mlsanityData to 14 Oct 2026

Autonomous labeling of surgical resection margins using a foundation model

arXiv 2511.22131 ↗First posted 27 Nov 2025cs.CV cs.LG physics.med-phcited by 0

Not on the map. Why?

Abstract (arXiv)

Assessing resection margins is central to pathological specimen evaluation and has profound implications for patient outcomes. Current practice employs physical inking, which is applied variably, and cautery artifacts can obscure the true margin on histological sections. We present a virtual inking network (VIN) that autonomously localizes the surgical cut surface on whole-slide images, reducing reliance on inks and standardizing margin-focused review. VIN uses a frozen foundation model as the feature extractor and a compact two-layer multilayer perceptron trained for patch-level classification of cautery-consistent features. The dataset comprised 120 hematoxylin and eosin (H&E) stained slides from 12 human tonsil tissue blocks, resulting in ~2 TB of uncompressed raw image data, where a board-certified pathologist provided boundary annotations. In blind testing with 20 slides from previously unseen blocks, VIN produced coherent margin overlays that qualitatively aligned with expert annotations across serial sections. Quantitatively, region-level accuracy was ~73.3% across the test set, with errors largely confined to limited areas that did not disrupt continuity of the whole-slide margin map. These results indicate that VIN captures cautery-related histomorphology and can provide a reproducible, ink-free margin delineation suitable for integration into routine digital pathology workflows and for downstream measurement of margin distances.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 37 references that are in the map. First posted on arXiv 27 Nov 2025.

Builds on

17 of 37 references.

References · 17

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2020End-to-End Object Detection with Transformerscited by 7,414
  3. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  4. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  5. 2018Attention-based Deep Multiple Instance Learningcited by 1,095
  6. 2022Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learningcited by 359
  7. 2023LongNet: Scaling Transformers to 1,000,000,000 Tokenscited by 204
  8. 2024Multimodal Whole Slide Foundation Model for Pathologycited by 162
  9. 2023Segment Anything Model (SAM) for Digital Pathology: Assess Zero-shot Segmentation on Whole Slide Imagingcited by 161
  10. 2024Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathologycited by 161
  11. 2021Line Segment Detection Using Transformers without Edgescited by 73
  12. 2018Deep learning-based virtual histology staining using auto-fluorescence of label-free tissuecited by 70
5 more
  1. 2022Deep Learning-enabled Virtual Histological Staining of Biological Samplescited by 42
  2. 2020Digital synthesis of histological stains using micro-structured and multiplexed virtual staining of label-free tissuecited by 29
  3. 2024Towards Large-Scale Training of Pathology Foundation Modelscited by 23
  4. 2024Virtual birefringence imaging and histological staining of amyloid deposits in label-free tissue using autofluorescence microscopy and deep learningcited by 8
  5. 2025Deep learning-enabled virtual multiplexed immunostaining of label-free tissue for vascular invasion assessmentcited by 1

Built on by

Not cited yet.