mlsanityData to 14 Oct 2026

Diffusion Attention Expert Model for Predicting and Semi-automatic Localizing STAS in Lung Cancer Histopathological Images

arXiv 2605.16444 ↗First posted 15 May 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Accurate intraoperative and postoperative diagnosis of spread through air spaces (STAS) is essential for guiding surgical decisions and postoperative management in lung cancer. However, histopathological assessment is labor-intensive and is prone to missed or incorrect diagnoses. We propose a Diffusion Attention Expert Model (DAEM) to detect STAS in frozen sections (FSs) and paraffin sections (PSs). Its diffusion attention expert module leverages full attention aggregation to learn multi-scale features from histopathological images, while a dual-branch architecture strengthens multi-scale feature representation. On an internal dataset, DAEM achieves AUCs of 0.8946 for FSs and 0.9112 for PSs. Validation on external multi-center datasets from eight institutions demonstrates strong generalizability and interpretability. Using tumor microenvironment (TME) features in PSs, we further enable semi-automatic measurement of STAS location and its distance from the primary tumor. Several quantitative TME metrics are identified as potential biomarkers for STAS, including micropapillary-type STAS. Overall, DAEM offers a clinically actionable framework for STAS assessment by enabling accurate and interpretable detection on FSs and PSs, supporting postoperative risk stratification through quantitative TME-based analysis.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 90 references that are in the map. First posted on arXiv 15 May 2026.

Builds on

27 of 90 references.

References · 27

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2017Mask R-CNNcited by 7,277
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,525
  6. 2018Attention-based Deep Multiple Instance Learningcited by 1,095
  7. 2020On Layer Normalization in the Transformer Architecturecited by 922
  8. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 745
  9. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 555
  10. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 478
  11. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  12. 2018HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Imagescited by 388
15 more
  1. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 256
  2. 2020Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networkscited by 178
  3. 2015Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classificationcited by 159
  4. 2023Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Imagescited by 91
  5. 2023Attention-Challenging Multiple Instance Learning for Whole Slide Image Classificationcited by 61
  6. 2021Fine-Tuning and Training of DenseNet for Histopathology Image Representation Using TCGA Diagnostic Slidescited by 52
  7. 2019Pan-Cancer Diagnostic Consensus Through Searching Archival Histopathology Images Using Artificial Intelligencecited by 26
  8. 2022Transformer based multiple instance learning for weakly supervised histopathology image segmentationcited by 26
  9. 2024DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classificationcited by 25
  10. 2022pathGCN: Learning General Graph Spatial Operators from Pathscited by 15
  11. 2022Interventional Multi-Instance Learning with Deconfounded Instance-Level Predictioncited by 13
  12. 2024Efficient Quality Control of Whole Slide Pathology Images with Human-in-the-loop Trainingcited by 12
  13. 2024Aligning Knowledge Concepts to Whole Slide Images for Precise Histopathology Image Analysiscited by 10
  14. 2017Label Stability in Multiple Instance Learningcited by 8
  15. 2024Feature-interactive Siamese graph encoder-based image analysis to predict STAS from histopathology images in lung cancercited by 4

Built on by

Not cited yet.