BRACETS: Bimodal repository of auscultation coupled with electrical impedance thoracic signals.

BACKGROUND AND OBJECTIVE: Respiratory diseases are among the most significant causes of morbidity and mortality worldwide, causing substantial strain on society and health systems. Over the last few decades, there has been increasing interest in the automatic analysis of respiratory sounds and electrical impedance tomography (EIT). Nevertheless, no publicly available databases with both respiratory sound and EIT data are available. METHODS: In this work, we have assembled the first open-access bimodal database focusing on the differential diagnosis of respiratory diseases (BRACETS: Bimodal Repository of Auscultation Coupled with Electrical Impedance Thoracic Signals). It includes simultaneous recordings of single and multi-channel respiratory sounds and EIT. Furthermore, we have proposed several machine learning-based baseline systems for automatically classifying respiratory diseases in six distinct evaluation tasks using respiratory sound and EIT (A1, A2, A3, B1, B2, B3). These tasks included classifying respiratory diseases at sample and subject levels. The performance of the classification models was evaluated using a 5-fold cross-validation scheme (with subject isolation between folds). RESULTS: The resulting database consists of 1097 respiratory sounds and 795 EIT recordings acquired from 78 adult subjects in two countries (Portugal and Greece). In the task of automatically classifying respiratory diseases, the baseline classification models have achieved the following average balanced accuracy: Task A1 - 77.9±13.1%; Task A2 - 51.6±9.7%; Task A3 - 38.6±13.1%; Task B1 - 90.0±22.4%; Task B2 - 61.4±11.8%; Task B3 - 50.8±10.6%. CONCLUSION: The creation of this database and its public release will aid the research community in developing automated methodologies to assess and monitor respiratory function, and it might serve as a benchmark in the field of digital medicine for managing respiratory diseases. Moreover, it could pave the way for creating multi-modal robust approaches for that same purpose.

Automated Lung Sound Classification Using a Hybrid CNN-LSTM Network and Focal Loss Function.

Respiratory diseases constitute one of the leading causes of death worldwide and directly affect the patient's quality of life. Early diagnosis and patient monitoring, which conventionally include lung auscultation, are essential for the efficient management of respiratory diseases. Manual lung sound interpretation is a subjective and time-consuming process that requires high medical expertise. The capabilities that deep learning offers could be exploited in order that robust lung sound classification models can be designed. In this paper, we propose a novel hybrid neural model that implements the focal loss (FL) function to deal with training data imbalance. Features initially extracted from short-time Fourier transform (STFT) spectrograms via a convolutional neural network (CNN) are given as input to a long short-term memory (LSTM) network that memorizes the temporal dependencies between data and classifies four types of lung sounds, including normal, crackles, wheezes, and both crackles and wheezes. The model was trained and tested on the ICBHI 2017 Respiratory Sound Database and achieved state-of-the-art results using three different data splitting strategies-namely, sensitivity 47.37%, specificity 82.46%, score 64.92% and accuracy 73.69% for the official 60/40 split, sensitivity 52.78%, specificity 84.26%, score 68.52% and accuracy 76.39% using interpatient 10-fold cross validation, and sensitivity 60.29% and accuracy 74.57% using leave-one-out cross validation.

Classification of Electrical Impedance Tomography Data Using Machine Learning.

Patients suffering from pulmonary diseases typically exhibit pathological lung ventilation in terms of homogeneity. Electrical Impedance Tomography (EIT) is a non- invasive imaging method that allows to analyze and quantify the distribution of ventilation in the lungs. In this article, we present a new approach to promote the use of EIT data and the implementation of new clinical applications for differential diagnosis, with the development of several machine learning models to discriminate between EIT data from healthy and nonhealthy subjects. EIT data from 16 subjects were acquired: 5 healthy and 11 non-healthy subjects (with multiple pulmonary conditions). Preliminary results have shown accuracy percentages of 66% in challenging evaluation scenarios. The results suggest that the pairing of EIT feature engineering methods with machine learning methods could be further explored and applied in the diagnostic and monitoring of patients suffering from lung diseases. Also, we introduce the use of a new feature in the context of EIT data analysis (Impedance Curve Correlation).

Detection of squawks in respiratory sounds of mechanically ventilated COVID-19 patients.

Mechanically ventilated patients typically exhibit abnormal respiratory sounds. Squawks are short inspiratory adventitious sounds that may occur in patients with pneumonia, such as COVID-19 patients. In this work we devised a method for squawk detection in mechanically ventilated patients by developing algorithms for respiratory cycle estimation, squawk candidate identification, feature extraction, and clustering. The best classifier reached an F1 of 0.48 at the sound file level and an F1 of 0.66 at the recording session level. These preliminary results are promising, as they were obtained in noisy environments. This method will give health professionals a new feature to assess the potential deterioration of critically ill patients.

Does Quantification of Carotid Plaque Surface Irregularities Better Detect Symptomatic Plaques Compared to the Subjective Classification?

OBJECTIVES: To evaluate the interobserver agreement of color Doppler ultrasound (CDUS) and contrast-enhanced ultrasound (CEUS) for quantification of carotid plaque surface irregularities and to correlate objective and subjective measures with stroke occurrence. METHODS: This work was an observational study involving 54 patients with 62 internal carotid artery or carotid bulb plaques (31 symptomatic) undergoing CDUS and CEUS between February 2016 and February 2018, with retrospective interpretation of prospectively acquired data. Plaques were included if causing moderate (50%-69%) or severe (70%-99%) stenosis based on velocity criteria, and their surface was classified as smooth, irregular, or ulcerated based on CEUS. The surface irregularities were quantified in the form of a surface irregularity index by 2 observers, based on CDUS and CEUS. The surface irregularity index was evaluated for interobserver agreement with CDUS and CEUS and correlated with the occurrence of stroke, as was the subjective characterization of the plaque surface. RESULTS: Color Doppler ultrasound and CEUS showed good interobserver agreement (intraclass correlation coefficients, 0.979 and 0.952, respectively). Plaques were characterized as smooth in 30.6% of cases, irregular in 50%, and ulcerated in 19.4%. The subjective classification of the plaque surface did not correlate with stroke occurrence (P > .05, χ2 ). Surface irregularity index values were significantly higher for symptomatic plaques with both CDUS and CEUS (P < .05). CONCLUSIONS: Color Doppler ultrasound and CEUS can quantify carotid plaque surface irregularities with good interobserver agreement. The resulting quantitative measure was significantly higher in symptomatic plaques, whereas the subjective characterization of plaque surface failed to differ between symptomatic and asymptomatic plaques.

Automatic lung segmentation in functional SPECT images using active shape models trained on reference lung shapes from CT.

OBJECTIVE: Image segmentation is an essential step in quantifying the extent of reduced or absent lung function. The aim of this study is to develop and validate a new tool for automatic segmentation of lungs in ventilation and perfusion SPECT images and compare automatic and manual SPECT lung segmentations with reference computed tomography (CT) volumes. METHODS: A total of 77 subjects (69 patients with obstructive lung disease, and 8 subjects without apparent perfusion of ventilation loss) performed low-dose CT followed by ventilation/perfusion (V/P) SPECT examination in a hybrid gamma camera system. In the training phase, lung shapes from the 57 anatomical low-dose CT images were used to construct two active shape models (right lung and left lung) which were then used for image segmentation. The algorithm was validated in 20 patients, comparing its results to reference delineation of corresponding CT images, and by comparing automatic segmentation to manual delineations in SPECT images. RESULTS: The Dice coefficient between automatic SPECT delineations and manual SPECT delineations were 0.83 ± 0.04% for the right and 0.82 ± 0.05% for the left lung. There was statistically significant difference between reference volumes from CT and automatic delineations for the right (R = 0.53, p = 0.02) and left lung (R = 0.69, p < 0.001) in SPECT. There were similar observations when comparing reference volumes from CT and manual delineations in SPECT images, left lung (bias was - 10 ± 491, R = 0.60, p = 0.005) right lung (bias 36 ± 524 ml, R = 0.62, p = 0.004). CONCLUSION: Automated segmentation on SPECT images are on par with manual segmentation on SPECT images. Relative large volumetric differences between manual delineations of functional SPECT images and anatomical CT images confirms that lung segmentation of functional SPECT images is a challenging task. The current algorithm is a first step towards automatic quantification of wide range of measurements.

ARCOCT: Automatic detection of lumen border in intravascular OCT images.

BACKGROUND AND OBJECTIVE: Intravascular optical coherence tomography (OCT) is an invaluable tool for the detection of pathological features on the arterial wall and the investigation of post-stenting complications. Computational lumen border detection in OCT images is highly advantageous, since it may support rapid morphometric analysis. However, automatic detection is very challenging, since OCT images typically include various artifacts that impact image clarity, including features such as side branches and intraluminal blood presence. This paper presents ARCOCT, a segmentation method for fully-automatic detection of lumen border in OCT images. METHODS: ARCOCT relies on multiple, consecutive processing steps, accounting for image preparation, contour extraction and refinement. In particular, for contour extraction ARCOCT employs the transformation of OCT images based on physical characteristics such as reflectivity and absorption of the tissue and, for contour refinement, local regression using weighted linear least squares and a 2nd degree polynomial model is employed to achieve artifact and small-branch correction as well as smoothness of the artery mesh. Our major focus was to achieve accurate contour delineation in the various types of OCT images, i.e., even in challenging cases with branches and artifacts. RESULTS: ARCOCT has been assessed in a dataset of 1812 images (308 from stented and 1504 from native segments) obtained from 20 patients. ARCOCT was compared against ground-truth manual segmentation performed by experts on the basis of various geometric features (e.g. area, perimeter, radius, diameter, centroid, etc.) and closed contour matching indicators (the Dice index, the Hausdorff distance and the undirected average distance), using standard statistical analysis methods. The proposed method was proven very efficient and close to the ground-truth, exhibiting non statistically-significant differences for most of the examined metrics. CONCLUSIONS: ARCOCT allows accurate and fully-automated lumen border detection in OCT images.