81 102

Cited 0 times in

DeepPDT-Net: predicting the outcome of photodynamic therapy for chronic central serous chorioretinopathy using two-stage multimodal transfer learning

 Tae Keun Yoo  ;  Seo Hee Kim  ;  Min Kim  ;  Christopher Seungkyu Lee  ;  Suk Ho Byeon  ;  Sung Soo Kim  ;  Jinyoung Yeo  ;  Eun Young Choi 
 SCIENTIFIC REPORTS, Vol.12(1) : 18689, 2022-11 
Journal Title
Issue Date
Case-Control Studies ; Central Serous Chorioretinopathy* / diagnostic imaging ; Central Serous Chorioretinopathy* / drug therapy ; Chronic Disease ; Fluorescein Angiography ; Humans ; Machine Learning ; Photochemotherapy* / methods ; Photosensitizing Agents / therapeutic use ; Porphyrins* ; Retina / diagnostic imaging ; Retrospective Studies ; Tomography, Optical Coherence ; Verteporfin / therapeutic use ; Visual Acuity
Central serous chorioretinopathy (CSC), characterized by serous detachment of the macular retina, can cause permanent vision loss in the chronic course. Chronic CSC is generally treated with photodynamic therapy (PDT), which is costly and quite invasive, and the results are unpredictable. In a retrospective case-control study design, we developed a two-stage deep learning model to predict 1-year outcome of PDT using initial multimodal clinical data. The training dataset included 166 eyes with chronic CSC and an additional learning dataset containing 745 healthy control eyes. A pre-trained ResNet50-based convolutional neural network was first trained with normal fundus photographs (FPs) to detect CSC and then adapted to predict CSC treatability through transfer learning. The domain-specific ResNet50 successfully predicted treatable and refractory CSC (accuracy, 83.9%). Then other multimodal clinical data were integrated with the FP deep features using XGBoost.The final combined model (DeepPDT-Net) outperformed the domain-specific ResNet50 (accuracy, 88.0%). The FP deep features had the greatest impact on DeepPDT-Net performance, followed by central foveal thickness and age. In conclusion, DeepPDT-Net could solve the PDT outcome prediction task challenging even to retinal specialists. This two-stage strategy, adopting transfer learning and concatenating multimodal data, can overcome the clinical prediction obstacles arising from insufficient datasets.
Files in This Item:
T202205527.pdf Download
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Ophthalmology (안과학교실) > 1. Journal Papers
Yonsei Authors
Kim, Min(김민) ORCID logo https://orcid.org/0000-0003-1873-6959
Kim, Sung Soo(김성수) ORCID logo https://orcid.org/0000-0002-0574-7993
Byeon, Suk Ho(변석호) ORCID logo https://orcid.org/0000-0001-8101-0830
Lee, Christopher Seungkyu(이승규) ORCID logo https://orcid.org/0000-0001-5054-9470
Choi, Eun Young(최은영) ORCID logo https://orcid.org/0000-0002-1668-6452
사서에게 알리기


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.