mlsanityData to 13 Oct 2026

REASON: Probability map-guided dual-branch fusion framework for gastric content assessment

arXiv 2511.01302 ↗First posted 3 Nov 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Accurate assessment of gastric content from ultrasound is critical for stratifying aspiration risk at induction of general anesthesia. However, traditional methods rely on manual tracing of gastric antra and empirical formulas, which face significant limitations in both efficiency and accuracy. To address these challenges, a novel two-stage probability map-guided dual-branch fusion framework (REASON) for gastric content assessment is proposed. In stage 1, a segmentation model generates probability maps that suppress artifacts and highlight gastric anatomy. In stage 2, a dual-branch classifier fuses information from two standard views, right lateral decubitus (RLD) and supine (SUP), to improve the discrimination of learned features. Experimental results on a self-collected dataset demonstrate that the proposed framework outperforms current state-of-the-art approaches by a significant margin. This framework shows great promise for automated preoperative aspiration risk assessment, offering a more robust, efficient, and accurate solution for clinical practice.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 32 of its 65 references that are in the map. First posted on arXiv 3 Nov 2025.

Builds on

32 of 65 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,656
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,321
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,111
  6. 2016Densely Connected Convolutional Networkscited by 6,707
  7. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,426
  8. 2017Squeeze-and-Excitation Networkscited by 4,772
  9. 2022A ConvNet for the 2020scited by 3,563
  10. 2019Searching for MobileNetV3cited by 1,990
  11. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,554
  12. 2020A Survey on Visual Transformercited by 654
20 more
  1. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 539
  2. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 462
  3. 2021A Survey on Deep Semi-supervised Learningcited by 250
  4. 2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
  5. 2021Fine-Grained Image Analysis with Deep Learning: A Surveycited by 135
  6. 2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
  7. 2021CAT: Cross Attention in Vision Transformercited by 92
  8. 2023MedViT: A Robust Vision Transformer for Generalized Medical Image Classificationcited by 89
  9. 2024MedMamba: Vision Mamba for Medical Image Classificationcited by 86
  10. 2022Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentationcited by 74
  11. 2020Semi-supervised Medical Image Classification with Relation-driven Self-ensembling Modelcited by 59
  12. 2022Enhancing Pseudo Label Quality for Semi-Supervised Domain-Generalized Medical Image Segmentationcited by 51
  13. 2021Contrastive Learning with Continuous Proxy Meta-Data for 3D MRI Classificationcited by 49
  14. 2023Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspectivecited by 43
  15. 2019Deep learning in ultrasound imagingcited by 39
  16. 2023Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentationcited by 33
  17. 2023Self-aware and Cross-sample Prototypical Learning for Semi-supervised Medical Image Segmentationcited by 20
  18. 2021Exploring Feature Representation Learning for Semi-supervised Medical Image Segmentationcited by 11
  19. 2024SPIRONet: Spatial-Frequency Learning and Graph-based Channel Interaction Network for Vessel Segmentationcited by 6
  20. 2022Bayesian Pseudo Labels: Expectation Maximization for Robust and Efficient Semi-Supervised Segmentationcited by 5

Built on by

Not cited yet.