Evidential learning driven Breast Tumor Segmentation with Stage-divided Vision-Language Interaction

• URL: http://arxiv.org/abs/2603.11206v1
• Date: Wed, 11 Mar 2026 18:24:07 GMT
• Title: Evidential learning driven Breast Tumor Segmentation with Stage-divided Vision-Language Interaction
• Abstract summary: Breast cancer is one of the most common causes of death among women worldwide, with millions of fatalities annually.<n>Previous deep-learning based tumor segmentation methods have limitations in accurately locating tumor contours.<n>We propose text-guided Breast Tumor model (TextBCS) with stage-divided vision-language interaction and evidential learning.
• Score: 2.195014842786437
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Breast cancer is one of the most common causes of death among women worldwide, with millions of fatalities annually. Magnetic Resonance Imaging (MRI) can provide various sequences for characterizing tumor morphology and internal patterns, and becomes an effective tool for detection and diagnosis of breast tumors. However, previous deep-learning based tumor segmentation methods have limitations in accurately locating tumor contours due to the challenge of low contrast between cancer and normal areas and blurred boundaries. Leveraging text prompt information holds promise in ameliorating tumor segmentation effect by delineating segmentation regions. Inspired by this, we propose text-guided Breast Tumor Segmentation model (TextBCS) with stage-divided vision-language interaction and evidential learning. Specifically, the proposed stage-divided vision-language interaction facilitates information mutual between visual and text features at each stage of down-sampling, further exerting the advantages of text prompts to assist in locating lesion areas in low contrast scenarios. Moreover, the evidential learning is adopted to quantify the segmentation uncertainty of the model for blurred boundary. It utilizes the variational Dirichlet to characterize the distribution of the segmentation probabilities, addressing the segmentation uncertainties of the boundaries. Extensive experiments validate the superiority of our TextBCS over other segmentation networks, showcasing the best breast tumor segmentation performance on publicly available datasets.

Related papers

• Diffusion-Refined Segmentation and Vision-Language Interpretation for Pediatric Brain Tumor MRI [0.0]
  We present a two-stage deep learning framework for improving pediatric brain MRI segmentation.<n>First, we evaluate 3D Res U-Net and Swin-UNETR baselines on BraTS-PEDs MRI scans.<n>Second, we introduce diffusion-based refinement models conditioned on coarse Swin-UNETR predictions.
  arXiv  Detail & Related papers  (2026-06-12T03:38:40Z)
• Advancing Generalizable Tumor Segmentation with Anomaly-Aware Open-Vocabulary Attention Maps and Frozen Foundation Diffusion Models [11.774375458215193]
  Generalizable Tumor aims to train a single model for zero-shot tumor segmentation across diverse anatomical regions.<n>DiffuGTS creates anomaly-aware open-vocabulary attention maps based on text prompts.<n>Experiments on four datasets and seven tumor categories demonstrate the superior performance of our method.
  arXiv  Detail & Related papers  (2025-05-05T16:05:37Z)
• Task-oriented Uncertainty Collaborative Learning for Label-Efficient Brain Tumor Segmentation [6.722672686635773]
  Multi-contrast magnetic resonance imaging (MRI) plays a vital role in brain tumor segmentation and diagnosis.<n>Existing methods still face the challenges of multi-level specificity perception across different contrasts.<n>We propose a Task-oriented Uncertainty Collaborative Learning framework for multi-contrast MRI segmentation.
  arXiv  Detail & Related papers  (2025-03-07T18:44:53Z)
• Enhanced MRI Representation via Cross-series Masking [48.09478307927716]
  Cross-Series Masking (CSM) Strategy for effectively learning MRI representation in a self-supervised manner.<n>Method achieves state-of-the-art performance on both public and in-house datasets.
  arXiv  Detail & Related papers  (2024-12-10T10:32:09Z)
• Mask-Enhanced Segment Anything Model for Tumor Lesion Semantic Segmentation [48.107348956719775]
  We introduce Mask-Enhanced SAM (M-SAM), an innovative architecture tailored for 3D tumor lesion segmentation. We propose a novel Mask-Enhanced Adapter (MEA) within M-SAM that enriches the semantic information of medical images with positional data from coarse segmentation masks. Our M-SAM achieves high segmentation accuracy and also exhibits robust generalization.
  arXiv  Detail & Related papers  (2024-03-09T13:37:02Z)
• Multilevel Perception Boundary-guided Network for Breast Lesion Segmentation in Ultrasound Images [9.252383213566947]
  We propose a PBNet composed by a multilevel global perception module (MGPM) and a boundary guided module (BGM) to segment breast tumors from ultrasound images. In MGPM, the long-range spatial dependence between the voxels in a single level feature maps are modeled, and then the multilevel semantic information is fused. In BGM, the tumor boundaries are extracted from the high-level semantic maps using the dilation and erosion effects of max pooling.
  arXiv  Detail & Related papers  (2023-10-23T07:21:02Z)
• BreastSAM: A Study of Segment Anything Model for Breast Tumor Detection in Ultrasound Images [2.752682633344525]
  We investigated the Segment Anything Model (SAM) for the task of interactive segmentation of breast tumors in ultrasound images. We explored three pre-trained model variants: ViT_h, ViT_l, and ViT_b, among which ViT_l demonstrated superior performance in terms of mean pixel accuracy, Dice score, and IoU score. The study further evaluated the model's differential performance in segmenting malignant and benign breast tumors, with the model showing exceptional proficiency in both categories.
  arXiv  Detail & Related papers  (2023-05-21T12:40:25Z)
• Global Guidance Network for Breast Lesion Segmentation in Ultrasound Images [84.03487786163781]
  We develop a deep convolutional neural network equipped with a global guidance block (GGB) and breast lesion boundary detection modules. Our network outperforms other medical image segmentation methods and the recent semantic segmentation methods on breast ultrasound lesion segmentation.
  arXiv  Detail & Related papers  (2021-04-05T13:15:22Z)
• Sequential Learning on Liver Tumor Boundary Semantics and Prognostic Biomarker Mining [73.23533486979166]
  Capsular invasion on tumor boundary has proven to be clinically correlated with the prognostic indicator, microvascular invasion (MVI) In this paper, we propose the first and novel computational framework that disentangles the task into two components.
  arXiv  Detail & Related papers  (2021-03-09T01:43:05Z)
• ESTAN: Enhanced Small Tumor-Aware Network for Breast Ultrasound Image Segmentation [0.0]
  We propose a novel deep neural network architecture, namely Enhanced Small Tumor-Aware Network (ESTAN) to accurately segment breast tumors. ESTAN introduces two encoders to extract and fuse image context information at different scales and utilizes row-column-wise kernels in the encoder to adapt to breast anatomy.
  arXiv  Detail & Related papers  (2020-09-27T16:42:59Z)
• Weakly supervised multiple instance learning histopathological tumor segmentation [51.085268272912415]
  We propose a weakly supervised framework for whole slide imaging segmentation. We exploit a multiple instance learning scheme for training models. The proposed framework has been evaluated on multi-locations and multi-centric public data from The Cancer Genome Atlas and the PatchCamelyon dataset.
  arXiv  Detail & Related papers  (2020-04-10T13:12:47Z)
• Stan: Small tumor-aware network for breast ultrasound image segmentation [68.8204255655161]
  We propose a novel deep learning architecture called Small Tumor-Aware Network (STAN) to improve the performance of segmenting tumors with different size. The proposed approach outperformed the state-of-the-art approaches in segmenting small breast tumors.
  arXiv  Detail & Related papers  (2020-02-03T22:25:01Z)

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.