Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jul 25;27(9):110579.
doi: 10.1016/j.isci.2024.110579. eCollection 2024 Sep 20.

Quickly diagnosing Bietti crystalline dystrophy with deep learning

Haihan Zhang  1 , Kai Zhang  2 , Jinyuan Wang  1   3 , Shicheng Yu  4 , Zhixi Li  5   6 , Shiyi Yin  1 , Jingyuan Zhu  1 , Wenbin Wei  1
Affiliations

Quickly diagnosing Bietti crystalline dystrophy with deep learning

Haihan Zhang et al. iScience. .

Abstract

Bietti crystalline dystrophy (BCD) is an autosomal recessive inherited retinal disease (IRD) and its early precise diagnosis is much challenging. This study aims to diagnose BCD and classify the clinical stage based on ultra-wide-field (UWF) color fundus photographs (CFPs) via deep learning (DL). All CFPs were labeled as BCD, retinitis pigmentosa (RP) or normal, and the BCD patients were further divided into three stages. DL models ResNeXt, Wide ResNet, and ResNeSt were developed, and model performance was evaluated using accuracy and confusion matrix. Then the diagnostic interpretability was verified by the heatmaps. The models achieved good classification results. Our study established the largest BCD database of Chinese population. We developed a quick diagnosing method for BCD and evaluated the potential efficacy of an automatic diagnosis and grading DL algorithm based on UWF fundus photography in a Chinese cohort of BCD patients.

Keywords: Bioinformatics; Clinical neuroscience.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

None
Graphical abstract
Figure 1
Figure 1
The most representative photos in the current study population were selected as a reference (A–C) CFPs of typical stage 1, 2, and 3 BCD subjects; (D) normal fundus; (E) CFP of the RP subject.
Figure 2
Figure 2
Confusion matrix: differential diagnosis of RP and BCD and the grading of BCD in internal cross validation dataset
Figure 3
Figure 3
Confusion matrix: differential diagnosis of RP and BCD and the grading of BCD in external validation dataset
Figure 4
Figure 4
Heatmap visualization of internal dataset
Figure 5
Figure 5
Heatmap visualization of external validation dataset
See this image and copyright information in PMC

References

    1. Bietti G. Ueber familiares Vorkommen von" Retinitis punkutata albescens"(verbunden mit" Dystrophia marginalis cristallinea corneae"), Glitzern des Glaskorpers und anderen degenerativen Augenveranderungen. Klin. Monatsbl. Augenheilkd. 1937;99:737–756.
    1. Li A., Jiao X., Munier F.L., Schorderet D.F., Yao W., Iwata F., Hayakawa M., Kanai A., Shy Chen M., Alan Lewis R., et al. Bietti crystalline corneoretinal dystrophy is caused by mutations in the novel gene CYP4V2. Am. J. Hum. Genet. 2004;74:817–826. doi: 10.1086/383228. - DOI - PMC - PubMed
    1. García-García G.P., Martínez-Rubio M., Moya-Moya M.-A., Pérez Santonja J.J., Escribano J. Current perspectives in Bietti crystalline dystrophy. Clin. Ophthalmol. 2019;13:1379–1399. doi: 10.2147/opth.S185744. - DOI - PMC - PubMed
    1. Shan M., Dong B., Zhao X., Wang J., Li G., Yang Y., Li Y. Novel mutations in the CYP4V2 gene associated with Bietti crystalline corneoretinal dystrophy. Mol. Vis. 2005;11:738–743. - PubMed
    1. Mataftsi A., Zografos L., Millá E., Secrétan M., Munier F.L. Bietti's crystalline corneoretinal dystrophy: a cross-sectional study. Retina. 2004;24:416–426. doi: 10.1097/00006982-200406000-00013. - DOI - PubMed

LinkOut - more resources