Automated Volumetric Segmentation of Microaneurysms on OCT Using Artificial Intelligence

Abstract

Purpose: To develop and validate a deep learning-based method for the automated identification and volumetric segmentation of microaneurysms (MAs) in diabetic retinopathy (DR) using OCT. Participants: A total of 125 participants were enrolled, including 20 healthy eyes, 27 with mild NPDR, 30 with moderate NPDR, 30 with severe NPDR, and 18 with PDR. Methods: We obtained multiple repeated 3x3-mm scans from each participant using a commercial 120-kHz spectral-domain OCT system (Solix; Visionix/Optovue, Inc., California, USA), which were registered and averaged to generate high-definition volumes. We developed a 3D deep learning network to segment MAs volumetrically. The input to the network consists of the original OCT volume concatenated with its reflectance-inverted counterpart. Expert graders manually delineated MAs to generate annotations. We evaluated model performance at multiple levels, including voxel-level segmentation, lesion-level detection, and eye-level diagnosis. Results: In the test dataset (20 healthy, 20 DR eyes), the algorithm demonstrated high voxel-level accuracy, with F1 scores of 79.2% on single volumes and 86.1% on averaged volumes. Lesion-level detection reached an F1 score of 96.0% (single) and 97.1% (averaged), while scan-level diagnostic accuracy for MA presence was 97.5% (single and averaged). Conclusions: A deep learning-based method can accurately identify and segment MAs volumetrically on OCT, enabling quantification and characterization, and potentially aiding in the diagnosis, monitoring, and management of DR.

A general route to volumetric segmentation under annotation scarcity
s. radhakrishnan, s. mathur, a. aleksandrov +3
bioRxiv16 Sep 2026PreprintCC BY-NCFull textBioinformatics & computational biologybioRxiv
3D-MAESTRO: A scalable, modular, portable pipeline for automated processing of large-scale volumetric brain microscopy data
C. Laiton, N. Lusk, Y. Browning +27
bioRxiv9 Sep 2026PreprintCC BY-NCFull textNeurosciencebioRxiv
Fully automated diaphragm segmentation on routine 2D-cine and 3D thoracic MRI: multireader validation
Samia Boussouar, Alexiane Pasquier, Damien Vaurs +16
European radiology experimental16 Oct 2026Peer-reviewedCC BYFull textSystems & synthetic biology Medical imaging & radiologyEurope PMCHAL
Organotchi: an open-source tool for the automated segmentation, morphological characterization, and longitudinal tracking of organoids
L. Branco, T. Lautenschlager, D. Andreeva +9
bioRxiv4 Nov 2026PreprintCC BYFull textBioinformatics & computational biologybioRxiv
FDUNet-LRSA: efficient frequency-adaptive segmentation for automated crop disease inspection
Ru Han, Lei Shu, Grzegorz Cielniak +6
Frontiers in Plant Science16 Oct 2026Peer-reviewedCC BY 4.0Full textPlant biologyCrossrefEurope PMCPMC

Cite

BibTeX RIS

BibTeX

@misc{gao2026automated,
  title = {{Automated Volumetric Segmentation of Microaneurysms on OCT Using Artificial Intelligence}},
  author = {Min Gao and Yukun Guo and Tristan T. Hormel and Jinyi Hao and Azaz Khan and Steven T. Bailey and Thomas S. Hwang and Yali Jia},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.13508},
  eprint = {2609.13508},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.13508},
  note = {CC BY-NC-ND 4.0},
}

RIS

TY  - UNPB
TI  - Automated Volumetric Segmentation of Microaneurysms on OCT Using Artificial Intelligence
AU  - Min Gao
AU  - Yukun Guo
AU  - Tristan T. Hormel
AU  - Jinyi Hao
AU  - Azaz Khan
AU  - Steven T. Bailey
AU  - Thomas S. Hwang
AU  - Yali Jia
PY  - 2026
DA  - 2026/09/11
PB  - arXiv
DO  - 10.48550/arxiv.2609.13508
UR  - https://arxiv.org/abs/2609.13508
AB  - Purpose: To develop and validate a deep learning-based method for the automated identification and volumetric segmentation of microaneurysms (MAs) in diabetic retinopathy (DR) using OCT. Participants: A total of 125 participants were enrolled, including 20 healthy eyes, 27 with mild NPDR, 30 with moderate NPDR, 30 with severe NPDR, and 18 with PDR. Methods: We obtained multiple repeated 3x3-mm scans from each participant using a commercial 120-kHz spectral-domain OCT system (Solix; Visionix/Optovue, Inc., California, USA), which were registered and averaged to generate high-definition volumes. We developed a 3D deep learning network to segment MAs volumetrically. The input to the network consists of the original OCT volume concatenated with its reflectance-inverted counterpart. Expert graders manually delineated MAs to generate annotations. We evaluated model performance at multiple levels, including voxel-level segmentation, lesion-level detection, and eye-level diagnosis. Results: In the test dataset (20 healthy, 20 DR eyes), the algorithm demonstrated high voxel-level accuracy, with F1 scores of 79.2% on single volumes and 86.1% on averaged volumes. Lesion-level detection reached an F1 score of 96.0% (single) and 97.1% (averaged), while scan-level diagnostic accuracy for MA presence was 97.5% (single and averaged). Conclusions: A deep learning-based method can accurately identify and segment MAs volumetrically on OCT, enabling quantification and characterization, and potentially aiding in the diagnosis, monitoring, and management of DR.
ER  -

Abstract

Related

Cite