Addressing Annotation Scarcity in Hyperspectral Brain Image Segmentation with Unsupervised Domain Adaptation

• URL: http://arxiv.org/abs/2508.16934v1
• Date: Sat, 23 Aug 2025 07:55:42 GMT
• Title: Addressing Annotation Scarcity in Hyperspectral Brain Image Segmentation with Unsupervised Domain Adaptation
• Abstract summary: This work presents a novel deep learning framework for segmenting cerebral vasculature in hyperspectral brain images.<n>We address the critical challenge of severe label scarcity, which impedes conventional supervised training.
• Score: 19.825726661157965
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This work presents a novel deep learning framework for segmenting cerebral vasculature in hyperspectral brain images. We address the critical challenge of severe label scarcity, which impedes conventional supervised training. Our approach utilizes a novel unsupervised domain adaptation methodology, using a small, expert-annotated ground truth alongside unlabeled data. Quantitative and qualitative evaluations confirm that our method significantly outperforms existing state-of-the-art approaches, demonstrating the efficacy of domain adaptation for label-scarce biomedical imaging tasks.

Related papers

• SegMix:Shuffle-based Feedback Learning for Semantic Segmentation of Pathology Images [6.139957222494142]
  We propose a novel shuffle-based feedback learning method inspired by curriculum learning to generate higher-quality pseudo-semantic segmentation masks.<n> Experimental results demonstrate that our proposed approach outperforms state-of-the-arts on three different datasets.
  arXiv  Detail & Related papers  (2026-04-17T07:33:54Z)
• Instance-Aware Pseudo-Labeling and Class-Focused Contrastive Learning for Weakly Supervised Domain Adaptive Segmentation of Electron Microscopy [4.145365369120085]
  unsupervised domain adaptation (UDA) methods have relatively low performance in practical applications.<n>We introduce a novel instance-aware pseudo-label (IPL) selection strategy.<n>Our method outperforms existing UDA and WDA methods, significantly narrowing the performance gap with the supervised upper bound.
  arXiv  Detail & Related papers  (2025-10-18T11:05:37Z)
• Semi-Supervised Medical Image Segmentation via Dual Networks [1.904929457002693]
  We propose an innovative semi-supervised 3D medical image segmentation method to reduce the dependency on large, expert-labeled datasets.<n>We introduce a dual-network architecture to address the limitations of existing methods in using contextual information.<n> Experiments on clinical magnetic resonance imaging demonstrate that our approach outperforms state-of-the-art techniques.
  arXiv  Detail & Related papers  (2025-05-23T09:59:26Z)
• Adaptive Semi-Supervised Segmentation of Brain Vessels with Ambiguous Labels [63.415444378608214]
  Our approach incorporates innovative techniques including progressive semi-supervised learning, adaptative training strategy, and boundary enhancement. Experimental results on 3DRA datasets demonstrate the superiority of our method in terms of mesh-based segmentation metrics.
  arXiv  Detail & Related papers  (2023-08-07T14:16:52Z)
• Domain Adaptive Multiple Instance Learning for Instance-level Prediction of Pathological Images [45.132775668689604]
  We propose a new task setting to improve the classification performance of the target dataset without increasing annotation costs. In order to combine the supervisory information of both methods effectively, we propose a method to create pseudo-labels with high confidence.
  arXiv  Detail & Related papers  (2023-04-07T08:31:06Z)
• Self-Supervised Domain Adaptation for Diabetic Retinopathy Grading using Vessel Image Reconstruction [61.58601145792065]
  We learn invariant target-domain features by defining a novel self-supervised task based on retinal vessel image reconstructions. It can be shown that our approach outperforms existing domain strategies.
  arXiv  Detail & Related papers  (2021-07-20T09:44:07Z)
• Pathological Image Segmentation with Noisy Labels [13.8002043402326]
  We propose a novel label re-weighting framework to account for the reliability of different experts' labels on each pixel. We also devise a new attention heatmap, which takes roughness as prior knowledge to guide the model to focus on important regions.
  arXiv  Detail & Related papers  (2021-03-20T03:36:06Z)
• Towards Unbiased COVID-19 Lesion Localisation and Segmentation via Weakly Supervised Learning [66.36706284671291]
  We propose a data-driven framework supervised by only image-level labels to support unbiased lesion localisation. The framework can explicitly separate potential lesions from original images, with the help of a generative adversarial network and a lesion-specific decoder.
  arXiv  Detail & Related papers  (2021-03-01T06:05:49Z)
• Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation [116.48885692054724]
  We propose a reinforcement learning based selective pseudo-labeling method for semi-supervised domain adaptation. We develop a deep Q-learning model to select both accurate and representative pseudo-labeled instances. Our proposed method is evaluated on several benchmark datasets for SSDA, and demonstrates superior performance to all the comparison methods.
  arXiv  Detail & Related papers  (2020-12-07T03:37:38Z)
• Contrastive Registration for Unsupervised Medical Image Segmentation [1.5125686694430571]
  We present a novel contrastive registration architecture for unsupervised medical image segmentation. Firstly, we propose an architecture to capture the image-to-image transformation pattern via registration for unsupervised medical image segmentation. Secondly, we embed a contrastive learning mechanism into the registration architecture to enhance the discriminating capacity of the network in the feature-level.
  arXiv  Detail & Related papers  (2020-11-17T19:29:08Z)
• Multi-label Thoracic Disease Image Classification with Cross-Attention Networks [65.37531731899837]
  We propose a novel scheme of Cross-Attention Networks (CAN) for automated thoracic disease classification from chest x-ray images. We also design a new loss function that beyond cross-entropy loss to help cross-attention process and is able to overcome the imbalance between classes and easy-dominated samples within each class.
  arXiv  Detail & Related papers  (2020-07-21T14:37:00Z)
• Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis [102.40869566439514]
  We seek to exploit rich labeled data from relevant domains to help the learning in the target task via Unsupervised Domain Adaptation (UDA) Unlike most UDA methods that rely on clean labeled data or assume samples are equally transferable, we innovatively propose a Collaborative Unsupervised Domain Adaptation algorithm. We theoretically analyze the generalization performance of the proposed method, and also empirically evaluate it on both medical and general images.
  arXiv  Detail & Related papers  (2020-07-05T11:49:17Z)

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.