Adaptive Routing for Efficient Diffusion Transformer-Based PNI Prediction

• URL: http://arxiv.org/abs/2607.11533v1
• Date: Mon, 13 Jul 2026 13:18:21 GMT
• Title: Adaptive Routing for Efficient Diffusion Transformer-Based PNI Prediction
• Abstract summary: Perineural invasion (PNI) is a critical prognostic factor in cholangiocarcinoma.<n>Traditional convolutional neural networks are limited in capturing long-range spatial cues.<n>Transformer-based MRI improves global modeling of volumetric by aggregating spatially distributed contextual cues.
• Score: 9.156688576258206
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Perineural invasion (PNI) is a critical prognostic factor in cholangiocarcinoma. However, its preoperative prediction from magnetic resonance imaging (MRI) remains challenging due to subtle imaging features that extend beyond tumor boundaries into surrounding regions. Conventional convolutional neural networks are limited in capturing long-range spatial dependencies. Transformer-based architectures improve global modeling of volumetric MRI by aggregating spatially distributed contextual cues, yet capturing subtle and noise-sensitive patterns in peritumoral regions remains challenging. Diffusion-based classifiers offer an alternative formulation by leveraging denoising-based class scoring to better capture such subtle patterns. However, these approaches introduce substantial computational overhead due to the combination of transformer-based modeling and iterative denoising processes. To address these challenges, we formulate PNI prediction as a diffusion-based classification problem and implement the denoising network using a transformer-based representation. To improve computational efficiency, we introduce adaptive routing across attention heads, spatial tokens, and MLP width. Experimental results demonstrate that the proposed approach achieves an AUC of 0.731 with 257.57 GFLOPs.

Related papers

• Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images [48.646448077284276]
  We propose Spatial-FAD, a framework for effective few-shot medical anomaly detection.<n>It improves lesion localization by combining VFM spatial priors with CLIP semantics.<n>Our method achieves an average improvement of over 11.4% in Dice score and 1.8% in AUC.
  arXiv  Detail & Related papers  (2026-09-11T05:21:01Z)
• Enhancing MRI Brain Tumor Edge Detection: A Hybrid Preprocessing Approach Utilizing CLAHE [0.0]
  Accurate boundary delineation of brain tumors in Magnetic Resonance Imaging (MRI) is a critical yet formidable challenge.<n>Traditional edge detection algorithms, while computationally lightweight and mathematically interpretable, frequently fail to capture the diffuse, localized boundaries of edema.<n>We propose a hybrid automated edge detection pipeline to overcome these limitations.
  arXiv  Detail & Related papers  (2026-08-27T22:30:32Z)
• SHFormer: Dynamic Spectral Filtering Convolutional Neural Network and High-pass Kernel Generation Transformer for Adaptive MRI Reconstruction [3.520703534171746]
  We propose a neuromodulation-based discriminative multi-spectral AM for scalable MRI reconstruction.<n>Our method offers scalable, high-quality reconstruction with best improvement margins of 1 dB in PSNR and 0.01 in SSIM under unseen scenarios.
  arXiv  Detail & Related papers  (2026-07-22T13:55:27Z)
• LoSA-Net: A Localized and Scale-Adaptive Network for Boundary-Sensitive Prediction of Perineural Invasion in 3D MRI [10.952583431192279]
  We present LoSA-Net, a localized and scale-adaptive architecture for boundary-sensitive PNI prediction in 3D MRI.<n>Talking Neighborhood Attention (TNA) preserves nerve-aligned detail through localized self-attention with head-wise mixing, and Scale-Adaptive Feature Mixing (SAFM) modulates the receptive field using multi-scale depthwise processing.<n>In contrast-enhanced MRI scans from 168 patients with cholangiocarcinoma, LoSA-Net achieves an AUC of 0.7567 and outperforms representative convolutional and transformer baselines under matched preprocessing and optimization settings.
  arXiv  Detail & Related papers  (2026-07-13T01:31:01Z)
• Towards Generalized Image Manipulation Localization via Score-based Model [38.03898206912958]
  We propose DiffIML, a novel framework that introduces score-based generative modeling to IML.<n>Under this formulation, diffusion models serve as an effective numerical solver for the learned score function.<n>Experiments on eight non-generative and three generative benchmarks demonstrate that DiffIML consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-16T08:39:54Z)
• DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction [42.4365911571903]
  We propose DiffNR, a novel framework that enhances NR optimization with diffusion priors.<n>At its core is SliceFixer, a single-step diffusion model designed to correct artifacts in degraded slices.<n>In experiments, DiffNR improves PSNR by 3.99 dB on average, generalizes well across domains, and maintains efficient optimization.
  arXiv  Detail & Related papers  (2026-04-23T10:27:54Z)
• PolarMAE: Efficient Fetal Ultrasound Pre-training via Semantic Screening and Polar-Guided Masking [47.59361789212719]
  PolarMAE is a novel and efficient pre-training framework tailored for US images.<n>To mitigate continuous scanning redundancy, we introduce a Progressive Visual-Semantic Screening.<n>We also propose a Polar-Texture Collaborative Masking.
  arXiv  Detail & Related papers  (2026-04-17T09:45:04Z)
• Stochastic Generative Plug-and-Play Priors [9.429516239444922]
  Plug-and-play (M) methods are widely used for solving inverse imaging problems by incorporating a denoiser into optimization algorithms.<n>Score-based diffusion models (SBDMs) have recently demonstrated strong generative performance through a denoiser trained across a range of levels.<n>It remains unclear how to systematically use SBDMs as priors within a framework without relying on reverse diffusion sampling.
  arXiv  Detail & Related papers  (2026-04-04T06:14:38Z)
• Search-Augmented Masked Diffusion Models for Constrained Generation [47.47350674873298]
  Search-Augmented Masked Diffusion (SearchDiff) is a training-free neurosymbolic inference framework that integrates informed search directly into the reverse denoising process.<n>SearchDiff substantially improves constraint satisfaction and property adherence, while consistently outperforming discrete diffusion and autoregressive baselines.
  arXiv  Detail & Related papers  (2026-02-02T19:43:25Z)
• NNDM: NN_UNet Diffusion Model for Brain Tumor Segmentation [0.0]
  We propose NNDM (NN_UNet Diffusion Model) a hybrid framework that integrates the robust feature extraction of NN-UNet with the generative capabilities of diffusion probabilistic models.<n>In our approach, the diffusion model progressively refines the segmentation masks generated by NN-UNet by learning the residual error distribution between predicted and ground-truth masks.<n>Experiments conducted on the BraTS 2021 datasets demonstrate that NNDM achieves superior performance compared to conventional U-Net and transformer-based baselines.
  arXiv  Detail & Related papers  (2025-10-08T22:19:08Z)
• Diffusion Models for Solving Inverse Problems via Posterior Sampling with Piecewise Guidance [52.705112811734566]
  A novel diffusion-based framework is introduced for solving inverse problems using a piecewise guidance scheme.<n>The proposed method is problem-agnostic and readily adaptable to a variety of inverse problems.<n>The framework achieves a reduction in inference time of (25%) for inpainting with both random and center masks, and (23%) and (24%) for (4times) and (8times) super-resolution tasks.
  arXiv  Detail & Related papers  (2025-07-22T19:35:14Z)
• DPER: Diffusion Prior Driven Neural Representation for Limited Angle and Sparse View CT Reconstruction [45.00528216648563]
  Diffusion Prior Driven Neural Representation (DPER) is an unsupervised framework designed to address the exceptionally ill-posed CT reconstruction inverse problems. DPER adopts the Half Quadratic Splitting (HQS) algorithm to decompose the inverse problem into data fidelity and distribution prior sub-problems. We conduct comprehensive experiments to evaluate the performance of DPER on LACT and ultra-SVCT reconstruction with two public datasets.
  arXiv  Detail & Related papers  (2024-04-27T12:55:13Z)
• ArSDM: Colonoscopy Images Synthesis with Adaptive Refinement Semantic Diffusion Models [69.9178140563928]
  Colonoscopy analysis is essential for assisting clinical diagnosis and treatment. The scarcity of annotated data limits the effectiveness and generalization of existing methods. We propose an Adaptive Refinement Semantic Diffusion Model (ArSDM) to generate colonoscopy images that benefit the downstream tasks.
  arXiv  Detail & Related papers  (2023-09-03T07:55:46Z)
• Brain Imaging-to-Graph Generation using Adversarial Hierarchical Diffusion Models for MCI Causality Analysis [44.45598796591008]
  Brain imaging-to-graph generation (BIGG) framework is proposed to map functional magnetic resonance imaging (fMRI) into effective connectivity for mild cognitive impairment analysis. The hierarchical transformers in the generator are designed to estimate the noise at multiple scales. Evaluations of the ADNI dataset demonstrate the feasibility and efficacy of the proposed model.
  arXiv  Detail & Related papers  (2023-05-18T06:54:56Z)
• DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection [80.20339155618612]
  DiffusionAD is a novel anomaly detection pipeline comprising a reconstruction sub-network and a segmentation sub-network.<n>A rapid one-step denoising paradigm achieves hundreds of times acceleration while preserving comparable reconstruction quality.<n>Considering the diversity in the manifestation of anomalies, we propose a norm-guided paradigm to integrate the benefits of multiple noise scales.
  arXiv  Detail & Related papers  (2023-03-15T16:14:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.