Comparative performance analysis of Deep Convolutional Neural Network for Gastrointestinal Polyp Image Segmentation

Nisa, Syed Qamrun and Ismail, Amelia Ritahani (2021) Comparative performance analysis of Deep Convolutional Neural Network for Gastrointestinal Polyp Image Segmentation. International Journal of Innovative Science, Engineering & Technology, 8 (4). pp. 149-156. E-ISSN 2348–7968

PDF - Published Version Restricted to Repository staff only Download (220kB) | Request a copy

Abstract

Image segmentation is the most challenging and emerging field nowadays for medical image analysis. Polyp image segmentation is a difficult task due to the variations in the appearance and color intensity of the polyps in colonoscopy images. In this paper, we use a dataset of gastrointestinal polyp images for segmentation. The segmentation methods for gastrointestinal polyp images in this paper are based on three deep convolutional neural network models that are FCN, U-NET, and, hybrid Unet_Resnet. Data augmentation is applied to the dataset to increase the accuracy rate. The performance of the three models is evaluated by metrics that are Intersection of Union (IOU) and Dice Similarity Coefficient (DSC). The hybrid model, Unet_Resnet achieves higher IOU, and DSC of 0.75 and 0.86 respectively, which outperforms the other two models FCN and U-Net in gastrointestinal polyp image segmentation

Item Type:	Article (Journal)
Uncontrolled Keywords:	Images Segmentation, Gastrointestinal Polyp Images, Deep Convolutional Neural Network, IOU, DSC
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Information and Communication Technology Kulliyyah of Information and Communication Technology Kulliyyah of Information and Communication Technology > Department of Computer Science Kulliyyah of Information and Communication Technology > Department of Computer Science
Depositing User:	Amelia Ritahani Ismail
Date Deposited:	19 Nov 2021 09:59
Last Modified:	19 Nov 2021 09:59
URI:	http://irep.iium.edu.my/id/eprint/93868

Actions (login required)

View Item