# Retinal Vessel Segmentation on CHASE\_DB1 (test) Source: [Retinal Vessel Segmentation on CHASE\_DB1 (test)]() Collection index: [llms.txt]() Data updated: 2026-06-23T09:23:23.085Z Evaluation of retinal vessel segmentation performance on the test split of the CHASE\_DB1 dataset, reporting standard binary classification metrics including Dice, IoU, Sensitivity, Specificity, Accuracy, and AUC. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Retinal Vessel Segmentation | | Dataset (including any stated split) | CHASE\_DB1 (test) | | Metric | Accuracy | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 26 of 26 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: SCALAR. - [Dice](): Higher is better; unit: SCALAR. - [IoU](): Higher is better; unit: SCALAR. - [Sensitivity](): Higher is better; unit: SCALAR. - [Precision](): Higher is better; unit: SCALAR. - [Specificity](): Higher is better; unit: SCALAR. - [MCC](): Higher is better; unit: SCALAR. - [AUC-ROC](): Higher is better; unit: SCALAR. - [AUC-PR](): Higher is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | D-GaussianNet 2021 | 0.9798 | Not recorded | 6a3a134e206542251d7c72a5 | | CurvSegFlow | 0.9772 | Not recorded | 6a3a134e206542251d7c72a5 | | MVM-UNet (2026) | 0.9762 | Not recorded | 6a3a134e206542251d7c72a5 | | CAR-Unet 2021 | 0.9751 | Not recorded | 6a3a134e206542251d7c72a5 | | ARU-net 2022 | 0.9746 | Not recorded | 6a3a134e206542251d7c72a5 | | MSTP-Net 2025 | 0.9745 | Not recorded | 6a3a134e206542251d7c72a5 | | Zhu et al. 2025 | 0.9744 | Not recorded | 6a3a134e206542251d7c72a5 | | RVS-FDSC 2024 | 0.9743 | Not recorded | 6a3a134e206542251d7c72a5 | | Swin-UNet 2022 | 0.9721 | Not recorded | 6a3a134e206542251d7c72a5 | | GEA-UNet 2025 | 0.9696 | Not recorded | 6a3a134e206542251d7c72a5 | | Cherukuri et al. 2020 | 0.9693 | Not recorded | 6a3a134e206542251d7c72a5 | | ResDO-UNet 2023 | 0.9672 | Not recorded | 6a3a134e206542251d7c72a5 | | MDUNet 2023 | 0.966 | Not recorded | 6a3a134e206542251d7c72a5 | | IterNet 2020 | 0.9655 | Not recorded | 6a3a134e206542251d7c72a5 | | DDPM 2023 | 0.9649 | Not recorded | 6a3a134e206542251d7c72a5 | | CTF-Net 2020 | 0.9648 | Not recorded | 6a3a134e206542251d7c72a5 | | IterMiU-Net 2023 | 0.9646 | Not recorded | 6a3a134e206542251d7c72a5 | | TransUNet 2021 | 0.9637 | Not recorded | 6a3a134e206542251d7c72a5 | | R2U-Net 2018 | 0.9634 | Not recorded | 6a3a134e206542251d7c72a5 | | AttU-Net 2018 | 0.9629 | Not recorded | 6a3a134e206542251d7c72a5 | | LadderNet 2018 | 0.962 | Not recorded | 6a3a134e206542251d7c72a5 | | Dense-UNet 2019 | 0.962 | Not recorded | 6a3a134e206542251d7c72a5 | | U-Net 2015 | 0.9578 | Not recorded | 6a3a134e206542251d7c72a5 | | RCAR-UNet 2024 | 0.9566 | Not recorded | 6a3a134e206542251d7c72a5 | | WS-DMF 2024 | 0.9566 | Not recorded | 6a3a134e206542251d7c72a5 | | GViTRSNet 2025 | 0.8386 | Not recorded | 6a3a134e206542251d7c72a5 | ### D-GaussianNet 2021 Accuracy: 0.9798. Result ID: 6a3a507bfbc373592c35b425. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CurvSegFlow Accuracy: 0.9772. Result ID: 6a3a507bfbc373592c35b436. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MVM-UNet (2026) Accuracy: 0.9762. Result ID: 6a3a507bfbc373592c35b435. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CAR-Unet 2021 Accuracy: 0.9751. Result ID: 6a3a507bfbc373592c35b427. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ARU-net 2022 Accuracy: 0.9746. Result ID: 6a3a507bfbc373592c35b429. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MSTP-Net 2025 Accuracy: 0.9745. Result ID: 6a3a507bfbc373592c35b433. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Zhu et al. 2025 Accuracy: 0.9744. Result ID: 6a3a507bfbc373592c35b434. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### RVS-FDSC 2024 Accuracy: 0.9743. Result ID: 6a3a507bfbc373592c35b42f. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Swin-UNet 2022 Accuracy: 0.9721. Result ID: 6a3a507bfbc373592c35b428. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GEA-UNet 2025 Accuracy: 0.9696. Result ID: 6a3a507bfbc373592c35b432. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Cherukuri et al. 2020 Accuracy: 0.9693. Result ID: 6a3a507bfbc373592c35b422. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ResDO-UNet 2023 Accuracy: 0.9672. Result ID: 6a3a507bfbc373592c35b42a. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MDUNet 2023 Accuracy: 0.966. Result ID: 6a3a507bfbc373592c35b42c. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### IterNet 2020 Accuracy: 0.9655. Result ID: 6a3a507bfbc373592c35b424. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DDPM 2023 Accuracy: 0.9649. Result ID: 6a3a507bfbc373592c35b42b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CTF-Net 2020 Accuracy: 0.9648. Result ID: 6a3a507bfbc373592c35b423. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### IterMiU-Net 2023 Accuracy: 0.9646. Result ID: 6a3a507bfbc373592c35b42d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### TransUNet 2021 Accuracy: 0.9637. Result ID: 6a3a507bfbc373592c35b426. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### R2U-Net 2018 Accuracy: 0.9634. Result ID: 6a3a507bfbc373592c35b420. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### AttU-Net 2018 Accuracy: 0.9629. Result ID: 6a3a507bfbc373592c35b41f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LadderNet 2018 Accuracy: 0.962. Result ID: 6a3a507bfbc373592c35b41e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Dense-UNet 2019 Accuracy: 0.962. Result ID: 6a3a507bfbc373592c35b421. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### U-Net 2015 Accuracy: 0.9578. Result ID: 6a3a507bfbc373592c35b41d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### RCAR-UNet 2024 Accuracy: 0.9566. Result ID: 6a3a507bfbc373592c35b42e. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### WS-DMF 2024 Accuracy: 0.9566. Result ID: 6a3a507bfbc373592c35b430. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GViTRSNet 2025 Accuracy: 0.8386. Result ID: 6a3a507bfbc373592c35b431. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.