DTU-Net: Learning Topological Similarity for Curvilinear Structure Segmentation

• URL: http://arxiv.org/abs/2205.11115v1
• Date: Mon, 23 May 2022 08:15:26 GMT
• Title: DTU-Net: Learning Topological Similarity for Curvilinear Structure Segmentation
• Authors: Manxi Lin, Zahra Bashir, Martin Gr{\o}nneb{\ae}k Tolsgaard, Anders Nymark Christensen, Aasa Feragen
• Abstract summary: We present DTU-Net, a dual-decoder and topology-aware deep neural network consisting of two sequential light-weight U-Nets. The texture net makes a coarse prediction using image texture information. The topology net learns topological information from the coarse prediction by employing a triplet loss trained to recognize false and missed splits.
• Score: 2.9398911304923447
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Curvilinear structure segmentation plays an important role in many applications. The standard formulation of segmentation as pixel-wise classification often fails to capture these structures due to the small size and low contrast. Some works introduce prior topological information to address this problem with the cost of expensive computations and the need for extra labels. Moreover, prior work primarily focuses on avoiding false splits by encouraging the connection of small gaps. Less attention has been given to avoiding missed splits, namely the incorrect inference of structures that are not visible in the image. In this paper, we present DTU-Net, a dual-decoder and topology-aware deep neural network consisting of two sequential light-weight U-Nets, namely a texture net, and a topology net. The texture net makes a coarse prediction using image texture information. The topology net learns topological information from the coarse prediction by employing a triplet loss trained to recognize false and missed splits, and provides a topology-aware separation of the foreground and background. The separation is further utilized to correct the coarse prediction. We conducted experiments on a challenging multi-class ultrasound scan segmentation dataset and an open dataset for road extraction. Results show that our model achieves state-of-the-art results in both segmentation accuracy and continuity. Compared to existing methods, our model corrects both false positive and false negative examples more effectively with no need for prior knowledge.

Related papers

• Deep Loss Convexification for Learning Iterative Models [11.36644967267829]
  Iterative methods such as iterative closest point (ICP) for point cloud registration often suffer from bad local optimality. We propose learning to form a convex landscape around each ground truth.
  arXiv  Detail & Related papers  (2024-11-16T01:13:04Z)
• PI-Att: Topology Attention for Segmentation Networks through Adaptive Persistence Image Representation [1.4680035572775534]
  We introduce a new topology-aware loss function, which explicitly forces the network to minimize the topological dissimilarity between the ground truth and prediction maps. We quantify the topology of each map by the persistence image representation, for the first time in the context of a segmentation network loss. The effectiveness of the proposed PI-Att loss is demonstrated on two different datasets for aorta and great vessel segmentation in computed tomography images.
  arXiv  Detail & Related papers  (2024-08-15T09:06:49Z)
• SINDER: Repairing the Singular Defects of DINOv2 [61.98878352956125]
  Vision Transformer models trained on large-scale datasets often exhibit artifacts in the patch token they extract. We propose a novel fine-tuning smooth regularization that rectifies structural deficiencies using only a small dataset.
  arXiv  Detail & Related papers  (2024-07-23T20:34:23Z)
• BuyTheDips: PathLoss for improved topology-preserving deep learning-based image segmentation [1.8899300124593648]
  We propose a new deep image segmentation method which relies on a new leakage loss: the Pathloss. Our method outperforms state-of-the-art topology-aware methods on two representative datasets of different natures.
  arXiv  Detail & Related papers  (2022-07-23T07:19:30Z)
• Topology-Preserving Segmentation Network: A Deep Learning Segmentation Framework for Connected Component [7.95119530218428]
  In medical imaging, the topology of the structure, such as the kidney or lung, is usually known. A it topology-preserving segmentation network (TPSN) is trained to give an accurate segmentation result. TPSN is a deformation-based model that yields a deformation map through a UNet. A multi-scale TPSN is developed in this paper that incorporates multi-level information of images to produce more precise segmentation results.
  arXiv  Detail & Related papers  (2022-02-27T09:56:33Z)
• TA-Net: Topology-Aware Network for Gland Segmentation [71.52681611057271]
  We propose a novel topology-aware network (TA-Net) to accurately separate densely clustered and severely deformed glands. TA-Net has a multitask learning architecture and enhances the generalization of gland segmentation. It achieves state-of-the-art performance on the two datasets.
  arXiv  Detail & Related papers  (2021-10-27T17:10:58Z)
• Residual Moment Loss for Medical Image Segmentation [56.72261489147506]
  Location information is proven to benefit the deep learning models on capturing the manifold structure of target objects. Most existing methods encode the location information in an implicit way, for the network to learn. We propose a novel loss function, namely residual moment (RM) loss, to explicitly embed the location information of segmentation targets.
  arXiv  Detail & Related papers  (2021-06-27T09:31:49Z)
• Generic Perceptual Loss for Modeling Structured Output Dependencies [78.59700528239141]
  We show that, what matters is the network structure instead of the trained weights. We demonstrate that a randomly-weighted deep CNN can be used to model the structured dependencies of outputs.
  arXiv  Detail & Related papers  (2021-03-18T23:56:07Z)
• Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition [126.51241919472356]
  We design a simple and highly modularized graph convolutional network architecture for skeleton-based action recognition. Our network is constructed by repeating a building block that aggregates multi-granularity information from both the spatial and temporal paths.
  arXiv  Detail & Related papers  (2020-11-26T14:43:04Z)
• Pairwise Relation Learning for Semi-supervised Gland Segmentation [90.45303394358493]
  We propose a pairwise relation-based semi-supervised (PRS2) model for gland segmentation on histology images. This model consists of a segmentation network (S-Net) and a pairwise relation network (PR-Net) We evaluate our model against five recent methods on the GlaS dataset and three recent methods on the CRAG dataset.
  arXiv  Detail & Related papers  (2020-08-06T15:02:38Z)
• Learning to segment from misaligned and partial labels [0.0]
  Many non-urban settings lack the ground-truth needed for accurate segmentation. Open source infrastructure annotations like OpenStreetMaps (OSM) are representative of this issue. We present a novel and generalizable two-stage framework that enables improved pixel-wise image segmentation given misaligned and missing annotations.
  arXiv  Detail & Related papers  (2020-05-27T06:02:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.