AMN: An Adaptive Multi-Scale Fusion Network with Boundary and Uncertainty Modeling for Nuclei Segmentation
Quick Answer
This paper shows that AMN, a dual-encoder segmentation framework combining Swin Transformer and ResNet-50, achieves a mean Dice of 0.82 and F1 of 0.68 on the CoNIC benchmark for nuclei segmentation, outperforming eight baseline models.
Quick Take
AMN, a dual-encoder segmentation framework combining Swin Transformer and ResNet-50, achieves a mean Dice of 0.82 and F1 of 0.68 on the CoNIC benchmark for nuclei segmentation, outperforming eight baseline models. Its innovative multi-objective loss function enhances accuracy by addressing boundary awareness and uncertainty in predictions.
Key Points
- AMN uses a learned gating mechanism to fuse features from two encoders.
- Achieved F1 score of 0.67 on the challenging lymphocyte class.
- Demonstrated strong generalization on MoNuSeg without retraining.
- Combines class-weighted focal loss with boundary-aware and uncertainty-modulated terms.
- Outperformed U-Net, DeepLabV3+, and other hybrid architectures.
Article Content
From source RSS / original summaryarXiv:2606. 07633v1 Announce Type: new Abstract: Accurate classification of nuclei subtypes in histopathology images is critical for downstream tasks including tumor grading, immune infiltrate quantification, and prognosis prediction. Existing approaches rely on either convolutional or transformer-based encoders in isolation, limiting their ability to simultaneously capture fine-grained local texture and long-range spatial context.
We present AMN (Adaptive Multi-Scale Nuclei Network), a dual-encoder segmentation framework that jointly leverages a Swin Transformer and a ResNet-50 feature pyramid, fused via a learned per-channel gating mechanism that dynamically weighs each encoder's contribution at every scale. AMN is trained with a multi-objective loss combining class-weighted focal loss, boundary-aware loss with positive-pixel emphasis, and a novel uncertainty-modulated classification term that suppresses overconfident erroneous predictions.
Evaluated on the CoNIC benchmark across seven nuclei classes, AMN achieves a mean Dice of 0. 82 and mean F1 of 0. 68, with an F1 of 0. 67 on the diagnostically challenging lymphocyte class. AMN outperforms eight baseline models spanning pure-CNN, pure-transformer, and recent hybrid architectures: U-Net, ResU-Net, DeepLabV3+, SegNet, ViT-Small, HmsU-Net, ConvFormer-UNet, and BEFUnet.
Cross-dataset evaluation on MoNuSeg demonstrates strong generalization without retraining and validating the domain robustness of the learned representations.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
A phase-aware LLM agent optimizes human-object interaction retrieval, outperforming Optuna TPE by 33.3% and VDTuner by 34.2% on the HICO-DET benchmark. This method enhances throughput by 15.3x over UniIR and demonstrates strong transferability across vector database management systems.