Technegas, A Universal Technique for Lung Imaging in Nuclear Medicine: Technology, Physicochemical Properties, and Clinical Applications.

Technegas was developed in Australia as an imaging radioaerosol in the late 1980s and is now commercialized by Cyclomedica, Pty Ltd. for diagnosing pulmonary embolism (PE). Technegas is produced by heating technetium-99m in a carbon crucible for a few seconds at high temperatures (2750 °C) to generate technetium-carbon nanoparticles with a gas-like behaviour. The submicron particulates formed allow easy diffusion to the lung periphery when inhaled. Technegas has been used for diagnosis in over 4.4 m patients across 60 countries and now offers exciting opportunities in areas outside of PE, including asthma and chronic obstructive pulmonary disease (COPD). The Technegas generation process and the physicochemical attributes of the aerosol have been studied over the past 30 years in parallel with the advancement in different analytical methodologies. Thus, it is now well established that the Technegas aerosol has a radioactivity aerodynamic diameter of <500 nm and is composed of agglomerated nanoparticles. With a plethora of literature studying different aspects of Technegas, this review focuses on a historical evaluation of the different methodologies' findings over the years that provides insight into a scientific consensus of this technology. Also, we briefly discuss recent clinical innovations using Technegas and a brief history of Technegas patents.

Lung Cancer Screening Program via Primary Care Clinics

Lung Cancer Screening (LCS) reduces lung cancer mortality by 20 to 24% however in the US only 5.7% of eligiblepatients participate. Increasing screening of individuals at risk for lung cancer is an unmet need. We started a LCSprogram using primary care physicians (PCP) visits where the intake nurse asked age appropriate patients abouttheir smoking status. If patients met criteria, the physician was alerted to perform shared decision making, offersmoking cessation and order a low dose screening CT scan (LDCT). The results were managed by a physician'sassistant dedicated to the LCS program. This quality improvement study analyzed all patients enrolled from June2019 to July 2021. The LCS program rolled out slowly beginning with 6 PCPs in June to November 2019, 26 PCPsfrom November 2019 to February 2020 and all 56 PCPs from February 2020 to July 2021. COVID-19 stopped LDCTsfrom March 2020 to August 2020. Use of a LCS program run through PCP clinics screened 1,247 (21.3%) eligibleveterans, a 3.7 fold increase over the national average. Of the 2,069 (35.3%) eligible patients initially identified by thecomputer based reminder, 1,824 (88.2%) accepted LCS, 1,383 (66.8%) completed the initial LDCT and 136 (9.8%)were ultimately found to be ineligible after completion of the LDCT. The 136 ineligible patients received 173 LDCTs ofwhich 91% were Lung-RADS 1 or 2 and 0.6% were Lung-RADS 4A. Within the appropriately screened patients, 12(1%) lung cancers and 1 papillary thyroid cancer were found and 26.5% of scans showed evidence of Chronic Obstructive Pulmonary Disease and 11.9% showed coronary artery disease. Use of PCP clinics increased enrollment 3.7 fold over national averages.

Three-dimensional printing of patient-specific computed tomography lung phantoms: a reader study.

In modern clinical decision-support algorithms, heterogeneity in image characteristics due to variations in imaging systems and protocols hinders the development of reproducible quantitative measures including for feature extraction pipelines. With the help of a reader study, we investigate the ability to provide consistent ground-truth targets by using patient-specific 3D-printed lung phantoms. PixelPrint was developed for 3D-printing lifelike computed tomography (CT) lung phantoms by directly translating clinical images into printer instructions that control density on a voxel-by-voxel basis. Data sets of three COVID-19 patients served as input for 3D-printing lung phantoms. Five radiologists rated patient and phantom images for imaging characteristics and diagnostic confidence in a blinded reader study. Effect sizes of evaluating phantom as opposed to patient images were assessed using linear mixed models. Finally, PixelPrint's production reproducibility was evaluated. Images of patients and phantoms had little variation in the estimated mean (0.03-0.29, using a 1-5 scale). When comparing phantom images to patient images, effect size analysis revealed that the difference was within one-third of the inter- and intrareader variabilities. High correspondence between the four phantoms created using the same patient images was demonstrated by PixelPrint's production repeatability tests, with greater similarity scores between high-dose acquisitions of the phantoms than between clinical-dose acquisitions of a single phantom. We demonstrated PixelPrint's ability to produce lifelike CT lung phantoms reliably. These phantoms have the potential to provide ground-truth targets for validating the generalizability of inference-based decision-support algorithms between different health centers and imaging protocols and for optimizing examination protocols with realistic patient-based phantoms. Classification: CT lung phantoms, reader study.

PP01.22 First Lung Cancer Screening Program in Greece - Initial Experience, Preliminary Data and Pitfalls

Background: Poor prognosis of lung cancer is linked to its late diagnosis, typically in the advanced stage 4 in 50-70% of incidental cases. Lung Cancer Screening Programs provide low-dose lung CT screening to current and former smokers who are at high risk for developing this disease. Greece is an EU country, returning strong from a long period of economic recession, ranked 2nd place in overall age-standardized tobacco smoking prevalence in the EU. In December 2020, at the Metropolitan Hospital of Athens, we started the 1st Screening Program in the country. We present our initial results and pitfalls met. Method(s): A weekly outpatient clinic offers consultation to possible candidates. LDCT (<=3.0mGy), Siemens VIA, Artificial Intelligence multi-computer-aided diagnosis (multi-CAD) system and LungRADS (v.1.1) are used for the validation of any abnormal findings with semi-auto measurement of volume and volume doubling time. Patients get connected when necessary with the smoking cessation and Pulmonology clinic. USPSTF guidelines are used, (plus updated version). Abnormal CT findings are discussed by an MDT board with radiologists, pulmonologists/interventional pulmonologists, oncologists and thoracic surgeons. A collaboration with Fairlife Lung Cancer Care the first non-profit organization in Greece is done, in order to offer the program to population with low income too. An advertisement campaign was organized to inform family doctors and the people about screening programs, together with an anti-tobacco campaign. Result(s): 106 people were screened, 74 males & 32 females (mean age 62yo), 27/106 had an abnormal finding (25%). 2 were diagnosed with a resectable lung cancer tumor (primary adenocarcinoma) of early-stage (1.8%). 2 with extended SCLC (lung lesion & mediastinal adenopathy). 1 with multiple nodules (pancreatic cancer not known until then). 3 patients with mediastinal and hilar lymphadenopathy (2 diagnosed with lymphoma, 1 with sarcoidosis). 19 patients were diagnosed with pulmonary nodules (RADS 2-3, 17%) - CT follow up algorithm. Conclusion(s): We are presenting our initial results, from the first lung cancer screening program in Greece. Greece represents a country many smokers, who also started smoking at a young age, with a both public and private health sector, returning from a long period of economic recession. COVID-19 pandemia has cause practical difficulties along the way. LDCT with AI software, with an MDT board and availability of modern diagnostic and therapeutic alternatives should be considered as essential. A collaboration spirit with other hospitals around the country is being built, in order to share current experience and expertise. Copyright © 2022

Performance of spiral UTE-MRI of the lung in post-COVID patients.

Patients recovered from COVID-19 may develop long-COVID symptoms in the lung. For this patient population (post-COVID patients), they may benefit from longitudinal, radiation-free lung MRI exams for monitoring lung lesion development and progression. The purpose of this study was to investigate the performance of a spiral ultrashort echo time MRI sequence (Spiral-VIBE-UTE) in a cohort of post-COVID patients in comparison with CT and to compare image quality obtained using different spiral MRI acquisition protocols. Lung MRI was performed in 36 post-COVID patients with different acquisition protocols, including different spiral sampling reordering schemes (line in partition or partition in line) and different breath-hold positions (inspiration or expiration). Three experienced chest radiologists independently scored all the MR images for different pulmonary structures. Lung MR images from spiral acquisition protocol that received the highest image quality scores were also compared against corresponding CT images in 27 patients for evaluating diagnostic image quality and lesion identification. Spiral-VIBE-UTE MRI acquired with the line in partition reordering scheme in an inspiratory breath-holding position achieved the highest image quality scores (score range = 2.17-3.69) compared to others (score range = 1.7-3.29). Compared to corresponding chest CT images, three readers found that 81.5% (22 out of 27), 81.5% (22 out of 27) and 37% (10 out of 27) of the MR images were useful, respectively. Meanwhile, they all agreed that MRI could identify significant lesions in the lungs. The Spiral-VIBE-UTE sequence allows for fast imaging of the lung in a single breath hold. It could be a valuable tool for lung imaging without radiation and could provide great value for managing different lung diseases including assessment of post-COVID lesions.

Analysis of clinical imaging and prevention and control strategy of COVID-19 pneumonia in different families

Objective To increase the understanding of the clinical and imaging changes of family clustered novel coronavirus pneumonia, and to explore the targeted epidemic prevention and control strategies. Methods The clinical symptoms and imaging examination data of 27 cases in 10 groups of new coronavirus pneumonia families were retrospectively analyzed. Results Among the 27 cases, 12 males and 15 females, aged 6 months old -57 years old, 12 cases were the mild type and 15 cases were the common type. Among all cases, 5 cases were manifested by fever, 20 cases by cough and expectoration, 13 cases by nasal congestion and runny nose, 5 cases by dry throat and sore throat, 5 cases by loss of smell and taste and 2 cases by dizziness and headache. Among the 15 cases of common type, 10 cases involved both lungs;5 cases involved unilateral lung;8 cases involved the lower lobe, and 9 cases involved subpleural;9 cases showed the ground-glass opacity;7 cases showed the high density film;there were 3 cases of pleural thickening;no pleural effusion, mediastinal and axillary lymph node enlargement signs were observed. Conclusion The family clusters of novel coronavirus pneumonia have certain clinical and imaging characteristics. Attaching the importance to sentinel surveillance in fever clinics, actively controlling the source of infection, and adopting the non-drug intervention combined with intensive vaccination are the important strategies to win the battle against the epidemic. (English) [ FROM AUTHOR]

Long-Term Effect of COVID-19 on Lung Imaging and Function, Cardiorespiratory Symptoms, Fatigue, Exercise Capacity, and Functional Capacity in Children and Adolescents: A Systematic Review and Meta-Analysis.

BACKGROUND: The long-term sequela of COVID-19 on young people is still unknown. This systematic review explored the effect of COVID-19 on lung imaging and function, cardiorespiratory symptoms, fatigue, exercise capacity and functional capacity in children and adolescents ≥ 3 months after infection. METHODS: A systemic search was completed in the electronic databases of PubMed, Web of Science and Ovid MEDLINE on 27 May 2022. Data on the proportion of participants who had long-term effects were collected, and one-group meta-analysis were used to estimate the pooled prevalence of the outcomes studied. RESULTS: 17 articles met the inclusion criteria, presented data on 124,568 children and adolescents. The pooled prevalence of abnormalities in lung imaging was 10% (95% CI 1-19, I2 = 73%), abnormal pulmonary function was 24% (95% CI 4-43, I2 = 90%), chest pain/tightness was 6% (95% CI 3-8, I2 = 100%), heart rhythm disturbances/palpitations was 6% (95% CI 4-7, I2 = 98%), dyspnea/breathing problems was 16% (95% CI 14-19, I2 = 99%), and fatigue was 24% (95% CI 20-27, I2 = 100%). Decreased exercise capacity and functional limitations were found in 20% (95% CI 4-37, I2 = 88%) and 48% (95% CI 25-70, I2 = 91%) of the participants studied, respectively. CONCLUSION: Children and adolescents may have persistent abnormalities in lung imaging and function, cardiorespiratory symptoms, fatigue, and decreased functional capacity between 3 to 12 months after infection. More research is needed to understand the long-term effect of COVID-19 on young people, and to clarify its causes and effective management.

Application of Jiawei Maxing Shigan Tang in the treatment of COVID-19: An observational study.

Objective: To explore the clinical efficacy and adverse reactions of Jiawei Maxing Shigan Tang (JMST; a modified decoction of ephedra, apricot kernel, gypsum, and licorice) combined with western medicine in the symptomatic treatment of COVID-19. Methods: In this study, we retrospectively collected the basic data of 48 patients with COVID-19 who were discharged from our hospital between January 20 and February 28, 2020. Besides, the blood routines, biochemical indexes, nucleic acid detection results, clinical symptoms, lung imaging improvements, adverse reactions, and other clinical data of these patients before and after treatment were recorded. Finally, we drew comparisons between the outcomes and adverse reactions of patients in the combined treatment group (therapeutic regimen recommended by authoritative guidelines and supplemented by JMST) and the conventional treatment group (therapeutic regimen recommended by authoritative guidelines). Results: There were no significant differences in age, gender, clinical classification, and underlying medical conditions between the combined treatment group (28 cases) and the conventional treatment group (20 cases). However, the combined treatment group presented superior results to the conventional treatment group in several key areas. For instance, patients produced negative nasal/throat swab-based nucleic acid detection results in a shorter time, clinical symptoms were more effectively alleviated, and the absorption time of lung exudation was shorter (P < 0.05). Furthermore, the combined treatment group had a shorter length of stay (LOS) and faster lymphocyte recovery duration than the conventional treatment group, although the differences were not statistically significant. Moreover, there were no significant differences concerning gastrointestinal reaction, hepatic injury, renal impairment, myocardial injury, and other adverse reactions between the two groups. Conclusion: The results of this study indicate that JMST combined with the recommended therapeutic regimen enhances the recovery of COVID-19 patients without increasing the risk of adverse reactions. Therefore, this therapy promotes positive outcomes for COVID-19 patients.

A Programmatic Approach to Improve Efficiency in Lung Cancer Screening

Introduction: Largely as a result of the COVID pandemic, our lung cancer screening (LCS) program was underperforming entering 2021. The program serves a majority minority, socio-economically disadvantaged community. Loss of personnel and reallocated resources, allied to pandemic focus, led to decreased referrals and excessive time from referral to low dose computed tomography (LDCT) appointments. Here we describe our programmatic approach to improve LCS metrics. Methods: LCS transitioned from a Department of Radiology program into a Cancer Center-administered collaborative effort under surgical oncology and radiology leadership. Outreach efforts were reinitiated. To facilitate referrals from our primary care network, the cancer service line created a practical guide, “6 Steps to Lung Cancer Screening”, directly linked to an e-referral mechanism in our EMR. Monthly review and quality assurance meetings were held with a multidisciplinary team, specifically focused on program volume and on addressing delays to LDCT appointments. An additional Nurse Practitioner was brought in to enhance the existing LCS Nurse Navigator and Cancer Center staff were utilized to contact and schedule patients and to perform data compilation and analysis. Results: In 2020, LCS referrals had decreased 13% from 2019. In Q1/2021, the median monthly number of LCS referrals was 132 which increased steadily by quarter to 218 in Q4/2021 (p=0.16, Figure 1A). In January 2021, the average time from LCS referral to LDCT appointment was 101 days. Despite the increasing number of referrals through 2021, we were able to decrease the time to appointment from a median of 86 days in Q1/2021 to a median of 29 days in Q4/2021 (p=0.02, Figure 1B). By December 2021, the average time from LCS referral to LDCT appointment was just 18 days. Our LCS referral population was predominantly non-white (76%). Among them, 7.4% of patients with LDCT scans were found to have Lung RADS 3 or 4 nodules. All of these patients were referred to a newly created high-risk lung nodule clinic for management and follow up. Conclusions: We employed a multidisciplinary team approach to improve inefficiencies in our LCS program. The resources, support, and leadership of the health care system’s Cancer Center were crucial to this multi-pronged initiative. The decreased time from LCS referral to LDCT facilitates our ability to handle the anticipated growth in referral volume. This has been shown to enhance engagement with LCS and to improved annual screening compliance, translating to earlier detection of lung cancer and to improved patient outcomes. [Formula presented] Keywords: Lung cancer screening, Adherence, Disparity

Current status of High-risk Smokers Participating in Population-based National Lung Cancer Screening Program in Korea

Introduction: Following assessment of the effectiveness and feasibility based on the results from a two-year population-based nationwide prospective multi-center trial, the Korean government implemented a national lung cancer screening program using low-dose computed tomography (LDCT) for high-risk smokers in 2019. Methods: National Health Insurance Corporation selected high risk targets who are current smokers aged 54 to 74 years with 30 packs per year or more smoking history on the basis of national health-screening database. (Figure 1). Those eligible were offered lung cancer screening by invitation letters in every two years. Screening units provide LDCT using radiation less than 3mGy by at least 16-row multi-detector CT scanners. Screening results were reported by Lung Imaging Reporting and Data System (Lung-RADS). The examinee received results by mail or e-mail;after then, counseling on results and mandatory smoking cessation counselling were provided by certified doctors. National Cancer Center monitored participation rates, post-counseling rates and statistics of screening result for quality control. Screening positive rate is defined as proportion of Lung-RADS category 3 and 4 nodules. Results: The participation rate gradually increased from 24.8% among 332,244 eligible targets in 2019, 25.9% in 2020, to 38.7% among 310,260 targets in 2021, however, the proportion of examinees who participated in post-counseling decreased from 46.3% in 2019 to 32.7% in 2021 due to the COVID-19 pandemic (Figure 2). The positive rates slightly decreased from 9.2% in 2019 to 8.7% in 2021. The variation in positive rates of screening units showed a tendency to decrease (in 2019, the 1st quartile was 4.3%, and the 3rd quartile was 12.9%;and in 2021, 5.2% and 12.5% respectively). Conclusions: National lung cancer screening program has been implemented successfully in Korea with controlling screening positive rates not so high. Controlling false negatives and strengthening post-screening management including smoking cessation counselling needs to improve. [Formula presented] [Formula presented] Keywords: National Lung Cancer Screening, Quality control

A Simplified Convolutional Neural Network Design for COVID-19 Classification on Chest X-ray Images

COVID-19 is a respiratory virus that causes the spread of infection and has affected human around the world. The infection frequently results in pneumonia in human which can be detected using lung imaging, chest X-ray images. Deep learning models have been demonstrated to an effective COVID-19 interpretation on chest radiography. In this paper, we have proposed a simplified convolutional neural network model for COVID-19 screening that can classify the appearance of COVID-19 lesion into two classes. The proposed model;despite using fewer layers and the utilization of data augmentation approach in training process, can achieve the greater outcome. To evaluate the proposed model, we have used a partial of the public dataset, COVID-19 Radiography Database which is a collection of 13,808 chest X-ray images. At the final stage, the Grad-CAM visualization method has been used to enhance the important region of chest X-ray images in order to provide the explanations of COVID-19 predictions. © 2022 IEEE.

The short-term impact of COVID-19 on lung cancer screening participation and adherence

Objective: Screening with low-dose CT (LDCT) effectively reduces mortality from lung cancer. Elective imaging procedures, including lung cancer screening (LCS) LDCT exams, were paused during the height of the COVID-19 pandemic at our institution to conserve healthcare resources and minimize risk as we learned how to mitigate the spread of COVID-19. We aimed to investigate the short-term impact of this COVID-related screening pause on patient participation and adherence to LCS. Methods: We analyzed data of 5133 LDCT screening exams performed at our institution from 2961 patients who were aged 50-80 at each screen between July 31, 2013 and Dec 30, 2020. Independent t-test, Pearson's chi-square and Fisher's exact tests were used to compare monthly average number of LDCTs, on-time adherence rates (i.e., completion of recommended or more invasive follow-up within 15, 9, 5, and 3 months for Lung-RADS 1/2, 3, 4A, and 4B/4X, respectively), percentages of positive screens (Lung-RADS 3 and 4), and lung cancer diagnoses across pre- (July 31, 2013 ∼ Mar 18, 2020), during (Mar 19, 2020 ∼ May 19, 2020), and post-COVID screening pause (May 20, 2020 and after) periods. Results: As expected, compared with the pre-COVID screening pause, there was a significant decrease in monthly average number of LDCTs during the COVID screening pause period (total monthly mean ± sd: pre 55±28 vs during 17±1, p<0.05;new patient monthly mean ± sd: pre 34±16 vs during 6±2, p<0.05). However, a surge in LCS activities was observed after the COVID screening pause period (total: during 17±1 vs post 89±10, p<0.05;new: during 6±2 vs post 42±8, p<0.05), surpassing monthly means in the pre-COVID period (total: pre 55±28 vs post 89±10, p<0.05;new: pre 34±16 vs post 42±8, p<0.05). Overall on-time adherence decreased in the post-COVID period as opposed to the pre-COVID period (p<0.05). There were no significant changes in the percent of positive screens across the three periods (p>0.05). Among the 88 patients diagnosed with lung cancers, 76 diagnoses were made before COVID, 12 diagnoses were made after the COVID pause, and no lung cancer diagnoses were made during the COVID screening pause period. There were no significant differences in terms of the rate of lung cancer (pre 2.9% vs post 1.9%, p>0.05) and the percent of advanced lung cancers (pre 20% vs post 0%, p>0.05) during the two periods. Conclusion: The rate of LCS exams performed at our institution declined during the early days of the COVID-19 pandemic, as elective exams were paused. Once screening resumed, we experienced a surge in the rate of LCS that surpassed pre-COVID rates. Although there were no significant changes in the percentages of positive screens and lung cancer diagnoses shortly after the COVID screening pause period, long-term follow-up is needed to monitor these trends. Additionally, interventions may be needed to improve rates of patients' timely adherence to LCS follow-up recommendations, which decreased in the post-COVID period.

PixelPrint: Three-dimensional printing of realistic patient-specific lung phantoms for CT imaging.

Phantoms are essential tools for assessing and verifying performance in computed tomography (CT). Realistic patient-based lung phantoms that accurately represent textures and densities are essential in developing and evaluating novel CT hardware and software. This study introduces PixelPrint, a 3D-printing solution to create patient-specific lung phantoms with accurate contrast and textures. PixelPrint converts patient images directly into printer instructions, where density is modeled as the ratio of filament to voxel volume to emulate local attenuation values. For evaluation of PixelPrint, phantoms based on four COVID-19 pneumonia patients were manufactured and scanned with the original (clinical) CT scanners and protocols. Density and geometrical accuracies between phantom and patient images were evaluated for various anatomical features in the lung, and a radiomic feature comparison was performed for mild, moderate, and severe COVID-19 pneumonia patient-based phantoms. Qualitatively, CT images of the patient-based phantoms closely resemble the original CT images, both in texture and contrast levels, with clearly visible vascular and parenchymal structures. Regions-of-interest (ROIs) comparing attenuation demonstrated differences below 15 HU. Manual size measurements performed by an experienced thoracic radiologist revealed a high degree of geometrical correlation between identical patient and phantom features, with differences smaller than the intrinsic spatial resolution of the images. Radiomic feature analysis revealed high correspondence, with correlations of 0.95-0.99 between patient and phantom images. Our study demonstrates the feasibility of 3D-printed patient-based lung phantoms with accurate geometry, texture, and contrast that will enable protocol optimization, CT research and development advancements, and generation of ground-truth datasets for radiomic evaluations.

A Microwave Imaging Procedure for Lung Lesion Detection: Preliminary Results on Multilayer Phantoms

In this work, a feasibility study for lung lesion detection through microwave imaging based on Huygens’ principle (HP) has been performed using multilayer oval shaped phantoms mimicking human torso having a cylindrically shaped inclusion simulating lung lesion. First, validation of the proposed imaging method has been performed through phantom experiments using a dedicated realistic human torso model inside an anechoic chamber, employing a frequency range of 1–5 GHz. Subsequently, the miniaturized torso phantom validation (using both single and double inclusion scenarios) has been accomplished using a microwave imaging (MWI) device, which operates in free space using two antennas in multi-bistatic configuration. The identification of the target’s presence in the lung layer has been achieved on the obtained images after applying both of the following artifact removal procedures: (i) the “rotation subtraction” method using two adjacent transmitting antenna positions, and (ii) the “ideal” artifact removal procedure utilizing the difference between received signals from unhealthy and healthy scenarios. In addition, a quantitative analysis of the obtained images was executed based on the definition of signal to clutter ratio (SCR). The obtained results verify that HP can be utilized successfully to discover the presence and location of the inclusion in the lung-mimicking phantom, achieving an SCR of 9.88 dB.

COVID-19 detection from lung ultrasound images

Early-stage detection of Coronavirus Disease 2019 (COVID-19) is crucial for patient medical attention. Since lungs are the most affected organs, monitoring them constantly is an effective way to observe sickness evolution. The most common technique for lung-imaging and evaluation is Computed Tomography (CT). However, its costs and effects over human health has made Lung Ultrasound (LUS) a good alternative. LUS does not expose the patient to radiation and minimizes the risk of contamination. Also, there is evidence of a relation between different artifacts on LUS and lung’s diseases coming from the pleura, whose abnormalities are related with most acute respiratory disorders. However, LUS often requires an expert clinical interpretation that may increase diagnosis time or decrease diagnosis performance. This paper describes and compares machine learning classification methods namely Naive Bayes (NB) Support Vector Machine (SVM), K-Nearest Neighbor (K-NN) and Random Forest (RF) over several LUS images. They obtain a classification between lung images with COVID-19, pneumonia, and healthy patients, using image’s features previously extracted from Gray Level Co-Occurrence Matrix (GLCM) and histogram’s statistics. Furthermore, this paper compares the above classic methods with different Convolutional Neural Networks (CNN) that classifies the images in order to identify these lung’s diseases. © 2022 SPIE.

What is new in respiratory monitoring?

This paper provides a review of a selection of papers published in the Journal of Clinical Monitoring and Computing in 2020 and 2021 highlighting what is new within the field of respiratory monitoring. Selected papers cover work in pulse oximetry monitoring, acoustic monitoring, respiratory system mechanics, monitoring during surgery, electrical impedance tomography, respiratory rate monitoring, lung ultrasound and detection of patient-ventilator asynchrony.

ACCELERATING COVID-19 DIFFERENTIAL DIAGNOSISWITH EXPLAINABLE ULTRASOUND IMAGE ANALYSIS: AN AI TOOL

Lung ultrasound with an artificial intelligence (AI) application provides a low-cost, non-invasive diagnostic that can play a supporting role in diagnosing COVID-19, especially in areas without PCR/CT access. [1][2] Especially throughout the COVID-19 pandemic fast, safe and highly sensitive diagnostic tools are crucial. [3] The goal of this work was twofold: 1. create a publicly available dataset of lung ultrasound images/videos and 2. train an AI algorithm to detect and classify COVID-19 on lung ultrasound images and videos. The largest publicly available COVID-19 lung ultrasound dataset was created from a variety of sources, with > 200 videos and > 50 images. The dataset is heterogeneous, mostly acquired with a convex transducer and according to BLUE protocol. Using available additional patient information, lung ultrasound images in the dataset were categorized as COVID-19, bacterial pneumonia, other viral pneumonia, and healthy. In addition, two independent reviewers evaluated the visible pathologies in the lung ultrasound images. On the dataset, an in-depth study of deep learning methods for differential diagnosis of lung pathologies was performed. In the COVID-19 ultrasound images and videos lung ultrasound signs of a nonspecific pneuomia (fragmented pleural lines, B-lines, (subpleural) consolidations, aero bronchograms and pleural effusions) were visible.The frame-based model correctly distinguished COVID-19 lung ultrasound images from healthy and bacterial pneumonia with a sensitivity of 0.90 ± 0.08 and a specificity of 0.96 ± 0.04. Our work shows promising results of AI application in the field of lung sonography using COVID-19 as an example. Currently, the AI model is in the clinical trial phase. The data set as well as the code for the CNN are publicly available: https://github.com/BorgwardtLab/covid19%5fultrasound. The provided dataset facilitates the validation of lung ultrasound based neural networks to develop fast, accessible screening methods for pulmonary diseases. [ FROM AUTHOR] Copyright of Ultrasound in Medicine & Biology is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)

Prognostic value of computed tomographic findings in acute respiratory distress syndrome and the response to prone positioning.

BACKGROUND: Prone positioning enables the redistribution of lung weight, leading to the improvement of gas exchange and respiratory mechanics. We aimed to evaluate whether the initial findings of acute respiratory distress syndrome (ARDS) on computed tomography (CT) are associated with the subsequent response to prone positioning in terms of oxygenation and 60-day mortality. METHODS: We retrospectively included patients who underwent prone positioning for moderate to severe ARDS from October 2014 to November 2020 at a medical center in Taiwan. A semiquantitative CT rating scale was used to quantify the extent of consolidation and ground-glass opacification (GGO) in the sternal, central and vertebral regions at three levels (apex, hilum and base) of the lungs. A prone responder was identified by a 20% increase in the ratio of arterial oxygen pressure (PaO2) to the fraction of oxygen (FiO2) or a 20 mmHg increase in PaO2. RESULTS: Ninety-six patients were included, of whom 68 (70.8%) were responders. Compared with nonresponders, responders had a significantly greater median dorsal-ventral difference in CT-consolidation scores (10 vs. 7, p = 0.046) but not in CT-GGO scores (- 1 vs. - 1, p = 0.974). Although dorsal-ventral differences in neither CT-consolidation scores nor CT-GGO scores were associated with 60-day mortality, high total CT-GGO scores (≥ 15) were an independent factor associated with 60-day mortality (odds ratio = 4.07, 95% confidence interval, 1.39-11.89, p = 0.010). CONCLUSIONS: In patients with moderate to severe ARDS, a greater difference in the extent of consolidation along the dependent-independent axis on CT scan is associated with subsequent prone positioning oxygenation response, but not clinical outcome regarding survival. High total CT-GGO scores were independently associated with 60-day mortality.

Enhancement of Covid-19 Segmentation Using Machine Learning Analyses of Lung Imaging

The Covid-19 pandemic has caused more then 193 million cases and 4.1 million deaths worldwide as of July 2021. The Fleischner Society reported that Computerized Tomography (CT) is a useful tool for the early identification of Covid-19. Covid-19 disease induces lung changes which can be observed in lung CT predominantly as ground-glass opacification (GGO) and occasional consolidation in the peripheries. Moreover, it was reported that the percentage of lung showing disease correlates with the severity of the disease. Therefore, segmentation of the disease areas in CT images is a logical first step to quantify disease severity. In this paper, we propose g CoviSegNet Enhanced' based on a U-Net with an 813-layer EfficientNetB7 encoder having an attention mechanism to segment the Covid-19 disease area observed in CT images of Covid-19 patients. CoviSegNet Enhanced is an improvement of our previous work g CoviSegNet'. The experiments performed on three public CT datasets and a detailed comparison with recently published work confirms that the proposed CoviNet Enhanced using deep learning approaches is highly effective for Covid-19 segmentation. © 2021 ACM.