DeepGraFT: A novel semantic segmentation auxiliary ROI-based deep learning framework for effective fundus tessellation classification

Yinghao Yao; Jiaying Yang; Haojun Sun; Hengte Kong; Sheng Wang; Ke Xu; Wei Dai; Siyi Jiang; QingShi Bai; Shilai Xing; Jian Yuan; Xinting Liu; Fan Lu; Zhenhui Chen; Jia Qu; Jianzhong Su

doi:10.1016/j.compbiomed.2023.107881

DeepGraFT: A novel semantic segmentation auxiliary ROI-based deep learning framework for effective fundus tessellation classification

Comput Biol Med. 2024 Feb:169:107881. doi: 10.1016/j.compbiomed.2023.107881. Epub 2023 Dec 23.

Authors

Yinghao Yao¹, Jiaying Yang¹, Haojun Sun¹, Hengte Kong¹, Sheng Wang¹, Ke Xu², Wei Dai², Siyi Jiang¹, QingShi Bai¹, Shilai Xing³, Jian Yuan², Xinting Liu⁴, Fan Lu⁵, Zhenhui Chen⁶, Jia Qu⁷, Jianzhong Su⁸

Affiliations

¹ Oujiang Laboratory (Zhejiang Lab for Regenerative Medicine, Vision and Brain Health), Eye Hospital, Wenzhou Medical University, Wenzhou, 325011, Zhejiang, China; National Engineering Research Center of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, 325027, Zhejiang, China.
² National Engineering Research Center of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, 325027, Zhejiang, China.
³ Institute of PSI Genomics, Wenzhou Global Eye & Vision Innovation Center, Wenzhou, 325024, China.
⁴ National Engineering Research Center of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, 325027, Zhejiang, China; National Clinical Research Center for Ocular Diseases, Eye Hospital, Wenzhou Medical University, Wenzhou, 325027, China.
⁵ Oujiang Laboratory (Zhejiang Lab for Regenerative Medicine, Vision and Brain Health), Eye Hospital, Wenzhou Medical University, Wenzhou, 325011, Zhejiang, China; National Engineering Research Center of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, 325027, Zhejiang, China; National Clinical Research Center for Ocular Diseases, Eye Hospital, Wenzhou Medical University, Wenzhou, 325027, China.
⁶ National Engineering Research Center of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, 325027, Zhejiang, China; National Clinical Research Center for Ocular Diseases, Eye Hospital, Wenzhou Medical University, Wenzhou, 325027, China. Electronic address: chenzhenhui@ojlab.ac.cn.
⁷ Oujiang Laboratory (Zhejiang Lab for Regenerative Medicine, Vision and Brain Health), Eye Hospital, Wenzhou Medical University, Wenzhou, 325011, Zhejiang, China; National Engineering Research Center of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, 325027, Zhejiang, China; National Clinical Research Center for Ocular Diseases, Eye Hospital, Wenzhou Medical University, Wenzhou, 325027, China. Electronic address: qujia@eye.ac.cn.
⁸ Oujiang Laboratory (Zhejiang Lab for Regenerative Medicine, Vision and Brain Health), Eye Hospital, Wenzhou Medical University, Wenzhou, 325011, Zhejiang, China; National Engineering Research Center of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, 325027, Zhejiang, China; National Clinical Research Center for Ocular Diseases, Eye Hospital, Wenzhou Medical University, Wenzhou, 325027, China. Electronic address: sujz@wmu.edu.cn.

PMID: 38159401
DOI: 10.1016/j.compbiomed.2023.107881

Abstract

Fundus tessellation (FT) is a prevalent clinical feature associated with myopia and has implications in the development of myopic maculopathy, which causes irreversible visual impairment. Accurate classification of FT in color fundus photo can help predict the disease progression and prognosis. However, the lack of precise detection and classification tools has created an unmet medical need, underscoring the importance of exploring the clinical utility of FT. Thus, to address this gap, we introduce an automatic FT grading system (called DeepGraFT) using classification-and-segmentation co-decision models by deep learning. ConvNeXt, utilizing transfer learning from pretrained ImageNet weights, was employed for the classification algorithm, aligning with a region of interest based on the ETDRS grading system to boost performance. A segmentation model was developed to detect FT exits, complementing the classification for improved grading accuracy. The training set of DeepGraFT was from our in-house cohort (MAGIC), and the validation sets consisted of the rest part of in-house cohort and an independent public cohort (UK Biobank). DeepGraFT demonstrated a high performance in the training stage and achieved an impressive accuracy in validation phase (in-house cohort: 86.85 %; public cohort: 81.50 %). Furthermore, our findings demonstrated that DeepGraFT surpasses machine learning-based classification models in FT classification, achieving a 5.57 % increase in accuracy. Ablation analysis revealed that the introduced modules significantly enhanced classification effectiveness and elevated accuracy from 79.85 % to 86.85 %. Further analysis using the results provided by DeepGraFT unveiled a significant negative association between FT and spherical equivalent (SE) in the UK Biobank cohort. In conclusion, DeepGraFT accentuates potential benefits of the deep learning model in automating the grading of FT and allows for potential utility as a clinical-decision support tool for predicting progression of pathological myopia.

Keywords: Deep learning; Epidemiology; Fundus image; Fundus tessellation; High myopia.

MeSH terms

Algorithms
Deep Learning*
Fundus Oculi
Humans
Machine Learning
Semantics