Lymphocyte Mimicry Correction via Region-Level Tissue Reasoning and Unbalanced Optimal Transport
On the map: LLM reasoning → Clinical and biomedical applications
Abstract (arXiv)
Cell mimicry arises when different cell types appear morphologically similar. Human pathologists resolve this ambiguity using surrounding tissue context, whereas current vision models either lack contextual reasoning (cell foundation models) or cannot operate at the cell level (pathology MLLMs). We present Loki-OT, which propagates region-level tissue reasoning to individual cell predictions via Unbalanced Optimal Transport, using MLLM-derived density priors as soft guidance for ambiguous cell reassignment. Loki-OT is motivated by the observation that pretrained cell foundation model features already encode discriminative information, including tissue context, but standard cell-level supervision fails to use tissue context effectively. The resulting transport plan is distilled into a lightweight student MLP classifier that learns context-aware decision boundaries within the pretrained feature space. On the independent TCGA-BRCA cohort, Loki-OT achieved lower patient-level MAE than the fully supervised in-domain PanopTILs classifier and improved F1 in epithelium-rich mimicry tissues, using 278 weak region-level MLLM estimates built on a general-domain cell foundation model. Code: https://github.com/xiangli980/Lymphocyte_Mimicry_Correction_via_Loki_OT
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 11 of its 25 references that are in the map. First posted on arXiv 17 Aug 2026.
Builds on
11 of 25 references.
References · 11
- 2015Distilling the Knowledge in a Neural Networkcited by 10,076
- 2020Knowledge Distillation: A Surveycited by 1,578
- 2018Attention-based Deep Multiple Instance Learningcited by 1,077
- 2018HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Imagescited by 387
- 2018DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptationcited by 212
- 2023CellViT: Vision Transformers for Precise Cell Segmentation and Classificationcited by 108
- 2021Hierarchical Graph Representations in Digital Pathologycited by 58
- 2019CGC-Net: Cell Graph Convolutional Network for Grading of Colorectal Cancer Histology Imagescited by 57
- 2023The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classificationcited by 41
- 2023OCELOT: Overlapped Cell on Tissue Dataset for Histopathologycited by 29
- 2025CellViT++: Energy-Efficient and Adaptive Cell Segmentation and Classification Using Foundation Modelscited by 20
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026See, Measure, and Reason: Learning Visually Grounded Reasoning in Pathology
- 2026Multiscale Supervised Unbalanced Optimal Transport Flow Matching
- 2024Mask-guided cross-image attention for zero-shot in-silico histopathologic image generation with a diffusion model
- 2025Cell-o1: Training LLMs to Solve Single-Cell Reasoning Puzzles with Reinforcement Learning
- 2026Pathology Transport: Optimal-Transport Explanations for Clinical Data, and When Their Heatmaps (Fail to) Localize Disease
- 2026HistDiT: A Structure-Aware Latent Conditional Diffusion Model for High-Fidelity Virtual Staining in Histopathology
- 2026Towards Reliable Stain Transfer: An Iterative Data-Model Co-Optimization Framework Based on Multimodal Expert-Guided Assessment
- 2026Refining Cytology Predictions with Conditional Random Fields