Selected work

Representative Papers

WeakMedSAM: Weakly-Supervised Medical Image Segmentation via SAM with Sub-Class Exploration and Prompt Affinity Mining

Mar 06, 2025

This work addresses the high cost of pixel-level annotations in medical image segmentation by proposing WeakMedSAM, a weakly supervised framework requiring only image-level or coarse-grained labels—no pixel-wise supervision. Methodologically, it introduces a novel subclass exploration module to mitigate interference from co-occurring lesions; a prompt affinity mining module that leverages SAM’s prompting capability to generate high-quality activation maps and guides random walk for precise segmentation; and integrates subclass contrastive learning, prompt-driven affinity graph modeling, and random-walk post-processing within a SAM-based architecture (compatible with SAMUS/EfficientSAM). Evaluated on BraTS 2019, AbdomenCT-1K, and MSD Cardiac benchmarks, WeakMedSAM significantly outperforms existing weakly supervised approaches and achieves performance comparable to state-of-the-art fully supervised methods.

0 citationsRead paper

CDI: Blind Image Restoration Fidelity Evaluation based on Consistency with Degraded Image

Jan 24, 2025

Addressing the lack of reliable no-reference image quality assessment (IQA) methods in blind image restoration (BIR), this paper proposes a novel fidelity evaluation paradigm centered on degradation image consistency (CDI). We systematically reveal, for the first time, how solution non-uniqueness and degradation uncertainty in BIR negatively impact traditional image quality metrics (IQMs). To address this, we design a dual-path CDI framework: one path leverages wavelet-domain reference guidance, while the other operates in a fully reference-free manner. Furthermore, we introduce DISDCD—the first human-annotated dataset specifically designed for subjective fidelity evaluation in BIR. On DISDCD, CDI substantially outperforms full-reference metrics including PSNR, LPIPS, and DISTS, achieving strong alignment with human perception (SROCC > 0.89). Both the code and the DISDCD dataset will be publicly released.

0 citationsRead paper

Recent publications

Latest Papers

WeakMedSAM: Weakly-Supervised Medical Image Segmentation via SAM with Sub-Class Exploration and Prompt Affinity Mining

Mar 06, 2025

This work addresses the high cost of pixel-level annotations in medical image segmentation by proposing WeakMedSAM, a weakly supervised framework requiring only image-level or coarse-grained labels—no pixel-wise supervision. Methodologically, it introduces a novel subclass exploration module to mitigate interference from co-occurring lesions; a prompt affinity mining module that leverages SAM’s prompting capability to generate high-quality activation maps and guides random walk for precise segmentation; and integrates subclass contrastive learning, prompt-driven affinity graph modeling, and random-walk post-processing within a SAM-based architecture (compatible with SAMUS/EfficientSAM). Evaluated on BraTS 2019, AbdomenCT-1K, and MSD Cardiac benchmarks, WeakMedSAM significantly outperforms existing weakly supervised approaches and achieves performance comparable to state-of-the-art fully supervised methods.

0 citationsRead paper

CDI: Blind Image Restoration Fidelity Evaluation based on Consistency with Degraded Image

Jan 24, 2025

Addressing the lack of reliable no-reference image quality assessment (IQA) methods in blind image restoration (BIR), this paper proposes a novel fidelity evaluation paradigm centered on degradation image consistency (CDI). We systematically reveal, for the first time, how solution non-uniqueness and degradation uncertainty in BIR negatively impact traditional image quality metrics (IQMs). To address this, we design a dual-path CDI framework: one path leverages wavelet-domain reference guidance, while the other operates in a fully reference-free manner. Furthermore, we introduce DISDCD—the first human-annotated dataset specifically designed for subjective fidelity evaluation in BIR. On DISDCD, CDI substantially outperforms full-reference metrics including PSNR, LPIPS, and DISTS, achieving strong alignment with human perception (SROCC > 0.89). Both the code and the DISDCD dataset will be publicly released.

0 citationsRead paper