Pneumonia Detection Using Artificial Neural Networks and Transfer Learning Model
U. M. Prakash1, Hitarth Pandey2, Abhishek Suryavanshi3, K. R. Gokul Anand4
1U. M. Prakash, Department of CSE, SRM Institute Chennai (Tamil Nadu), India.
2Hitarth Pandey, Department of CSE, SRM Institute Chennai (Tamil Nadu), India.
3Abhishek Suryavanshi, Department of CSE, SRM Institute Chennai (Tamil Nadu), India.
Manuscript received on 02 July 2019 | Revised Manuscript received on 12 August 2019 | Manuscript Published on 27 August 2019 | PP: 149-151 | Volume-8 Issue-2S4 July 2019 | Retrieval Number: B10260782S419/2019©BEIESP | DOI: 10.35940/ijrte.B1026.0782S419
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Developing a system that helps in detecting pneumonia in chest x-ray images of lungs at a high accuracy. Firstly, a raw image is being preprocessed with the help of Otsu Thresholding and an equalizer. This helps in detecting pneumonia clouds and identifying the ratio of healthy lung region to the total region minimum. The above task is determined by importing the original chest x-ray images in the dataset and then calculating the ratio. The preprocessed data is then fed into Inception V3 model that accurately predicts the percentage of how much pneumonia is spread. This helps in identifying pneumonia present in that area and helps determining the prescribed drugs to help them clear off the symptoms.
Keywords: Otsu Thresholding, Transfer Learning, Inception V3, White Clouds, CNN.
Scope of the Article: Artificial Intelligence