Breath Sounds Research Articles

Clinical predictors of hypoxic pneumonia in children from the Eastern Highlands Province, Papua New Guinea: secondary analysis of two prospective observational studies

BackgroundPneumonia is the leading cause of death in young children globally and is prevalent in the Papua New Guinea highlands. We investigated clinical predictors of hypoxic pneumonia to inform local treatment guidelines in this resource-limited setting. MethodsBetween 2013 and 2020, two consecutive prospective observational studies were undertaken enrolling children 0-4 years presenting with pneumonia to health-care facilities in Goroka Town, Eastern Highlands Province. Logistic regression models were developed to identify clinical predictors of hypoxic pneumonia (oxygen saturation <90% on presentation). Model performance was compared against established criteria to identify severe pneumonia. FindingsThere were 2067 cases of pneumonia; hypoxaemia was detected in 36·1%. The strongest independent predictors of hypoxic pneumonia were central cyanosis on examination (adjusted odds ratio [aOR] 5·14; 95%CI 3·47-7·60), reduced breath sounds (aOR 2·92; 95%CI 2·30-3·71), and nasal flaring or grunting (aOR 2·34; 95%CI 1·62-3·38). While the model developed to predict hypoxic pneumonia outperformed established pneumonia severity criteria, it was not sensitive enough to be clinically useful at this time. InterpretationGiven signs and symptoms are unable to accurately detect hypoxia, all health care facilities should be equipped with pulse oximeters. However, for the health care worker without access to pulse oximetry, consideration of central cyanosis, reduced breath sounds, nasal flaring or grunting, age-specific tachycardia, wheezing, parent-reported drowsiness, or bronchial breathing as suggestive of hypoxaemic pneumonia, and thus severe disease, may prove useful in guiding management, hospital referral and use of oxygen therapy.

Massive diaphragmatic eventration: plication

Diaphragmatic eventration (DE) is a distinctive condition characterised by the abnormal elevation or displacement of a portion of the diaphragm, often leading to a protrusion of abdominal contents into the thoracic cavity. Unlike diaphragmatic hernias, eventrations involve a congenital or acquired weakness of the diaphragmatic muscle itself rather than a structural defect. Congenital eventrations typically arise from the incomplete development or muscular hypoplasia of the diaphragm, while acquired forms may result from trauma, surgery, or neurological disorders affecting the phrenic nerve. Clinical manifestations vary widely, with some individuals remaining asymptomatic, while others may experience respiratory difficulties, especially when lying down. The case involves a 65-year-old female with a history of breathlessness exacerbated in the lying position, improved when upright. Examination revealed low oxygen saturation, absent breath sounds on the left chest, and bowel sounds in that region. Chest X-ray and HRCT indicated bowel loops in the left chest due to eventration of the left hemidiaphragm. Surgical intervention involved thoracotomy, identifying a lax left hemidiaphragm, mobilising abdominal contents, and performing plication with proline 1-0. Closure was completed with an intercostal drainage (ICD) in the left thoracic cavity. Postoperative period was uneventful. This case emphasises the significance of prompt diagnosis and surgical intervention in managing DE, showcasing the effectiveness of thoracotomy, hemidiaphragm plication, and ICD placement.

Research on lung sound classification model based on dual-channel CNN-LSTM algorithm

ulmonary diseases have a significant impact on human health and life safety, and abnormalities in the lungs are a direct response to lung diseases. Establishing an effective lung sound classification model that can assist in diagnosis is of great significance for electronic auscultation.In addressing the issue of lung sound signal classification, this study introduces a deep learning classification model based on a dual-channel CNN-LSTM algorithm. Initially, Mel-scale Frequency Cepstral Coefficients (MFCC) are employed for feature extraction from the dataset, transforming lung sound signals into Mel spectrograms. On this foundation, a dual-channel algorithm classification model is constructed, with parallel Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) modules. The CNN module is designed to capture spatial dimension features of the input data, while the LSTM module focuses on temporal dimension features. These two feature sets are fused together, enabling the model to classify lung sounds and thereby assisting in diagnosing pulmonary diseases for healthcare practitioners. This experiment used the ICBHI2017 Challenge Lungs dataset and obtained 5054 pieces of data through data augmentation and sampling techniques.The results show that the accuracy, recall, and F1 score of this model reach 99.01%, 99.13%, and 0.9915, respectively, significantly superior to other models, highlighting its practical application value.

Successful resolution of mesenteric tuberculosis and HIV co-infection following 6 months of anti-tuberculosis therapy: a case report

BACKGROUND: Mesenteric tuberculosis (TB), a rare extrapulmonary variant of TB, poses diagnostic and therapeutic challenges in its management. Therefore, discussing a case of mesenteric TB is both intriguing and informative for gaining insights into its clinical presentation and optimal treatment strategies. CASE PRESENTATION: A 50-year-old male presented symptoms of blackish stools three days post-gallstone surgery, accompanied by approximately two months of abdominal discomfort, described as squeezing or stabbing, alleviated temporarily by analgesics, alongside abdominal distension, rigidity, decreased appetite, and afternoon fevers. Physical examination revealed normal vital signs, with pale conjunctiva and asymmetrical chest wall movement, dull percussion, and decreased breath sounds in the lower left hemithorax. Abdominal inspection indicated distension, postsurgical signs, and ascites. Following laboratory investigations, chest and abdominal radiographs, and tissue biopsies, the patient was diagnosed with HIV co-infection along with pulmonary and mesenteric TB. Treatment comprised an intensive phase of four fixed-dose combinations (FDC) of anti-TB drugs, followed by a continuation phase of two FDC tablets, alongside first-line antiretroviral (ARV) therapy and cotrimoxazole prophylaxis. By the sixth month follow-up, clinical improvement was observed, with resolution of symptoms and weight gain to 56 kg. CONCLUSION: This case highlights the effective management of mesenteric TB and HIV co-infection, emphasizing the importance of comprehensive care and collaborative efforts between TB and HIV/AIDS control programs.

Hybrid method for noise rejection from breath sound using transient artifact reduction algorithm and spectral subtraction.

Computerized breath sound based diagnostic methods are one of the emerging technologies gaining popularity in terms of detecting respiratory disorders. However, the breath sound signal used in such automated systems used to be too noisy, which affects the quality of the diagnostic interpretations. To address this problem, the proposed work presents the new hybrid approach to reject the noises from breath sound. In this method, 80 chronic obstructive pulmonary disease (COPD), 75 asthmatics and 80 normal breath sounds were recorded from the participants of a hospital. Each of these breath sound data were decontaminated using hybrid method of Butterworth band-pass filter, transient artifact reduction algorithm and spectral subtraction algorithm. The study examined the algorithms noise rejection potential over each category of breath sound by estimating the noise rejection performance metrics, i.e.,mean absolute error (MAE), mean square error (MSE), peak signal to noise ratio (PSNR), and signal to noise ratio (SNR). Using this algorithm, the study obtained a high value of SNR of 70 dB and that of PSNR of 72 dB. The study could definitely a suitable one to suppress noises and to produce noise free breath sound signal.

A novel method in COPD diagnosing using respiratory signal generation based on CycleGAN and machine learning

Objective The main goal of this research is to use distinctive features in respiratory sounds for diagnosing Chronic Obstructive Pulmonary Disease (COPD). This study develops a classification method by utilizing inverse transforms to effectively identify COPD based on unique respiratory features while comparing the classification performance of various optimal algorithms. Method Respiratory sounds are divided into individual breathing cycles. In the data standardization and augmentation phase, the CycleGAN model enhances data diversity. Comprehensive analyses for these segments are then implemented using various Wavelet families and different spectral transformations representing characteristic signals. Advanced convolutional neural networks, including VGG16, ResNet50, and InceptionV3, are used for the classification task. Results The results of this study demonstrate the effectiveness of the mentioned method. Notably, the best-performing method utilizes Wavelet Bior1.3 after standardization in combination with InceptionV3, achieving a remarkable 99.75% F1-score, the gold standard for classification accuracy. Conclusion Inverse transformation techniques combined with deep learning models show significant accuracy in detecting COPD disease. These findings suggest the feasibility of early COPD diagnosis through AI-powered characterization of acoustic features. Motivation and Significance The motivation behind this research stems from the urgent need for early and accurate diagnosis of Chronic Obstructive Pulmonary Disease (COPD). COPD is a respiratory disease that poses many difficulties when detected late, potentially causing severe harm to the patient’s quality of life and increasing the healthcare burden. Timely identification and intervention are crucial to reduce the progression of the disease and improve patient outcomes.

A deep CNN-based acoustic model for the identification of lung diseases utilizing extracted MFCC features from respiratory sounds

A deep CNN-based acoustic model for the identification of lung diseases utilizing extracted MFCC features from respiratory sounds

Analysis of respiratory properties using the low-frequency piezoelectric sensor in patients undergoing intravenous sedation: a prospective observational study

BackgroundPatients who undergo general anesthesia may experience respiratory failure postoperatively because of respiratory depression or upper airway obstruction. AimWe investigated whether a piezoelectric sensor (AYA-P sensor) can be used to detect upper airway obstruction in patients undergoing intravenous sedation. MethodsThis prospective observational study included 26 patients who underwent dental treatment under sedation at a dental clinic. Participants were evaluated using a newly defined airway obstruction score (AOS). The AYA-P sensors were attached to the suprasternal notch and the midpoint between the umbilicus and xiphoid process. The patient's respiratory status was classified into four categories based on thoracic movements, capnography, and breathing sounds from recorded data (S1: no airflow, S2: hypoventilation, S3: normal breathing, and S4: artifact). The data obtained from the AYA-P sensors were processed using a 0.4-Hz low-pass filter, calculated using the moving standard deviation (MSD) method, and further processed using a 0.1-Hz low-pass filter (fMSD). Next, these data were differentiated (D-fMSD). We defined the positive predictive value (PPV) as fMSD or D-fMSD values higher than a threshold α in categories S1 and S2. PPV(αMAX) was defined as the maximum PPV, and the negative predictive value (NPV[αMAX]) was defined using the same αMAX. ResultsWe compared each of the apnea-hypopnea time ratio (AHT%) and AOS with PPV(αMAX) and NPV(αMAX). The AHT% and AOS were correlated with PPV(αMAX) and NPV(αMAX) in the neck and abdomen, respectively. These findings suggest that an AYA-P sensor attached to the neck and abdomen can detect a patient's respiratory status. ConclusionProcessed data obtained from AYA-P sensors can predict upper airway obstruction in patients, and the predicted data may be dependent on individual anatomical differences. Clinical trial registrationThis study was registrated in the University Hospital Medical Information Network Clinical Trials Registry (UMIN-CTR) clinical trial: Unique ID: UMIN000047007.

Artificial intelligence-based framework to identify the abnormalities in the COVID-19 disease and other common respiratory diseases from digital stethoscope data using deep CNN.

The utilization of lung sounds to diagnose lung diseases using respiratory sound features has significantly increased in the past few years. The Digital Stethoscope data has been examined extensively by medical researchers and technical scientists to diagnose the symptoms of respiratory diseases. Artificial intelligence-based approaches are applied in the real universe to distinguish respiratory disease signs from human pulmonary auscultation sounds. The Deep CNN model is implemented with combined multi-feature channels (Modified MFCC, Log Mel, and Soft Mel) to obtain the sound parameters from lung-based Digital Stethoscope data. The model analysis is observed with max-pooling and without max-pool operations using multi-feature channels on respiratory digital stethoscope data. In addition, COVID-19 sound data and enriched data, which are recently acquired data to enhance model performance using a combination of L2 regularization to overcome the risk of overfitting because of less respiratory sound data, are included in the work. The suggested DCNN with Max-Pooling on the improved dataset demonstrates cutting-edge performance employing a multi-feature channels spectrogram. The model has been developed with different convolutional filter sizes (, , , , and ) that helped to test the proposed neural network. According to the experimental findings, the suggested DCNN architecture with a max-pooling function performs better to identify respiratory disease symptoms than DCNN without max-pooling. In order to demonstrate the model's effectiveness in categorization, it is trained and tested with the DCNN model that extract several modalities of respiratory sound data.

DeepRespNet: A deep neural network for classification of respiratory sounds

Respiratory sounds convey significant information about the pulmonary status. This study proposes a deep learning-based framework to create an automatic, non-invasive, diagnostic method of categorizing pulmonary sounds. A labelled database of pulmonary sounds has been collected using an electronic stethoscope and audio recording instrument. Two deep learning architectures, 1D DeepRespNet and 2D DeepRespNet are proposed in this work that were trained and evaluated with normalised 1-D time series and 2-D spectrograms of acoustic signals of six types of lung sounds, respectively. The models were highly optimized to yield superior performance on the considered dataset. Experimental results demonstrate that the 2D DeepRespNet model trained with spectrogram-based representations yields higher accuracy of 95.2% on the test data as compared to the 1D DeepRespNet trained on the time-series data. The proposed model may be deployed on a single board computer or integrated into a smartphone to develop a standalone diagnostic tool to accurately and objectively classify abnormal lung sounds with low time complexity.

A Retrospective Analysis of Needle Thoracostomies at a Tertiary Level 2 Trauma Center.

A tension pneumothorax is a condition that results in elevated pressure within the pleural space. The effective management of tension pneumothorax relies on needle decompression, commonly performed at the second intercostal space (ICS) midclavicular line (MCL). However, some literature suggests that catheters placed in the second intercostal space midclavicular line are prone to higher failure rates compared to the fifth intercostal space midaxillary line (MAL) (42.5% versus 16.7%, respectively). In this study, we aim to identify and scrutinize the prevalence of prehospital needle decompression from one tertiary care center over eight years and examine their trends, efficacies, or pitfalls. It is hypothesized that preclinical providers are performing needle decompression prematurely and unnecessarily. A set of 90 patient records obtained using the trauma registry at Saint Francis Hospital, Tulsa, Oklahoma, were retrospectively reviewed to evaluate the management and outcomes of tension pneumothorax, as well as the indications documented for needle decompression. Patient charts were reviewed via Epic Hyperspace (Epic, Madison, WI). The Oklahoma Emergency Medical Service Information System (OKEMSIS) also provided information contributing to the sample population. The most documented indications for needle decompressions included diminished or absent breath sounds (52.70%), hypoxia (15.54%), hypotension, and hemodynamic instability (6.76%). Emergency medical services (EMS) reported improvements in 51 (56.67%) patients after needle thoracostomy. Improvements in vital signs after needle decompression were sporadic. The most common complication was catheter dislodging, which occurred most in the second intercostal space midclavicular line. Only nine patients had an oxygen saturation (SpO2) below 92% and a systolic blood pressure (SBP) below 100 mm Hg prior to receiving needle decompression. Current practices for tension pneumothorax show little improvement in vital signs before and after needle decompression. Vital signs prior to needle decompression often do not indicate tension pneumothorax physiology. Preclinical providers may be inappropriately performing needle decompressions, an invasive procedure with complications.

Clinical characteristics of treatment-seeking youth with misophonia.

Misophonia is a psychiatric condition characterized by strong emotional and/or behavioral responses to auditory stimuli, leading to distress and functional impairment. Despite previous attempts to define and categorize this condition, misophonia is not currently included in the Diagnostic and Statistical Manual of Mental Disorders or International Classification of Diseases. The lack of formal diagnostic consensus presents challenges for research aimed at assessing and treating this clinical presentation. The current study presents clinical characteristics of youth (N = 47) with misophonia in the largest treatment-seeking sample to date. We examined demographic characteristics of the sample, frequency of comorbid disorders, frequency of specific misophonia symptoms (i.e., triggers, emotionaland behavioral responses, and impairments), and caregiver-child symptom agreement. Misophonia symptoms were evaluated using a multimodal assessment including clinician, youth, and caregiver reports on empirically established misophonia measures, and concordance among measures was assessed. Youth seeking treatment for misophonia presented with marked misophonia symptoms and an array of comorbid conditions. Youth and caregivers identified various triggers of misophonia symptoms (e.g., chewing sounds, breathing sounds), as well as a wide range of emotional (e.g., anger, annoyance, disgust) and behavioral (e.g., aggression, avoidance) responses to triggers. Youth and caregivers exhibited high agreement on misophonia triggers but lower agreement on symptom severity and associated impairment. Compared to younger children (aged 8-13), older children (aged 14+) appeared to report symptom severity and associated impairment more reliably. Misophonia is a heterogenous and impairing clinical condition that warrants future investigation and evidence-based treatment development.

Breath Measurement Method for Synchronized Reproduction of Biological Tones in an Augmented Reality Auscultation Training System.

An educational augmented reality auscultation system (EARS) is proposed to enhance the reality of auscultation training using a simulated patient. The conventional EARS cannot accurately reproduce breath sounds according to the breathing of a simulated patient because the system instructs the breathing rhythm. In this study, we propose breath measurement methods that can be integrated into the chest piece of a stethoscope. We investigate methods using the thoracic variations and frequency characteristics of breath sounds. An accelerometer, a magnetic sensor, a gyro sensor, a pressure sensor, and a microphone were selected as the sensors. For measurement with the magnetic sensor, we proposed a method by detecting the breathing waveform in terms of changes in the magnetic field accompanying the surface deformation of the stethoscope based on thoracic variations using a magnet. During breath sound measurement, the frequency spectra of the breath sounds acquired by the built-in microphone were calculated. The breathing waveforms were obtained from the difference in characteristics between the breath sounds during exhalation and inhalation. The result showed the average value of the correlation coefficient with the reference value reached 0.45, indicating the effectiveness of this method as a breath measurement method. And the evaluations suggest more accurate breathing waveforms can be obtained by selecting the measurement method according to breathing method and measurement point.

COVID-19 Detection From Respiratory Sounds With Hierarchical Spectrogram Transformers.

Monitoring of prevalent airborne diseases such as COVID-19 characteristically involves respiratory assessments. While auscultation is a mainstream method for preliminary screening of disease symptoms, its utility is hampered by the need for dedicated hospital visits. Remote monitoring based on recordings of respiratory sounds on portable devices is a promising alternative, which can assist in early assessment of COVID-19 that primarily affects the lower respiratory tract. In this study, we introduce a novel deep learning approach to distinguish patients with COVID-19 from healthy controls given audio recordings of cough or breathing sounds. The proposed approach leverages a novel hierarchical spectrogram transformer (HST) on spectrogram representations of respiratory sounds. HST embodies self-attention mechanisms over local windows in spectrograms, and window size is progressively grown over model stages to capture local to global context. HST is compared against state-of-the-art conventional and deep-learning baselines. Demonstrations on crowd-sourced multi-national datasets indicate that HST outperforms competing methods, achieving over 90% area under the receiver operating characteristic curve (AUC) in detecting COVID-19 cases.

Simultaneous in-air versus in-water measurements of humpback whale breathing sounds

Humpback whales produce an assortment of sounds ranging from moans and songs to surface-breaching, breathing, and foreflipper flaps. During a sea trial of Northeastern University’s coherent hydrophone array at the Great South Channel in US Northeastern coastal waters, the HF subaperture consisting of 32 hydrophone elements at 0.375 m spacings was deployed vertically with half of the hydrophones in air and the other half submerged underwater on September 6th, 2021. Many instances of humpback whale breathing sounds were recorded over several hours of observation. Visual sightings and video recordings were used to coregister sounds recorded on individual hydrophones of the HF subaperture. Here, we examine and compare the simultaneously recorded humpback whale breathing sound spectra, bandwidth, and duration for in-air versus underwater hydrophones. Whale distances to the vertical HF subaperture could be calculated from curved time of arrival differences due to close proximity of the array. These distances are applied to correct the received underwater sound pressure level for transmission loss and estimate underwater recorded whale breathing sound source level. A consistent broadband dip in the measured underwater sound spectra with null centered at 15 kHz is investigated by propagation modelling, considering both modal interference and attenuation from loud bubbles.

A survey study on antibiotic prescription practices for acute asthma exacerbations: An European academy of allergy and clinical immunology task force report.

Guidelines recommend treating asthma exacerbations (AAEs) with bronchodilators combined with inhaled and/or systemic corticosteroids. Indications for antibiotic prescriptions for AAEs are usually not incorporated although the literature shows antibiotics are frequently prescribed. To investigate the antibiotic prescription rates in AAEs and explore the possible determining factors of those practices. A digital survey was created to determine the antibiotic prescription rates in AAEs and the influencing factors for the prescription practices. The survey was distributed among European academy of allergy and clinical immunology (EAACI) members by mass emailing and through regional/national societies in the Netherlands, Italy, Greece, and Poland. Furthermore, we retrieved local antibiotic prescription rates. In total, 252 participants completed the survey. Respondents stated that there is a lack of guidelines to prescribe antibiotics in AAEs. The median antibiotic prescription rate in this study was 19% [IQR: 0%-40%] and was significantly different between 4 professions: paediatrics 0% [IQR: 0%-37%], pulmonologists 25% [IQR: 10%-50%], general practitioners 25% [IQR: 0%-50%], and allergologists 17% [IQR: 0%-33%]) (p=0.046). Additional diagnostic tests were performed in 71.4% of patients before prescription and the most common antibiotic classes prescribed were macrolides (46.0%) and penicillin (42.9%). Important clinical factors for health care providers to prescribe antibiotics were colorised/purulent sputum, abnormal lung sounds during auscultation, fever, and presence of comorbidities. In 19% of patients with AAEs, antibiotics were prescribed in various classes with a broad range among different subspecialities. This study stresses the urgency to compose evidence-based guidelines to aim for more rational antibiotic prescriptions for AAE.

SUPER-COUGH: A Super Learner-based ensemble machine learning method for detecting disease on cough acoustic signals

Sound classification has obtained considerable attention in recent years due to its wide range of applications in various fields, such as speech recognition, sound surveillance, music analysis, and environmental monitoring. Because of its success, audio classification can also be employed in medical applications. Coughing is the most common disease symptom, and cough sounds might be used to diagnose them. This research focuses on identifying observable features of cough and classifying them into positive, negative, or symptomatic categories. A novel ensemble learning model based on the super learner (SL) is proposed to diagnose the disease using cough sounds utilizing various audio features such as Frequency Distribution, Time Domain Features, Spectral Features, and Time–Frequency Features. The SL method is a cross-validated approach to stacked generalization, and it can select an optimal learner from a set of learners and improve performance by selecting and merging models using cross-validation. The proposed SL model comprises DT, RF, LR, SVM, ET, and k-NN algorithms. We use the public Coughvid dataset, and the proposed model achieves a correct classification rate for symptomatic cases, which was 90.90%, and the positive predictive value for COVID-19 cases was 84.50%. The SL3 model attains 72%, 78%, 73%, 74.4%, and 78.85% precision, recall, f1-score, accuracy, and average AUC values, respectively. The numerical results show that the proposed model might be implemented to diagnose various other diseases that can be determined from respiratory sounds.

Successful Surgical Management of Giant Mediastinal Teratoma – A Case Report of a Difficult Case without Any Post-Operative Complication

Introduction. Mediastinal teratoma is a rare germ cell tumor, located in anterior mediastinum and is lack of population-based study. It usually occurs in the age of 20-40 years, accounting for 15% of anterior mediastinal masses in adults and 25% of anterior mediastinal masses in children. It is frequently diagnosed accidentally on chest imaging due to its asymptomatic nature. Hereby, we presented a case of giant anterior mediastinum teratoma with complete surgical excision without any post-operative complication. This case is unique due to its uneventful result after excision. From our literature research, we successfully avoid the potential post operative complications of resecting this tumor such as bleeding, wound dehiscence and even death. It is due to early diagnosis, treatment and good intraoperative management of lesion &amp; hemodynamics. Case Report. A 21-year old male was referred from pulmonologist oncologist to our Thoracic Surgical Unit with complains of dyspnea and chest pain. Physical examination showed no lung sounds in (R) hemithorax and was dull to percussion, ictus cordis shifted 2 fingerbreadths towards left-side. Chest X-ray showed a large well-defined lesion in (R) hemithorax and chest CT-scan with contrast showed hypodense mass on (R) hemithorax adhering &amp; compressing the lung, diaphragm, pericardium &amp; chest wall, with estimation size of 60 x 20 x 12 cm, lesion displaced the heart. Patient was then treated with complete surgical excision and found a huge cystic tumor with a size of 60 x 20 x 12 cm adhering to all parts of (R) lung, diaphragm and pericardium. He underwent (R) pneumonectomy due to adhesion. Histologic examination was consistent with mature teratoma. Patient showed no complication after surgery and was discharged uneventfully from our hospital after 5 days. Discussion. Approximately 95% of benign teratomas arise in the anterior mediastinum. The tumor grows progressively, mostly asymptomatic, dyspnea and substernal chest pain are the most common symptoms if present. Productive Cough of hair or sebum is a pathognomonic sign. Chest radiograph typically reveals a well-circumscribed anterior mediastinal mass that often protrudes into one of the lung, they are usually large at the time of diagnosis. Complete surgical excision is a treatment of choice of mediastinal teratoma, which can be performed through median sternotomy or thoracotomy or thoracoscopy. Some patients require additional procedures (eg, lobectomy, pericardiectomy) for complete tumor resection. Conclusion. There is still limited data on mediastinal teratoma. Early referral &amp; treatment show good prognosis. Benign Mediastinal Teratomas was tricky to be diagnosed, when it is diagnosed, it is usually very large in size. Complete Surgical Excision can be performed safely without any complications.

Comparative study of respiratory sounds classification methods based on cepstral analysis and artificial neural networks

In this paper, we investigated and evaluated various machine learning-based approaches for automatically detecting wheezing sounds. We conducted a comprehensive comparison of these proposed systems, assessing their classification performance through metrics such as Sensitivity, Specificity, and Accuracy. The main approach to developing a machine learning-based system for classifying respiratory sounds involved the combination of a technique for extracting features from an unknown input sound with a classification method to determine its belonging class. The characterization techniques used in this study are based on the cepstral analysis, which was extensively employed in the automatic speech recognition field. While MFCC (Mel-Frequency Cepstral Coefficients) feature extraction methods are commonly used in respiratory sounds classification, our study introduces a novelty by employing GFCC (Gammatone-Frequency Cepstral Coefficients) and BFCC (Bark-Frequency Cepstral Coefficients) for this purpose. For the classification task, we employed two types of neural networks: the MLP (Multilayer Perceptron), a feedforward neural network, and a variant of the LSTM (Long Short-Term Memory) recurrent neural network called BiLSTM (Bidirectional LSTM). The proposed classification systems are evaluated using a database consisting of 497 wheezing segments and 915 normal respiratory segments, which are recorded from individuals diagnosticated with asthma and individuals without any respiratory issues, respectively. The highest classification performance was achieved by the BFCC-BiLSTM model, which demonstrated an exceptional accuracy rate of 99.8%.

Elimination of heart sound from respiratory sound using adaptive variational mode decomposition for pulmonary diseases diagnosis

Lung sound (LS) signals are a vital source of information for the identification of pulmonary disorders. Heart sound (HS) is the most common contaminant of lung sounds during auscultation from the chest walls. This directly affects the efficiency of lung sound processing in diagnosing lung diseases. In this work, Adaptive Variational Mode Decomposition (AVMD) technique is proposed to remove heart sound contaminants from lung sounds. The proposed AVMD method initially breakdown the noisy lung sound signal into a collective of bandlimited modes called variational mode functions (VMF). Then, based on the frequency spectrum, the HS is filtered out from the LS. The real time lung sound data is collected from 95 participants and the performance of VMD technique is evaluated using the statistical metrics measures. Thus, the proposed topology exhibits Higher SNR (29.6587dB, lowest Root Mean Square (RMSE) of 0.0102, lowest normalized Mean Absolute Error (nMAE) of 0.0336, and highest percentage in correlation coefficient Factor (CCF) of 99.79% respectively. These experimental results are found to be superior and outperform all other recently proposed techniques.