Prediction of the response to photodynamic therapy in patients with chronic central serous chorioretinopathy based on optical coherence tomography using deep learning
![Thumbnail](/dspace/bitstream/handle/2183/37770/Moura_Joaquim_de_2022_Prediction_of_the_response_to_photodynamic_therapy.pdf.jpg?sequence=5&isAllowed=y)
Use this link to cite
http://hdl.handle.net/2183/37770
Except where otherwise noted, this item's license is described as Atribución-NoComercial-SinDerivadas 4.0 Internacional
Collections
- GI-VARPA - Artigos [76]
Metadata
Show full item recordTitle
Prediction of the response to photodynamic therapy in patients with chronic central serous chorioretinopathy based on optical coherence tomography using deep learningAuthor(s)
Date
2022-12Citation
Fernández-Vigo, J. I., Calleja, V. G., de Moura Ramos, J. J., Novo-Bujan, J., Burgos-Blasco, B., López-Guajardo, L., ... & Ortega-Hortas, M. (2022). Prediction of the response to photodynamic therapy in patients with chronic central serous chorioretinopathy based on optical coherence tomography using deep learning. Photodiagnosis and Photodynamic Therapy, 40, 103107. https://doi.org/10.1016/j.pdpdt.2022.103107
Abstract
[Abstract]: Purpose
To assess the prediction of the response to photodynamic therapy (PDT) in chronic central serous chorioretinopathy (CSCR) based on spectral-domain optical coherence tomography (SD-OCT) images using deep learning (DL).
Methods
Retrospective study including 216 eyes of 175 patients with CSCR and persistent subretinal fluid (SRF) who underwent half-fluence PDT. SD-OCT macular examination was performed before (baseline) and 3 months after treatment. Patients were classified into groups by experts based on the response to PDT: Group 1, complete SRF resorption (n = 100); Group 2, partial SRF resorption (n = 66); and Group 3, absence of any SRF resorption (n = 50). This work proposes different computational approaches: 1st approach compares all groups; 2nd compares groups 1 vs. 2 and 3 together; 3rd compares groups 2 vs. 3.
Results
The mean age was 55.6 ± 10.9 years and 70.3% were males. In the first approach, the algorithm showed a precision of up to 57% to detect the response to treatment in group 1 based on the initial scan, with a mean average accuracy of 0.529 ± 0.035. In the second model, the mean accuracy was higher (0.670 ± 0.046). In the third approach, the algorithm showed a precision of 0.74 ± 0.12 to detect the response to treatment in group 2 (partial SRF resolution) and 0.69 ± 0.15 in group 3 (absence of SRF resolution).
Conclusion
Despite the high clinical variability in the response of chronic CSCR to PDT, this DL algorithm offers an objective and promising tool to predict the response to PDT treatment in clinical practice.
Keywords
Central serous chorioretinopathy
Photodynamic therapy
Deep learning
Optical Coherence Tomography
Photodynamic therapy
Deep learning
Optical Coherence Tomography
Description
This version of the article has been accepted for publication in: Photodiagnosis and Photodynamic Therapy, 40, 103107. The Version of Record is available online at https://doi.org/10.1016/j.ins.2018.09.045
Editor version
Rights
Atribución-NoComercial-SinDerivadas 4.0 Internacional
ISSN
1572-1000