Deep Learning-Based Assessment of ILD Designs in HRCT Pictures

The main objective of this work is to develop a screening tool that can identify distinct ILD patterns in HRCT scans automatically. ILD is the term for a collection of lung conditions that impact the lung's surrounding tissue and air sacs. Interstitial lung disease, or ILD for short, is a colle...

Full description

Saved in:
Bibliographic Details
Published in:2024 Second International Conference on Intelligent Cyber Physical Systems and Internet of Things (ICoICI) pp. 738 - 741
Main Authors: A, Balamanikandan, M, Sukanya, M, Dhanalakshmi, M, Vimala, N, Arul, Yatm, Narayana Reddy
Format: Conference Proceeding
Language:English
Published: IEEE 28.08.2024
Subjects:
Atmospheric modeling
Classification algorithms
Computational modeling
Computed tomography
Convolutional neural networks
Deep learning
High-resolution computed tomography (HRCT)
Interstitial lung disease (ILD)
Lung
Lung cancer
Pattern recognition
Prediction algorithms
Residual neural networks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The main objective of this work is to develop a screening tool that can identify distinct ILD patterns in HRCT scans automatically. ILD is the term for a collection of lung conditions that impact the lung's surrounding tissue and air sacs. Interstitial lung disease, or ILD for short, is a collective term for a range of lung conditions affecting the tissue and surrounding lung air sacs. High-resolution computed tomography, or HRCT, is a kind of imaging method that creates finely detailed images of the lungs. A novel deep learning model that can recognise and categorise various ILD patterns from HRCT pictures is proposed in this research. Several parts make up the model, including a fully convolutional network, a sparse stack autoencoder and decoder, an edge depth CNN, and a dilated convolution. The proposed model's performance is also contrasted with those of other models that are currently in use, including ResNet50, VGG16, and VGG19.
DOI:10.1109/ICoICI62503.2024.10696385