Convolutional Neural Network Classification of Exhaled Aerosol Images for Diagnosis of Obstructive Respiratory Diseases

Abstract

Aerosols exhaled from the lungs have distinctive patterns that can be linked to the abnormalities of the lungs. Yet, due to their intricate nature, it is highly challenging to analyze and distinguish these aerosol patterns. Small airway diseases pose an even greater challenge, as the disturbance signals tend to be weak. The objective of this study was to evaluate the performance of four convolutional neural network (CNN) models (AlexNet, ResNet-50, MobileNet, and EfficientNet) in detecting and staging airway abnormalities in small airways using exhaled aerosol images. Specifically, the model’s capacity to classify images inside and outside the original design space was assessed. In doing so, multi-level testing on images with decreasing similarities was conducted for each model. A total of 2745 images were generated using physiology-based simulations from normal and obstructed lungs of varying stages. Multiple-round training on datasets with increasing images (and new features) was also conducted to evaluate the benefits of continuous learning. Results show reasonably high classification accuracy on inbox images for models but significantly lower accuracy on outbox images (i.e., outside design space). ResNet-50 was the most robust among the four models for both diagnostic (2-class: normal vs. disease) and staging (3-class) purposes, as well as on both inbox and outbox test datasets. Variation in flow rate was observed to play a more important role in classification decisions than particle size and throat variation. Continuous learning/training with appropriate images could substantially enhance classification accuracy, even with a small number (~100) of new images. This study shows that CNN transfer-learning models could detect small airway remodeling (<1 mm) amidst a variety of variants and that ResNet-50 can be a promising model for the future development of obstructive lung diagnostic systems.

Data-Driven Discovery of Anomaly-Sensitive Parameters from Uvula Wake Flows Using Wavelet Analyses and Poincaré Maps

“…Moreover, CNN models can learn label-related features during training in the form of activation layers and/or heat maps. One drawback of these features is that they become increasingly abstract in deeper layers, as demonstrated in [76]. This trend mirrors the diminishing consistency observed in PC curves as scales rise (Figure 4), and the transition from simplicity to complexity with growing frequencies in scalograms in Figures 6-8.…”

Datasets of Simulated Exhaled Aerosol Images from Normal and Diseased Lungs with Multi-Level Similarities for Neural Network Training/Testing and Continuous Learning

“…The dataset in this study was designed to test the hypothesis that the exhaled aerosol distributions could be correlated to the underlying lung structures and associated airway abnormalities [11]. In doing so, breath tests were simulated that inhaled and exhaled an aerosol bolus under varying breathing conditions, which was intended to train and validate convolutional neural network (CNN) models.…”

Schlieren imaging and video classification of alphabet pronunciations: exploiting phonetic flows for speech recognition and speech therapy

“…Video classification has progressed significantly with the advent of deep learning, facilitating the integration of a pre-trained convolutional neural network (CNN) with a long short-term memory (LSTM) network. In this integrative approach, video frames are initially transformed into feature vectors by the convolutional network, capturing essential attributes of each frame [ 32 , 33 ]. These vectors are subsequently fed into an LSTM network, which captures temporal information inherent in the video frame sequences [ 34 ].…”