Multi-Kernel Gated Decoder Adapters for Robust Multi-Task Thyroid Ultrasound under Cross-Center Shift

• URL: http://arxiv.org/abs/2603.08906v1
• Date: Mon, 09 Mar 2026 20:18:35 GMT
• Title: Multi-Kernel Gated Decoder Adapters for Robust Multi-Task Thyroid Ultrasound under Cross-Center Shift
• Abstract summary: We describe interference across CNN (ResNet34) and medical ViT (MedSAM) backbones.<n>Motivated by this failure mode, we propose a lightweight family of decoder-side adapters.
• Score: 3.6219347779447038
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Thyroid ultrasound (US) automation couples two competing requirements: global, geometry-driven reasoning for nodule delineation and local, texture-driven reasoning for malignancy risk assessment. Under cross-center domain shift, these cues degrade asymmetrically, yet most multi-task pipelines rely on a single shared backbone, often inducing negative transfer. In this paper, we characterize this interference across CNN (ResNet34) and medical ViT (MedSAM) backbones, and observe a consistent trend: ViTs transfer geometric priors that benefit segmentation, whereas CNNs more reliably preserve texture cues for malignancy discrimination under strong shift and artifacts. Motivated by this failure mode, we propose a lightweight family of decoder-side adapters, the Multi-Kernel Gated Adapter (MKGA) and a residual variant (ResMKGA), which refine multi-scale skip features using complementary receptive fields and apply semantic, context-conditioned gating to suppress artifact-prone content before fusion. Across two US benchmarks, the proposed adapters improve cross-center robustness: they strengthen out-of-domain segmentation and, in the CNN setting, yield clear gains in clinical TI-RADS diagnostic accuracy compared to standard multi-task baselines. Code and models will be released.

Related papers

• MSA-DCNN: A Data-Efficient Multi-Scale Deformable CNN for Medical Image Classification [1.6566053195631467]
  Existing deep learning methods struggle with multi-scale morphology and limited annotations due to fixed sampling and data-hungry training.<n>We propose MSA-DCNN, a scale-consistent deformable attention learning framework that introduces adaptive multi-scale sampling, within-scale saliency refinement, learned cross-scale fusion, and auxiliary self-distillation within a unified optimisation scheme.
  arXiv  Detail & Related papers  (2026-07-07T09:52:46Z)
• Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs [59.973833105841685]
  A key challenge for improving adversarial transferability is to effectively capture the intrinsic visual focus shared across different models.<n>We propose FRA-Attack, which addresses both challenges from a unified frequency-domain regularization perspective.<n>For feature alignment, a high-pass DCT objective on patch features suppresses redundant global structures and concentrates the loss on the high-frequency band that carries the MLLMs' intrinsic visual focus.<n>For gradient optimization, we introduce Frequency-domain Gradient Regularization (FGR), a textitmodel-agnostic low-pass regularizer that modulates the surrogate gradient using
  arXiv  Detail & Related papers  (2026-05-20T08:15:56Z)
• VISTA: Variance-Gated Inter-Sequence Test-Time Adaptation for Multi-Sequence MRI Segmentation [26.129902154272298]
  Variance-gated Inter-Sequence Test-time Adaptation (VISTA) is a source-free framework that tackles modality-interaction shifts.<n>We introduce Cross-View Disagreement-Aware Pseudo Labeling (CDPL) to dynamically gate self-training and enforce interventional consistency.
  arXiv  Detail & Related papers  (2026-05-17T12:57:29Z)
• SPEGC: Continual Test-Time Adaptation via Semantic-Prompt-Enhanced Graph Clustering for Medical Image Segmentation [12.0982298854338]
  Continual Test-Time Adaptation (CTTA) aims to enable pre-trained models to adapt to continuously changing unlabeled domains.<n>We propose a CTTA via Semantic-Prompt-Enhanced Graph Clustering (SPEGC) for medical image segmentation.
  arXiv  Detail & Related papers  (2026-03-12T03:22:43Z)
• Gated Differential Linear Attention: A Linear-Time Decoder for High-Fidelity Medical Segmentation [15.30336007288786]
  PVT-GDLA is a decoder-centric Transformer that restores sharp, long-range dependencies at linear time.<n>It achieves state-of-the-art accuracy across CT, MRI, ultrasound, and dermoscopy benchmarks under equal training budgets.
  arXiv  Detail & Related papers  (2026-03-03T08:26:08Z)
• Uncertainty-Guided Selective Adaptation Enables Cross-Platform Predictive Fluorescence Microscopy [65.15943255667733]
  We introduce Subnetwork Image Translation ADDA with automatic depth selection (SIT-ADDA-Auto)<n>We show that adapting only the earliest convolutional layers, while freezing deeper layers, yields reliable transfer.<n>Our results provide a design rule for label-free adaptation in microscopy and a recipe for field settings; the code is publicly available.
  arXiv  Detail & Related papers  (2025-11-15T03:01:05Z)
• Unleashing Vision Foundation Models for Coronary Artery Segmentation: Parallel ViT-CNN Encoding and Variational Fusion [12.839049648094893]
  coronary artery segmentation is critical for computeraided diagnosis of coronary artery disease (CAD)<n>We propose a novel framework that leverages the power of vision foundation models (VFMs) through a parallel encoding architecture.<n>The proposed framework significantly outperforms state-of-the-art methods, achieving superior performance in accurate coronary artery segmentation.
  arXiv  Detail & Related papers  (2025-07-17T09:25:00Z)
• Diagnosis for Less-Prevalent Thyroid Carcinoma Subtype Using a Dual-Branch Attention Deep Network with Ultrasound Images [5.558034869630433]
  Heterogeneous morphological features and data imbalance pose significant challenges in rare thyroid carcinoma classification using ultrasound imaging.<n>We propose a novel multitask learning framework, Channel-Spatial Attention Synergy Network (CSASN), which integrates a dual-branch feature extractor.
  arXiv  Detail & Related papers  (2025-05-04T18:23:03Z)
• Prototype Learning Guided Hybrid Network for Breast Tumor Segmentation in DCE-MRI [58.809276442508256]
  We propose a hybrid network via the combination of convolution neural network (CNN) and transformer layers. The experimental results on private and public DCE-MRI datasets demonstrate that the proposed hybrid network superior performance than the state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-08-11T15:46:00Z)
• Multi-Source and Test-Time Domain Adaptation on Multivariate Signals using Spatio-Temporal Monge Alignment [59.75420353684495]
  Machine learning applications on signals such as computer vision or biomedical data often face challenges due to the variability that exists across hardware devices or session recordings. In this work, we propose Spatio-Temporal Monge Alignment (STMA) to mitigate these variabilities. We show that STMA leads to significant and consistent performance gains between datasets acquired with very different settings.
  arXiv  Detail & Related papers  (2024-07-19T13:33:38Z)
• Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation [37.79819260918366]
  Continual Test-Time Adaptation (CTTA) aims to adapt the pre-trained model to ever-evolving target domains. We explore the integration of a Mixture-of-Activation-Sparsity-Experts (MoASE) as an adapter for the CTTA task.
  arXiv  Detail & Related papers  (2024-05-26T08:51:39Z)
• Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection [76.11864242047074]
  We propose a novel Affine-Consistent Transformer (AC-Former), which directly yields a sequence of nucleus positions. We introduce an Adaptive Affine Transformer (AAT) module, which can automatically learn the key spatial transformations to warp original images for local network training. Experimental results demonstrate that the proposed method significantly outperforms existing state-of-the-art algorithms on various benchmarks.
  arXiv  Detail & Related papers  (2023-10-22T02:27:02Z)
• MS-DETR: Multispectral Pedestrian Detection Transformer with Loosely Coupled Fusion and Modality-Balanced Optimization [43.04788370184486]
  misalignment and modality imbalance are the most significant issues in multispectral pedestrian detection. MS-DETR consists of two modality-specific backbones and Transformer encoders, followed by a multi-modal Transformer decoder. Our end-to-end MS-DETR shows superior performance on the challenging KAIST, CVC-14 and LLVIP benchmark datasets.
  arXiv  Detail & Related papers  (2023-02-01T07:45:10Z)
• ARPM-net: A novel CNN-based adversarial method with Markov Random Field enhancement for prostate and organs at risk segmentation in pelvic CT images [10.011212599949541]
  The research is to develop a novel CNN-based adversarial deep learning method to improve and expedite the multi-organ semantic segmentation of CT images. The proposed adversarial multi-residual multi-scale pooling Markov Random Field (MRF) enhanced network (ARPM-net) implements an adversarial training scheme. The accuracy of modeled contours was measured with the Dice similarity coefficient (DSC), Average Hausdorff Distance (AHD), Average Surface Hausdorff Distance (ASHD), and relative Volume Difference (VD) using clinical contours as references.
  arXiv  Detail & Related papers  (2020-08-11T02:40:53Z)

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.