Papers › LUNet: Deep Learning for the Segmentation of Arterioles and Venules in High Resolution...

LUNet: Deep Learning for the Segmentation of Arterioles and Venules in High Resolution Fundus Images

11 Sep 2023arXiv:2309.05780archive 2025-07-28

Jonathan Fhima, Jan Van Eijgen, Hana Kulenovic, Valérie Debeuf, Marie Vangilbergen, Marie-Isaline Billen, Heloïse Brackenier, Moti Freiman, Ingeborg Stalmans, Joachim A. Behar

The retina is the only part of the human body in which blood vessels can be accessed non-invasively using imaging techniques such as digital fundus images (DFI). The spatial distribution of the retinal microvasculature may change with cardiovascular diseases and thus the eyes may be regarded as a window to our hearts. Computerized segmentation of the retinal arterioles and venules (A/V) is essential for automated microvasculature analysis. Using active learning, we created a new DFI dataset containing 240 crowd-sourced manual A/V segmentations performed by fifteen medical students and reviewed by an ophthalmologist, and developed LUNet, a novel deep learning architecture for high resolution A/V segmentation. LUNet architecture includes a double dilated convolutional block that aims to enhance the receptive field of the model and reduce its parameter count. Furthermore, LUNet has a long tail that operates at high resolution to refine the segmentation. The custom loss function emphasizes the continuity of the blood vessels. LUNet is shown to significantly outperform two state-of-the-art segmentation algorithms on the local test set as well as on four external test sets simulating distribution shifts across ethnicity, comorbidities, and annotators. We make the newly created dataset open access (upon publication).

PaperPDFCode

Code

aim-lab/LUNet officialtf 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

Active LearningArtery/Veins Retinal Vessel SegmentationRetinal Vessel SegmentationSegmentation

Datasets

Introduced by this paper, per the archive.

INSPIRE-AVR (LUNet subset)UZLF

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Artery/Veins Retinal Vessel Segmentation INSPIRE-AVR (LUNet subset) LUNet Average Dice (0.5*Dice_a + 0.5*Dice_v) 75.6 #1 of 1 Archive leaderboard report
Artery/Veins Retinal Vessel Segmentation UZLF LUNet Average Dice (0.5*Dice_a + 0.5*Dice_v) 83.2 #1 of 5 Archive leaderboard report
Artery/Veins Retinal Vessel Segmentation UZLF Junior Ophtalmologist Average Dice (0.5*Dice_a + 0.5*Dice_v) 82.6 #2 of 5 Archive leaderboard report
Retinal Vessel Segmentation INSPIRE-AVR (LUNet subset) LUNet Average Dice 75.6 #1 of 1 Archive leaderboard report
Retinal Vessel Segmentation UZLF LUNet Average Dice (0.5*Dice_a + 0.5*Dice_v) 83.2 #1 of 5 Archive leaderboard report
Retinal Vessel Segmentation UZLF Junior Ophtalmologist Average Dice (0.5*Dice_a + 0.5*Dice_v) 82.6 #2 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.

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