Papers › A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation

A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation

18 Oct 2018arXiv:1810.07842archive 2025-07-28

Nabila Abraham, Naimul Mefraz Khan

We propose a generalized focal loss function based on the Tversky index to address the issue of data imbalance in medical image segmentation. Compared to the commonly used Dice loss, our loss function achieves a better trade off between precision and recall when training on small structures such as lesions. To evaluate our loss function, we improve the attention U-Net model by incorporating an image pyramid to preserve contextual features. We experiment on the BUS 2017 dataset and ISIC 2018 dataset where lesions occupy 4.84% and 21.4% of the images area and improve segmentation accuracy when compared to the standard U-Net by 25.7% and 3.6%, respectively.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

nabsabraham/focal-tversky-unet officialmentioned in papermentioned on GitHubtfSyntology: not harvested report
EvgenyDyshlyuk/Oil_Seep_Detection mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to U-Net: Convolutional Networks for Biomedical Image Segmentation (arXiv:1505.04597; that paper's own run record: 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified); nothing checks that they implement this paper's method. report
Jo-dsa/SemanticSeg mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to U-Net: Convolutional Networks for Biomedical Image Segmentation (arXiv:1505.04597; that paper's own run record: 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified); nothing checks that they implement this paper's method. report
SahinTiryaki/Brain-tumor-segmentation-Vgg19UNet mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to U-Net: Convolutional Networks for Biomedical Image Segmentation (arXiv:1505.04597; that paper's own run record: 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified); nothing checks that they implement this paper's method. report
woans0104/project_review mentioned on GitHubSyntology: not harvested report
woans0104/sk_project mentioned on GitHubSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Image SegmentationLesion SegmentationMedical Image SegmentationSegmentationSemantic SegmentationSkin Lesion Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Lesion Segmentation BUS 2017 Dataset B Attn U-Net + Multi-Input + FTL Dice Score 0.804 #1 of 4 Archive leaderboard report
Lesion Segmentation BUS 2017 Dataset B U-Net + FTL Dice Score 0.669 #3 of 4 Archive leaderboard report
Lesion Segmentation BUS 2017 Dataset B Attn U-Net + DL Dice Score 0.615 #4 of 4 Archive leaderboard report
Lesion Segmentation ISIC 2018 Attn U-Net + Multi-Input + FTL mean Dice 0.856 #12 of 17 Archive leaderboard report
Lesion Segmentation ISIC 2018 U-Net + FTL mean Dice 0.829 #15 of 17 Archive leaderboard report
Lesion Segmentation ISIC 2018 Attn U-Net + DL mean Dice 0.806 #16 of 17 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

Concatenated Skip ConnectionConvolutionFocal LossMax PoolingReLUU-Net

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