Alzheimer-OCT Veri Kümesi ve Derin Ö?grenme ile Alzheimer Hastali?gi Tespiti

Busra Sahin; Yasemin Turkan; Fatih Arpaci; Ozan Arslan; Sude Dilay Tunc; Gonca Kaplan; Devrim Toslak; Mehmet Bulut; Aylin Yaman; Faik Boray Tek

doi:10.1109/SIU71813.2026.11636401

Alzheimer-OCT Veri Kümesi ve Derin Ö?grenme ile Alzheimer Hastali?gi Tespiti

Busra Sahin^*
, Yasemin Turkan
, Fatih Arpaci
, Ozan Arslan
, Sude Dilay Tunc
, Gonca Kaplan
, Devrim Toslak
, Mehmet Bulut
, Aylin Yaman
, Faik Boray Tek

^*Bu çalışma için yazışmadan sorumlu yazar

Yapay Zeka ve Veri Mühendisliği Bölümü

Istanbul Technical University
Bilgisayar Mühendisliǧi
Isik University
Göz Polikliniǧi
Nöroloji Polikliniǧi
Antalya Belek Üniversitesi
Tip Fakültesi Nöroloji Anabilim Dali
Istinye University

Araştırma çıktısı: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › Hakemli

Özet

This study introduces a new clinical dataset for the detection of Alzheimer's disease (AD), the Alzheimer-OCT (AOCT) Set, and presents deep learning-based analyses. The dataset includes optical coherence tomography (OCT), angiography (OCTA) and fundus images from 31 volunteer participants. To overcome the limited data constraint, transfer learning strategies were employed; 2D slice-based deep learning architectures were compared with the 3D PointNet++ approach, which directly models spatial relationships by converting OCT volumes into point clouds. The results show that the developed 2D and 3D models are able to distinguish retinal structural changes associated with AD and that clinical OCT data may be a potential biomarker for AD diagnosis.

Tercüme edilen katkı başlığı	Alzheimer-OCT Dataset and Detection of Alzheimer's Disease using Deep Learning
Orijinal dil	Türkçe
Ana bilgisayar yayını başlığı	SIU 2026 - 34th Signal Processing and Communications Applications Conference, Conference Proceedings
Yayınlayan	Institute of Electrical and Electronics Engineers Inc.
ISBN (Elektronik)	9798319510464
DOI'lar	https://doi.org/10.1109/SIU71813.2026.11636401
Yayın durumu	Yayınlandı - 2026
Etkinlik	34th Signal Processing and Communications Applications Conference, SIU 2026 - Istanbul, Türkiye Süre: 7 Tem 2026 → 10 Tem 2026

Yayın serisi

Adı	SIU 2026 - 34th Signal Processing and Communications Applications Conference, Conference Proceedings

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	34th Signal Processing and Communications Applications Conference, SIU 2026
Ülke/Bölge	Türkiye
Şehir	Istanbul
Periyot	7/07/26 → 10/07/26

Bibliyografik not

Publisher Copyright:
© 2026 IEEE.

Keywords

Alzheimer's Disease
Deep Learning
Fundus
Optical Coherence Tomography
Point Cloud
PointNet++
Transfer Learning

Belgeye Erişim

10.1109/SIU71813.2026.11636401

Diğer Dosyalar ve Linkler

Link to publication in Scopus

Alıntı Yap

Sahin, B., Turkan, Y., Arpaci, F., Arslan, O., Tunc, S. D., Kaplan, G., Toslak, D., Bulut, M., Yaman, A., & Tek, F. B. (2026). Alzheimer-OCT Veri Kümesi ve Derin Ö?grenme ile Alzheimer Hastali?gi Tespiti. In SIU 2026 - 34th Signal Processing and Communications Applications Conference, Conference Proceedings (SIU 2026 - 34th Signal Processing and Communications Applications Conference, Conference Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SIU71813.2026.11636401

Sahin, Busra ; Turkan, Yasemin ; Arpaci, Fatih et al. / Alzheimer-OCT Veri Kümesi ve Derin Ö?grenme ile Alzheimer Hastali?gi Tespiti. SIU 2026 - 34th Signal Processing and Communications Applications Conference, Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2026. (SIU 2026 - 34th Signal Processing and Communications Applications Conference, Conference Proceedings).

@inproceedings{bc3c972598174307b8eb789193630a67,

title = "Alzheimer-OCT Veri K{\"u}mesi ve Derin {\"O}?grenme ile Alzheimer Hastali?gi Tespiti",

abstract = "This study introduces a new clinical dataset for the detection of Alzheimer's disease (AD), the Alzheimer-OCT (AOCT) Set, and presents deep learning-based analyses. The dataset includes optical coherence tomography (OCT), angiography (OCTA) and fundus images from 31 volunteer participants. To overcome the limited data constraint, transfer learning strategies were employed; 2D slice-based deep learning architectures were compared with the 3D PointNet++ approach, which directly models spatial relationships by converting OCT volumes into point clouds. The results show that the developed 2D and 3D models are able to distinguish retinal structural changes associated with AD and that clinical OCT data may be a potential biomarker for AD diagnosis.",

keywords = "Alzheimer's Disease, Deep Learning, Fundus, Optical Coherence Tomography, Point Cloud, PointNet++, Transfer Learning",

author = "Busra Sahin and Yasemin Turkan and Fatih Arpaci and Ozan Arslan and Tunc, \{Sude Dilay\} and Gonca Kaplan and Devrim Toslak and Mehmet Bulut and Aylin Yaman and Tek, \{Faik Boray\}",

note = "Publisher Copyright: {\textcopyright} 2026 IEEE.; 34th Signal Processing and Communications Applications Conference, SIU 2026 ; Conference date: 07-07-2026 Through 10-07-2026",

year = "2026",

doi = "10.1109/SIU71813.2026.11636401",

language = "T{\"u}rk{\c c}e",

series = "SIU 2026 - 34th Signal Processing and Communications Applications Conference, Conference Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "SIU 2026 - 34th Signal Processing and Communications Applications Conference, Conference Proceedings",

address = "United States",

}

Sahin, B, Turkan, Y, Arpaci, F, Arslan, O, Tunc, SD, Kaplan, G, Toslak, D, Bulut, M, Yaman, A & Tek, FB 2026, Alzheimer-OCT Veri Kümesi ve Derin Ö?grenme ile Alzheimer Hastali?gi Tespiti. in SIU 2026 - 34th Signal Processing and Communications Applications Conference, Conference Proceedings. SIU 2026 - 34th Signal Processing and Communications Applications Conference, Conference Proceedings, Institute of Electrical and Electronics Engineers Inc., 34th Signal Processing and Communications Applications Conference, SIU 2026, Istanbul, Türkiye, 7/07/26. https://doi.org/10.1109/SIU71813.2026.11636401

Alzheimer-OCT Veri Kümesi ve Derin Ö?grenme ile Alzheimer Hastali?gi Tespiti. / Sahin, Busra; Turkan, Yasemin; Arpaci, Fatih et al.
SIU 2026 - 34th Signal Processing and Communications Applications Conference, Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2026. (SIU 2026 - 34th Signal Processing and Communications Applications Conference, Conference Proceedings).

Araştırma çıktısı: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › Hakemli

TY - GEN

T1 - Alzheimer-OCT Veri Kümesi ve Derin Ö?grenme ile Alzheimer Hastali?gi Tespiti

AU - Sahin, Busra

AU - Turkan, Yasemin

AU - Arpaci, Fatih

AU - Arslan, Ozan

AU - Tunc, Sude Dilay

AU - Kaplan, Gonca

AU - Toslak, Devrim

AU - Bulut, Mehmet

AU - Yaman, Aylin

AU - Tek, Faik Boray

PY - 2026

Y1 - 2026

N2 - This study introduces a new clinical dataset for the detection of Alzheimer's disease (AD), the Alzheimer-OCT (AOCT) Set, and presents deep learning-based analyses. The dataset includes optical coherence tomography (OCT), angiography (OCTA) and fundus images from 31 volunteer participants. To overcome the limited data constraint, transfer learning strategies were employed; 2D slice-based deep learning architectures were compared with the 3D PointNet++ approach, which directly models spatial relationships by converting OCT volumes into point clouds. The results show that the developed 2D and 3D models are able to distinguish retinal structural changes associated with AD and that clinical OCT data may be a potential biomarker for AD diagnosis.

AB - This study introduces a new clinical dataset for the detection of Alzheimer's disease (AD), the Alzheimer-OCT (AOCT) Set, and presents deep learning-based analyses. The dataset includes optical coherence tomography (OCT), angiography (OCTA) and fundus images from 31 volunteer participants. To overcome the limited data constraint, transfer learning strategies were employed; 2D slice-based deep learning architectures were compared with the 3D PointNet++ approach, which directly models spatial relationships by converting OCT volumes into point clouds. The results show that the developed 2D and 3D models are able to distinguish retinal structural changes associated with AD and that clinical OCT data may be a potential biomarker for AD diagnosis.

KW - Alzheimer's Disease

KW - Deep Learning

KW - Fundus

KW - Optical Coherence Tomography

KW - Point Cloud

KW - PointNet++

KW - Transfer Learning

UR - https://www.scopus.com/pages/publications/105048756796

U2 - 10.1109/SIU71813.2026.11636401

DO - 10.1109/SIU71813.2026.11636401

M3 - Konferans katkısı

AN - SCOPUS:105048756796

T3 - SIU 2026 - 34th Signal Processing and Communications Applications Conference, Conference Proceedings

BT - SIU 2026 - 34th Signal Processing and Communications Applications Conference, Conference Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 34th Signal Processing and Communications Applications Conference, SIU 2026

Y2 - 7 July 2026 through 10 July 2026

ER -

Sahin B, Turkan Y, Arpaci F, Arslan O, Tunc SD, Kaplan G et al. Alzheimer-OCT Veri Kümesi ve Derin Ö?grenme ile Alzheimer Hastali?gi Tespiti. In SIU 2026 - 34th Signal Processing and Communications Applications Conference, Conference Proceedings. Institute of Electrical and Electronics Engineers Inc. 2026. (SIU 2026 - 34th Signal Processing and Communications Applications Conference, Conference Proceedings). doi: 10.1109/SIU71813.2026.11636401

Alzheimer-OCT Veri Kümesi ve Derin Ö?grenme ile Alzheimer Hastali?gi Tespiti

Özet

Yayın serisi

???event.eventtypes.event.conference???

Bibliyografik not

Keywords

Belgeye Erişim

Diğer Dosyalar ve Linkler

Parmak izi

Alıntı Yap