analiza aiqbench
This paper introduces FreNet, a novel framework that integrates visual priors from Segment Anything Model (SAM) and dual-domain feature reconfiguration to tackle the complexities of medical lesion segmentation. By decoupling features in the frequency domain and applying spatial localization during encoding, the method significantly improves foreground-background discriminability on diverse imaging modalities. The approach demonstrates substantial performance gains over state-of-the-art models, addressing critical challenges in clinical diagnosis through advanced computer vision techniques.
Feature Reconfiguration With Visual Prior for Medical Lesion Segmentation
arXiv:2609.03535v1 Announce Type: new Abstract: Lesion segmentation in medical images plays a critical role in clinical diagnosis and treatment planning. Despite significant advances, lesion segmentation remains challenging due to two major factors: (1) complex background interference; (2) diverse lesion morphology. Existing encoder-decoder based methods mainly focus on enhancing feature extraction or redesigning decoding strategies. However, they lack early prior guidance and feature reconfiguration during the encoding stage, limiting their effectiveness in handling these challenges. To address these limitations, we propose FreNet, a feature reconfiguration framework with visual priors, which performs pixel-level reconfiguration before encoding and feature-level reconfiguration during encoding for precise medical lesion segmentation. To suppress background responses, we propose an Implicit Prior Neural Network (IPNN), which models a continuous spatial field and leverages visual prior from SAM to reconfigure input image before encoding stage. To better handle diverse lesion morphology, we design a Dual-domain Feature Reconfiguration (DFR) module to progressively reconfigure backbone features during encoding stage. Within DFR, the Frequency Decoupling Module (FDM) decouples backbone features in frequency domain to enhance foreground-background discriminability, while the Spatial Localization Module (SLM) spatially relocates and improving spatial stability after frequency decoupling. Extensive experiments on 9 medical image segmentation benchmarks across three imaging modalities demonstrate that FreNet significantly outperforms state-of-the-art (SOTA) methods. On the challenging ETIS dataset, our method achieves Dice improvements of 5.0% over SOTA method and 7.2% over SAM.
Abstract:Lesion segmentation in medical images plays a critical role in clinical diagnosis and treatment planning. Despite significant advances, lesion segmentation remains challenging due to two major factors: (1) complex background interference; (2) diverse lesion morphology. Existing encoder-decoder based methods mainly focus on enhancing feature extraction or redesigning decoding strategies. However, they lack early prior guidance and feature reconfiguration during the encoding stage, limiting their effectiveness in handling these challenges. To address these limitations, we propose FreNet, a feature reconfiguration framework with visual priors, which performs pixel-level reconfiguration before encoding and feature-level reconfiguration during encoding for precise medical lesion segmentation. To suppress background responses, we propose an Implicit Prior Neural Network (IPNN), which models a continuous spatial field and leverages visual prior from SAM to reconfigure input image before encoding stage. To better handle diverse lesion morphology, we design a Dual-domain Feature Reconfiguration (DFR) module to progressively reconfigure backbone features during encoding stage. Within DFR, the Frequency Decoupling Module (FDM) decouples backbone features in frequency domain to enhance foreground-background discriminability, while the Spatial Localization Module (SLM) spatially relocates and improving spatial stability after frequency decoupling. Extensive experiments on 9 medical image segmentation benchmarks across three imaging modalities demonstrate that FreNet significantly outperforms state-of-the-art (SOTA) methods. On the challenging ETIS dataset, our method achieves Dice improvements of 5.0% over SOTA method and 7.2% over SAM.
Artificial Intelligence (cs.AI); Image and Video Processing (eess.IV)
arXiv:2609.03535 [cs.AI]
(or arXiv:2609.03535v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.03535 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 322 cuvinte
Subiecte conexe
InstEditSeg: Instruction-Driven Image Editing for Polyp and Skin Lesion Segmentation
arXiv · 3 sept. 2026
Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images
arXiv · 14 sept. 2026
NVIDIA’s NV-Reason-CT brings AI reasoning to 3D CT scans
Quantum Zeitgeist · 24 sept. 2026
Beyond Visual Cues: CoT-Enhanced Reasoning for Semi-supervised Medical Image Segmentation
arXiv · 17 iun. 2026