Lung Segmentation-Based Pulmonary Disease Classification Using Deep Neural Networks

Zaidi, Syeda Zainab Yousuf; Akram, M. Usman; Jameel, Amina; Alghamdi, Norah Saleh

doi:10.1109/access.2021.3110904

Cited by 15 publications

(3 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4.1 Dataset description: In this study, two benchmark databases are considered which is briefly illustrated below. CXR data: The CXR dataset [17], which includes 112,120 frontal-view X-ray images of 30,805 patients with 14 thoracic pathologies, includes bacterial or viral diseases, chronic obstructive lung disease, and COVID-19 and non-Covid chest X-ray instances [ A quantitative performance is conducted to evaluate the efficiency of SLST-U-Net+EDEPLDP model by comparing with as CNN [7], E2E-DNN [12], LungNet22 [13], EfficientNet-SE [14], LDDNet [16] and EDepLDP [8] which are also implemented and tested using the above-considered datasets. Table 3 lists parameter settings for the proposed SLST-U-Net + EDEPLDP and existing models.…”

Section: Author Name(s) and Affiliation(s)mentioning

confidence: 99%

“…CNN is a common DL approach that trains clinical image structures and features to identify all disease types using improved clinical images [6]. For example, an automatic DL-based lung ailment detection model [7] has been developed to categorize healthy and infected CXR scans. The model utilizes manual lung masks to segment the lung area and a new CNN architecture with extra layers and tweaked hyper-parameters.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Semantic Location Aware Swin Transformer Based U-Net Model for Improving Lung Disease Prediction

2024

IJIES

View full text Add to dashboard Cite

Lung diseases have been a significant concern throughout history, necessitating early disease prediction using high-level knowledge. Deep Learning models have proven effective in diagnosing lung disorders using clinical imaging modalities like Computerized Tomography (CT) and Chest X-Ray (CXR) images. The Ensemble Deep Lung Disease Predictor (EDEPLDP) framework has been proposed for the rapid detection of various diseases using CT and CXR images. However, the U-Net model used for segmentation tasks lacks sufficient low-level localization abilities. To address this, a Semantic Location enhanced Swin Transformer-based U-Net (SLST-U-Net)+EDEPLDP model is proposed in this article. This model leverages Location Attention (LA) and De Mejora Progresiva (DMP) to enhance feature discrimination at the level of spatial information and semantic position. The Contextual Guidance Attention (CGA) method combines spatial and semantic information. The DMP enhances feature discrimination by increasing edge data inference and providing a richer depiction of the target position. The CGA reduces the semantic gap and effectively fuses spatial texture information and semantic information. The LA mechanism improves computational capacity for semantic features and precision of semantic position data, enabling retrieval of longrange contextual data in channel and geographic contexts. Additionally, Swin Transformer (ST) is added in the encoder and decoder section of U-net to increase the finer details of spatial and semantic information. Finally, the features extraction and classification part of EDEPLDP is employed to detect and classify the lung diseases. Experimental results revealed that the proposed SLST-U-Net+EDEPLDP model outperforms the CNN, E2E-DNN LungNet22, EfficientNet-SE, LDDNet and EDepLDP models with an accuracy of 94.94% and 95.42% on CXR and CT images, respectively.

show abstract

Section: Author Name(s) and Affiliation(s)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Semantic Location Aware Swin Transformer Based U-Net Model for Improving Lung Disease Prediction

2024

IJIES

View full text Add to dashboard Cite

show abstract

“…The limitation of the study is its lowered accuracy of 93% only. The work carried out by Zaidi et al [26] has used a tailored make CNN model to perform lung segmentation. The limitation of the study is its inclusion of a higher number of iterations in order to achieve below-average accuracy.…”

Section: Related Workmentioning

confidence: 99%

An Add-on CNN based Model for the Detection of Tuberculosis using Chest X-ray Images

Roopa¹,

Mamatha²

2023

IJACSA

View full text Add to dashboard Cite

MachineLearning has been potentially contributing towards smart diagnosis in the medical domain for more than a decade with a target towards achieving higher accuracy in detection and classification. However, from the perspective of medical image processing, the contribution of machine learning towards segmentation is not been much to find in recent times. The proposed study considers a use case of Tuberculosis detection and classification from chest x-rays where a unique machine learning approach of Convolution Neural Network is adopted for segmentation of lung images from CXR. A computational framework is developed that performs segmentation, feature extraction, detection, and classification. The proposed system's study outcome is analyzed with and without segmentation over existing machine learning models to exhibit 99.85% accuracy, which is the highest score to date in contrast to existing approaches found in the literature. The study outcome based on the comparative analysis exhibits the effectiveness of the proposed system.

show abstract

Anatomic boundary‐aware explanation for convolutional neural networks in diagnostic radiology

Yuan

2024

iRADIOLOGY

View full text Add to dashboard Cite

BackgroundConvolutional neural networks (CNN) have achieved remarkable success in medical image analysis. However, unlike some general‐domain tasks where model accuracy is paramount, medical applications demand both accuracy and explainability due to the high stakes affecting patients' lives. Based on model explanations, clinicians can evaluate the diagnostic decisions suggested by CNN. Nevertheless, prior explainable artificial intelligence methods treat medical image tasks akin to general vision tasks, following end‐to‐end paradigms to generate explanations and frequently overlooking crucial clinical domain knowledge.MethodsWe propose a plug‐and‐play module that explicitly integrates anatomic boundary information into the explanation process for CNN‐based thoracopathy classifiers. To generate the anatomic boundary of the lung parenchyma, we utilize a lung segmentation model developed on external public datasets and deploy it on the unseen target dataset to constrain model explanations within the lung parenchyma for the clinical task of thoracopathy classification.ResultsAssessed by the intersection over union and dice similarity coefficient between model‐extracted explanations and expert‐annotated lesion areas, our method consistently outperformed the baseline devoid of clinical domain knowledge in 71 out of 72 scenarios, encompassing 3 CNN architectures (VGG‐11, ResNet‐18, and AlexNet), 2 classification settings (binary and multi‐label), 3 explanation methods (Saliency Map, Grad‐CAM, and Integrated Gradients), and 4 co‐occurred thoracic diseases (Atelectasis, Fracture, Mass, and Pneumothorax).ConclusionsWe underscore the effectiveness of leveraging radiology knowledge in improving model explanations for CNN and envisage that it could inspire future efforts to integrate clinical domain knowledge into medical image analysis.

show abstract

Lung Segmentation-Based Pulmonary Disease Classification Using Deep Neural Networks

Cited by 15 publications

References 44 publications

Semantic Location Aware Swin Transformer Based U-Net Model for Improving Lung Disease Prediction

Semantic Location Aware Swin Transformer Based U-Net Model for Improving Lung Disease Prediction

An Add-on CNN based Model for the Detection of Tuberculosis using Chest X-ray Images

Anatomic boundary‐aware explanation for convolutional neural networks in diagnostic radiology

Contact Info

Product

Resources

About