Diagnosis of Polypoidal Choroidal Vasculopathy From Fluorescein Angiography Using Deep Learning

Tsai, Yu-Yeh; Lin, Wei-Yang; Chen, Shih‐Jen; Ruamviboonsuk, Paisan; King, Cheng-Ho; Tsai, Chia-Ling

doi:10.1167/tvst.11.2.6

Cited by 5 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They found that InceptionResNetV2 had the best performance, which achieved an AUC of 0.996 with 98.7% sensitivity and 99.2% specificity. In addition, AI has also been employed in the automated identification of retinal detachment, 74 pathologic myopia, 75 polypoidal choroidal vasculopathy, 76 etc.…”

Section: Application Of Ai Algorithms In Posterior-segment Eye Diseasesmentioning

confidence: 99%

Artificial intelligence in ophthalmology: The path to the real-world clinic

Wang

et al. 2023

Cell Reports Medicine

View full text Add to dashboard Cite

Section: Application Of Ai Algorithms In Posterior-segment Eye Diseasesmentioning

confidence: 99%

Artificial intelligence in ophthalmology: The path to the real-world clinic

Wang

et al. 2023

Cell Reports Medicine

View full text Add to dashboard Cite

“…Additional DL model was developed to highlight heatmap regions for detecting PCV lesions on FA where the agreement of 21.9% with experts was found. The third model was applied for segmentation of PCV lesions on FA and achieved the average dice similarity score of 0.88 75. The main limitation of using images from fundus angiography for AI would be the selection of images from a series of time-dependent series.…”

Section: Updates On Diagnosis Of Pcvmentioning

confidence: 99%

“…The third model was applied for segmentation of PCV lesions on FA and achieved the average dice similarity score of 0.88. 75 The main limitation of using images from fundus angiography for AI would be the selection of images from a series of time-dependent series. This can be problematic for standardization in both the development of AI and the application of AI in the real world.…”

Section: Artificial Intelligence (Ai)mentioning

confidence: 99%

Polypoidal Choroidal Vasculopathy: Updates on Risk Factors, Diagnosis, and Treatments

Ruamviboonsuk

Cheung

Chainakul

et al. 2023

Asia-Pacific Journal of Ophthalmology

Self Cite

View full text Add to dashboard Cite

There have been recent advances in basic research and clinical studies in polypoidal choroidal vasculopathy (PCV). A recent, large-scale, population-based study found systemic factors, such as male gender and smoking, were associated with PCV, and a recent systematic review reported plasma C-reactive protein, a systemic biomarker, was associated with PCV. Growing evidence points to an association between pachydrusen, recently proposed extracellular deposits associated with the thick choroid, and the risk of development of PCV. Many recent studies on diagnosis of PCV have focused on applying criteria from noninvasive multimodal retinal imaging without requirement of indocyanine green angiography. There have been attempts to develop deep learning models, a recent subset of artificial intelligence, for detecting PCV from different types of retinal imaging modality. Some of these deep learning models were found to have high performance when they were trained and tested on color retinal images with corresponding images from optical coherence tomography. The treatment of PCV is either a combination therapy using verteporfin photodynamic therapy and anti-vascular endothelial growth factor (VEGF), or anti-VEGF monotherapy, often used with a treat-and-extend regimen. New anti-VEGF agents may provide more durable treatment with similar efficacy, compared with existing anti-VEGF agents. It is not known if they can induce greater closure of polypoidal lesions, in which case, combination therapy may still be a mainstay. Recent evidence supports long-term follow-up of patients with PCV after treatment for early detection of recurrence, particularly in patients with incomplete closure of polypoidal lesions.

show abstract

“…AI tech-nologies can also be applied to reduce the number and invasiveness of examinations required to diagnose a specific disease. In example, Yi et al 7 recently developed a deep learning (DL) model able to differentiate polypoidal choroidal vasculopathy from Type I choroidal neovascularization based on fluorescein angiography acquisitions, thus overcoming the need for indocyanine green angiography for differential diagnosis. Nevertheless, the model only reached approximately 80% accuracy, which is still not accurate enough to propose substitution of indocyanine green angiography.…”

mentioning

confidence: 99%