Joint Extraction of Retinal Vessels and Centerlines Based on Deep Semantics and Multi-Scaled Cross-Task Aggregation
Retinal vessel segmentation and centerline extraction are crucial steps in building a computer-aided diagnosis system on retinal images. Previous works treat them as two isolated tasks, while ignoring their tight association. In this paper, we propose a deep semantics and multi-scaled cross-task aggregation network that takes advantage of the association to jointly improve their performances. Our network is featured by two sub-networks. The forepart is a deep semantics aggregation sub-network that aggregates strong semantic information to produce more powerful features for both tasks, and the tail is a multi-scaled cross-task aggregation sub-network that explores complementary information to refine the results. We evaluate the proposed method on three public databases, which are DRIVE, STARE and CHASE_DB1. Experimental results show that our method can not only simultaneously extract retinal vessels and their centerlines but also achieve the state-of-the-art performances on both tasks.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2021 |
---|---|
Erschienen: |
2021 |
Enthalten in: |
Zur Gesamtaufnahme - volume:25 |
---|---|
Enthalten in: |
IEEE journal of biomedical and health informatics - 25(2021), 7 vom: 15. Juli, Seite 2722-2732 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Xu, Rui [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Completed 24.09.2021 Date Revised 24.09.2021 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1109/JBHI.2020.3044957 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM318859599 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM318859599 | ||
003 | DE-627 | ||
005 | 20231225170235.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2021 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1109/JBHI.2020.3044957 |2 doi | |
028 | 5 | 2 | |a pubmed24n1062.xml |
035 | |a (DE-627)NLM318859599 | ||
035 | |a (NLM)33320815 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Xu, Rui |e verfasserin |4 aut | |
245 | 1 | 0 | |a Joint Extraction of Retinal Vessels and Centerlines Based on Deep Semantics and Multi-Scaled Cross-Task Aggregation |
264 | 1 | |c 2021 | |
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 24.09.2021 | ||
500 | |a Date Revised 24.09.2021 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Retinal vessel segmentation and centerline extraction are crucial steps in building a computer-aided diagnosis system on retinal images. Previous works treat them as two isolated tasks, while ignoring their tight association. In this paper, we propose a deep semantics and multi-scaled cross-task aggregation network that takes advantage of the association to jointly improve their performances. Our network is featured by two sub-networks. The forepart is a deep semantics aggregation sub-network that aggregates strong semantic information to produce more powerful features for both tasks, and the tail is a multi-scaled cross-task aggregation sub-network that explores complementary information to refine the results. We evaluate the proposed method on three public databases, which are DRIVE, STARE and CHASE_DB1. Experimental results show that our method can not only simultaneously extract retinal vessels and their centerlines but also achieve the state-of-the-art performances on both tasks | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, Non-U.S. Gov't | |
700 | 1 | |a Liu, Tiantian |e verfasserin |4 aut | |
700 | 1 | |a Ye, Xinchen |e verfasserin |4 aut | |
700 | 1 | |a Liu, Fei |e verfasserin |4 aut | |
700 | 1 | |a Lin, Lin |e verfasserin |4 aut | |
700 | 1 | |a Li, Liang |e verfasserin |4 aut | |
700 | 1 | |a Tanaka, Satoshi |e verfasserin |4 aut | |
700 | 1 | |a Chen, Yen-Wei |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t IEEE journal of biomedical and health informatics |d 2013 |g 25(2021), 7 vom: 15. Juli, Seite 2722-2732 |w (DE-627)NLM217081614 |x 2168-2208 |7 nnns |
773 | 1 | 8 | |g volume:25 |g year:2021 |g number:7 |g day:15 |g month:07 |g pages:2722-2732 |
856 | 4 | 0 | |u http://dx.doi.org/10.1109/JBHI.2020.3044957 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 25 |j 2021 |e 7 |b 15 |c 07 |h 2722-2732 |