Detection and Visualisation of Pneumoconiosis Using an Ensemble of Multi-Dimensional Deep Features Learned from Chest X-rays

Abstract

Pneumoconiosis is a group of occupational lung diseases induced by mineral dust inhalation and subsequent lung tissue reactions. It can eventually cause irreparable lung damage, as well as gradual and permanent physical impairments. It has affected millions of workers in hazardous industries throughout the world, and it is a leading cause of occupational death. It is difficult to diagnose early pneumoconiosis because of the low sensitivity of chest radiographs, the wide variation in interpretation between and among readers, and the scarcity of B-readers, which all add to the difficulty in diagnosing these occupational illnesses. In recent years, deep machine learning algorithms have been extremely successful at classifying and localising abnormality of medical images. In this study, we proposed an ensemble learning approach to improve pneumoconiosis detection in chest X-rays (CXRs) using nine machine learning classifiers and multi-dimensional deep features extracted using CheXNet-121 architecture. There were eight evaluation metrics utilised for each high-level feature set of the associated cross-validation datasets in order to compare the ensemble performance and state-of-the-art techniques from the literature that used the same cross-validation datasets. It is observed that integrated ensemble learning exhibits promising results (92.68% accuracy, 85.66% Matthews correlation coefficient (MCC), and 0.9302 area under the precision–recall (PR) curve, compared to individual CheXNet-121 and other state-of-the-art techniques. Finally, Grad-CAM was used to visualise the learned behaviour of individual dense blocks within CheXNet-121 and their ensembles into three-color channels of CXRs. We compared the Grad-CAM-indicated ROI to the ground-truth ROI using the intersection of the union (IOU) and average-precision (AP) values for each classifier and their ensemble. Through the visualisation of the Grad-CAM within the blue channel, the average IOU passed more than 90% of the pneumoconiosis detection in chest radiographs.

Development of a chest X-ray machine learning convolutional neural network model on a budget and using artificial intelligence explainability techniques to analyze patterns of machine learning inference

“… 39 Direct comparisons are difficult as other models often focus on targeted rather than general tasks, but this model has a comparable performance to many works. 9 , 11 , 40 Regardless we primarily use this model to explore ML concepts rather than focusing on its performance.…”

“…Future work could analyze other themes in ML work. An example could be the differences in inferencing behavior between DenseNet 8 , 9 and ResNet 31 architectures or the effect of the residual block itself. This could lead to the development of methods for forward-looking prediction of behavior.…”

“… 3 For instance, CheXNet (based on Densenet-121) has been employed by numerous authors to detect abnormalities on CXR. 8 , 9 Other model architectures such as Inception V3, VGG16, and even ResNet have been employed in the past. 10 , 11 …”

Stacking Ensemble and ECA-EfficientNetV2 Convolutional Neural Networks on Classification of Multiple Chest Diseases Including COVID-19

“…In recent years, due to the continuous improvement of computing power of computers, large-scale integrated models can be trained within a reasonable time, and have been applied on medical image recognition, face recognition, emotion recognition and financial decision-making, etc. Successful applications of ensemble classifiers could be seen in ( 42 , 43 , 44 , 45 ).…”

Machine Learning Approach for Metabolic Syndrome Diagnosis Using Explainable Data-Augmentation-Based Classification

“…Changes in way of life, nutrition, and exercise, as well as inactivity, have all been linked to the rise of metabolic illnesses [ 2 ]. The aforementioned risk factors may have contributed to the development of diseases such as metabolic syndrome, cardiovascular disorders, diabetes mellitus, cerebrovascular diseases, food-borne diseases, infectious diseases, and cancer [ 3 ]. Therefore, focusing on health indicators is an attractive opportunity to explore the health state of individual and population subjects in relation to biochemical changes in the body.…”