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

doi:10.1016/j.compbiomed.2023.107881

科研成果详情

题名	DeepGraFT: A novel semantic segmentation auxiliary ROI-based deep learning framework for effective fundus tessellation classification
作者	Yao, Yinghao 1,2; Yang, Jiaying1,2; Sun, Haojun1,2; Kong, Hengte1,2; Wang, Sheng 1,2; Xu, Ke 2; Dai, Wei2; Jiang, Siyi1,2; Bai, QingShi1,2; Xing, Shilai 4; Yuan, Jian 2; Liu, Xinting2,3; Lu, Fan1,2,3; Chen, Zhenhui2,3; Qu, Jia1,2,3; Su, Jianzhong1,2,3
发表日期	2024-02
发表期刊	Computers in Biology and Medicine 影响因子和分区
语种	英语
原始文献类型	Journal article (JA)
关键词	Decision support systems Deep learning Diagnosis Image classification Learning systems Ophthalmology Semantic Segmentation Semantics Biobanks Clinical features Deep learning Fundus image Fundus tessellation Grading system High myopia Learning frameworks Performance Semantic segmentation
摘要	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. © 2023
出版者	Elsevier Ltd
ISSN	0010-4825
EISSN	1879-0534
卷号	169
DOI	10.1016/j.compbiomed.2023.107881
收录类别	EI
EI入藏号	20240115310289
EI主题词	Grading
EI分类号	461.4 Ergonomics and Human Factors Engineering ; 461.6 Medicine and Pharmacology ; 723 Computer Software, Data Handling and Applications ; 723.2 Data Processing and Image Processing ; 723.4 Artificial Intelligence ; 912.2 Management
引用统计
文献类型	期刊论文
条目标识符	https://kms.wmu.edu.cn/handle/3ETUA0LF/223713
专题	眼视光学院（生物医学工程学院）、附属眼视光医院
通讯作者	Su, Jianzhong
作者单位	1.Oujiang Laboratory (Zhejiang Lab for Regenerative Medicine, Vision and Brain Health), Eye Hospital, Wenzhou Medical University, Zhejiang, Wenzhou; 325011, China 2.National Engineering Research Center of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Zhejiang, Wenzhou; 325027, China 3.National Clinical Research Center for Ocular Diseases, Eye Hospital, Wenzhou Medical University, Wenzhou; 325027, China 4.Institute of PSI Genomics, Wenzhou Global Eye & Vision Innovation Center, Wenzhou; 325024, China
第一作者单位	眼视光学院（生物医学工程学院）、附属眼视光医院
第一作者的第一单位	眼视光学院（生物医学工程学院）、附属眼视光医院
推荐引用方式 GB/T 7714	Yao, Yinghao,Yang, Jiaying,Sun, Haojun,et al. DeepGraFT: A novel semantic segmentation auxiliary ROI-based deep learning framework for effective fundus tessellation classification[J]. Computers in Biology and Medicine,2024,169.
APA	Yao, Yinghao., Yang, Jiaying., Sun, Haojun., Kong, Hengte., Wang, Sheng., ... & Su, Jianzhong. (2024). DeepGraFT: A novel semantic segmentation auxiliary ROI-based deep learning framework for effective fundus tessellation classification. Computers in Biology and Medicine, 169.
MLA	Yao, Yinghao,et al."DeepGraFT: A novel semantic segmentation auxiliary ROI-based deep learning framework for effective fundus tessellation classification".Computers in Biology and Medicine 169(2024).