个人科研网厅 | | 帮助
高级检索
当前位置： 首页 > 详情页

Deep learning-based classification of infectious keratitis on slit-lamp images

| 认领 | 导出 | |

文献详情

资源类型：
WOS体系：
Pubmed体系：

收录情况： ◇ SCIE

作者：
Zhang Zijun[1] * ; Wang Haoyu[2] ; Wang Shigeng[2] ; Wei Zhenyu[1] ; Zhang Yang[1] ; Wang Zhiqun[1] ; Chen Kexin[1] ; Ou Zhonghong[2] ; Liang Qingfeng[1,*1] ;
机构： [1]Beijing Institute of Ophthalmology, Beijing Tongren Eye Center and Beijing Key Laboratory of Ophthalmology and Visual Sciences, Beijing Tongren Hospital, Capital Medical University, Beijing, China. [2]Beijing University of Posts and Telecommunications, Beijing, China.
出处：
DOI： 10.1177/20406223221136071
ISSN：

关键词： auxiliary diagnosis deep learning infectious keratitis slit-lamp photos

摘要：
Infectious keratitis (IK) is an ocular emergency caused by a variety of microorganisms, including bacteria, fungi, viruses, and parasites. Culture-based methods were the gold standard for diagnosing IK, but difficult biopsy, delaying report, and low positive rate limited their clinical application.This study aims to construct a deep-learning-based auxiliary diagnostic model for early IK diagnosis.A retrospective study.IK patients with pathological diagnosis were enrolled and their slit-lamp photos were collected. Image augmentation, normalization, and histogram equalization were applied, and five image classification networks were implemented and compared. Model blending technique was used to combine the advantages of single model. The performance of combined model was validated by 10-fold cross-validation, receiver operating characteristic curves (ROC), confusion matrix, Gradient-wright class activation mapping (Grad-CAM) visualization, and t-distributed Stochastic Neighbor Embedding (t-SNE). Three experienced cornea specialists were invited and competed with the combined model on making clinical decisions.Overall, 4830 slit-lamp images were collected from patients diagnosed with IK between June 2010 and May 2021, including 1490 (30.8%) bacterial keratitis (BK), 1670 (34.6%) fungal keratitis (FK), 600 (12.4%) herpes simplex keratitis (HSK), and 1070 (22.2%) Acanthamoeba keratitis (AK). KeratitisNet, the combination of ResNext101_32x16d and DenseNet169, reached the highest accuracy 77.08%. The accuracy of KeratitisNet for diagnosing BK, FK, AK, and HSK was 70.27%, 77.71%, 83.81%, and 79.31%, and AUC was 0.86, 0.91, 0.96, and 0.98, respectively. KeratitisNet was mainly confused in distinguishing BK and FK. There were 20% of BK cases mispredicted into FK and 16% of FK cases mispredicted into BK. In diagnosing each type of IK, the accuracy of model was significantly higher than that of human ophthalmologists (p < 0.001).KeratitisNet demonstrates a good performance on clinical IK diagnosis and classification. Deep learning could provide an auxiliary diagnostic method to help clinicians suspect IK using different corneal manifestations.© The Author(s), 2022.

基金：
The authors disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This work was supported by the Open Research Fund from National Key Research and Development Program of China (grant no. 2021YFC2301000); the Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Beijing Tongren Hospital, Beihang University and Capital Medical University (grant no. BHTR-KFJJ-202001).
语种：
外文
被引次数：
WOS：
PubmedID：
中科院(CAS)分区：
出版当年[2021]版：
大类 | 3 区 医学
小类 | 3 区 药学
最新[2023]版：
大类 | 3 区 医学
小类 | 3 区 药学
JCR分区：
出版当年[2020]版：
Q1 PHARMACOLOGY & PHARMACY
最新[2023]版：
Q2 PHARMACOLOGY & PHARMACY

影响因子： 最新[2023版] 最新五年平均 出版当年[2020版] 出版当年五年平均 出版前一年[2019版] 出版后一年[2021版]

第一作者：
第一作者机构： [1]Beijing Institute of Ophthalmology, Beijing Tongren Eye Center and Beijing Key Laboratory of Ophthalmology and Visual Sciences, Beijing Tongren Hospital, Capital Medical University, Beijing, China.
通讯作者：
通讯机构： [1]Beijing Institute of Ophthalmology, Beijing Tongren Eye Center and Beijing Key Laboratory of Ophthalmology and Visual Sciences, Beijing Tongren Hospital, Capital Medical University, Beijing, China. [*1]Beijing Institute of Ophthalmology, Beijing Tongren Eye Center and Beijing Key Laboratory of Ophthalmology and Visual Sciences, Beijing Tongren Hospital, Capital Medical University, Beijing 100005, China
推荐引用方式(GB/T 7714)：
Zhang Zijun,Wang Haoyu,Wang Shigeng,et al.Deep learning-based classification of infectious keratitis on slit-lamp images[J].THERAPEUTIC ADVANCES IN CHRONIC DISEASE.2022,13:doi:10.1177/20406223221136071.
APA：
Zhang Zijun,Wang Haoyu,Wang Shigeng,Wei Zhenyu,Zhang Yang...&Liang Qingfeng.(2022).Deep learning-based classification of infectious keratitis on slit-lamp images.THERAPEUTIC ADVANCES IN CHRONIC DISEASE,13,
MLA：
Zhang Zijun,et al."Deep learning-based classification of infectious keratitis on slit-lamp images".THERAPEUTIC ADVANCES IN CHRONIC DISEASE 13.(2022)

相关文献

[1]Infectious keratitis related to orthokeratology [2]Infectious Keratitis After Keratorefractive Surgery: Update and Review of the Literature [3]A Multi-Center, Cross-Sectional Study on the Burden of Infectious Keratitis in China [4]Deep Learning in Retinoblastoma Detection and Monitoring. [5]Tacrolimus dye drop treatment for the management of early post-operative intraocular inflammation after therapeutic keratoplasty for severe infectious keratitis [6]Deep Learning-based System and AIDS-related Cytomegalovirus Retinitis [7]Quickly diagnosing Bietti crystalline dystrophy with deep learning [8]Applications of deep learning in fundus images: A review [9]Clinical diagnosis system of glaucoma based on deep learning algorithm [10]机器学习在角膜相关疾病辅助诊断中的应用

资源点击量：21166 今日访问量：0 总访问量：1219 更新日期：2025-01-01 建议使用谷歌、火狐浏览器 常见问题

版权所有©2020 首都医科大学附属北京同仁医院 技术支持：重庆聚合科技有限公司 地址：北京市东城区东交民巷1号(100730)