C2RM-Seg: Causal Counterfactual Reasoning with Structural-Semantic Priors for Weakly Supervised Histopathological Tissue Segmentation

Hualong Zhang; Rushi Lan; Siyang Feng; Xipeng Pan; Yi Qian; Zhenbing Liu; Zihan Huan

arxiv: 2606.25508 · v1 · pith:DIXRGDLW · submitted 2026-06-24 · cs.CV

C2RM-Seg: Causal Counterfactual Reasoning with Structural-Semantic Priors for Weakly Supervised Histopathological Tissue Segmentation

Hualong Zhang , Siyang Feng , Zihan Huan , Yi Qian , Zhenbing Liu , Rushi Lan , Xipeng Pan This is my paper

Reviewed by Pith2026-06-25 21:35 UTCgrok-4.3pith:DIXRGDLW open to challenge →

classification cs.CV

keywords weakly supervised segmentationcausal counterfactual reasoningclass activation mappinghistopathological tissuepseudo-label refinementstructural semantic fusionuncertainty gated loss

0 comments

The pith

Causal counterfactual reasoning refines CAMs to focus on tissue morphology rather than staining artifacts for weakly supervised segmentation.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper seeks to fix noisy pseudo-labels in weakly supervised histopathological segmentation, where standard Class Activation Mapping often locks onto staining patterns instead of real tissue structure. It claims that decomposing features into latent factors and running counterfactual interventions through a learned causal structure matrix will suppress those confounders and yield activation maps aligned with morphology. These maps then feed into a dual-path network that blends local structural details with global semantic priors under adaptive gating, plus a loss that adjusts margins based on uncertainty. A sympathetic reader would care because reliable segmentation from image-level labels alone could reduce the annotation burden in computer-aided diagnosis.

Core claim

C2RM-Seg is a two-stage framework. The Causal Counterfactual Reasoning Module decomposes features into latent factors and performs counterfactual intervention via a learned causal structure matrix to suppress confounding context and produce morphology-aligned CAMs. This is paired with a Dual-Path Structural-Semantic Architecture that combines ResNeSt structural features with frozen DINOV3 semantic priors under cross-path gating to preserve boundaries, and an Uncertainty-Gated Margin loss that balances margin enforcement against prediction confidence to reduce residual pseudo-label noise, delivering state-of-the-art results on two public histopathological tissue datasets.

What carries the argument

The Causal Counterfactual Reasoning Module (C2RM), which decomposes features into latent factors and performs counterfactual intervention via a learned causal structure matrix to suppress confounding context and produce morphology-aligned CAMs.

If this is right

Higher-quality pseudo-labels from the refined CAMs directly improve downstream segmentation training under weak supervision.
The cross-path gating mechanism ensures semantic priors do not degrade local boundary accuracy.
The uncertainty-gated loss dynamically reduces the impact of noisy predictions during optimization.
The overall pipeline achieves state-of-the-art segmentation performance on the two evaluated histopathological datasets.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The learned causal structure matrix might serve as an interpretable map of morphology dependencies for pathologists.
The same decomposition-and-intervention pattern could extend to other medical imaging tasks where acquisition artifacts act as confounders.
Evaluating the method on datasets with deliberately varied staining protocols would test whether confounding suppression holds.

Load-bearing premise

The learned causal structure matrix obtained by decomposing features into latent factors will successfully suppress confounding context and yield morphology-aligned CAMs rather than introducing new artifacts or fitting to dataset-specific noise.

What would settle it

On the public datasets, if the refined CAMs still highlight staining-driven regions instead of expert-annotated morphological boundaries, or if segmentation metrics fail to exceed prior weakly supervised baselines after applying the full pipeline.

Figures

Figures reproduced from arXiv: 2606.25508 by Hualong Zhang, Rushi Lan, Siyang Feng, Xipeng Pan, Yi Qian, Zhenbing Liu, Zihan Huan.

**Figure 1.** Figure 1: Overview of C2RM-Seg. (a) Pseudo-Mask Generation: The C2RM rectifies CAMs by performing counterfactual intervention Z cf = Z − E on latent factors Z using a learnable causal matrix A. (b) Segmentation Training: A Dual-Path Structural-Semantic Architecture synergizes ResNeSt [23] features with frozen DINOV3 [24] priors via cross-path gating. The model is optimized using a UGM loss that dynamically re-weight… view at source ↗

**Figure 2.** Figure 2: Qualitative segmentation comparisons on the LUAD-HistoSeg and BCSS [PITH_FULL_IMAGE:figures/full_fig_p007_2.png] view at source ↗

**Figure 3.** Figure 3: t-SNE visualization. (a) Baseline features are severely entangled by spurious staining confounders. (b) C 2RM eliminates these biases via counterfactual intervention, yielding compact clusters and distinct inter-class separability. pearance bias, morphology–semantic mismatch, and label noise. In particular, C 2RM notably improves both region overlap and boundary quality, suggesting that removing staining-… view at source ↗

read the original abstract

Histopathological tissue segmentation is essential for computer-aided diagnosis, yet weakly supervised methods often suffer from noisy pseudo-labels generated by Class Activation Mapping (CAM). Existing CAM approaches tend to focus on staining-driven appearance cues rather than true causal tissue morphology, resulting in spurious localization and poor structural consistency. To address this issue, we propose C$^2$RM-Seg, a two-stage framework that integrates causal pseudo-label refinement with structure-aware semantic enhancement. For classification, we introduce a Causal Counterfactual Reasoning Module (C$^2$RM) that decomposes features into latent factors and performs counterfactual intervention via a learned causal structure matrix, suppressing confounding context and producing morphology-aligned CAMs. For segmentation, we design a Dual-Path Structural-Semantic Architecture that combines fine-grained structural features from ResNeSt with global semantic priors from a frozen DINOV3 foundation model. A cross-path gating mechanism adaptively regulates semantic injection using local structural cues to preserve boundary fidelity. To further mitigate residual pseudo-label noise, we propose an Uncertainty-Gated Margin (UGM) loss, which dynamically balances margin enforcement and confidence learning based on prediction uncertainty. Extensive experiments on two public histopathological tissue datasets show that C$^2$RM-Seg achieves state-of-the-art performance.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

C2RM-Seg adds a causal structure matrix and dual-path DINOv3 gating to CAM refinement for histopathology, but the matrix's causal status rests on unshown validation.

read the letter

The main takeaway is that this paper proposes C2RM-Seg, which inserts a causal counterfactual module to refine CAM pseudo-labels by learning a structure matrix that decomposes features and intervenes to reduce confounding context. It then runs a dual-path network (ResNeSt for local structure plus frozen DINOv3 for semantics) with cross-path gating and an uncertainty-gated margin loss, claiming SOTA numbers on two public histopathology datasets.

The concrete assembly is new enough: pairing the learned causal matrix with foundation-model semantic injection and the UGM loss is a fresh combination for this narrow setting. The dual-path gating idea is sensible for keeping boundary detail while pulling in global priors, and it directly targets the real problem that standard CAMs in stained slides often highlight staining artifacts over morphology.

The soft spot sits in the causal matrix itself. The abstract says the matrix is fitted after latent factor decomposition, yet supplies no checks—such as intervention consistency, comparison to known morphological relations, or ablation isolating the matrix from the rest of the pipeline. Without those, the module could simply act as an extra regularizer that fits dataset noise rather than true causality, which matches the stress-test concern about spurious correlations.

This work is for researchers already doing weakly supervised segmentation in histopathology who want an incremental architecture tweak. A reader focused on medical imaging would get usable ideas from the gating and loss details.

It deserves peer review because the problem is well-posed, the datasets are public, and the method is described at a level that allows checking the claims, even if the causal interpretation will need more evidence in revision.

Referee Report

2 major / 2 minor

Summary. The paper proposes C²RM-Seg, a two-stage weakly supervised framework for histopathological tissue segmentation. It introduces a Causal Counterfactual Reasoning Module (C²RM) that decomposes features into latent factors and applies counterfactual intervention via a learned causal structure matrix to refine Class Activation Maps (CAMs) by suppressing confounding context. This is paired with a Dual-Path Structural-Semantic Architecture combining ResNeSt structural features and frozen DINOV3 semantic priors via cross-path gating, plus an Uncertainty-Gated Margin (UGM) loss to handle pseudo-label noise. Experiments on two public datasets are reported to achieve state-of-the-art performance.

Significance. If the learned causal structure matrix reliably encodes morphological causality rather than staining artifacts, the approach could meaningfully improve localization consistency in weakly supervised medical segmentation where appearance-based cues dominate. The integration of counterfactual reasoning with foundation-model priors and uncertainty-aware loss is a coherent attempt to address a known limitation of standard CAM methods.

major comments (2)

[C²RM description (methods)] The central claim that the learned causal structure matrix produces morphology-aligned CAMs by suppressing confounding context (rather than fitting dataset-specific noise) is load-bearing, yet the manuscript provides no validation mechanism such as intervention consistency checks, sensitivity analysis under known morphological priors, or comparison against ground-truth causal graphs. This directly affects whether the C²RM module advances beyond an opaque regularizer.
[Experiments] §4 (experiments): the SOTA claim on the two datasets rests on the causal refinement step, but without ablations isolating the causal matrix contribution versus the dual-path architecture or UGM loss alone, it is impossible to attribute gains to the counterfactual intervention.

minor comments (2)

Notation for the causal structure matrix and latent factor decomposition should be formalized with explicit equations to allow reproducibility of the counterfactual intervention step.
Dataset statistics (class imbalance, staining variation, image counts) and exact train/val/test splits are not summarized in the main text, complicating assessment of generalization.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the thoughtful and constructive comments. We address each major point below and outline revisions that will strengthen the manuscript without overstating current results.

read point-by-point responses

Referee: The central claim that the learned causal structure matrix produces morphology-aligned CAMs by suppressing confounding context (rather than fitting dataset-specific noise) is load-bearing, yet the manuscript provides no validation mechanism such as intervention consistency checks, sensitivity analysis under known morphological priors, or comparison against ground-truth causal graphs. This directly affects whether the C²RM module advances beyond an opaque regularizer.

Authors: We agree that explicit validation of the causal structure matrix would increase confidence in its morphological rather than artifact-driven behavior. Ground-truth causal graphs do not exist for these histopathological datasets, precluding direct comparison. However, we will add (i) intervention consistency checks by re-applying the learned matrix to held-out test images and measuring CAM stability, and (ii) a sensitivity analysis that perturbs the matrix entries and quantifies resulting changes in CAM IoU and boundary metrics. These analyses will be reported in a new subsection of the methods and experiments. revision: yes
Referee: §4 (experiments): the SOTA claim on the two datasets rests on the causal refinement step, but without ablations isolating the causal matrix contribution versus the dual-path architecture or UGM loss alone, it is impossible to attribute gains to the counterfactual intervention.

Authors: We accept that the current experimental design does not isolate the causal matrix contribution. In the revised manuscript we will add a dedicated ablation table that reports performance for: (a) dual-path + UGM only, (b) dual-path + UGM + C²RM without the learned causal matrix (i.e., identity matrix), and (c) the full model. This will allow quantitative attribution of gains specifically to the counterfactual intervention step. revision: yes

Circularity Check

0 steps flagged

No circularity: framework introduces independent modeling choices validated on external data

full rationale

The paper defines C²RM as a new module that decomposes features and learns a causal structure matrix for counterfactual intervention, then reports empirical gains on two public datasets. No equations or steps are shown that reduce a claimed prediction back to its own fitted inputs by construction, nor any load-bearing self-citation chains or uniqueness theorems imported from the authors' prior work. The performance claims rest on experimental results rather than tautological re-labeling of inputs, making the derivation self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

1 free parameters · 0 axioms · 0 invented entities

Abstract-only review yields minimal information on free parameters or axioms; the central claim rests on an unverified learned causal structure matrix and the effectiveness of counterfactual intervention.

free parameters (1)

causal structure matrix
Described as learned to perform counterfactual intervention; no value or fitting procedure given in abstract.

pith-pipeline@v0.9.1-grok · 5779 in / 1177 out tokens · 22000 ms · 2026-06-25T21:35:44.438144+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

30 extracted references · 2 canonical work pages · 2 internal anchors

[1]

Nature Machine Intelligence7(8), 1292–1307 (2025)

Andani,S.,Chen,B.,Ficek-Pascual,J.,Heinke,S.,Casanova,R.,Hild,B.F.,Sobot- tka, B., Bodenmiller, B., Koelzer, V.H., et al.: Histopathology-based protein multi- plex generation using deep learning. Nature Machine Intelligence7(8), 1292–1307 (2025)

2025
[2]

Nature634(8035), 970–978 (2024)

Wang, X., Zhao, J., Marostica, E., Yuan, W., Jin, J., Zhang, J., Li, R., Tang, H., Wang, K., Li, Y., et al.: A pathology foundation model for cancer diagnosis and prognosis prediction. Nature634(8035), 970–978 (2024)

2024
[3]

In: Proceedings of the AAAI Conference on Artificial Intelligence

Feng, S., Wang, H., Han, C., Liu, Z., Zhang, H., Lan, R., Pan, X.: Weakly super- vised gland segmentation with class semantic consistency and purified labels fil- tration. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 39, pp. 2987–2995 (2025)

2025
[4]

In: Proceedings of the AAAI Conference on Artificial Intelligence

An, Y., Chen, J., Lin, H., Liu, Z., Feng, S., Zhang, H., Lan, R., Liu, Z., Pan, X.: Ca-mlif: Cross-attention and multimodal low-rank interaction fusion framework for tumor prognostic prediction. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 39, pp. 1764–1772 (2025)

2025
[5]

In: Proceedings of the Computer Vision and Pattern Recognition Conference

Tang, Q., Fan, L., Pagnucco, M., Song, Y.: Prototype-based image prompting for weakly supervised histopathological image segmentation. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 30271–30280 (2025)

2025
[6]

IEEE Transactions on Fuzzy Systems (2025)

Cheng, X., Ding, W., Huang, J., Ju, H., Zhou, T., Guo, J., Pedrycz, W.: Fcaformer: Fuzzy-enhanced class-aware attention based transformer for weakly supervised histopathology image segmentation. IEEE Transactions on Fuzzy Systems (2025)

2025
[7]

Engineering Applications of Artificial Intelligence156, 111100 (2025)

Pan, X., Zhang, H., Deng, H., Wang, H., Li, L., Liu, Z., Wang, L., An, Y., Lu, C., Liu, Z., et al.: Weakly supervised histopathology tissue semantic segmentation with multi-scale voting and online noise suppression. Engineering Applications of Artificial Intelligence156, 111100 (2025)

2025
[8]

Medical Image Analysis80, 102482 (2022)

Chikontwe, P., Sung, H.J., Jeong, J., Kim, M., Go, H., Nam, S.J., Park, S.H.: Weakly supervised segmentation on neural compressed histopathology with self- equivariant regularization. Medical Image Analysis80, 102482 (2022)

2022
[9]

Medical Image Analysis86, 102791 (2023)

Li, K., Qian, Z., Han, Y., Chang, E.I.C., Wei, B., Lai, M., Liao, J., Fan, Y., Xu, Y.: Weakly supervised histopathology image segmentation with self-attention. Medical Image Analysis86, 102791 (2023)

2023
[10]

Medical Image Analysis103, 103563 (2025) 10 H

Fan, J., Sun, Q., Di, Y., Bao, J., Lv, T., Liu, Y., Hu, X., Li, L., Cui, X., Pan, X.: Dipathmamba: A domain-incremental weakly supervised state space model for pathology image segmentation. Medical Image Analysis103, 103563 (2025) 10 H. Zhang et al

2025
[11]

In: International Conference on Medical Image Computing and Computer-Assisted Intervention

Zhang, H., Feng, S., Huan, Z., Wang, H., Liu, Z., Lan, R., Pan, X.: Edge-semantic synergy fusion and adaptive noise-aware for weakly supervised pathological tis- sue segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 160–169. Springer (2025)

2025
[12]

In: Proceedings of the IEEE/CVF Con- ference on Computer Vision and Pattern Recognition

Huan, Z., Pan, X., Zhang, H., Feng, S., Lan, R., Wang, H., Lu, H., Liu, Z.: Bridging rgb and hematoxylin components: An interleaved guidance and fusion framework for point supervised nuclei segmentation. In: Proceedings of the IEEE/CVF Con- ference on Computer Vision and Pattern Recognition. pp. 37518–37527 (2026)

2026
[13]

IEEE Transactions on Medical Imaging (2025)

Kang, Y., Li, H., Shi, X., Zhang, X., Xing, Y., Wen, Y., Wang, Y., Cui, L., Feng, J., Yang, L.: Exploring unbiased activation maps for weakly supervised tissue segmen- tation of histopathological images. IEEE Transactions on Medical Imaging (2025)

2025
[14]

Pattern Recognition160, 111204 (2025)

Fu,J.,Wang,G.,Lu,T.,Yue,Q.,Vercauteren,T.,Ourselin,S.,Zhang,S.:Um-cam: Uncertainty-weighted multi-resolution class activation maps for weakly-supervised segmentation. Pattern Recognition160, 111204 (2025)

2025
[15]

IEEE Transactions on Image Processing35, 2513–2528 (2026)

Feng, S., Pan, X., Wang, H., Liu, Z., Zhang, W., Lan, R.: Long-tailed and inter- class homogeneity matters in multi-class weakly supervised tissue segmentation of histopathology images. IEEE Transactions on Image Processing35, 2513–2528 (2026)

2026
[16]

IEEE transactions on medical imaging (2026)

Feng, S., Pan, X., Zhang, W., Pan, M., Han, C., Lan, R.: Qupas: Sam-based semi- supervised histopathological image segmentation with quantum force field finetun- ing and adversarial estimation. IEEE transactions on medical imaging (2026)

2026
[17]

IEEE Transactions on Medical Imaging (2025)

Feng, S., Zhang, H., Zhao, X., Shi, L., Liu, Z., Lan, R., Shi, L., Pan, X.: Wave-aware weakly supervised histopathological tissue segmentation with cross-scale logits dis- tillation. IEEE Transactions on Medical Imaging (2025)

2025
[18]

In: International Conference on Medical Image Computing and Computer-Assisted Intervention

Feng, S., Chen, J., Liu, Z., Liu, W., Wang, Z., Lan, R., Pan, X.: Mining gold from the sand: Weakly supervised histological tissue segmentation with activation relocalization and mutual learning. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 414–423. Springer (2024)

2024
[19]

IEEE Transactions on Medical Imaging42(10), 2912–2923 (2023)

Zhong, L., Wang, G., Liao, X., Zhang, S.: Hamil: High-resolution activation maps and interleaved learning for weakly supervised segmentation of histopathological images. IEEE Transactions on Medical Imaging42(10), 2912–2923 (2023)

2023
[20]

Medical Image Analysis80, 102487 (2022)

Han, C., Lin, J., Mai, J., Wang, Y., Zhang, Q., Zhao, B., Chen, X., Pan, X., Shi, Z., Xu, Z., et al.: Multi-layer pseudo-supervision for histopathology tissue semantic segmentation using patch-level classification labels. Medical Image Analysis80, 102487 (2022)

2022
[21]

Information Fusion125, 103432 (2026)

Hu, X., Cao, Y., Hu, W., Wang, S., Mukhopadhyay, S.C., Liu, Y., Li, H., Li, Y., Cai, Q., Liu, Z.: Expert knowledge-guided multi-granularity multi-scale fusion for weakly-supervised histological segmentation. Information Fusion125, 103432 (2026)

2026
[22]

In: International Conference on Medical Image Computing and Computer-Assisted Intervention

Li, Y., Yu, Y., Zou, Y., Xiang, T., Li, X.: Online easy example mining for weakly- supervised gland segmentation from histology images. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 578–587. Springer (2022)

2022
[23]

In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

Zhang, H., Wu, C., Zhang, Z., Zhu, Y., Lin, H., Zhang, Z., Sun, Y., He, T., Mueller, J., Manmatha, R., et al.: Resnest: Split-attention networks. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 2736–2746 (2022)

2022
[24]

DINOv3

Siméoni, O., Vo, H.V., Seitzer, M., Baldassarre, F., Oquab, M., Jose, C., Khali- dov, V., Szafraniec, M., Yi, S., Ramamonjisoa, M., et al.: Dinov3. arXiv preprint arXiv:2508.10104 (2025) C2RM-Seg for Histopathological Tissue Segmentation 11

work page internal anchor Pith review Pith/arXiv arXiv 2025
[25]

Bioinformatics 35(18), 3461–3467 (2019)

Amgad, M., Elfandy, H., Hussein, H., Atteya, L.A., Elsebaie, M.A., Abo Elnasr, L.S., Sakr, R.A., Salem, H.S., Ismail, A.F., Saad, A.M., et al.: Structured crowd- sourcing enables convolutional segmentation of histology images. Bioinformatics 35(18), 3461–3467 (2019)

2019
[26]

In: Proceedings of the IEEE/CVF international conference on computer vision

Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y., et al.: Segment anything. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 4015–4026 (2023)

2023
[27]

SAM 2: Segment Anything in Images and Videos

Ravi, N., Gabeur, V., Hu, Y.T., Hu, R., Ryali, C., Ma, T., Khedr, H., Rädle, R., Rolland, C., Gustafson, L., et al.: Sam 2: Segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)

work page internal anchor Pith review Pith/arXiv arXiv 2024
[28]

Nature Communications15(1), 654 (2024)

Ma, J., He, Y., Li, F., Han, L., You, C., Wang, B.: Segment anything in medical images. Nature Communications15(1), 654 (2024)

2024
[29]

In: International Conference on Medi- cal Image Computing and Computer-Assisted Intervention

Zhang, S., Zhang, J., Xie, Y., Xia, Y.: Tpro: Text-prompting-based weakly super- vised histopathology tissue segmentation. In: International Conference on Medi- cal Image Computing and Computer-Assisted Intervention. pp. 109–118. Springer (2023)

2023
[30]

In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

Chen, Q., Yang, L., Lai, J.H., Xie, X.: Self-supervised image-specific prototype exploration for weakly supervised semantic segmentation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 4288–4298 (2022)

2022

[1] [1]

Nature Machine Intelligence7(8), 1292–1307 (2025)

Andani,S.,Chen,B.,Ficek-Pascual,J.,Heinke,S.,Casanova,R.,Hild,B.F.,Sobot- tka, B., Bodenmiller, B., Koelzer, V.H., et al.: Histopathology-based protein multi- plex generation using deep learning. Nature Machine Intelligence7(8), 1292–1307 (2025)

2025

[2] [2]

Nature634(8035), 970–978 (2024)

Wang, X., Zhao, J., Marostica, E., Yuan, W., Jin, J., Zhang, J., Li, R., Tang, H., Wang, K., Li, Y., et al.: A pathology foundation model for cancer diagnosis and prognosis prediction. Nature634(8035), 970–978 (2024)

2024

[3] [3]

In: Proceedings of the AAAI Conference on Artificial Intelligence

Feng, S., Wang, H., Han, C., Liu, Z., Zhang, H., Lan, R., Pan, X.: Weakly super- vised gland segmentation with class semantic consistency and purified labels fil- tration. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 39, pp. 2987–2995 (2025)

2025

[4] [4]

In: Proceedings of the AAAI Conference on Artificial Intelligence

An, Y., Chen, J., Lin, H., Liu, Z., Feng, S., Zhang, H., Lan, R., Liu, Z., Pan, X.: Ca-mlif: Cross-attention and multimodal low-rank interaction fusion framework for tumor prognostic prediction. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 39, pp. 1764–1772 (2025)

2025

[5] [5]

In: Proceedings of the Computer Vision and Pattern Recognition Conference

Tang, Q., Fan, L., Pagnucco, M., Song, Y.: Prototype-based image prompting for weakly supervised histopathological image segmentation. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 30271–30280 (2025)

2025

[6] [6]

IEEE Transactions on Fuzzy Systems (2025)

Cheng, X., Ding, W., Huang, J., Ju, H., Zhou, T., Guo, J., Pedrycz, W.: Fcaformer: Fuzzy-enhanced class-aware attention based transformer for weakly supervised histopathology image segmentation. IEEE Transactions on Fuzzy Systems (2025)

2025

[7] [7]

Engineering Applications of Artificial Intelligence156, 111100 (2025)

Pan, X., Zhang, H., Deng, H., Wang, H., Li, L., Liu, Z., Wang, L., An, Y., Lu, C., Liu, Z., et al.: Weakly supervised histopathology tissue semantic segmentation with multi-scale voting and online noise suppression. Engineering Applications of Artificial Intelligence156, 111100 (2025)

2025

[8] [8]

Medical Image Analysis80, 102482 (2022)

Chikontwe, P., Sung, H.J., Jeong, J., Kim, M., Go, H., Nam, S.J., Park, S.H.: Weakly supervised segmentation on neural compressed histopathology with self- equivariant regularization. Medical Image Analysis80, 102482 (2022)

2022

[9] [9]

Medical Image Analysis86, 102791 (2023)

Li, K., Qian, Z., Han, Y., Chang, E.I.C., Wei, B., Lai, M., Liao, J., Fan, Y., Xu, Y.: Weakly supervised histopathology image segmentation with self-attention. Medical Image Analysis86, 102791 (2023)

2023

[10] [10]

Medical Image Analysis103, 103563 (2025) 10 H

Fan, J., Sun, Q., Di, Y., Bao, J., Lv, T., Liu, Y., Hu, X., Li, L., Cui, X., Pan, X.: Dipathmamba: A domain-incremental weakly supervised state space model for pathology image segmentation. Medical Image Analysis103, 103563 (2025) 10 H. Zhang et al

2025

[11] [11]

In: International Conference on Medical Image Computing and Computer-Assisted Intervention

Zhang, H., Feng, S., Huan, Z., Wang, H., Liu, Z., Lan, R., Pan, X.: Edge-semantic synergy fusion and adaptive noise-aware for weakly supervised pathological tis- sue segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 160–169. Springer (2025)

2025

[12] [12]

In: Proceedings of the IEEE/CVF Con- ference on Computer Vision and Pattern Recognition

Huan, Z., Pan, X., Zhang, H., Feng, S., Lan, R., Wang, H., Lu, H., Liu, Z.: Bridging rgb and hematoxylin components: An interleaved guidance and fusion framework for point supervised nuclei segmentation. In: Proceedings of the IEEE/CVF Con- ference on Computer Vision and Pattern Recognition. pp. 37518–37527 (2026)

2026

[13] [13]

IEEE Transactions on Medical Imaging (2025)

Kang, Y., Li, H., Shi, X., Zhang, X., Xing, Y., Wen, Y., Wang, Y., Cui, L., Feng, J., Yang, L.: Exploring unbiased activation maps for weakly supervised tissue segmen- tation of histopathological images. IEEE Transactions on Medical Imaging (2025)

2025

[14] [14]

Pattern Recognition160, 111204 (2025)

Fu,J.,Wang,G.,Lu,T.,Yue,Q.,Vercauteren,T.,Ourselin,S.,Zhang,S.:Um-cam: Uncertainty-weighted multi-resolution class activation maps for weakly-supervised segmentation. Pattern Recognition160, 111204 (2025)

2025

[15] [15]

IEEE Transactions on Image Processing35, 2513–2528 (2026)

Feng, S., Pan, X., Wang, H., Liu, Z., Zhang, W., Lan, R.: Long-tailed and inter- class homogeneity matters in multi-class weakly supervised tissue segmentation of histopathology images. IEEE Transactions on Image Processing35, 2513–2528 (2026)

2026

[16] [16]

IEEE transactions on medical imaging (2026)

Feng, S., Pan, X., Zhang, W., Pan, M., Han, C., Lan, R.: Qupas: Sam-based semi- supervised histopathological image segmentation with quantum force field finetun- ing and adversarial estimation. IEEE transactions on medical imaging (2026)

2026

[17] [17]

IEEE Transactions on Medical Imaging (2025)

Feng, S., Zhang, H., Zhao, X., Shi, L., Liu, Z., Lan, R., Shi, L., Pan, X.: Wave-aware weakly supervised histopathological tissue segmentation with cross-scale logits dis- tillation. IEEE Transactions on Medical Imaging (2025)

2025

[18] [18]

In: International Conference on Medical Image Computing and Computer-Assisted Intervention

Feng, S., Chen, J., Liu, Z., Liu, W., Wang, Z., Lan, R., Pan, X.: Mining gold from the sand: Weakly supervised histological tissue segmentation with activation relocalization and mutual learning. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 414–423. Springer (2024)

2024

[19] [19]

IEEE Transactions on Medical Imaging42(10), 2912–2923 (2023)

Zhong, L., Wang, G., Liao, X., Zhang, S.: Hamil: High-resolution activation maps and interleaved learning for weakly supervised segmentation of histopathological images. IEEE Transactions on Medical Imaging42(10), 2912–2923 (2023)

2023

[20] [20]

Medical Image Analysis80, 102487 (2022)

Han, C., Lin, J., Mai, J., Wang, Y., Zhang, Q., Zhao, B., Chen, X., Pan, X., Shi, Z., Xu, Z., et al.: Multi-layer pseudo-supervision for histopathology tissue semantic segmentation using patch-level classification labels. Medical Image Analysis80, 102487 (2022)

2022

[21] [21]

Information Fusion125, 103432 (2026)

Hu, X., Cao, Y., Hu, W., Wang, S., Mukhopadhyay, S.C., Liu, Y., Li, H., Li, Y., Cai, Q., Liu, Z.: Expert knowledge-guided multi-granularity multi-scale fusion for weakly-supervised histological segmentation. Information Fusion125, 103432 (2026)

2026

[22] [22]

In: International Conference on Medical Image Computing and Computer-Assisted Intervention

Li, Y., Yu, Y., Zou, Y., Xiang, T., Li, X.: Online easy example mining for weakly- supervised gland segmentation from histology images. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 578–587. Springer (2022)

2022

[23] [23]

In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

Zhang, H., Wu, C., Zhang, Z., Zhu, Y., Lin, H., Zhang, Z., Sun, Y., He, T., Mueller, J., Manmatha, R., et al.: Resnest: Split-attention networks. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 2736–2746 (2022)

2022

[24] [24]

DINOv3

Siméoni, O., Vo, H.V., Seitzer, M., Baldassarre, F., Oquab, M., Jose, C., Khali- dov, V., Szafraniec, M., Yi, S., Ramamonjisoa, M., et al.: Dinov3. arXiv preprint arXiv:2508.10104 (2025) C2RM-Seg for Histopathological Tissue Segmentation 11

work page internal anchor Pith review Pith/arXiv arXiv 2025

[25] [25]

Bioinformatics 35(18), 3461–3467 (2019)

Amgad, M., Elfandy, H., Hussein, H., Atteya, L.A., Elsebaie, M.A., Abo Elnasr, L.S., Sakr, R.A., Salem, H.S., Ismail, A.F., Saad, A.M., et al.: Structured crowd- sourcing enables convolutional segmentation of histology images. Bioinformatics 35(18), 3461–3467 (2019)

2019

[26] [26]

In: Proceedings of the IEEE/CVF international conference on computer vision

Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y., et al.: Segment anything. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 4015–4026 (2023)

2023

[27] [27]

SAM 2: Segment Anything in Images and Videos

Ravi, N., Gabeur, V., Hu, Y.T., Hu, R., Ryali, C., Ma, T., Khedr, H., Rädle, R., Rolland, C., Gustafson, L., et al.: Sam 2: Segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)

work page internal anchor Pith review Pith/arXiv arXiv 2024

[28] [28]

Nature Communications15(1), 654 (2024)

Ma, J., He, Y., Li, F., Han, L., You, C., Wang, B.: Segment anything in medical images. Nature Communications15(1), 654 (2024)

2024

[29] [29]

In: International Conference on Medi- cal Image Computing and Computer-Assisted Intervention

Zhang, S., Zhang, J., Xie, Y., Xia, Y.: Tpro: Text-prompting-based weakly super- vised histopathology tissue segmentation. In: International Conference on Medi- cal Image Computing and Computer-Assisted Intervention. pp. 109–118. Springer (2023)

2023

[30] [30]

In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

Chen, Q., Yang, L., Lai, J.H., Xie, X.: Self-supervised image-specific prototype exploration for weakly supervised semantic segmentation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 4288–4298 (2022)

2022