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
. 2021 Apr 1;10(4):22.
doi: 10.1167/tvst.10.4.22.

A Deep Learning Model for Screening Multiple Abnormal Findings in Ophthalmic Ultrasonography (With Video)

Di Chen  1 , Yi Yu  2 , Yiwen Zhou  2 , Bin Peng  2 , Yujing Wang  3 , Shan Hu  4 , Miao Tian  2 , Shanshan Wan  2 , Yuelan Gao  2 , Ying Wang  2 , Yulin Yan  2 , Lianlian Wu  1 , LiWen Yao  1 , Biqing Zheng  4 , Yang Wang  2 , Yuqing Huang  2 , Xi Chen  2 , Honggang Yu  1 , Yanning Yang  2
Affiliations

A Deep Learning Model for Screening Multiple Abnormal Findings in Ophthalmic Ultrasonography (With Video)

Di Chen et al. Transl Vis Sci Technol. .

Abstract

Purpose: The purpose of this study was to construct a deep learning system for rapidly and accurately screening retinal detachment (RD), vitreous detachment (VD), and vitreous hemorrhage (VH) in ophthalmic ultrasound in real time.

Methods: We used a deep convolutional neural network to develop a deep learning system to screen multiple abnormal findings in ophthalmic ultrasonography with 3580 images for classification and 941 images for segmentation. Sixty-two videos were used as the test dataset in real time. External data containing 598 images were also used for validation. Another 155 images were collected to compare the performance of the model to experts. In addition, a study was conducted to assess the effect of the model in improving lesions recognition of the trainees.

Results: The model achieved 0.94, 0.90, 0.92, 0.94, and 0.91 accuracy in recognizing normal, VD, VH, RD, and other lesions. Compared with the ophthalmologists, the modal achieved a 0.73 accuracy in classifying RD, VD, and VH, which has a better performance than most experts (P < 0.05). In the videos, the model had a 0.81 accuracy. With the model assistant, the accuracy of the trainees improved from 0.84 to 0.94.

Conclusions: The model could serve as a screening tool to rapidly identify patients with RD, VD, and VH. In addition, it also has potential to be a good tool to assist training.

Translational relevance: We developed a deep learning model to make the ultrasound work more accurately and efficiently.

PubMed Disclaimer

Conflict of interest statement

Disclosure: D. Chen, None; Y. Yu, None; Y. Zhou, None; B. Peng, None; Y. Wang, None; M. Tian, None; S. Wan, None; Y. Gao, None; Y. Wang, None; Y. Yan, None; L. Wu, None; L. Yao, None; B. Zheng, None; Y. Wang, None; Y. Huang, None; X. Chen, None; H. Yu, None; Y. Yang, None

Figures

Figure 1.
Figure 1.
The flowchart of the model. Images from videos were put into the proposed architectures, and firstly screened by DCNN1 to obtain clear images, and then segmented the eyeball by DCNN2. Next, the images would be classified to abnormal and normal by DCNN3. Finally, the abnormal images will be further classified to VD, VH, RD, and others by DCNN4 to DCNN7, respectively.
Figure 2.
Figure 2.
Flowchart of the model development and validation. RD, Retinal detachment; VD, vitreous detachment; VH, vitreous hemorrhage.
Figure 3.
Figure 3.
The changes of the accuracy in the trainees. Horizontal lines depict the change in accuracy for each trainee with and without model assistant. The orange dot represents performance without model assistant, and the red dot represents performance with the model assistant.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Khairallah M, Kahloun R, Bourne R, et al. .. Number of people blind or visually impaired by cataract worldwide and in world regions, 1990 to 2010. Invest Ophthalmol Vis Sci. 2015; 56: 6762–6769. - PubMed
    1. Bello T, Adeoti C.. Ultrasonic assessment in pre-operative cataract patients. Niger Postgrad Med J. 2006; 13: 326–328. - PubMed
    1. Ahmed J, Shaikh FF, Rizwan A, Memon MF.. Evaluation of vitreo-retinal pathologies using B-scan ultrasound. Pak J Ophthalmol. 2009; 25;1–5.
    1. Mitry D, Charteris DG, Fleck BW, Campbell H, Singh J.. The epidemiology of rhegmatogenous retinal detachment: geographical variation and clinical associations. Br J Ophthalmol. 2010; 94: 678–684. - PubMed
    1. Pastor J, Fernandez I, De La, Rua ER, et al. .. Surgical outcomes for primary rhegmatogenous retinal detachments in phakic and pseudophakic patients: the Retina 1 Project—report 2. Br J Ophthalmol. 2008; 92: 378–382. - PubMed

Publication types