Inception-Based Network and Multi-Spectrogram Ensemble Applied To Predict Respiratory Anomalies and Lung Diseases

  title={Inception-Based Network and Multi-Spectrogram Ensemble Applied To Predict Respiratory Anomalies and Lung Diseases},
  author={Lam Dang Pham and Huy Phan and Ross King and Alfred Mertins and Ian Mcloughlin},
  journal={2021 43rd Annual International Conference of the IEEE Engineering in Medicine \& Biology Society (EMBC)},
  • L. PhamHuy Phan I. Mcloughlin
  • Published 26 December 2020
  • Computer Science
  • 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
This paper presents an inception-based deep neural network for detecting lung diseases using respiratory sound input. Recordings of respiratory sound collected from patients are first transformed into spectrograms where both spectral and temporal information are well represented, in a process referred to as front-end feature extraction. These spectrograms are then fed into the proposed network, in a process referred to as back-end classification, for detecting whether patients suffer from lung… 

Figures and Tables from this paper

An Ensemble of Deep Learning Frameworks Applied For Predicting Respiratory Anomalies

This paper firstly transforms audio respiratory cycles collected from patients into spectrograms where both temporal and spectral features are presented, referred to as the front-end feature extraction, which is fed into back-end deep learning networks for classifying these respiratory cycles into certain categories.

An Ensemble of Deep Learning Frameworks for Predicting Respiratory Anomalies

This paper evaluates a range of deep learning frameworks for detecting respiratory anomalies from input audio using time-frequency spectrograms to serve as front-end two-dimensional features and achieves the highest ICBHI score to date.

Classify Respiratory Abnormality in Lung Sounds Using STFT and a Fine-Tuned ResNet18 Network

This work took a data-driven approach to classify abnormal lung sounds and compared the performance using three different feature extraction techniques, which are short-time Fourier transformation (STFT), Mel spectrograms, and Wav2vec, as well as three different classifiers, including pre-trained ResNet18, LightCNN, and Audio Spectrogram Transformer.

Audio-Based Deep Learning Frameworks for Detecting COVID-19

This paper evaluates a wide range of audio-based deep learning frameworks applied to the breathing, cough, and speech sounds for detecting COVID-19, and finds that the method outperforms the state-of-the-art systems, and improves the challenge baseline.

An Effective Lung Sound Classification System for Respiratory Disease Diagnosis Using DenseNet CNN Model with Sound Pre-processing Engine

A deep learning model is built for classifying lung sounds, which can provide physicians with a more consistent reference for accurate diagnosis, based on lung sound dataset obtained on children aged from 1 month to 18 years old.

Multi-path Convolutional Neural Networks Efficiently Improve Feature Extraction in Continuous Adventitious Lung Sound Detection

This paper presents a meta-anatomical simulation of the response of the immune system to treatment-side-by-side injections, and some examples show the effects of chemotherapy and radiation therapy.

Benchmarking of eight recurrent neural network variants for breath phase and adventitious sound detection on a self-developed open-access lung sound database—HF_Lung_V1

A performance comparison between the LSTM-based and GRU-based models, between unidirectional and bidirectional models, and between models with and without a CNN revealed that these models exhibited adequate performance in lung sound analysis.



Robust Deep Learning Framework For Predicting Respiratory Anomalies and Diseases

A novel deep learning based framework is proposed for detection of respiratory diseases and shown to perform extremely well compared to state of the art methods.

CNN-MoE Based Framework for Classification of Respiratory Anomalies and Lung Disease Detection

A novel deep learning system is proposed, built on the proposed framework, which outperforms current state-of-the-art methods and applies a Teacher-Student scheme to achieve a trade-off between model performance and model complexity which holds promise for building real-time applications.

Deep Auscultation: Predicting Respiratory Anomalies and Diseases via Recurrent Neural Networks

  • D. PernaA. Tagarelli
  • Computer Science
    2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)
  • 2019
This work is the first to model a recurrent-neural-network based learning framework to support the clinician in detecting respiratory diseases, at either level of abnormal sounds or pathology classes, thus advancing the state-of-the-art in respiratory disease analysis.

Automatic Classification of Large-Scale Respiratory Sound Dataset Based on Convolutional Neural Network

The development of an algorithm for the automatic classification of the large-scale respiratory sound dataset used in ICBHI 2017 Challenge as containing crackles, containing wheeze, containing both, and normal is described.

Deep Neural Network for Respiratory Sound Classification in Wearable Devices Enabled by Patient Specific Model Tuning

A deep CNN-RNN model that classifies respiratory sounds based on Mel-spectrograms is proposed that is able to achieve state of the art score on the ICBHI’17 dataset and deep learning models are shown to successfully learn domain specific knowledge when pre-trained with breathing data and produce significantly superior performance compared to generalized models.

An Automated Lung Sound Preprocessing and Classification System Based OnSpectral Analysis Methods

The proposed algorithm, which has achieved 49.86% accuracy on a very challenging and rich dataset, is a promising tool to be used as preprocessor in lung disease decision support systems.

LungBRN: A Smart Digital Stethoscope for Detecting Respiratory Disease Using bi-ResNet Deep Learning Algorithm

  • Yi MaXinzi Xu Guoxing Wang
  • Computer Science, Medicine
    2019 IEEE Biomedical Circuits and Systems Conference (BioCAS)
  • 2019
An improved bi-ResNet deep learning architecture, LungBRN, is developed, which uses STFT and wavelet feature extraction techniques to improve the accuracy compared to the state-of-the-art works and is able to achieve the best result in terms of accuracy among participating teams from ICBHI 2017.

Noise Masking Recurrent Neural Network for Respiratory Sound Classification

A novel architecture called noise masking recurrent neural network (NMRNN) for lung sound classification that reaches state-of-the-art performance on recently introduced publicly available respiratory sound database.

Automatic Detection of Patient with Respiratory Diseases Using Lung Sound Analysis

A new model is created at the patient level, which is able to decide if a patient sounds sick or not, by taking as input the predicted results of the first classification model, which permits to reach 85% of good predictions and could be used as a tool for helping doctors to make better diagnosis.

Feature Extraction for Machine Learning Based Crackle Detection in Lung Sounds from a Health Survey

A machine learning based approach for detecting crackles in lung sounds recorded using a stethoscope in a large health survey that is accurate, fast, and has low resource requirements is proposed.