Keratoconus detection using deep learning of colour-coded maps with anterior segment optical coherence tomography: a diagnostic accuracy study.

Journal: BMJ open

Published Date: Sep 27, 2019

Abstract

OBJECTIVE: To evaluate the diagnostic accuracy of keratoconus using deep learning of the colour-coded maps measured with the swept-source anterior segment optical coherence tomography (AS-OCT).

Authors

Kazutaka Kamiya

Visual Phisiology, School of Allied Health Sciences, Kitasato University, Sagamihara, Japan kamiyak-tky@umin.ac.jp.
Yuji Ayatsuka

Cresco Ltd, Technology Laboratory, Tokyo, Japan.
Yudai Kato

Cresco Ltd, Technology Laboratory, Tokyo, Japan.
Fusako Fujimura

Visual Phisiology, School of Allied Health Sciences, Kitasato University, Sagamihara, Japan.
Masahide Takahashi

Department of Ophthalmology, School of Medicine, Kitasato University, Sagamihara, Japan.
Nobuyuki Shoji

Department of Ophthalmology, School of Medicine, Kitasato University, Kanagawa, Japan.
Yosai Mori

Miyata Eye Hospital, Department of Ophthalmology, Miyakonojo, Japan.
Kazunori Miyata

Miyata Eye Hospital, Department of Ophthalmology, Miyakonojo, Japan.

Keywords

Case-Control Studies Deep Learning Disease Progression Humans Keratoconus Retrospective Studies Sensitivity and Specificity Tomography, Optical Coherence

External Resources

View on PubMed Access via DOI PubMed (31562158)

Keratoconus detection using deep learning of colour-coded maps with anterior segment optical coherence tomography: a diagnostic accuracy study.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals