted features are then combined with COVID-19 patient's vitals, lab tests and medical histories to predict the possibility of airway intubation in 72 hours, which is strongly associated with patient prognosis, and is crucial for patient care and hospital resource planning. These results demonstrate our deep metric learning based image retrieval model is highly efficient in the CXR retrieval, diagnosis and prognosis, and thus has great clinical value for the treatment and management of COVID-19 patients.

Artificial intelligence matches subjective severity assessment of pneumonia for prediction of patient outcome and need for mechanical ventilation: a cohort study

To compare the performance of artificial intelligence (AI) and Radiographic Assessment of Lung Edema (RALE) scores from frontal chest radiographs (CXRs) for predicting patient outcomes and the need for mechanical ventilation in COVID-19 pneumonia. Our IRB-approved study included 1367 serial CXRs from 405 adult patients (mean age 65 ± 16 years) from two sites in the US (Site A) and South Korea (Site B). We recorded information pertaining to patient demographics (age, gender), smoking history, comorbid conditions (such as cancer, cardiovascular and other diseases), vital signs (temperature, oxygen saturation), and available laboratory data (such as WBC count and CRP). Two thoracic radiologists performed the qualitative assessment of all CXRs based on the RALE score for assessing the severity of lung involvement. All CXRs were processed with a commercial AI algorithm to obtain the percentage of the lung affected with findings related to COVID-19 (AI score). Independent t- and chi-square tests were used in addition to multiple logistic regression with Area Under the Curve (AUC) as output for predicting disease outcome and the need for mechanical ventilation. The RALE and AI scores had a strong positive correlation in CXRs from each site (r2 = 0.79-0.86; p < 0.0001). Patients who died or received mechanical ventilation had significantly higher RALE and AI scores than those with recovery or without the need for mechanical ventilation (p < 0.001). Patients with a more substantial difference in baseline and maximum RALE scores and AI scores had a higher prevalence of death and mechanical ventilation (p < 0.001). The addition of patients' age, gender, WBC count, and peripheral oxygen saturation increased the outcome prediction from 0.87 to 0.94 (95% CI 0.90-0.97) for RALE scores and from 0.82 to 0.91 (95% CI 0.87-0.95) for the AI scores. AI algorithm is as robust a predictor of adverse patient outcome (death or need for mechanical ventilation) as subjective RALE scores in patients with COVID-19 pneumonia.

Federated Learning used for predicting outcomes in SARS-COV-2 patients

'Federated Learning' (FL) is a method to train Artificial Intelligence (AI) models with data from multiple sources while maintaining anonymity of the data thus removing many barriers to data sharing. During the SARS-COV-2 pandemic, 20 institutes collaborated on a healthcare FL study to predict future oxygen requirements of infected patients using inputs of vital signs, laboratory data, and chest x-rays, constituting the "EXAM" (EMR CXR AI Model) model. EXAM achieved an average Area Under the Curve (AUC) of over 0.92, an average improvement of 16%, and a 38% increase in generalisability over local models. The FL paradigm was successfully applied to facilitate a rapid data science collaboration without data exchange, resulting in a model that generalised across heterogeneous, unharmonized datasets. This provided the broader healthcare community with a validated model to respond to COVID-19 challenges, as well as set the stage for broader use of FL in healthcare.

Severity and Consolidation Quantification of COVID-19 From CT Images Using Deep Learning Based on Hybrid Weak Labels

Early and accurate diagnosis of Coronavirus disease (COVID-19) is essential for patient isolation and contact tracing so that the spread of infection can be limited. Computed tomography (CT) can provide important information in COVID-19, especially for patients with moderate to severe disease as well as those with worsening cardiopulmonary status. As an automatic tool, deep learning methods can be utilized to perform semantic segmentation of affected lung regions, which is important to establish disease severity and prognosis prediction. Both the extent and type of pulmonary opacities help assess disease severity. However, manually pixel-level multi-class labelling is time-consuming, subjective, and non-quantitative. In this article, we proposed a hybrid weak label-based deep learning method that utilize both the manually annotated pulmonary opacities from COVID-19 pneumonia and the patient-level disease-type information available from the clinical report. A UNet was firstly trained with semantic labels to segment the total infected region. It was used to initialize another UNet, which was trained to segment the consolidations with patient-level information using the Expectation-Maximization (EM) algorithm. To demonstrate the performance of the proposed method, multi-institutional CT datasets from Iran, Italy, South Korea, and the United States were utilized. Results show that our proposed method can predict the infected regions as well as the consolidation regions with good correlation to human annotation.

The price of a 15-year delay in diagnosis of Sheehan's syndrome

We describe a case of a 48-year-old woman who presented with a 15-year history of recurrent episodes of hypoglycemia and hyponatremia leading to altered behavior and generalized seizures. She underwent full clinical assessment, endocrine tests, and a pituitary magnetic resonance scan that showed pananterior hypopituitarism secondary to postpartum pituitary necrosis (Sheehan's syndrome). She was commenced on appropriate hormone replacement therapy, which led to significant improvement in lethargy, anorexia, muscle weakness, and episodes of hypoglycemia. In addition to the alleviation of her physical symptoms, she experienced a significant improvement in her psychological well-being and reduction in hospital visits. This case illustrates the impact of delay in diagnosis of an easily treatable medical condition and its socioeconomic implications, especially for the population of a developing country like India.

HCl hydrates as model systems for protonated water

Ab initio molecular dynamics simulations are presented of vibrational dynamics and spectra of crystal HCl hydrates. Depending on the composition, the hydrates include distinct protonated water forms, which in their equilibrium structures approximate either the Eigen ion H3O+(H2O)3 (in the hexahydrate) or the Zundel H2O...H+...OH2 ion (in the di- and trihydrate). Thus, the hydrates offer the opportunity to study spectra and dynamics of distinct species of protonated water trapped in a semirigid solvating environment. The experimentally measured spectra are reproduced quite well by BLYP/DZVP-level calculations employing Fourier transform of the system dipole. The large overall width (800-1000 cm-1) of structured proton bands reflects a broad range of solvating environments generated by crystal vibrations. The aqueous HCl solution was also examined in search of an objective criterion for separating the contributions of "Zundel-like" and "Eigen-like" protonated forms. It is suggested that no such criterion exists since distributions of proton-related structural properties appear continuous and unimodal. Dipole derivatives with respect to OH and O...H+ stretches in water and protonated water were also investigated to advance the understanding of the corresponding IR intensities. The effects of H bonding and solvation on the intensities were analyzed with the help of the Wannier centers' representation of electron density.

Exploration of NVE classical trajectories as a tool for molecular crystal structure prediction, with tests on ice polymorphs

Following an initial Communication [Buch et al., J. Chem. Phys. 123, 051108 (2005)], a new molecular-dynamics-based approach is explored to search for candidate crystal structures of molecular solids corresponding to minima of the enthalpy. The approach is based on the observation of phase transitions in an artificial periodic system with a small unit cell and relies on the existence of an optimal energy range for observing freezing to low-lying minima in the course of classical trajectories. Tests are carried out for O structures of nine H2O-ice polymorphs. NVE trajectories for a range of preimposed box shapes display freezing to the different crystal polymorphs whenever the box dimensions approximate roughly the appropriate unit cell; the exception is ice II for which freezing requires unit cell dimensions close to the correct ones. In an alternate version of the algorithm, an initial box shape is picked at random and subsequently readjusted at short trajectory intervals by enthalpy minimization. Tests reveal the existence of ice forms which are "difficult" and "easy" to locate in this way. The former include ice IV, which is also difficult to crystallize experimentally from the liquid, and ice II, which does not interface with the liquid in the phase diagram. On the other hand, the latter crystal search procedure located successfully the remaining seven ice polymorphs, including ice V, which corresponds to the most complicated structure of all ice phases, with a monoclinic cell of 28 molecules.

Elusive structure of HCl monohydrate

The study addresses the structure of crystalline HCl monohydrate which is composed of H3O+ and Cl-. The published x-ray diffraction patterns indicate an element of disorder, the nature of which is debated in the literature and is addressed in the present study. The computational investigations include searches for alternative crystal structures employing an empirical potential, and on-the-fly simulations as implemented in the density functional code QUICKSTEP employing Gaussian basis sets. The experimental work focuses on Fourier-transform infrared (FTIR) spectra of crystal nanoparticles. Simulations of FTIR spectra and of the x-ray diffraction patterns are consistent with crystal monohydrate structure composed of ferroelectric domains, joined by "boundary tissue" of antiferroelectric structure.

A new glance at HCl-monohydrate spectroscopy, using on-the-fly dynamics

On-the-fly dynamics is used to analyze the remarkably anharmonic infrared spectroscopy of crystalline HCl monohydrate, an ionic solid composed of H3O+ and Cl-. The dominant intense infrared feature is shown to originate from specific sections of the hydronium trajectory, in which one of the H-atoms interacts strongly with a neighboring Cl-.

Molecular Structure and OH-Stretch Spectra of Liquid Water Surface

Molecular dynamics simulations are used to investigate typical coordination shells of molecules in the liquid water surface, for two potential energy surfaces. The major undercoordinated species found in the surface include three-coordinated H2O with either a dangling-H or a dangling-O atom and two-coordinated H2O with one hydrogen bond via H, and another via O. Vibrational signatures of the different coordinations are calculated. The 3400 cm(-1) band in the surface sum frequency generation (SFG) spectrum is assigned to four-coordinated molecules within the surface layer. The low-frequency wing of the OH-stretch band, near 3200 cm(-1) in the SFG spectrum, is proposed to be due to collective excitations of a relatively small number of intermolecularly coupled O-H bond vibrations.

A new molecular-dynamics based approach for molecular crystal structure search

A new molecular-dynamics based approach is proposed to search for candidate crystal structures of molecular solids. The procedure is based on the observation of spontaneous transitions between ordered and disordered states in molecular-dynamics simulations of an artificial periodic system with a small unit cell. In such a way only the most stable structures are automatically selected. The method can be applied to the solution of crystal structures from low-quality or very complex diffraction data. Tests are presented for H2O-ice polymorphs.

Comparative FTIR Spectroscopy of HX Adsorbed on Solid Water: Ragout-Jet Water Clusters vs Ice Nanocrystal Arrays

In addition to revealing the stretch-mode bands of the smallest mixed clusters of HCl and HBr (HX) with water, the ragout-jet FTIR spectra of dense mixed water-acid supersonic jets include bands that result from the interaction of HX with larger water clusters. It is argued here that low jet temperatures prevent the water-cluster-bound HX molecules from becoming sufficiently solvated to induce ionic dissociation. The molecular nature of the HX can be deduced directly from the observed influence of changing from HCl to HBr and from replacing H2O with D2O. Furthermore, the band positions of HX are roughly coincidental with bands assigned to molecular HCl and HBr adsorbed on ice nanocrystal surfaces at temperatures below 100 K. It is also interesting that the HX band positions and widths approximate those of HX bound to the surface of amorphous ice films at <60 K. Though computational results suggest the adsorbed HX molecules observed in the jet expansions are weakly distorted by single coordination with surface dangling-oxygen atoms, on-the-fly trajectories indicate that the cluster skeletons undergo large-amplitude low-frequency vibrations. Local HX solvation, the extent of proton sharing, and the HX vibrational spectra undergo serious modulation on a picosecond time scale.

Monte Carlo simulation for the formation of a mixed crystal from two solids in contact

The study focuses on nucleation and growth of a binary mixed crystal phase from two pure crystals in contact. Monte Carlo simulations of this process are conducted, with the dynamics proceeding via activated atom-vacancy exchanges. Intermolecular interactions, ranging up to next-nearest neighbors, are of size typical of hydrogen bonded systems. The process is driven by the formation of strong AB bonds at the expense of weaker AA and BB bonds. In the resulting model, the material is channeled and transported through the mixed phase crust along antiphase boundaries. The flow of molecules through the channels is directed, due to molecular energy lowering via gradual acquisition of an increasing number of nearest neighbors of the second species. On the other hand, defect motion is quasirandom. The model accounts partially for the t(1/alpha) (alpha>3) time dependence observed for conversion of nanoparticles of HBr dihydrate to monohydrate, by exposure to acid adsorbate.

Structure and dynamics of orientational defects in ice I

Orientational defects in hexagonal ice were investigated using molecular dynamics simulations. Energy relaxation during L- and D-defect migration was shown to be associated with improved alignment of water molecules along the local electric fields. Two new forms of defects, an "L+D complex," and a "5+7 defect," were characterized. These forms appear in ice trajectories close to the melting point, and in the course of L- and D-pair recombination process. Defect pair recombination was shown to be a complex process, involving collective H-bond changes in groups of molecules.

Solvation states of HCl in mixed ether:acid crystals: A computational study

Acid solvation states are investigated in the recently discovered mixed ether:acid crystalline solids. The solids are simulated using on-the-fly molecular dynamics as implemented in the density functional code QUICKSTEP employing Gaussian basis sets. The solids are shown to display a remarkably broad range of acid solvation states, depending on the ether:acid ratio, including proton sharing in the 1:1 case, proton transfer to the ether in 1:2, and perturbed molecular acid in 1:6. The observed variation of the infrared spectra with the composition is accounted for qualitatively with the help of the calculations.

Discrete stages in the solvation and ionization of hydrogen chloride adsorbed on ice particles

Ionization and dissociation reactions play a fundamental role in aqueous chemistry. A basic and well-understood example is the reaction between hydrogen chloride (HCl) and water to form chloride ions (Cl(-)) and hydrated protons (H(3)O(+) or H(5)O(2)(+)). This acid ionization process also occurs in small water clusters and on ice surfaces, and recent attention has focused on the mechanism of this reaction in confined-water media and the extent of solvation needed for it to proceed. In fact, the transformation of HCl adsorbed on ice surfaces from a predominantly molecular form to ionic species during heating from 50 to 140 K has been observed. But the molecular details of this process remain poorly understood. Here we report infrared transmission spectroscopic signatures of distinct stages in the solvation and ionization of HCl adsorbed on ice nanoparticles kept at progressively higher temperatures. By using Monte Carlo and ab initio simulations to interpret the spectra, we are able to identify slightly stretched HCl molecules, strongly stretched molecules on the verge of ionization, contact ion pairs comprising H(3)O(+) and Cl(-), and an ionic surface phase rich in Zundel ions, H(5)O(2)(+).