PMID- 37954444
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20231122
IS  - 1664-042X (Print)
IS  - 1664-042X (Electronic)
IS  - 1664-042X (Linking)
VI  - 14
DP  - 2023
TI  - DRI-Net: segmentation of polyp in colonoscopy images using dense 
      residual-inception network.
PG  - 1290820
LID - 10.3389/fphys.2023.1290820 [doi]
LID - 1290820
AB  - Colorectal cancer is a common malignant tumor in the gastrointestinal tract, 
      which usually evolves from adenomatous polyps. However, due to the similarity in 
      color between polyps and their surrounding tissues in colonoscopy images, and 
      their diversity in size, shape, and texture, intelligent diagnosis still remains 
      great challenges. For this reason, we present a novel dense residual-inception 
      network (DRI-Net) which utilizes U-Net as the backbone. Firstly, in order to 
      increase the width of the network, a modified residual-inception block is 
      designed to replace the traditional convolutional, thereby improving its capacity 
      and expressiveness. Moreover, the dense connection scheme is adopted to increase 
      the network depth so that more complex feature inputs can be fitted. Finally, an 
      improved down-sampling module is built to reduce the loss of image feature 
      information. For fair comparison, we validated all method on the Kvasir-SEG 
      dataset using three popular evaluation metrics. Experimental results consistently 
      illustrates that the values of DRI-Net on IoU, Mcc and Dice attain 77.72%, 85.94% 
      and 86.51%, which were 1.41%, 0.66% and 0.75% higher than the suboptimal model. 
      Similarly, through ablation studies, it also demonstrated the effectiveness of 
      our approach in colorectal semantic segmentation.
CI  - Copyright (c) 2023 Lan, Chen and Jin.
FAU - Lan, Xiaoke
AU  - Lan X
AD  - College of Internet of Things Technology, Hangzhou Polytechnic, Hangzhou, China.
FAU - Chen, Honghuan
AU  - Chen H
AD  - College of Internet of Things Technology, Hangzhou Polytechnic, Hangzhou, China.
FAU - Jin, Wenbing
AU  - Jin W
AD  - College of Internet of Things Technology, Hangzhou Polytechnic, Hangzhou, China.
LA  - eng
PT  - Journal Article
DEP - 20231025
PL  - Switzerland
TA  - Front Physiol
JT  - Frontiers in physiology
JID - 101549006
PMC - PMC10634602
OTO - NOTNLM
OT  - colonoscopy
OT  - dense
OT  - down-sampling
OT  - image segmentation
OT  - residual-inception
COIS- The authors declare that the research was conducted in the absence of any 
      commercial or financial relationships that could be construed as a potential 
      conflict of interest.
EDAT- 2023/11/13 06:42
MHDA- 2023/11/13 06:43
PMCR- 2023/10/25
CRDT- 2023/11/13 04:30
PHST- 2023/09/08 00:00 [received]
PHST- 2023/10/04 00:00 [accepted]
PHST- 2023/11/13 06:43 [medline]
PHST- 2023/11/13 06:42 [pubmed]
PHST- 2023/11/13 04:30 [entrez]
PHST- 2023/10/25 00:00 [pmc-release]
AID - 1290820 [pii]
AID - 10.3389/fphys.2023.1290820 [doi]
PST - epublish
SO  - Front Physiol. 2023 Oct 25;14:1290820. doi: 10.3389/fphys.2023.1290820. 
      eCollection 2023.