Author Correction: Development and clinical deployment of a smartphone-based visual field deep learning system for glaucoma detection

Fei Li, Diping Song, Han Chen, Jian Xiong, Xingyi Li, Hua Zhong, Guangxian Tang, Sujie Fan, Dennis S. C. Lam, Weihua Pan, Yajuan Zheng, Ying Li, Guoxiang Qu, Junjun He, Zhe Wang, Ling Jin, Rouxi Zhou, Yunhe Song, Yi Sun, Weijing Cheng, Chunman Yang, Yazhi Fan, Hengli Zhang, Ye Yuan, Yang Xu, Yunfan Xiong, Aiguo Lv, Lingzhi Niu, Yuhong Liu, Shaoli Li, Jiani Zhang, Linda M. Zangwill, Alejandro F. Frangi, Tin Aung, Ching-Yu Cheng, Yu Qiao, Xiulan Zhang, Daniel S. W. Ting

TL;DR

This paper is an author correction for a previous publication, clarifying missing affiliation details for two authors. The original paper, which is not fully provided here but is referenced, likely details a deep learning system for glaucoma detection using smartphone-based visual field testing. This technology aims to make visual field testing more accessible and affordable, which is crucial for early glaucoma diagnosis and management.

What Problem Does This Paper Address?

The provided text is an "Author Correction" for a previously published article. Therefore, the problem addressed is not directly detailed in this correction. However, based on the title of the original article, "Development and clinical deployment of a smartphone-based visual field deep learning system for glaucoma detection," the underlying problem is the need for more accessible, affordable, and potentially automated methods for visual field testing. Traditional visual field testing devices are expensive, bulky, and require trained personnel, limiting their widespread use, especially in resource-limited settings. Glaucoma is a leading cause of irreversible blindness, and early detection through visual field testing is critical for preventing vision loss. A smartphone-based system, coupled with deep learning, could democratize this diagnostic tool.

Methods

This document is an author correction and does not describe the methods used in the original research. The original article likely details the development of a deep learning model for analyzing visual field data obtained from a smartphone-based device. This would typically involve data preprocessing, model architecture design (e.g., convolutional neural networks), training procedures, and validation strategies. The "clinical deployment" aspect suggests that the system was tested or implemented in a clinical setting.

Datasets

This document is an author correction and does not describe the datasets used in the original research. The original article would have likely used datasets of visual field test results, potentially collected from patients with and without glaucoma, to train and evaluate the deep learning model. The nature of these datasets (size, diversity, source) would be crucial for the model's performance and generalizability.

Key Insights and Ideas

  • Correction of Author Affiliation: The primary insight from this document is the correction of missing affiliation information for authors Diping Song and Han Chen. Their affiliation is now listed as 'University of Chinese Academy of Sciences, Beijing, People's Republic of China'. This ensures accurate attribution and academic record-keeping.
  • Importance of Accurate Metadata: This correction highlights the importance of meticulous attention to detail in academic publishing, even for seemingly minor aspects like author affiliations, as they are crucial for proper citation and understanding the research context.

Key Results

This document is an author correction and does not present any key results from the original research. The original article would have contained quantitative results related to the performance of the deep learning system, such as accuracy, sensitivity, specificity, or other relevant metrics for glaucoma detection.

Limitations and Future Work

This document is an author correction and does not discuss the limitations or future work of the original research. The original article would have likely outlined any shortcomings of the smartphone-based visual field system and suggested avenues for future research, such as expanding the dataset, improving the model's robustness, or conducting larger-scale clinical trials.

Summary updated

BibTeX
@article{li2022author,
  author = {Fei Li and Diping Song and Han Chen and Jian Xiong and Xingyi Li and Hua Zhong and Guangxian Tang and Sujie Fan and Dennis S. C. Lam and Weihua Pan and Yajuan Zheng and Ying Li and Guoxiang Qu and Junjun He and Zhe Wang and Ling Jin and Rouxi Zhou and Yunhe Song and Yi Sun and Weijing Cheng and Chunman Yang and Yazhi Fan and Yingjie Li and Hengli Zhang and Ye Yuan and Yang Xu and Yunfan Xiong and Lingfei Jin and Aiguo Lv and Lingzhi Niu and Yuhong Liu and Shaoli Li and Jiani Zhang and Linda M. Zangwill and Alejandro F. Frangi and Tin Aung and Ching-Yu Cheng and Yu Qiao and Xiulan Zhang and Daniel S. W. Ting},
  title = {{Author Correction: Development and clinical deployment of a smartphone-based visual field deep learning system for glaucoma detection}},
  journal = {Npj Digit. Medicine},
  year = {2022},
  doi = {10.1038/s41746-022-00585-x},
}
Figure