Semi-supervised COVID-19 volumetric pulmonary lesion estimation on CT images using probabilistic active contour and CNN segmentation.

Purpose: A semi-supervised two-step methodology is proposed to obtain a volumetric estimation of COVID-19-related lesions on Computed Tomography (CT) images. Methods: First, damaged tissue was segmented from CT images using a probabilistic active contours approach. Second, lung parenchyma was extracted using a previously trained U-Net. Finally, volumetric estimation of COVID-19 lesions was calculated considering the lung parenchyma masks.Our approach was validated using a publicly available dataset containing 20 CT COVID-19 images previously labeled and manually segmented. Then, it was applied to 295 COVID-19 patients CT scans admitted to an intensive care unit. We compared the lesion estimation between deceased and survived patients for high and low-resolution images. Results: A comparable median Dice similarity coefficient of 0.66 for the 20 validation images was achieved. For the 295 images dataset, results show a significant difference in lesion percentages between deceased and survived patients, with a p-value of 9.1 × 10-4 in low-resolution and 5.1 × 10-5 in high-resolution images. Furthermore, the difference in lesion percentages between high and low-resolution images was 10 % on average. Conclusion: The proposed approach could help estimate the lesion size caused by COVID-19 in CT images and may be considered an alternative to getting a volumetric segmentation for this novel disease without the requirement of large amounts of COVID-19 labeled data to train an artificial intelligence algorithm. The low variation between the estimated percentage of lesions in high and low-resolution CT images suggests that the proposed approach is robust, and it may provide valuable information to differentiate between survived and deceased patients.

Effects of Supplemental Oxygen on Cardiovascular and Respiratory Interactions by Extended Partial Directed Coherence in Idiopathic Pulmonary Fibrosis.

Idiopathic pulmonary fibrosis (IPF) is a chronic and restrictive disease characterized by fibrosis and inflammatory changes in lung tissue producing a reduction in diffusion capacity and leading to exertional chronic arterial hypoxemia and dyspnea. Furthermore, clinically, supplemental oxygen (SupplO2) has been prescribed to IPF patients to improve symptoms. However, the evidence about the benefits or disadvantages of oxygen supplementation is not conclusive. In addition, the impact of SupplO2 on the autonomic nervous system (ANS) regulation in respiratory diseases needs to be evaluated. In this study the interactions between cardiovascular and respiratory systems in IPF patients, during ambient air (AA) and SupplO2 breathing, are compared to those from a matched healthy group. Interactions were estimated by time series of successive beat-to-beat intervals (BBI), respiratory amplitude (RESP) at BBI onset, arterial systolic (SYS) and diastolic (DIA) blood pressures. The paper explores the Granger causality (GC) between systems in the frequency domain by the extended partial directed coherence (ePDC), considering instantaneous effects. Also, traditional linear and nonlinear markers as power in low (LF) and high frequency (HF) bands, symbolic dynamic indices as well as arterial baroreflex, were calculated. The results showed that for IPF during AA phase: 1) mean BBI and power of BBI-HF band, as well as mean respiratory frequency were significantly lower (p < 0.05) and higher (p < 0.001), respectively, indicating a strong sympathetic influence, and 2) the RESP → SYS interaction was characterized by Mayer waves and diminished RESP → BBI, i.e., decreased respiratory sinus arrhythmia. In contrast, during short-term SupplO2 phase: 1) oxygen might produce a negative influence on the systolic blood pressure variability, 2) the arterial baroreflex reduced significantly (p < 0.01) and 3) reduction of RSA reflected by RESP → BBI with simultaneous increase of Traube-Hering waves in RESP → SYS (p < 0.001), reflected increased sympathetic modulation to the vessels. The results gathered in this study may be helpful in the management of the administration of SupplO2.

Simultaneous Estimation of Instantaneous Heart and Respiratory Rates using Image Photoplethysmography on a Single Smartphone.

Heart rate (HR) and respiratory rate (RR) are very important physiological variables useful to evaluate the cardiorespiratory system. At present, there is a great interest by the general population in knowing their health status, quickly and easily. Accordingly, several approaches have been proposed to achieve that goal. In this study, the simultaneous estimation of the instantaneous HR and RR values was achieved by the image photoplethysmography (iPPG) technique, in the contact mode directly implemented in a smartphone. iPPG results were compared with those obtained using specialized biomedical sensors such as the electrocardiogram and the respiratory effort band. Performance evaluation included three different respiratory maneuvers in five healthy volunteers. The absolute mean error for instantaneous HR and RR estimations reached 0.94 ± 0.28 beats per minute and 0.40 ± 0.11 breaths per minute, respectively. The mean correlation index was 0.69 ± 0.14 between the iPPG-derived respiratory signal and the respiratory effort reference signal.Clinical Relevance- These results appear to indicate that the contact iPPG method implemented directly on the smartphone is a good option, accessible to the common population to estimate the instantaneous HR and RR values outside specialized clinical environments, e.g., in the point-of-contact office.

Hemodynamic response to low-flow acute supplemental oxygen in idiopathic pulmonary fibrosis and elderly healthy subjects.

BACKGROUND: Hemodynamic response to supplemental oxygen in idiopathic pulmonary fibrosis (IPF) is still not well known. OBJECTIVE: To determine and compare the effect of low-flow acute supplemental oxygen on the hemodynamics of IPF patients and matched healthy subjects. METHODS: Descriptive and comparative study in 20 IPF-patients and 19 Control-subjects, (60-80 years old) breathing ambient air followed by acute nasal low-flow (3 L/min) supplemental oxygen. Non-invasive methods were used during the supine position to evaluate oxygen saturation, heart rate, stroke volume index, cardiac output index, total peripheral resistance and arterial blood pressure. RESULTS: Breathing ambient air, IPF (vs. Control) presented lower values in stroke volume index (38.7 [29.4-43.2] vs. 45.4 [38.4-50.9] mL•kg-1•m2; p=0.009) and cardiac output index (2.484 [2.268 - 2.946] vs. 2.857 [2.628 - 3.054] L•min-1•m-2; p=0.028), with higher total peripheral resistance (1644 [1559-2076] vs. 1505 [1366-1784] dyne•s•cm-5; p=0.017). During supplemental oxygen (vs. ambient air), both groups increased oxygen saturation above 94% (p<0.001) while heart rate decreased about 6 to 8% (p<0.001); stroke volume index increased around 7% in the Control-group (p=0.004) but only 1% in the IPF-group (p=0.017). In addition, IPF showed increments in total peripheral resistance (1644 [1559-2076] vs. 1706 [1554-2278] dyne•s•cm-5; p=0.017) with subsequent decrements in cardiac output index (2.484 [2.268 - 2.946] vs. 2.362 [2.139 - 2.664] L•min-1•m-2; p<0.001). CONCLUSION: Low-flow acute supplemental oxygen in IPF causes a meaningful decrement in cardiac output due to greater reduction in heart rate and increment in total peripheral resistance than matched healthy subjects. Knowing the hemodynamic profile of IPF patients may be helpful in determining their management with supplemental oxygen.

Time-Frequency Analysis of Cardiovascular and Cardiorespiratory Interactions During Orthostatic Stress by Extended Partial Directed Coherence.

In this study, the linear method of extended partial directed coherence (ePDC) was applied to establish the temporal dynamic behavior of cardiovascular and cardiorespiratory interactions during orthostatic stress at a 70° head-up tilt (HUT) test on young age-matched healthy subjects and patients with orthostatic intolerance (OI), both male and female. Twenty 5-min windows were used to analyze the minute-wise progression of interactions from 5 min in a supine position (baseline, BL) until 18 min of the orthostatic phase (OP) without including pre-syncopal phases. Gender differences in controls were present in cardiorespiratory interactions during OP without compromised autonomic regulation. However in patients, analysis by ePDC revealed considerable dynamic alterations within cardiovascular and cardiorespiratory interactions over the temporal course during the HUT test. Considering the young female patients with OI, the information flow from heart rate to systolic blood pressure (mechanical modulation) was already increased before the tilt-up, the information flow from systolic blood pressure to heart rate (neural baroreflex) increased during OP, while the information flow from respiration to heart rate (respiratory sinus arrhythmia) decreased during the complete HUT test. Findings revealed impaired cardiovascular interactions in patients with orthostatic intolerance and confirmed the usefulness of ePDC for causality analysis.

A Smartphone-Based System for Automated Bedside Detection of Crackle Sounds in Diffuse Interstitial Pneumonia Patients.

In this work, we present a mobile health system for the automated detection of crackle sounds comprised by an acoustical sensor, a smartphone device, and a mobile application (app) implemented in Android. Although pulmonary auscultation with traditional stethoscopes had been used for decades, it has limitations for detecting discontinuous adventitious respiratory sounds (crackles) that commonly occur in respiratory diseases. The proposed app allows the physician to record, store, reproduce, and analyze respiratory sounds directly on the smartphone. Furthermore, the algorithm for crackle detection was based on a time-varying autoregressive modeling. The performance of the automated detector was analyzed using: (1) synthetic fine and coarse crackle sounds randomly inserted to the basal respiratory sounds acquired from healthy subjects with different signal to noise ratios, and (2) real bedside acquired respiratory sounds from patients with interstitial diffuse pneumonia. In simulated scenarios, for fine crackles, an accuracy ranging from 84.86% to 89.16%, a sensitivity ranging from 93.45% to 97.65%, and a specificity ranging from 99.82% to 99.84% were found. The detection of coarse crackles was found to be a more challenging task in the simulated scenarios. In the case of real data, the results show the feasibility of using the developed mobile health system in clinical no controlled environment to help the expert in evaluating the pulmonary state of a subject.

Detection of Respiratory Crackle Sounds via an Android Smartphone-based System.

Pulmonary auscultation with traditional stethoscope, although useful, has limitations for detecting discontinuous adventitious respiratory sounds (crackles) that commonly occur in respiratory diseases. In this work, we present the development of a mobile health system for the automated detection of crackle sounds, comprised by an acoustical sensor, a smart phone device, and a mobile application (app) implemented in Android. The app allows the physician to record, store, reproduce, and analyze respiratory sounds directly on the smart phone. The algorithm for crackle detection was based on a time-varying autoregressive modeling. Performance of the automated detector was analyzed using synthetic fine and coarse crackle sounds randomly added to the basal respiratory sounds acquired from healthy subjects with different signal to noise ratios. Accuracy and sensitivity were found to range from 90.7% to 94.0% and from 91.2% to 94.2%, respectively. Application of the proposed mobile system to real acquired data from a patient with pulmonary fibrosis is also exemplified.

Dynamics of the cardiovascular autonomic regulation during orthostatic challenge is more relaxed in women.

Linear dynamic analysis of cardiovascular and respiratory time series was performed in healthy subjects with respect to gender by shifted short-term segments throughout a head-up tilt (HUT) test. Beat-to-beat intervals (BBI), systolic (SYS) and diastolic (DIA) blood pressure and respiratory interval (RESP) time series were acquired in 14 men and 15 women. In time domain (TD), the descending slope of the auto-correlation function (ACF) (BBI_a31cor) was more pronounced in women than in men (p<0.05) during the HUT test and considerably steeper (p<0.01) at the end of orthostatic phase (OP). The index SYS_meanNN was slightly but significantly lower (p<0.05) in women during the complete test, while higher respiratory frequency and variability (RESP_sdNN) were found in women (p<0.05), during 10-20 min after tilt-up. In frequency domain (FD), during baseline (BL), BBI-normalized low frequency (BBI_LFN) and BBI_LF/HF were slightly but significantly lower (p<0.05), while normalized high frequency (BBI_HFN) was significantly higher in women. These differences were highly significant from the first 5 min after tilt-up (p<0.01) and highly significant (p<0.001) during 10-14 min of OP. Findings revealed that men showed instantaneously a pronounced and sustained increase in sympathetic activity to compensate orthostatism. In women, sympathetic activity was just increased slightly with delayed onset without considerably affecting sympatho-vagal balance.

Temporal Analysis of Cardiovascular and Respiratory Complexity by Multiscale Entropy Based on Symbolic Dynamics.

The effect of an orthostatic stress on cardiovascular and respiratory complexity was investigated to detect impaired autonomic regulation in patients with vasovagal syncope (VVS). A total of 16 female patients and 12 age-matched healthy female subjects were enrolled in a passive 70° head-up tilt test. Also, 12 age-matched healthy male subjects were enrolled to study gender differences. Analysis was performed dynamically using various short-term (5 min) windows shifted by 1 min as well as by 20 min of orthostatic phase (OP) to evaluate local and global complexity. Complexity was determined over multiple time scales by the established method of refined composite multiscale entropy (RCMSE) and by a new proposed method of multiscale entropy based on symbolic dynamics (MSE-SD). Concerning heart rate variability (HRV) during OP, both methods revealed the highest complexity for female controls followed by lower complexity in male controls (p < 0.01) and by the lowest complexity in female patients (p < 0.01). For blood pressure variability (BPV), no gender differences in controls were shown by any method. However, MSE-SD demonstrated highly significantly increased BPV complexity in patients during OP (p < 0.01 on 4 time-scales after 7 min, p < 0.001 on 5 time-scales after 11 min) while RCMSE did not reveal considerable differences (p < 0.05 on 2 time scales after 7 min). Respiratory complexity was further increased in patients primary shown by MSE-SD. Findings indicated impaired autonomic regulation in VVS patients characterized by predominantly increased BPV complexity accompanied with decreased HRV complexity. In addition, results suggested extending the concept of complexity loss with disease.

A multichannel acoustic approach to define a pulmonary pathology as combined pulmonary fibrosis and emphysema syndrome.

Interstitial lung diseases (ILDs) have been increasing their relevance in loss of lives according to a recent world wide medical information. Idiopathic pulmonary fibrosis (IPF) and combined pulmonary fibrosis and emphysema syndrome (CPFES) belong to ILD class with the latter having a limited survival prognosis. In clinical environment high resolution computed tomography (HRCT) is used to detect CPFE; however, there is still controversy about the amount of emphysema observed in HRCT to declare CPFES. Consequently, to help in the diagnosis of CPFES to develop an alternative technique seems to be attractive. In this study, we propose a multichannel acoustic approach to discriminate between IPF and CPFES parameterizing the multichannel lung sounds information linearly and classifying it by neural networks (NN). The NN performance using different features provided values above 90% in the validation phase. Furthermore, to test the trained NN, the proposed approach was applied on new data from five patients 3 diagnosed by experts as CPFES and 2 with IPF. The univariate autoregressive model obtained the best classification followed by the feature vector formed by the percentile frequencies augmented by the total power of the acoustic information. Results indicate that multichannel acoustic analysis is promising to discern between these two ILDs.

Power Spectral Density Analysis of Electrodermal Activity for Sympathetic Function Assessment.

Time-domain features of electrodermal activity (EDA), the measurable changes in conductance at the skin surface, are typically used to assess overall activation of the sympathetic system. These time domain features, the skin conductance level (SCL) and the nonspecific skin conductance responses (NS.SCRs), are consistently elevated with sympathetic nervous arousal, but highly variable between subjects. A novel frequency-domain approach to quantify sympathetic function using the power spectral density (PSD) of EDA is proposed. This analysis was used to examine if some of the induced stimuli invoke the sympathetic nervous system's dynamics which can be discernible as a large spectral peak, conjectured to be present in the low frequency band. The resulting indices were compared to the power of low-frequency components of heart rate variability (HRVLF) time series, as well as to time-domain features of EDA. Twelve healthy subjects were subjected to orthostatic, physical and cognitive stress, to test these techniques. We found that the increase in the spectral powers of the EDA was largely confined to 0.045-0.15 Hz, which is in the prescribed band for HRVLF. These low frequency components are known to be, in part, influenced by the sympathetic nervous dynamics. However, we found an additional 5-10% of the spectral power in the frequency range of 0.15-0.25 Hz with all three stimuli. Thus, dynamics of the normalized sympathetic component of the EDA, termed EDASympn, are represented in the frequency band 0.045-0.25 Hz; only a small amount of spectral power is present in frequencies higher than 0.25 Hz. Our results showed that the time-domain indices (the SCL and NS.SCRs), and EDASympn, exhibited significant increases under orthostatic, physical, and cognitive stress. However, EDASympn was more responsive than the SCL and NS.SCRs to the cold pressor stimulus, while the latter two were more sensitive to the postural and Stroop tests. Additionally, EDASympn exhibited an acceptable degree of consistency and a lower coefficient of variation compared to the time-domain features. Therefore, PSD analysis of EDA is a promising technique for sympathetic function assessment.

Acoustic evaluation of pirfenidone on patients with combined pulmonary fibrosis emphysema syndrome.

The combined pulmonary fibrosis emphysema syndrome (CPFES) overall has a poor prognosis with a 5-year survival of 35-80%. Consequently, to evaluate possible positive effects on patients of novel agents as pirfenidone is relevant. However, the efficacy of pirfenidone in CPFES patients is still not well-known. In this study we propose an alternative to evaluate the effects of pirfenidone treatment on CPFES patients via acoustic information. Quantitative analysis of discontinuous adventitious lung sounds (DLS), known as crackles, has been promising to detect and characterize diverse pulmonary pathologies. The present study combines independent components (ICs) analysis of LS and the automated selection of ICs associated with DLS. ICs's features as fractal dimension, entropy and sparsity produce several clusters by kmeans. Those clusters containing ICs of DLS are exclusively considered to finally estimate the number of DLS per ICs by a time-variant AR modeling. For the evaluation of the effects of pirfenidone, the 2D DLS-ICs spatial distribution in conjunction with the estimated number of DLS events are shown. The methodology is applied to two real cases of CPFES with 6 and 12 months of treatment. The acoustical evaluation indicates that pirfenidone treatment may not be satisfactory for CPFES patients but further evaluation has to be performed.

Automated clustering of independent components for discontinuous sounds thoracic imaging.

Discontinuous lung sounds (DLS), also known as crackles, are abnormal sounds produced by different pulmonary pathologies (PP) whose thoracic spatial distribution and prevalence are relevant for diagnosis purpose. Recently, DLS imaging has been proposed to help diagnose and follow-up PP where automated recognition of DLS is meaningful. The present study focuses on the automated selection of independent components (ICs) associated with DLS. Extraction of ICs information for clustering by k-means is achieved in two ways: (1) forming features vectors (FVs) containing the kurtosis, entropy and sparsity of each IC or (2) by applying mutual information (MI) or Euclidean distance (ED) to all ICs. Next, silhouette index is computed to estimate the number of necessary clusters (C). Afterward, to detect just the clusters containing ICs of DLS a selection index is proposed. Finally, to estimate the number of DLS per ICs in each selected cluster a time-variant AR modeling is applied; the estimated number is shown in conjunction with the 2D-ICs spatial distribution. The methodology is applied to simulated and real cases; DLS imaging results are also compared against clinical auscultation. The results showed that the automated selection via FVs is promising to imaging DLS.

Acoustic thoracic image of crackle sounds using linear and nonlinear processing techniques.

In this study, a novel approach is proposed, the imaging of crackle sounds distribution on the thorax based on processing techniques that could contend with the detection and count of crackles; hence, the normalized fractal dimension (NFD), the univariate AR modeling combined with a supervised neural network (UAR-SNN), and the time-variant autoregressive (TVAR) model were assessed. The proposed processing schemes were tested inserting simulated crackles in normal lung sounds acquired by a multichannel system on the posterior thoracic surface. In order to evaluate the robustness of the processing schemes, different scenarios were created by manipulating the number of crackles, the type of crackles, the spatial distribution, and the signal to noise ratio (SNR) at different pulmonary regions. The results indicate that TVAR scheme showed the best performance, compared with NFD and UAR-SNN schemes, for detecting and counting simulated crackles with an average specificity very close to 100%, and average sensitivity of 98 ± 7.5% even with overlapped crackles and with SNR corresponding to a scaling factor as low as 1.5. Finally, the performance of the TVAR scheme was tested against a human expert using simulated and real acoustic information. We conclude that a confident image of crackle sounds distribution by crackles counting using TVAR on the thoracic surface is thoroughly possible. The crackles imaging might represent an aid to the clinical evaluation of pulmonary diseases that produce this sort of adventitious discontinuous lung sounds.