Literature DB >> 34159761

Multimodal deep learning with feature level fusion for identification of choroidal neovascularization activity in age-related macular degeneration.

Kai Jin1, Yan Yan1, Menglu Chen1, Jun Wang2, Xiangji Pan1, Xindi Liu1, Mushui Liu3, Lixia Lou1, Yao Wang1, Juan Ye1.   

Abstract

PURPOSE: This study aimed to determine the efficacy of a multimodal deep learning (DL) model using optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA) images for the assessment of choroidal neovascularization (CNV) in neovascular age-related macular degeneration (AMD).
METHODS: This retrospective and cross-sectional study was performed at a multicentre, and the inclusion criteria were age >50 years and a diagnosis of typical neovascular AMD. The OCT and OCTA data for an internal data set and two external data sets were collected. A DL model was developed with a novel feature-level fusion (FLF) method utilized to combine the multimodal data. The results were compared with identification performed by an ophthalmologist. The best model was tested on two external data sets to show its potential for clinical use.
RESULTS: Our best model achieved an accuracy of 95.5% and an area under the curve (AUC) of 0.9796 on multimodal data inputs for the internal data set, which is comparable to the performance of retinal specialists. The proposed model reached an accuracy of 100.00% and an AUC of 1.0 for the Ningbo data set, and these performance indicators were 90.48% and an AUC of 0.9727 for the Jinhua data set.
CONCLUSION: The FLF method is feasible and highly accurate, and could enhance the power of the existing computer-aided diagnosis systems. The bi-modal computer-aided diagnosis (CADx) system for the automated identification of CNV activity is an accurate and promising tool in the realm of public health.
© 2021 Acta Ophthalmologica Scandinavica Foundation. Published by John Wiley & Sons Ltd.

Entities:  

Keywords:  age-related macular degeneration; choroidal neovascularization activity; feature level fusion; multimodal deep learning

Mesh:

Year:  2021        PMID: 34159761     DOI: 10.1111/aos.14928

Source DB:  PubMed          Journal:  Acta Ophthalmol        ISSN: 1755-375X            Impact factor:   3.761


  17 in total

1.  A molecular modeling on the potential application of beryllium oxide nanotube for delivery of hydroxyurea anticancer drug.

Authors:  Mustafa M Kadhim; Ali Jihad; Safa K Hachim; Sallal A H Abdullaha; Taleeb Zedan Taban; Ahmed Mahdi Rheima
Journal:  J Mol Model       Date:  2022-10-12       Impact factor: 2.172

2.  Salviae miltiorrhizae Liguspyragine Hydrochloride and Glucose Injection Protects against Myocardial Ischemia-Reperfusion Injury and Heart Failure.

Authors:  Shang Kong; Dan Zhou; Qinghong Fan; Tingting Zhao; Chunguang Ren; Hong Nie
Journal:  Comput Math Methods Med       Date:  2022-06-29       Impact factor: 2.809

3.  Pharmaceutical Reagent Inventory Strategy Based on Contract Shelf Life and Patient Demand.

Authors:  Lingling Li; Zheng Liu; Qingshan Qian; Zhao Zhao; Yuanjun Zhao
Journal:  Contrast Media Mol Imaging       Date:  2022-04-21       Impact factor: 3.009

4.  A multimodal deep learning system to distinguish late stages of AMD and to compare expert vs. AI ocular biomarkers.

Authors:  Kaveri A Thakoor; Jiaang Yao; Darius Bordbar; Omar Moussa; Weijie Lin; Paul Sajda; Royce W S Chen
Journal:  Sci Rep       Date:  2022-02-16       Impact factor: 4.379

5.  Relationship between Coronary VH-IVUS Plaque Characteristics and CTRP9, SAA, and Hcy in Patients with Coronary Heart Disease.

Authors:  Yongli Liu; Xubo Wang; Ting Wang; Wenbin Zhang; Ying Chang; Weixin Dai; Jun Zhao; Zhuoqun Wang; Yingying Qi; Hongtao Pan
Journal:  J Healthc Eng       Date:  2022-03-27       Impact factor: 2.682

Review 6.  Molecular dynamics simulation approach for discovering potential inhibitors against SARS-CoV-2: A structural review.

Authors:  Shabnam Ghahremanian; Mohammad Mehdi Rashidi; Kimai Raeisi; Davood Toghraie
Journal:  J Mol Liq       Date:  2022-03-09       Impact factor: 6.633

7.  Analysis of Influencing Factors of Serum Stress Index and Prognosis of HICH Patients by Different Anesthesia Methods Combined with Small Bone Window Microsurgery.

Authors:  Guangping Zhao; Jiong Shi; Yongxue Chen
Journal:  J Healthc Eng       Date:  2022-03-25       Impact factor: 2.682

8.  A Clinical Study on the Brain Protection Effect of Propofol Anesthesia on Patients Undergoing Acute Craniocerebral Trauma Surgery Based on Blockchain.

Authors:  Hu Li; Jinfeng Li; Peng Su; JianJun Zhang; Ding Ma
Journal:  J Healthc Eng       Date:  2022-04-09       Impact factor: 3.822

9.  Risk Analysis of Positive PD-L1 Expression and Clinicopathological Features and Survival Prognosis in Patients with Colorectal Cancer: Systematic Review and Meta-Analysis.

Authors:  Maocai Tang; Ziling Zheng; Jingkun Shang; Shouru Zhang
Journal:  J Healthc Eng       Date:  2022-04-11       Impact factor: 3.822

10.  Vascular Analysis of Type 1, 2, and 3 Macular Neovascularization in Age-Related Macular Degeneration Using Swept-Source Optical Coherence Tomography Angiography Shows New Insights into Differences of Pathologic Vasculature and May Lead to a More Personalized Understanding.

Authors:  Henrik Faatz; Kai Rothaus; Martin Ziegler; Marius Book; Britta Heimes-Bussmann; Daniel Pauleikhoff; Albrecht Lommatzsch
Journal:  Biomedicines       Date:  2022-03-17
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.