Toward human intervention-free clinical diagnosis of intracranial aneurysm via deep neural network
© 2020 The Authors..
Intracranial aneurysm (IA) is an enormous threat to human health, which often results in nontraumatic subarachnoid hemorrhage or dismal prognosis. Diagnosing IAs on commonly used computed tomographic angiography (CTA) examinations remains laborious and time consuming, leading to error-prone results in clinical practice, especially for small targets. In this study, we propose a fully automatic deep-learning model for IA segmentation that can be applied to CTA images. Our model, called Global Localization-based IA Network (GLIA-Net), can incorporate the global localization prior and generates the fine-grain three-dimensional segmentation. GLIA-Net is trained and evaluated on a big internal dataset (1,338 scans from six institutions) and two external datasets. Evaluations show that our model exhibits good tolerance to different settings and achieves superior performance to other models. A clinical experiment further demonstrates the clinical utility of our technique, which helps radiologists in the diagnosis of IAs.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2021 |
---|---|
Erschienen: |
2021 |
Enthalten in: |
Zur Gesamtaufnahme - volume:2 |
---|---|
Enthalten in: |
Patterns (New York, N.Y.) - 2(2021), 2 vom: 12. Feb., Seite 100197 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Bo, Zi-Hao [VerfasserIn] |
---|
Links: |
---|
Themen: |
Computer-aided diagnosis |
---|
Anmerkungen: |
Date Revised 05.03.2021 published: Electronic-eCollection Citation Status PubMed-not-MEDLINE |
---|
doi: |
10.1016/j.patter.2020.100197 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM32217368X |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM32217368X | ||
003 | DE-627 | ||
005 | 20231225181454.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2021 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.patter.2020.100197 |2 doi | |
028 | 5 | 2 | |a pubmed24n1073.xml |
035 | |a (DE-627)NLM32217368X | ||
035 | |a (NLM)33659913 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Bo, Zi-Hao |e verfasserin |4 aut | |
245 | 1 | 0 | |a Toward human intervention-free clinical diagnosis of intracranial aneurysm via deep neural network |
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 Revised 05.03.2021 | ||
500 | |a published: Electronic-eCollection | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a © 2020 The Authors. | ||
520 | |a Intracranial aneurysm (IA) is an enormous threat to human health, which often results in nontraumatic subarachnoid hemorrhage or dismal prognosis. Diagnosing IAs on commonly used computed tomographic angiography (CTA) examinations remains laborious and time consuming, leading to error-prone results in clinical practice, especially for small targets. In this study, we propose a fully automatic deep-learning model for IA segmentation that can be applied to CTA images. Our model, called Global Localization-based IA Network (GLIA-Net), can incorporate the global localization prior and generates the fine-grain three-dimensional segmentation. GLIA-Net is trained and evaluated on a big internal dataset (1,338 scans from six institutions) and two external datasets. Evaluations show that our model exhibits good tolerance to different settings and achieves superior performance to other models. A clinical experiment further demonstrates the clinical utility of our technique, which helps radiologists in the diagnosis of IAs | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a computer-aided diagnosis | |
650 | 4 | |a deep learning | |
650 | 4 | |a intracranial aneurysm | |
700 | 1 | |a Qiao, Hui |e verfasserin |4 aut | |
700 | 1 | |a Tian, Chong |e verfasserin |4 aut | |
700 | 1 | |a Guo, Yuchen |e verfasserin |4 aut | |
700 | 1 | |a Li, Wuchao |e verfasserin |4 aut | |
700 | 1 | |a Liang, Tiantian |e verfasserin |4 aut | |
700 | 1 | |a Li, Dongxue |e verfasserin |4 aut | |
700 | 1 | |a Liao, Dan |e verfasserin |4 aut | |
700 | 1 | |a Zeng, Xianchun |e verfasserin |4 aut | |
700 | 1 | |a Mei, Leilei |e verfasserin |4 aut | |
700 | 1 | |a Shi, Tianliang |e verfasserin |4 aut | |
700 | 1 | |a Wu, Bo |e verfasserin |4 aut | |
700 | 1 | |a Huang, Chao |e verfasserin |4 aut | |
700 | 1 | |a Liu, Lu |e verfasserin |4 aut | |
700 | 1 | |a Jin, Can |e verfasserin |4 aut | |
700 | 1 | |a Guo, Qiping |e verfasserin |4 aut | |
700 | 1 | |a Yong, Jun-Hai |e verfasserin |4 aut | |
700 | 1 | |a Xu, Feng |e verfasserin |4 aut | |
700 | 1 | |a Zhang, Tijiang |e verfasserin |4 aut | |
700 | 1 | |a Wang, Rongpin |e verfasserin |4 aut | |
700 | 1 | |a Dai, Qionghai |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Patterns (New York, N.Y.) |d 2020 |g 2(2021), 2 vom: 12. Feb., Seite 100197 |w (DE-627)NLM311273858 |x 2666-3899 |7 nnns |
773 | 1 | 8 | |g volume:2 |g year:2021 |g number:2 |g day:12 |g month:02 |g pages:100197 |
856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.patter.2020.100197 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 2 |j 2021 |e 2 |b 12 |c 02 |h 100197 |