Predicting Pulmonary Fibrosis Progression

Authors

  • Pranav Pradeep Student, Department of Information Science Engineering, Dayananda Sagar Academy of Technology and Management, Bangalore, India
  • H. S. Mansi Student, Department of Information Science Engineering, Dayananda Sagar Academy of Technology and Management, Bangalore, India
  • Likitha Keerthi Student, Department of Information Science Engineering, Dayananda Sagar Academy of Technology and Management, Bangalore, India
  • Dev Narayanan Student, Department of Information Science Engineering, Dayananda Sagar Academy of Technology and Management, Bangalore, India
  • K. A. Sumithra Devi Head of the Department, Department of Information Science Engineering, Dayananda Sagar Academy of Technology and Management, Bangalore, India

Keywords:

Convolutional Neural Network, Quantile regression, Relu, Adam optimizer

Abstract

Fibrosis is an incurable, fatal, and debilitating disease that damages the patient's respiratory system, making it difficult to live with. Modern medicine can help to postpone the disease's prognosis. The ability of the doctor to determine the severity of the sickness becomes critical for appropriate therapy, yet this is a highly risky decision. We will present how to use vital capacity (FVC) as a measure of lung condition to predict regression of idiopathic pulmonary fibrosis from CT images and tabular data characteristics. Features Combines the features of quantile regression extracted from a convolutional neural network to predict a decline in FCV values. We have also developed a web-based application that allows pulmonologists to enter data, retrieve results, and distribute reports.

Downloads

Download data is not yet available.

Downloads

Published

02-07-2022

How to Cite

[1]
P. Pradeep, H. S. Mansi, L. Keerthi, D. Narayanan, and K. A. S. Devi, “Predicting Pulmonary Fibrosis Progression”, IJRESM, vol. 5, no. 6, pp. 306–308, Jul. 2022.

Issue

Section

Articles