Papers › OCTAve: 2D en face Optical Coherence Tomography Angiography Vessel Segmentation in...

OCTAve: 2D en face Optical Coherence Tomography Angiography Vessel Segmentation in Weakly-Supervised Learning with Locality Augmentation

25 Jul 2022arXiv:2207.12238archive 2025-07-28

Amrest Chinkamol, Vetit Kanjaras, Phattarapong Sawangjai, Yitian Zhao, Thapanun Sudhawiyangkul, Chantana Chantrapornchai, Cuntai Guan, Theerawit Wilaiprasitporn

While there have been increased researches using deep learning techniques for the extraction of vascular structure from the 2D en face OCTA, for such approach, it is known that the data annotation process on the curvilinear structure like the retinal vasculature is very costly and time consuming, albeit few tried to address the annotation problem. In this work, we propose the application of the scribble-base weakly-supervised learning method to automate the pixel-level annotation. The proposed method, called OCTAve, combines the weakly-supervised learning using scribble-annotated ground truth augmented with an adversarial and a novel self-supervised deep supervision. Our novel mechanism is designed to utilize the discriminative outputs from the discrimination layer of a UNet-like architecture where the Kullback-Liebler Divergence between the aggregate discriminative outputs and the segmentation map predicate is minimized during the training. This combined method leads to the better localization of the vascular structure as shown in our experiments. We validate our proposed method on the large public datasets i.e., ROSE, OCTA-500. The segmentation performance is compared against both state-of-the-art fully-supervised and scribble-based weakly-supervised approaches. The implementation of our work used in the experiments is located at [LINK].

PaperPDFCode

Code

IoBT-VISTEC/OCTAve officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image SegmentationMedical Image SegmentationRetinal Vessel SegmentationWeakly supervised segmentationWeakly-supervised Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Retinal Vessel Segmentation ROSE-1 DVC OCTAve: OCTA-Net Dice Score 62.55 #4 of 5 Archive leaderboard report
Retinal Vessel Segmentation ROSE-1 SVC OCTAve: OCTA-Net Dice Score 78.03 #1 of 5 Archive leaderboard report
Retinal Vessel Segmentation ROSE-1 SVC-DVC OCTAve: OCTA-Net Dice Score 81.42 #1 of 5 Archive leaderboard report
Retinal Vessel Segmentation ROSE-2 OCTAve: OCTA-Net Dice Score 71.18 #1 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: SSDS

Concatenated Skip ConnectionMax PoolingReLUResNeStSSDSU-NetU-Net GAN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections