Presentation | 2023-11-14 [Short Paper] Choroid layer extraction for 3D OCT images using a deep learning network fusing CNN and Transformer Shingo Tamachi, Takayuki Okamoto, Takehito Iwase, Yuto Kawamata, Hirotaka Yokouchi, Hideaki Haneishi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The choroid, a dense vascular layer located in the fundus, accounts for the majority of the blood supply to the retina. In recent years, the correlation between choroidal structure and pathophysiology has been revealed in various eye diseases, emphasizing the significance of the quantitative evaluation of choroidal structures for understanding the pathogenesis of ocular diseases and illnesses. This study aims to develop a method for extracting choroidal structures from three-dimensional (3D) optical coherence tomography (OCT) images of both normal and diseased eyes. The extraction method incorporates preprocessing techniques capable of reducing tailing artifacts and uses a transformer-based 3D deep learning network which embedded convolutional operations. The experimental results show that the proposed method achieved highly accurate choroidal structure extraction with an F-score of 97.9% for both normal and central serous chorioretinopathy (CSC) cases. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Choroid / Deep Learning / Optical Coherence Tomography / Transformer |
Paper # | MICT2023-28,MI2023-21 |
Date of Issue | 2023-11-07 (MICT, MI) |
Conference Information | |
Committee | MI / MICT |
---|---|
Conference Date | 2023/11/14(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Ryo Haraguchi(Univ. of Hyogo) / Hirokazu Tanaka(Hiroshima City Univ.) |
Vice Chair | Hideaki Haneishi(Chiba Univ.) / Takayuki Kitasaka(Aichi Inst. of Tech.) / Chika Sugimoto(Yokohama National Univ.) / Daisuke Anzai(Nagoya Inst. of Tech.) |
Secretary | Hideaki Haneishi(Yamaguchi Univ.) / Takayuki Kitasaka(NAIST) / Chika Sugimoto(Okayama Pref. Univ.) / Daisuke Anzai(Hiroshima City Univ) |
Assistant | Takeshi Hara(Gifu Univ.) / Kenichi Morooka(Okayama Univ.) / Dairoku Muramatsu(Univ. of Electro & Comm.) / Natsuki Nakayama(Nagoya Univ.) / Ami Tanaka(Ritsumeikan Univ.) / Kun Li(Kagawa Univ.) |
Paper Information | |
Registration To | Technical Committee on Medical Imaging / Technical Committee on Healthcare and Medical Information Communication Technology |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | [Short Paper] Choroid layer extraction for 3D OCT images using a deep learning network fusing CNN and Transformer |
Sub Title (in English) | |
Keyword(1) | Choroid |
Keyword(2) | Deep Learning |
Keyword(3) | Optical Coherence Tomography |
Keyword(4) | Transformer |
1st Author's Name | Shingo Tamachi |
1st Author's Affiliation | Chiba University(Chiba Univ.) |
2nd Author's Name | Takayuki Okamoto |
2nd Author's Affiliation | Chiba University(Chiba Univ.) |
3rd Author's Name | Takehito Iwase |
3rd Author's Affiliation | Chiba University(Chiba Univ.) |
4th Author's Name | Yuto Kawamata |
4th Author's Affiliation | Chiba University(Chiba Univ.) |
5th Author's Name | Hirotaka Yokouchi |
5th Author's Affiliation | Chiba University(Chiba Univ.) |
6th Author's Name | Hideaki Haneishi |
6th Author's Affiliation | Chiba University(Chiba Univ.) |
Date | 2023-11-14 |
Paper # | MICT2023-28,MI2023-21 |
Volume (vol) | vol.123 |
Number (no) | MICT-256,MI-257 |
Page | pp.pp.13-14(MICT), pp.13-14(MI), |
#Pages | 2 |
Date of Issue | 2023-11-07 (MICT, MI) |