Authors :
Harshkumar Modi; Shashwat Misra; Shashwat Gaur
Volume/Issue :
Volume 6 - 2021, Issue 7 - July
Google Scholar :
http://bitly.ws/9nMw
Scribd :
https://bit.ly/3lbb1j4
Abstract :
Wireless capsule endoscopy (WCE) is proving
to an extremely beneficial method for perceiving ailments
inside of human gastric pathway. Through WCE Doctors
identify the diverse irregularities like chronic diarrhoea,
ulcer, bleeding, polyps, cancer/tumour in small intestine
and Crohn's disease, any of it in the gastrointestinal tract
that is invasive. It is a method that used a pill-size
wireless camera to get visual data of the digestive tract of
a human body. It is a method that helps doctor to see
inside your intestine, an area which is normally difficult to
reach to through standard endoscopy procedure or
imaging methods. Scholars are finding new ways to
progress and enhance the metrics of performance of WCE
using models that detect these ailments at a quicker rate
of improvement, on their own. With datasets produced
from this dataset are imporving with better technology
and imaging services, machine learning grants us an
opportunity to diagonis and get better insights from this
data. Utilizing these methods, we propose a system to
train and predict 13 classes of anomalies inside the
digestive tract. The proposed model has achieved an
accuracy of 97.82%
Keywords :
Wireless Capsule Endoscopy, Machine Learning, Digestive Tract
Wireless capsule endoscopy (WCE) is proving
to an extremely beneficial method for perceiving ailments
inside of human gastric pathway. Through WCE Doctors
identify the diverse irregularities like chronic diarrhoea,
ulcer, bleeding, polyps, cancer/tumour in small intestine
and Crohn's disease, any of it in the gastrointestinal tract
that is invasive. It is a method that used a pill-size
wireless camera to get visual data of the digestive tract of
a human body. It is a method that helps doctor to see
inside your intestine, an area which is normally difficult to
reach to through standard endoscopy procedure or
imaging methods. Scholars are finding new ways to
progress and enhance the metrics of performance of WCE
using models that detect these ailments at a quicker rate
of improvement, on their own. With datasets produced
from this dataset are imporving with better technology
and imaging services, machine learning grants us an
opportunity to diagonis and get better insights from this
data. Utilizing these methods, we propose a system to
train and predict 13 classes of anomalies inside the
digestive tract. The proposed model has achieved an
accuracy of 97.82%
Keywords :
Wireless Capsule Endoscopy, Machine Learning, Digestive Tract
