CX-Net: an efficient ensemble semantic deep neural network for ROI identification from chest-x-ray images for COPD diagnosis

Abstract

Automatic identification of salient features in large medical datasets, particularly in chest X-ray (CXR) images, is a crucial research area. Accurately detecting critical findings such as emphysema, pneumothorax, and chronic bronchitis can aid radiologists in prioritizing time-sensitive cases and screening for abnormalities. However, traditional deep neural network approaches often require bounding box annotations, which can be time-consuming and challenging to obtain. This study proposes an explainable ensemble learning approach, CX-Net, for lung segmentation and diagnosing lung disorders using CXR images.We compare four state-of-the-art convolutional neural network (CNN) models, including FPN, U-Net, LinkNet, and a customized U-Net model with ImageNet feature extraction, data augmentation, and dropout regularizations. All models are trained on the Montgomery and VinDR-CXR datasets with and without segmented ground-truth masks. To achieve model explainability, we integrate SHapley Additive exPlanations (SHAP) and Gradient-weighted Class Activation Mapping (Grad-CAM) techniques, which enable a better understanding of the decision-making process and provide visual explanations of critical regions within the CXR images. By employing ensembling, our outlier-resistant CX-Net achieves superior performance in lung segmentation, with Jaccard overlap similarity (JS) of 0.992, Dice coefficients (DC) of 0.994, precision (PPV) of 0.993, recall of 0.980, and accuracy of 0.976. The proposed approach demonstrates strong generalization capabilities on the VinDr-CXR dataset and is the first study to use these datasets for semantic lung segmentation with semi-supervised localization. In conclusion, this paper presents an explainable ensemble learning approach for lung segmentation and diagnosing lung disorders using CXR images. Extensive experimental results show that our method efficiently and accurately extracts regions of interest in CXR images from publicly available datasets, indicating its potential for integration into clinical decision support systems (CDSS). Furthermore, incorporating SHAP and Grad-CAM techniques further enhances the interpretability and trustworthiness of the AI-driven diagnostic system.

Semi-supervised labelling of chest x-ray images using unsupervised clustering for ground-truth generation

“…The thickness of each layer determines the features dimensionality. Our prior work [25] demonstrated the usefulness of such capabilities. Specifically, we define combination methods like majority voting and consensus voting for an ensemble of classifiers 𝐸𝑐, 𝑘 ξ {1, 2, 3, … 𝐾} where K is the total number of classifiers.…”

CRNN model for text detection and classification from natural scenes

“…We draw inspiration from Jaderberg et al [44], fine-tuning some hyperparameters to address the difficulties in Kannada text recognition. Equally, the framework for Kannada character recognition uses the VGG-16 [45], ResNet18 [46], and its various models, with a new proposed network comparable, but with skip connections. First, per-frame label sequence prediction is accomplished by layering a recurrent network with the feature extraction network, such as a BiLSTM, followed by a layer to map the predicted sequences to their final labels.…”

Energy-efficient deep Q-network: reinforcement learning for efficient routing protocol in wireless internet of things

“…A typical sensor has parts for power, sensing, processing, and communicating [7] [10]. While the power part supplies energy to others, the other parts use very little energy [11] [13]. This energy efficiency becomes paramount for devices deployed in challenging terrains and environment where frequent battery replacements or recharges are untenable [13], [14].…”

“…While the power part supplies energy to others, the other parts use very little energy [11] [13]. This energy efficiency becomes paramount for devices deployed in challenging terrains and environment where frequent battery replacements or recharges are untenable [13], [14]. It is a widely accepted notion that energy-efficient routing algorithms can judiciously control the power consumption, thereby helping prolong the network's operational longevity.…”