INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Understanding lung disease and its
consequences is one of the best research in recent years.
Along with the many uses of medical images in hospitals,
pathologies and laboratories, the scope of medical image
data has also expanded to capture hospital disease.
Although a great deal of research has been done on this
particular topic, area is still confusing and complex. There
are many ways to classify medical images in the literature.
The main disadvantage of traditional processing is the
difference between low-level image information captured
by imaging equipment and high-level information seen by
humans. Respiratory diseases are also one of the leading
infectious diseases responsible for deaths in children under
the age of five. Early diagnosis is important in lung disease.
Many image processing and machine learning models have
been developed for this purpose. Different types of existing
deep learning methods were used for lung disease
predictions, including neural network (CNN), vanilla
neural network, group view geometry-based neural
network (VGG). Basic CNNs do not perform well in
rotated, tilted, or other different image orientations.
Therefore, we combine by, segmentation and data
augmentation with CNNs to propose a new hybrid deep
learning framework. The Lung X-ray was key in
diagnosing this disease. In this project, we use deep
learning as a combination of image segmentation and
feature merging. We use the U-NET architecture for the
segmentation model. We tried different pre-trained models
for classification. We also use image magnification
techniques to resolve inconsistencies and increase
generality in the dataset. In this project, we use deep
learning to identify respiratory diseases. We use image
segmentation to accurately quantify more than lung
regions, then we first extract maps from the CNN model,
then do the fusion and finally classify the information.
First, the segmentation is used to complete the image
segmentation, which will be divided into lung regions.
Feature Fusion is an algorithm that can combine separate
features into features for easy operation of features.
Keywords:
Segmentation, Feature Extraction, and Feature Fusion, Classification, UNet.
Cite Article:
"CLASSIFICATION OF RESPIRATORY DISORDERS USING SEGMENTATION, FEATURE EXTRACTION AND FEATURE FUSION OF X-RAY IMAGES", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 4, page no.e269-e275, April-2023, Available :http://www.ijnrd.org/papers/IJNRD2304436.pdf
Downloads:
000118760
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn