Early gastric cancer segmentation in gastroscopic images using a co-spatial attention and channel attention based triple-branch ResUnet
Copyright © 2023 Elsevier B.V. All rights reserved..
BACKGROUND AND OBJECTIVE: The artificial segmentation of early gastric cancer (EGC) lesions in gastroscopic images remains a challenging task due to reasons including the diversity of mucosal features, irregular edges of EGC lesions and nuances between EGC lesions and healthy background mucosa. Hence, this study proposed an automatic segmentation framework: co-spatial attention and channel attention based triple-branch ResUnet (CSA-CA-TB-ResUnet) to achieve accurate segmentation of EGC lesions for aiding clinical diagnosis and treatment.
METHODS: The input gastroscopic image sequences of the triple-branch segmentation network CSA-CA-TB-ResUnet is firstly generated by the designed multi-branch input preprocessing (MBIP) module in order to fully utilize massive correlation information among multiple gastroscopic images of the same a lesion. Then, the proposed CSA-CA-TB-ResUnet performs the segmentation of EGC lesion, in which the co-spatial attention (CSA) mechanism is designed to activate the spatial location of EGC lesions by leveraging on the correlations among multiple gastroscopic images of the same EGC lesion, and the channel attention (CA) mechanism is introduced to extract subtle discriminative features of EGC lesions by capturing the interdependencies between channel features. Finally, two gastroscopic images datasets from different digestive endoscopic centers in the southwest and northeast regions of China respectively were collected to validate the performances of proposed segmentation method.
RESULTS: The correlation information among gastroscopic images was confirmed to be able to improve the accuracy of EGC segmentation. On another unseen dataset, our EGC segmentation method achieves Jaccard similarity index (JSI) of 84.54% (95% confidence interval (CI), 83.49%-85.56%), threshold Jaccard index (TJI) of 81.73% (95% CI, 79.70%-83.61%), Dice similarity coefficient (DSC) of 91.08% (95% CI, 90.40%-91.76%) and pixel-wise accuracy (PA) of 91.18% (95% CI, 90.43%-91.87%), which is superior to other state-of-the-art methods. Even on the challenging small lesions, the segmentation results of our CSA-CA-TB-ResUnet-based method are consistently and significantly better than other state-of-the-art methods. We also compared the segmentation result of our model with the diagnostic accuracy with junior/senior expert. The comparison results indicated that our model performed better than the junior expert.
CONCLUSIONS: This study proposed a novel CSA-CA-TB-ResUnet-based EGC segmentation method and it has a potential for real-time application in improving EGC clinical diagnosis and minimally invasive surgery.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:231 |
|---|---|
| Enthalten in: |
Computer methods and programs in biomedicine - 231(2023) vom: 15. Apr., Seite 107397 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Du, Wenju [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Attention mechanism |
|---|
| Anmerkungen: |
Date Completed 14.03.2023 Date Revised 14.03.2023 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1016/j.cmpb.2023.107397 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM352637714 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM352637714 | ||
| 003 | DE-627 | ||
| 005 | 20231226054203.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.cmpb.2023.107397 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1175.xml |
| 035 | |a (DE-627)NLM352637714 | ||
| 035 | |a (NLM)36753915 | ||
| 035 | |a (PII)S0169-2607(23)00064-0 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Du, Wenju |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Early gastric cancer segmentation in gastroscopic images using a co-spatial attention and channel attention based triple-branch ResUnet |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 14.03.2023 | ||
| 500 | |a Date Revised 14.03.2023 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright © 2023 Elsevier B.V. All rights reserved. | ||
| 520 | |a BACKGROUND AND OBJECTIVE: The artificial segmentation of early gastric cancer (EGC) lesions in gastroscopic images remains a challenging task due to reasons including the diversity of mucosal features, irregular edges of EGC lesions and nuances between EGC lesions and healthy background mucosa. Hence, this study proposed an automatic segmentation framework: co-spatial attention and channel attention based triple-branch ResUnet (CSA-CA-TB-ResUnet) to achieve accurate segmentation of EGC lesions for aiding clinical diagnosis and treatment | ||
| 520 | |a METHODS: The input gastroscopic image sequences of the triple-branch segmentation network CSA-CA-TB-ResUnet is firstly generated by the designed multi-branch input preprocessing (MBIP) module in order to fully utilize massive correlation information among multiple gastroscopic images of the same a lesion. Then, the proposed CSA-CA-TB-ResUnet performs the segmentation of EGC lesion, in which the co-spatial attention (CSA) mechanism is designed to activate the spatial location of EGC lesions by leveraging on the correlations among multiple gastroscopic images of the same EGC lesion, and the channel attention (CA) mechanism is introduced to extract subtle discriminative features of EGC lesions by capturing the interdependencies between channel features. Finally, two gastroscopic images datasets from different digestive endoscopic centers in the southwest and northeast regions of China respectively were collected to validate the performances of proposed segmentation method | ||
| 520 | |a RESULTS: The correlation information among gastroscopic images was confirmed to be able to improve the accuracy of EGC segmentation. On another unseen dataset, our EGC segmentation method achieves Jaccard similarity index (JSI) of 84.54% (95% confidence interval (CI), 83.49%-85.56%), threshold Jaccard index (TJI) of 81.73% (95% CI, 79.70%-83.61%), Dice similarity coefficient (DSC) of 91.08% (95% CI, 90.40%-91.76%) and pixel-wise accuracy (PA) of 91.18% (95% CI, 90.43%-91.87%), which is superior to other state-of-the-art methods. Even on the challenging small lesions, the segmentation results of our CSA-CA-TB-ResUnet-based method are consistently and significantly better than other state-of-the-art methods. We also compared the segmentation result of our model with the diagnostic accuracy with junior/senior expert. The comparison results indicated that our model performed better than the junior expert | ||
| 520 | |a CONCLUSIONS: This study proposed a novel CSA-CA-TB-ResUnet-based EGC segmentation method and it has a potential for real-time application in improving EGC clinical diagnosis and minimally invasive surgery | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Attention mechanism | |
| 650 | 4 | |a Deep learning | |
| 650 | 4 | |a Early gastric cancer | |
| 650 | 4 | |a Gastroscopic image | |
| 650 | 4 | |a Segmentation | |
| 700 | 1 | |a Rao, Nini |e verfasserin |4 aut | |
| 700 | 1 | |a Yong, Jiahao |e verfasserin |4 aut | |
| 700 | 1 | |a Adjei, Prince Ebenezer |e verfasserin |4 aut | |
| 700 | 1 | |a Hu, Xiaoming |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Xiaotong |e verfasserin |4 aut | |
| 700 | 1 | |a Gan, Tao |e verfasserin |4 aut | |
| 700 | 1 | |a Zhu, Linlin |e verfasserin |4 aut | |
| 700 | 1 | |a Zeng, Bing |e verfasserin |4 aut | |
| 700 | 1 | |a Liu, Mengyuan |e verfasserin |4 aut | |
| 700 | 1 | |a Xu, Yongxue |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Computer methods and programs in biomedicine |d 1993 |g 231(2023) vom: 15. Apr., Seite 107397 |w (DE-627)NLM012836133 |x 1872-7565 |7 nnns |
| 773 | 1 | 8 | |g volume:231 |g year:2023 |g day:15 |g month:04 |g pages:107397 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.cmpb.2023.107397 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 231 |j 2023 |b 15 |c 04 |h 107397 | ||