FundusNet: A Deep-Learning Approach for Fast Diagnosis of Neurodegenerative and Eye Diseases Using Fundus Images
Early-stage detection of neurodegenerative diseases is crucial for effective clinical treatment. However, current diagnostic methods are expensive and time-consuming. In this study, we present FundusNet, a deep-learning model trained on fundus images, for rapid and cost-effective diagnosis of neurod...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/12/1/57 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589043388383232 |
|---|---|
| author | Wenxing Hu Kejie Li Jake Gagnon Ye Wang Talia Raney Jeron Chen Yirui Chen Yoko Okunuki Will Chen Baohong Zhang |
| author_facet | Wenxing Hu Kejie Li Jake Gagnon Ye Wang Talia Raney Jeron Chen Yirui Chen Yoko Okunuki Will Chen Baohong Zhang |
| author_sort | Wenxing Hu |
| collection | DOAJ |
| description | Early-stage detection of neurodegenerative diseases is crucial for effective clinical treatment. However, current diagnostic methods are expensive and time-consuming. In this study, we present FundusNet, a deep-learning model trained on fundus images, for rapid and cost-effective diagnosis of neurodegenerative diseases. FundusNet achieved superior performance in age prediction (MAE 2.55 year), gender classification (AUC 0.98), and neurodegenerative disease diagnosis—Parkinson’s disease AUC 0.75 ± 0.03, multiple sclerosis AUC 0.77 ± 0.02. Grad-CAM was used to identify which part of the image contributes to diagnosis. Imaging biomarker interpretation demonstrated that FundusNet effectively identifies clinical retina structures associated with diseases. Additionally, the model’s high accuracy in predicting genetic risk suggests that its performance could be further enhanced with larger training datasets. |
| format | Article |
| id | doaj-art-5567b1af036949eb92339f2b9083c102 |
| institution | Kabale University |
| issn | 2306-5354 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj-art-5567b1af036949eb92339f2b9083c1022025-01-24T13:23:07ZengMDPI AGBioengineering2306-53542025-01-011215710.3390/bioengineering12010057FundusNet: A Deep-Learning Approach for Fast Diagnosis of Neurodegenerative and Eye Diseases Using Fundus ImagesWenxing Hu0Kejie Li1Jake Gagnon2Ye Wang3Talia Raney4Jeron Chen5Yirui Chen6Yoko Okunuki7Will Chen8Baohong Zhang9Research Department, Biogen, Inc., 225 Binney St., Cambridge, MA 02142, USAResearch Department, Biogen, Inc., 225 Binney St., Cambridge, MA 02142, USAResearch Department, Biogen, Inc., 225 Binney St., Cambridge, MA 02142, USAResearch Department, Biogen, Inc., 225 Binney St., Cambridge, MA 02142, USAResearch Department, Biogen, Inc., 225 Binney St., Cambridge, MA 02142, USAResearch Department, Biogen, Inc., 225 Binney St., Cambridge, MA 02142, USAResearch Department, Biogen, Inc., 225 Binney St., Cambridge, MA 02142, USAResearch Department, Biogen, Inc., 225 Binney St., Cambridge, MA 02142, USAResearch Department, Biogen, Inc., 225 Binney St., Cambridge, MA 02142, USAResearch Department, Biogen, Inc., 225 Binney St., Cambridge, MA 02142, USAEarly-stage detection of neurodegenerative diseases is crucial for effective clinical treatment. However, current diagnostic methods are expensive and time-consuming. In this study, we present FundusNet, a deep-learning model trained on fundus images, for rapid and cost-effective diagnosis of neurodegenerative diseases. FundusNet achieved superior performance in age prediction (MAE 2.55 year), gender classification (AUC 0.98), and neurodegenerative disease diagnosis—Parkinson’s disease AUC 0.75 ± 0.03, multiple sclerosis AUC 0.77 ± 0.02. Grad-CAM was used to identify which part of the image contributes to diagnosis. Imaging biomarker interpretation demonstrated that FundusNet effectively identifies clinical retina structures associated with diseases. Additionally, the model’s high accuracy in predicting genetic risk suggests that its performance could be further enhanced with larger training datasets.https://www.mdpi.com/2306-5354/12/1/57fundusneurodegenerative diseasevision transformer |
| spellingShingle | Wenxing Hu Kejie Li Jake Gagnon Ye Wang Talia Raney Jeron Chen Yirui Chen Yoko Okunuki Will Chen Baohong Zhang FundusNet: A Deep-Learning Approach for Fast Diagnosis of Neurodegenerative and Eye Diseases Using Fundus Images Bioengineering fundus neurodegenerative disease vision transformer |
| title | FundusNet: A Deep-Learning Approach for Fast Diagnosis of Neurodegenerative and Eye Diseases Using Fundus Images |
| title_full | FundusNet: A Deep-Learning Approach for Fast Diagnosis of Neurodegenerative and Eye Diseases Using Fundus Images |
| title_fullStr | FundusNet: A Deep-Learning Approach for Fast Diagnosis of Neurodegenerative and Eye Diseases Using Fundus Images |
| title_full_unstemmed | FundusNet: A Deep-Learning Approach for Fast Diagnosis of Neurodegenerative and Eye Diseases Using Fundus Images |
| title_short | FundusNet: A Deep-Learning Approach for Fast Diagnosis of Neurodegenerative and Eye Diseases Using Fundus Images |
| title_sort | fundusnet a deep learning approach for fast diagnosis of neurodegenerative and eye diseases using fundus images |
| topic | fundus neurodegenerative disease vision transformer |
| url | https://www.mdpi.com/2306-5354/12/1/57 |
| work_keys_str_mv | AT wenxinghu fundusnetadeeplearningapproachforfastdiagnosisofneurodegenerativeandeyediseasesusingfundusimages AT kejieli fundusnetadeeplearningapproachforfastdiagnosisofneurodegenerativeandeyediseasesusingfundusimages AT jakegagnon fundusnetadeeplearningapproachforfastdiagnosisofneurodegenerativeandeyediseasesusingfundusimages AT yewang fundusnetadeeplearningapproachforfastdiagnosisofneurodegenerativeandeyediseasesusingfundusimages AT taliaraney fundusnetadeeplearningapproachforfastdiagnosisofneurodegenerativeandeyediseasesusingfundusimages AT jeronchen fundusnetadeeplearningapproachforfastdiagnosisofneurodegenerativeandeyediseasesusingfundusimages AT yiruichen fundusnetadeeplearningapproachforfastdiagnosisofneurodegenerativeandeyediseasesusingfundusimages AT yokookunuki fundusnetadeeplearningapproachforfastdiagnosisofneurodegenerativeandeyediseasesusingfundusimages AT willchen fundusnetadeeplearningapproachforfastdiagnosisofneurodegenerativeandeyediseasesusingfundusimages AT baohongzhang fundusnetadeeplearningapproachforfastdiagnosisofneurodegenerativeandeyediseasesusingfundusimages |