Open Access Open Access  Restricted Access Subscription Access

Deep Learning-based Lung Disease Prediction and Management System

P J Joseph, Mridula P T, Jagath K, K K Krishnanjana Deepak, Suvarna V M

Abstract


Lung diseases such as pneumonia and COVID-19 pose significant challenges to global healthcare, requiring early detection and effective management to improve patient results. This paper presents PulmoXpert, a deep learning-based web application for the automated prediction and management of lung diseases, using chest radiograph images (CXR). This system employs an ensemble of Convolutional Neural Networks (CNNs) including VGG-16, DensNet-201 and EfficientNet-B0, to improve diagnostic accuracy [1],[3]. Advanceddata preprocessing tech- niques, such as histogram equalization, and Gaussian filtering to improve image quality, while data growth reduces class imbalance and enhance model generalization [4],[5].

The platform also has a healthcare chatbot operated by Nat- ural Language Processing (NLP), which allows real-time inter- action and personal health recommendations. Safe health record management and a user-friendly interface enables individuals to monitor their lung health. The proposed system is evaluated using standard performance metrics—including precision, accuracy, recall, and F1-score—demonstrating higher clinical reliability compared to individual deep learning models [6]. Future work involves expanding datasets, optimizing model for real-time clinical use and integrating additional imaging methods. This study highlights the ability of AI-managing solutions in detecting lung disease and bringing revolution in the patient’s care.


Full Text:

PDF

References


A. Elhanashi, S. Saponara, and Q. Zheng, ”Classification and Localiza- tion of Multi-Type Abnormalities on Chest X-Rays Images,” in IEEE Access, vol. 11, pp. 83264-83277, 2023.

A. Hussain, S. U. Amin, H. Lee, A. Khan, N. F. Khan, and S. Seo, ”An Automated Chest X-Ray Image Analysis for Covid-19 and Pneumonia Diagnosis Using Deep Ensemble Strategy,” in IEEE Access, vol. 11, pp. 97207-97220, 2023, doi: 10.1109/ACCESS.2023.3312533.

M. Irtaza, A. Ali, M. Gulzar, and A. Wali, ”Multi-Label Classification of Lung Diseases Using Deep Learning,” in IEEE Access, vol. 12, pp. 124062-124080, 2024, doi: 10.1109/ACCESS.2024.3454537.

H. Malik, T. Anees, M. U. Chaudhry, R. Gono, M. Jasin´ski, Z. Leonowicz, and P. Bernat, ”A Novel Fusion Model of Hand-Crafted Features With Deep Convolutional Neural Networks for Classification of Several Chest Diseases Using X-Ray Images,” in IEEE Access, vol. 11, pp. 39243-39268, 2023, doi: 10.1109/ACCESS.2023.3267492.

M. Ali, M. Shahroz, U. Akram, M. F. Mushtaq, S. C. Altamiranda,

S. A. Obregon, I. D. L. Torre, and I. Ashraf, ”Pneumonia Detec- tion Using Chest Radiographs With Novel EfficientNetV2L Model,” in IEEE Access, vol. 12, pp. 34691-34707, 2024, doi: 10.1109/AC- CESS.2024.3372588.

H. C. Shin, H. R. Roth, M. Gao, L. Lu, Z. Xu, I. Nogues, J. Yao, D. Mollura, and R. M. Summers, ”Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning,” IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1285–1298, May 2016, doi: 10.1109/TMI.2016.2528162.

X. Wang, Y. Peng, L. Lu, Z. Lu, M. Bagheri, and R. M. Summers, ”ChestX-ray8: Hospital-Scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases,” in Proceedings of the IEEE Conference on Computer Vi- sion and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017, pp. 3462–3471, doi: 10.1109/CVPR.2017.369.

K. Yan, X. Wang, L. Lu, and R. M. Summers, ”DeepLesion: Automated Mining of Large-Scale Lesion Annotations and Universal Lesion Detec- tion with Deep Learning,” Journal of Medical Imaging, vol. 5, no. 3, pp. 1–11, Jul. 2018, doi: 10.1117/1.JMI.5.3.036501.

P. Rajpurkar, J. Irvin, K. Zhu, B. Yang, H. Mehta, T. Duan, D. Ding,

A. Bagul, C. Langlotz, K. Shpanskaya, M. P. Lungren, and A. Y. Ng, ”CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning,” arXiv preprint arXiv:1711.05225, Nov. 2017.

M. G. Myronenko, ”3D MRI Brain Tumor Segmentation Using Au- toencoder Regularization,” in Proceedings of the International MIC- CAI Brainlesion Workshop, Granada, Spain, 2018, pp. 311–320, doi: 10.1007/978-3-030-11723-828.


Refbacks

  • There are currently no refbacks.