Login New user?  
Applied Mathematics & Information Sciences
An International Journal
               
 
 
 
 
 
 
 
 
 
 
 
 
 

Content
 

Volumes > Volume 17 > No. 5

 
   

Cloud Based Web-Application For Tuberculosis Detection Using Convolutional Neural Network(CNN)

PP: 1128-1139
doi:10.18576/amis/170567
Author(s)
A Kalaiyarsi, M Jayeskumar, V Jeevanantham, R Kiruthickraj, S Marimuthu,
Abstract
One of the top ten leading causes of death is tuberculosis (TB), a chronic lung disease brought on by a bacterial infection. Since TB can be life-threatening, accurate and prompt detection is critical. Using techniques like image preprocessing, data augmentation, image segmentation, and Support Vector classification, we were able to reliably identify TB from chest X-ray images in this study. For this study, a database of 1800TB infected and 3700 normal chest X-ray images was created using several public databases. Additionally, in order to improve accuracy, our work makes use of image enhancement techniques to improve the blurred image. The model is made accessible to the general public because the entire prediction is presented as a web-based user interface. For greater computing power, the entire model is hosted in the cloud. For tuberculosis detection using X-ray images, the best performing model, C hex Net, achieved 96.47% accuracy, precision, sensitivity, F1-score, and 96.51% specificity, respectively. The computer-aided, faster diagnosis of tuberculosis may benefit from the proposed method's cutting-edge performance.

  Home   About us   News   Journals   Conferences Contact us