Automated polyp segmentation in colonoscopy frames using fully convolutional neural network and textons

Zhang, Lei and Dolwani, Sunil and Ye, Xujiong (2017) Automated polyp segmentation in colonoscopy frames using fully convolutional neural network and textons. In: Medical Image Understanding and Analysis (Proceedings). Springer, Cham, pp. 707-717. ISBN 9783319609638, 9783319609645

Full content URL: https://link.springer.com/chapter/10.1007/978-3-31...

Documents
Automated Polyp Segmentation in Colonoscopy Frames Using Fully Convolutional Neural Network and Textons.pdf

Request a copy
[img] PDF
Automated Polyp Segmentation in Colonoscopy Frames Using Fully Convolutional Neural Network and Textons.pdf - Chapter
Restricted to Repository staff only

1MB
Item Type:Book Section
Item Status:Live Archive

Abstract

In this paper, we presented a novel hybrid classification based method for fully automated polyp segmentation in colonoscopy video frames. It contains two main steps: initial region proposals generation and regions refinement. Both machine learned features and hand crafted features are taken into account for polyp segmentation. More specifically, the hierarchical features of polyps are learned by fully convolutional neural network (FCN), while the context in-formation related to the polyp boundaries is modeled by texton patch represen-tation. The FCN provides pixel-wise prediction and initial polyp region candi-dates. Those candidates are further refined by patch-wise classification using texton based spatial features and a random forest classifier. The segmentation results are evaluated on a publicly available CVC-ColonDB database. On aver-age, our method achieves 97.54% of accuracy, 75.66% of sensitivity, 98.81% of specificity and DICE of 0.70%. The fast execution time (0.16 sec/frame) demonstrates the promise of our method to be used in real-time clinical colono-scopic examination.

Additional Information:21st Annual Conference, MIUA 2017, Edinburgh, UK, July 11–13, 2017, Proceedings
Keywords:Optical colonoscopy, Polyp segmentation, Fully convolutional neural network (FCN), Textons, Random forest classifier
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
Divisions:College of Science > School of Computer Science
ID Code:28050
Deposited On:28 Jul 2017 11:03

Repository Staff Only: item control page