Search

Bronchiectasis in children is a major health issue which can be life-threatening if not diagnosed and effectively treated. In the diagnosis of bronchiectasis, an increased broncho-arterial (BA) ratio is considered a significant marker. The BA ratio is measured by evaluating BA pairs, using high-resolution computed tomography (HRCT) scans. Detecting BA pairs automatically is challenging due to the complex characteristics of BA pairs and the ambiguous appearance of the bronchi. This study proposes an effective computerized approach to detect BA pairs and assess BA ratio using HRCT scans of children and employing computer-aided techniques and novel custom-build algorithms. Attention is given to reconstructing broken bronchial walls and identifying discrete BA pairs using custom-built kernel based and patch-based algorithms for pixel-level image analysis. To detect BA pairs, the lung region is segmented in the HRCT slices and image preprocessing techniques, including noise reduction, binarizing, largest contour detection and a hole-filling algorithm, are applied. A histogram analysis method is introduced to clean the images. A kernel-based algorithm is proposed to reconstruct the pixel distribution if the bronchial wall is so that the bronchi can be detected precisely. Potential arteries are detected using balanced histogram thresholding, morphological opening and an approach based on four conditions related to the object area circularity, rectangular boundary box ratio and enclosing circle area ratio. Potential bronchi are detected through matching of object coordinates with potential arteries, hole-filling and four condition based approaches. The potential BA pairs are detected by matching the coordinates of potential bronchi with those of potential arteries as the artery and bronchus are adjacent to each other in BA pairs. Finally, from the potential BA pairs, actual BA pairs are identified using a custom-built patch algorithm. The study is conducted using 2471 HRCT slices of seven children, obtained from the Royal Darwin Hospital, Australia. The BA ratio is derived based on the ratio of diameters, major axis lengths, minor axis lengths, area, convex hull and equivalent diameter where the BA ratios are respectively 0.51–0.65, 0.49–0.59, 0.59–0.77, 0.25–0.42, 0.29–0.47, 1.5–2 and 0.50–0.65.

Convolutional neural networks (CNNs) have been established for a comprehensive range of computer vision problems across several benchmarks. Visualization and analysis of feature maps generated by convolutional layers can be an effective approach to explore the hidden and complex characteristic of a CNN model. Convolutional layers provide diverse feature maps however, the extent of this diversity needs to be explored. This research attempts to provide five insights of the ‘Black box’ mechanism of CNNs, using skin cancer dermoscopy and lung scan computed tomography (CT) Scan datasets by statistically analyzing layer by layer (three convolutional layers) feature maps using 17 geometrical and 6 intensity-based features to determine the characteristics and level of diversity. Significance and difference of the feature maps layer by layer, black feature maps analysis, difference of the feature maps to each other and to the original image, variations among the feature maps when running the model multiple times and inter-class variation among the feature maps for different iteration are explored. Various statistical methods including T-test, analysis of variance (ANOVA), mean, median, mean squared error (MSE), peak signal to noise ratio (PSNR), structural similarity index (SSIM), root mean squared error (RMSE), dice similarity score (DSC), universal image quality index (UQI) and Spectral angle mapper (SAM) are employed. Experimental results show that for the skin cancer dermoscopy dataset, a large number of black feature maps are produced (20–60%) while the proportion of black feature maps for the CT Scan dataset is comparatively low (2–20%). This demonstrates that for different datasets, feature maps with diverse characteristics can be produced. The layer by layer differences between the feature maps is evaluated using T-tests and ANOVA for seventeen geometrical features and six intensity-based features. For both datasets across most of the geometrical features and across most of the intensity-based features a significant diversity can be observed. The difference of the feature maps to each other and to the original image is quite high, with MSE values for the dermoscopy and CT Scan datasets in the range of 1860–31,399 and 171–6089, respectively, PSNR 3–15 and 10–25, SSIM values of 0.01–0.84 and 0.3–0.81, RMSE values of 0.81–1 and 0.21–1, DSC values of 0.37–0.53 and 0.47–0.75, UQI values of 0.02–0.86 and 0.01–0.88 and SAM values of 0.12–1.53 and 0.19–1.55 for the dermoscopy and CT Scan datasets respectively. When running the model multiple times (three iterations), a notable iteration by iteration diversity is found in terms of mean, median, maximum and minimum values for most of the geometrical features. The inter-class variation among the feature maps for different iterations and layers are evaluated based on the F-value of the ANOVA test. For the dermoscopy dataset, the highest mean F-value is found for layer 1 and iteration 3 while for the CT scan dataset the highest mean F-value is found for layer 3 and iteration 3 indicating that for these feature maps the highest inter-class dissimilarity is generated. The findings of this study may aid in exploring the complex mechanism of convolutional layers, kernels and feature maps.

Early identification and adequate treatment can help prevent lung disorders from becoming chronic, severe, and life-threatening. X-ray images are commonly used and an automated and effective method involving deep learning techniques can potentially contribute to quick and accurate diagnosis of lung disorders. However, in the study of medical imaging using deep learning, two obstacles limit interpretability. One is an insufficient and imbalanced number of training samples in most medical datasets. The other is excessive training time. Although training time can be reduced by decreasing the number of pixels in the images, training with low resolution images tends to result in poor performance. This study represents a solution to overcome these impediments by balancing the number of images and reducing overall processing time while preserving accuracy. The dataset used in this research contains an unequal number of images in the different classes. The quantity of data in the classes is balanced by creating synthetic images based on the patterns and characteristics of the original images, using a Deep Convolutional Generative Adversarial Network (DCGAN). Unwanted regions are removed from the X-ray images, the brightness and contrast of the images are enhanced, and the abnormalities are highlighted by using different artifact removal, noise reduction, and enhancement techniques. We propose a Modified Compact Convolutional Transformer (MCCT) model using 32 × 32 sized images for the categorization of lung disorders into four classes. An ablation study of eleven cases is employed to adjust several hyper parameters and layer topologies. This reduces training time while preserving accuracy. Six transfer learning models, VGG19, VGG16, ResNet152, ResNet50, ResNet50V2, and MobileNet are applied with the same image size the performance is compared with the proposed MCCT model. Our MCCT model records the greatest test accuracy of 95.37%, requiring a short training time, 10-12 s/epoch, whereas the other models only reach near-moderate performance with accuracies ranging from 43% to 79% and training times of 80-90 s/epoch. The robustness of the model with regards to the number of training samples is validated by training the model multiple times reducing the number of training images gradually from 49621 images to 6204 images. Results suggest that even with a smaller dataset, the performance is sustained. Our proposed approach may contribute to an effective CAD based diagnostic system by addressing the issues of insufficient and imbalanced numbers of medical images, excessive training times and low-resolution images.