Artificial intelligence support improves diagnosis accuracy in anterior segment eye diseases

被引：0

作者：

Maehara, Hiroki ^{[1
,14
]}

Ueno, Yuta ^{[2
,14
]}

Yamaguchi, Takefumi ^{[3
,14
]}

Kitaguchi, Yoshiyuki ^{[4
,14
]}

Miyazaki, Dai ^{[5
,14
]}

Nejima, Ryohei ^{[6
,14
]}

Inomata, Takenori ^{[7
,14
]}

Kato, Naoko ^{[8
,14
]}

Chikama, Tai-ichiro ^{[9
,14
]}

Ominato, Jun ^{[10
,14
]}

Yunoki, Tatsuya ^{[11
,14
]}

Tsubota, Kinya ^{[12
,14
]}

Oda, Masahiro ^{[13
,14
]}

Suzutani, Manabu ^{[1
]}

Sekiryu, Tetsuju ^{[1
]}

Oshika, Tetsuro ^{[2
,14
]}

机构：

[1] Fukushima Med Univ, Sch Med, Dept Ophthalmol, Fukushima, Japan

[2] Univ Tsukuba, Fac Med, Dept Ophthalmol, 1-1-1 Tennoudai, Tsukuba, Ibaraki 3058576, Japan

[3] Ichikawa Gen Hosp, Tokyo Dent Coll, Dept Ophthalmol, Chiba, Japan

[4] Osaka Univ, Grad Sch Med, Dept Ophthalmol, Osaka, Japan

[5] Tottori Univ, Fac Med, Div Ophthalmol & Visual Sci, Tottori, Japan

[6] Miyata Eye Hosp, Dept Ophthalmol, Miyazaki, Japan

[7] Juntendo Univ, Grad Sch Med, Dept Ophthalmol, Tokyo, Japan

[8] Tsukazaki Hosp, Dept Ophthalmol, Himeji, Hyogo, Japan

[9] Hiroshima Univ, Grad Sch Biomed & Hlth Sci, Div Ophthalmol & Visual Sci, Hiroshima, Japan

[10] Niigata Univ, Grad Sch Med & Dent Sci, Div Ophthalmol & Visual Sci, Niigata, Japan

[11] Univ Toyama, Dept Ophthalmol, Toyama, Japan

[12] Tokyo Med Univ, Dept Ophthalmol, Tokyo, Japan

[13] Nagoya Univ, Grad Sch Informat, Nagoya, Japan

[14] Japan Anterior Segment Artificial Intelligence Res, Tsukuba, Japan

来源：

SCIENTIFIC REPORTS | 2025年 / 15卷 / 01期

关键词：

Artificial intelligence; Ocular surface; AI support; Smartphone image; Slit-lamp image; DEEP LEARNING ALGORITHM; DIABETIC-RETINOPATHY; VALIDATION; CARE;

D O I：

10.1038/s41598-025-89768-6

中图分类号：

O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

CorneAI, a deep learning model designed for diagnosing cataracts and corneal diseases, was assessed for its impact on ophthalmologists' diagnostic accuracy. In the study, 40 ophthalmologists (20 specialists and 20 residents) classified 100 images, including iPhone 13 Pro photos (50 images) and diffuser slit-lamp photos (50 images), into nine categories (normal condition, infectious keratitis, immunological keratitis, corneal scar, corneal deposit, bullous keratopathy, ocular surface tumor, cataract/intraocular lens opacity, and primary angle-closure glaucoma). The iPhone and slit-lamp images represented the same cases. After initially answering without CorneAI, the same ophthalmologists responded to the same cases with CorneAI 2-4 weeks later. With CorneAI's support, the overall accuracy of ophthalmologists increased significantly from 79.2 to 88.8% (P < 0.001). Specialists' accuracy rose from 82.8 to 90.0%, and residents' from 75.6 to 86.2% (P < 0.001). Smartphone image accuracy improved from 78.7 to 85.5% and slit-lamp image accuracy from 81.2 to 90.6% (both, P < 0.001). In this study, CorneAI's own accuracy was 86%, but its support enhanced ophthalmologists' accuracy beyond the CorneAI's baseline. This study demonstrated that CorneAI, despite being trained on diffuser slit-lamp images, effectively improved diagnostic accuracy, even with smartphone images.

引用

页数：10

共 33 条

[1] A study establishing sensitivity and accuracy of smartphone photography in ophthalmologic community outreach programs: Review of a smart eye camera [J].