Pleural Effusion Classification Based on Chest X-Ray Images using Convolutional Neural Network

Fauzan, Ahmad Rafiansyah; Wahyuddin, Mohammad Iwan; Ningsih, Sari

doi:10.21609/jiki.v14i1.898

Cited by 4 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These images are stored in PNG format and possess a matrix size of either 4020 x 4892 or 4892 x 4020 pixels. Notably, the pixel spacing is consistent at 0.0875 mm in both vertical and horizontal directions, and the images are encoded with 12 bits of gray levels [23].…”

Section: Literature Reviewmentioning

confidence: 99%

Transformative Approach for Prediction of Lung Disease Using Lung X-ray Images

Mehra,

Singh,

Kumar

et al. 2024

Preprint

View full text Add to dashboard Cite

Lung diseases pose a significant global health challenge, underscoring the critical need for prompt and precise diagnoses to facilitate effective treatments and enhance patient outcomes. In this research paper, we introduce an innovative method for the prediction of lung diseases by harnessing the capabilities of deep learning techniques, thereby streamlining and augmenting the diagnostic process. The Investigation commences by assembling an extensive dataset of chest Xray images sourced from diverse origins, encompassing both normal and diseased instances. Subsequently, we employ a specialized Pix2Pix Generative Adversarial Network architecture tailored for image classification. This network is meticulously trained on the comprehensive dataset, fine-tuning its abilities to discern distinctive features associated with a range of lung diseases, including pneumonia, tuberculosis, and lung cancer. The Empirical findings underscore the efficacy of the approach in diagnosing lung diseases, showcasing notable levels of accuracy, sensitivity, and specificity. Furthermore, we employ interpretability techniques to pinpoint the regions within the X-ray images that significantly contribute to the predictions, bolstering the transparency and credibility of the Model. This research presents a promising avenue for automating the diagnosis of lung diseases, with the potential to reduce human error and enhance patient care significantly. It holds the promise of aiding in early detection and intervention, potentially saving lives and alleviating the burden of lung diseases on healthcare systems worldwide. The integration of DenseNet architecture into our predictive model significantly enhances the accuracy and efficiency of diagnosing lung diseases from X-ray images. DenseNet’s interconnected layers facilitate collaborative learning, enabling the model to discern intricate details crucial for precise classifications. The adoption of DenseNet not only amplifies diagnostic precision but also paves the way for future strides in medical image analysis, particularly in advancing respiratory health diagnostics. Along with this under the investigation comprising the chest X-ray images in JPEG format, it is systematically categorized into train, test, and val directories, each further subdivided into folders representing Pneumonia and Normal classes. These images depict anterior-posterior chest radiographs obtained from pediatric patients aged one to five years at the Guangzhou Women and Children’s Medical Center, forming an integral part of routine clinical care for this specific demographic. To ensure the dataset’s integrity, a rigorous initial screening process is applied to exclude any low-quality or unreadable scans. Subsequently, two expert physicians meticulously evaluate and grade the diagnostic quality of the remaining images. Only those that successfully pass this comprehensive scrutiny are deemed suitable for the subsequent training of the artificial intelligence system. This meticulous curation underscores the reliability and high quality of the dataset, emphasizing its potential for advancing medical image analysis within the context of pediatric chest radiographs.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Transformative Approach for Prediction of Lung Disease Using Lung X-ray Images

Mehra,

Singh,

Kumar

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Atelectasis, Consolidation, Edema, Effusion, Emphysema, Fibrosis, Infiltration, and Mass are among the 10 lung disorders included in the dataset. In the study [ 41 ], the authors provide a CNN-based model for automatically detecting pleural effusion in chest X-rays. The research relies on X-ray scans of patients with pleural effusion and those in a healthy state.…”

Section: Literature Reviewmentioning

confidence: 99%

LungNet22: A Fine-Tuned Model for Multiclass Classification and Prediction of Lung Disease Using X-ray Images

Shamrat

Azam

Karim

et al. 2022

JPM

View full text Add to dashboard Cite

In recent years, lung disease has increased manyfold, causing millions of casualties annually. To combat the crisis, an efficient, reliable, and affordable lung disease diagnosis technique has become indispensable. In this study, a multiclass classification of lung disease from frontal chest X-ray imaging using a fine-tuned CNN model is proposed. The classification is conducted on 10 disease classes of the lungs, namely COVID-19, Effusion, Tuberculosis, Pneumonia, Lung Opacity, Mass, Nodule, Pneumothorax, and Pulmonary Fibrosis, along with the Normal class. The dataset is a collective dataset gathered from multiple sources. After pre-processing and balancing the dataset with eight augmentation techniques, a total of 80,000 X-ray images were fed to the model for classification purposes. Initially, eight pre-trained CNN models, AlexNet, GoogLeNet, InceptionV3, MobileNetV2, VGG16, ResNet 50, DenseNet121, and EfficientNetB7, were employed on the dataset. Among these, the VGG16 achieved the highest accuracy at 92.95%. To further improve the classification accuracy, LungNet22 was constructed upon the primary structure of the VGG16 model. An ablation study was used in the work to determine the different hyper-parameters. Using the Adam Optimizer, the proposed model achieved a commendable accuracy of 98.89%. To verify the performance of the model, several performance matrices, including the ROC curve and the AUC values, were computed as well.

show abstract

“…al., 2019): ........................... (8)Fully connected adalah lapisan terakhir pada CNN, yang berfungsi melakukan klasifikasi berdasarkan jumlah fitur yang dihasilkan pada perhitungan lapisan sebelumnya. Fungsi aktivasi pada lapisan fully connected adalah fungsi softmax(Fauzan et al, 2021). Fungsi softmax digunakan untuk mengurangi nilai error dari fungsi cross-entropy.…”

unclassified

“…Crossentropy digunakan untuk menyelesaikan permaslahan klasifikasi. Misalkan e adalah lapisan fully connected dengan jumlah fitur masukan maka lapisan e pada unit ke-i akan menghitung , dihitung menggunakan persamaan berikut(Rokhana et al, 2019 ;Fauzan et al, 2021):c ... (9) dengan menunjukkan bobot yang menghubungkan unit ke-j pada posisi (r,s) pada lapisan ( ) dan unit ke-i pada lapisan e.…”

unclassified

Klasifikasi Tiga Genus Ikan Karang Menggunakan Convolution Neural Network

Ariawan¹

2022

J. Ilmu dan Teknologi Kelautan Tropis

View full text Add to dashboard Cite

Ikan karang adalah salah satu organisme penting dalam kajian ekosistem terumbu karang, perlu dilakukan proses identifikasi untuk memahami pola, struktur dan distribusi keanekaragaman ikan karang. Selain itu, ikan karang memiliki jumlah yang sangat banyak dan hampir mirip satu sama lain. Oleh karena itu, untuk mempercepat proses identifikasi ikan dapat dilakukan secara komputerisasi. Salah satu teknik komputerisasi yang dapat dilakukan adalah pengolahan citra digital. Penelitian ini bertujuan untuk mengklasifikasikan citra genus Ikan (Epinephelus spp., Halichoeres spp., dan Lutjanus spp.) ekonomis penting. Data citra diperoleh dari situs https://www.kaggle.com/. Metode klasifikasi citra yang digunakan adalah Convolutional Neural Network (CNN) yang terdiri dari dua tahapan. Tahapan yang pertama adalah melakukan pelatihan dengan metode backpropagation, dan tahapan yang kedua adalah melakukan klasifikasi citra menggunakan feedforward. Hasil dari kombinasi dua metode tersebut diperoleh accuracy sebesar 85,31%. Selain itu, model yang dibangun cukup bagus karena selisih nilai rataan antara precision dan sensitivity tidak terlalu besar, precision sebesar 89,92% dan sensitivity sebesar 86,49%. Hasil analisis dan evaluasi yang telah dilakukan, dapat disimpulkan bahwa metode klasifikasi CNN dapat digunakan dengan baik dalam mengelompokkan citra Ikan berdasarkan genus.

show abstract

Pleural Effusion Classification Based on Chest X-Ray Images using Convolutional Neural Network

Cited by 4 publications

References 11 publications

Transformative Approach for Prediction of Lung Disease Using Lung X-ray Images

Transformative Approach for Prediction of Lung Disease Using Lung X-ray Images

LungNet22: A Fine-Tuned Model for Multiclass Classification and Prediction of Lung Disease Using X-ray Images

Klasifikasi Tiga Genus Ikan Karang Menggunakan Convolution Neural Network

Contact Info

Product

Resources

About