PolypSegNet: A modified encoder-decoder architecture for automated polyp segmentation from colonoscopy images

Colorectal cancer has become one of the major causes of death throughout the world. Early detection of Polyp, an early symptom of colorectal cancer, can increase the survival rate to 90%. Segmentation of Polyp regions from colonoscopy images can facilitate the faster diagnosis. Due to varying sizes,...

Full description

Saved in:
Bibliographic Details
Published in:Computers in biology and medicine Vol. 128; p. 104119
Main Authors: Mahmud, Tanvir, Paul, Bishmoy, Fattah, Shaikh Anowarul
Format: Journal Article
Language:English
Published: United States Elsevier Ltd 01.01.2021
Elsevier Limited
Subjects:
Architecture
Artificial neural networks
Automation
Cancer
Coders
Colonoscopy
Colorectal cancer
Colorectal carcinoma
Computer architecture
Computer-aided diagnosis
Diagnosis
Diagnostic systems
Encoders-Decoders
Feature maps
Image processing
Image segmentation
Internal Medicine
Medical diagnosis
Medical imaging
Modules
Neural network
Neural networks
Other
Polyp segmentation
Polyps
Reconstruction
Semantics
Neural network
Colonoscopy
Polyp segmentation
Computer-aided diagnosis
Colorectal cancer
colorectal cancer
computer-aided diagnosis
colonoscopy
neural network
ISSN:0010-4825, 1879-0534, 1879-0534
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Colorectal cancer has become one of the major causes of death throughout the world. Early detection of Polyp, an early symptom of colorectal cancer, can increase the survival rate to 90%. Segmentation of Polyp regions from colonoscopy images can facilitate the faster diagnosis. Due to varying sizes, shapes, and textures of polyps with subtle visible differences with the background, automated segmentation of polyps still poses a major challenge towards traditional diagnostic methods. Conventional Unet architecture and some of its variants have gained much popularity for its automated segmentation though having several architectural limitations that result in sub-optimal performance. In this paper, an encoder-decoder based modified deep neural network architecture is proposed, named as PolypSegNet, to overcome several limitations of traditional architectures for very precise automated segmentation of polyp regions from colonoscopy images. For achieving more generalized representation at each scale of both the encoder and decoder module, several sequential depth dilated inception (DDI) blocks are integrated into each unit layer for aggregating features from different receptive areas utilizing depthwise dilated convolutions. Different scales of contextual information from all encoder unit layers pass through the proposed deep fusion skip module (DFSM) to generate skip interconnection with each decoder layer rather than separately connecting different levels of encoder and decoder. For more efficient reconstruction in the decoder module, multi-scale decoded feature maps generated at various levels of the decoder are jointly optimized in the proposed deep reconstruction module (DRM) instead of only considering the decoded feature map from final decoder layer. Extensive experimentations on four publicly available databases provide very satisfactory performance with mean five-fold cross-validation dice scores of 91.52% in CVC-ClinicDB database, 92.8% in CVC-ColonDB database, 88.72% in Kvasir-SEG database, and 84.79% in ETIS-Larib database. The proposed network provides very accurate segmented polyp regions that will expedite the diagnosis of polyps even in challenging conditions. [Display omitted] •A highly efficient, novel deep neural network architecture is proposed for very precise Polyp segmentation.•Some major architectural limitations of conventional Unet architecture are determined.•Three basic building blocks are proposed for achieving optimum performances with increased efficiency.•A modified Focal Tversky Loss (MFTL) function is introduced for reducing false positives with better generalization in challenging conditions.•New state-of-the-art performances are achieved on four publicly available datasets.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0010-4825
1879-0534
1879-0534
DOI:10.1016/j.compbiomed.2020.104119