Prediction of causative genes in inherited retinal disorder from fundus photography and autofluorescence imaging using deep learning techniques. Issue 9 (20th April 2021)

• Record Type: Journal Article
• Authors: Fujinami-Yokokawa, Yu; Ninomiya, Hideki; Liu, Xiao; Yang, Lizhu; Pontikos, Nikolas; Yoshitake, Kazutoshi; Iwata, Takeshi; Sato, Yasunori; Hashimoto, Takeshi; Tsunoda, Kazushige; Miyata, Hiroaki; Fujinami, Kaoru
• Other Names: author non-byline.; Iwata Takeshi author non-byline.; Tsunoda Kazushige author non-byline.; Fujinami Kaoru author non-byline.; Ueno Shinji author non-byline.; Kuniyoshi Kazuki author non-byline.; Hayashi Takaaki author non-byline.; Kondo Mineo author non-byline.; Mizota Atsushi author non-byline.; Naoi Nobuhisa author non-byline.; Shinoda Kei author non-byline.; Kameya Shuhei author non-byline.; Kondo Hiroyuki author non-byline.; Kominami Taro author non-byline.; Terasaki Hiroko author non-byline.; Sakuramoto Hiroyuki author non-byline.; Katagiri Satoshi author non-byline.; Mizobuchi Kei author non-byline.; Nakamura Natsuko author non-byline.; Mawatari Go author non-byline.; Kurihara Toshihide author non-byline.; Tsubota Kazuo author non-byline.; Miyake Yozo author non-byline.; Yoshitake Kazutoshi author non-byline.; Nishimura Toshihide author non-byline.; Hayashizaki Yoshihide author non-byline.; Shimozawa Nobuhiro author non-byline.; Horiguchi Masayuki author non-byline.; Yamamoto Shuichi author non-byline.; Kuze Manami author non-byline.; Machida Shigeki author non-byline.; Shimada Yoshiaki author non-byline.; Nakamura Makoto author non-byline.; Fujikado Takashi author non-byline.; Hotta Yoshihiro author non-byline.; Takahashi Masayo author non-byline.; Mochizuki Kiyofumi author non-byline.; Murakami Akira author non-byline.; Kondo Hiroyuki author non-byline.; Ishida Susumu author non-byline.; Nakazawa Mitsuru author non-byline.; Hatase Tetsuhisa author non-byline.; Matsunaga Tatsuo author non-byline.; Maeda Akiko author non-byline.; Noda Kosuke author non-byline.; Tanikawa Atsuhiro author non-byline.; Yamamoto Syuji author non-byline.; Yamamoto Hiroyuki author non-byline.; Araie Makoto author non-byline.; Aihara Makoto author non-byline.; Nakazawa Toru author non-byline.; Sekiryu Tetsuju author non-byline.; Kashiwagi Kenji author non-byline.; Kosaki Kenjiro author non-byline.; Piero Carninci author non-byline.; Fukuchi Takeo author non-byline.; Hayashi Atsushi author non-byline.; Hosono Katsuhiro author non-byline.; Mori Keisuke author non-byline.; Tanaka Kouji author non-byline.; Furuya Koichi author non-byline.; Suzuki Keiichirou author non-byline.; Kohata Ryo author non-byline.; Yanagi Yasuo author non-byline.; Minegishi Yuriko author non-byline.; Iejima Daisuke author non-byline.; Suga Akiko author non-byline.; Rossmiller Brian P author non-byline.; Pan Yang author non-byline.; Oshima Tomoko author non-byline.; Nakayama Mao author non-byline.; Yamamoto Megumi author non-byline.; Minematsu Naoko author non-byline.; Mori Daisuke author non-byline.; Kijima Yusuke author non-byline.; Kurata Kentaro author non-byline.; Yamada Norihiro author non-byline.; Itoh Masayoshi author non-byline.; Kawaji Hideya author non-byline.; Murakawa Yasuhiro author non-byline.; Ando Ryo author non-byline.; Saito Wataru author non-byline.; Murakami Yusuke author non-byline.; Miyata Hiroaki author non-byline.; Yang Lizhu author non-byline.; Fujinami-Yokokawa Yu author non-byline.; Liu Xiao author non-byline.; Arno Gavin author non-byline.; Pontikos Nikolas author non-byline.; Kita Mihori author non-byline.; Hirose Hiroshi author non-byline.; Sakai Katsuyuki author non-byline.; Otori Yasumasa author non-byline.; Yamazawa Kazuki author non-byline.; Inoue Satomi author non-byline.; Kinoshita Takayuki author non-byline.;
• Is Part Of: British journal of ophthalmology. Volume 105:Issue 9(2021)
• Page Start: 1272
• Page End: 1279
• Publication Date: 2021-04-20
• Subjects: retina -- genetics -- imaging; Ophthalmology -- Periodicals; 617.7
• DOI: 10.1136/bjophthalmol-2020-318544
• Languages: English
• ISSNs: 0007-1161

Abstract

Abstract : Background/Aims: To investigate the utility of a data-driven deep learning approach in patients with inherited retinal disorder (IRD) and to predict the causative genes based on fundus photography and fundus autofluorescence (FAF) imaging. Methods: Clinical and genetic data from 1302 subjects from 729 genetically confirmed families with IRD registered with the Japan Eye Genetics Consortium were reviewed. Three categories of genetic diagnosis were selected, based on the high prevalence of their causative genes: Stargardt disease ( ABCA4 ), retinitis pigmentosa ( EYS ) and occult macular dystrophy ( RP1L1 ). Fundus photographs and FAF images were cropped in a standardised manner with a macro algorithm. Images for training/testing were selected using a randomised, fourfold cross-validation method. The application program interface was established to reach the learning accuracy of concordance (target: >80%) between the genetic diagnosis and the machine diagnosis ( ABCA4, EYS, RP1L1 and normal). Results: A total of 417 images from 156 Japanese subjects were examined, including 115 genetically confirmed patients caused by the three prevalent causative genes and 41 normal subjects. The mean overall test accuracy for fundus photographs and FAF images was 88.2% and 81.3%, respectively. The mean overall sensitivity/specificity values for fundus photographs and FAF images were 88.3%/97.4% and 81.8%/95.5%, respectively. Conclusion: A novel application of deep neural networks in the prediction of the causative IRD genes from fundus photographs and FAF, with a high prediction accuracy of over 80%, was highlighted. These achievements will extensively promote the quality of medical care by facilitating early diagnosis, especially by non-specialists, access to care, reducing the cost of referrals, and preventing unnecessary clinical and genetic testing.