13 papers · 1 filter
Linguistically-Aligned and Visually-Grounded Preference Optimization for Clinically-Augmented Medical Report Generation
Qiang Hu, Yuxuan Luo, Yingjie Guo +4
Despite significant advances in Medical Report Generation (MRG), the reliability remains constrained by the prevalence of factual errors. While Direct Preference Optimization (DPO)…
Mask to Concept: Auto-Promptable SAM3 via Efficient Test-Time Concept Embedding Search for Few-Shot Annotation
Quan Zhou, Shaoqing Zhai, Qiang Hu +3
Transforming foundation segmentation models from human-prompted tools into auto-promptable annotators is critical for scalable medical data annotation. Current methods commonly dep…
Pairing-free Group-level Knowledge Distillation for Robust Gastrointestinal Lesion Classification in White-Light Endoscopy
Qiang Hu, Qimei Wang, Yingjie Guo +2
White-Light Imaging (WLI) is the standard for endoscopic cancer screening, but Narrow-Band Imaging (NBI) offers superior diagnostic details. A key challenge is transferring knowled…
Moving Light Adaptive Colonoscopy Reconstruction via Illumination-Attenuation-Aware 3D Gaussian Splatting
Hao Wang, Ying Zhou, Haoyu Zhao +5
3D Gaussian Splatting (3DGS) enables real-time view synthesis in colonoscopy but assumes static illumination, making it incompatible with the strong photometric variations caused b…
FreeVPS: Repurposing Training-Free SAM2 for Generalizable Video Polyp Segmentation
Qiang Hu, Ying Zhou, Gepeng Ji +3
Existing video polyp segmentation (VPS) paradigms usually struggle to balance between spatiotemporal modeling and domain generalization, limiting their applicability in real clinic…
Targeted False Positive Synthesis via Detector-guided Adversarial Diffusion Attacker for Robust Polyp Detection
Quan Zhou, Gan Luo, Qiang Hu +5
Polyp detection is crucial for colorectal cancer screening, yet existing models are limited by the scale and diversity of available data. While generative models show promise for d…
Holistic White-light Polyp Classification via Alignment-free Dense Distillation of Auxiliary Optical Chromoendoscopy
Qiang Hu, Qimei Wang, Jia Chen +4
White Light Imaging (WLI) and Narrow Band Imaging (NBI) are the two main colonoscopic modalities for polyp classification. While NBI, as optical chromoendoscopy, offers valuable va…
First-frame Supervised Video Polyp Segmentation via Propagative and Semantic Dual-teacher Network
Qiang Hu, Mei Liu, Qiang Li +1
Automatic video polyp segmentation plays a critical role in gastrointestinal cancer screening, but the cost of frameby-frame annotations is prohibitively high. While sparse-frame s…
SALI: Short-term Alignment and Long-term Interaction Network for Colonoscopy Video Polyp Segmentation
Qiang Hu, Zhenyu Yi, Ying Zhou +4
Colonoscopy videos provide richer information in polyp segmentation for rectal cancer diagnosis. However, the endoscope's fast moving and close-up observing make the current method…
StyleSeg V2: Towards Robust One-shot Segmentation of Brain Tissue via Optimization-free Registration Error Perception
Zhiwei Wang, Xiaoyu Zeng, Chongwei Wu +4
One-shot segmentation of brain tissue requires training registration-segmentation (reg-seg) dual-model iteratively, where reg-model aims to provide pseudo masks of unlabeled images…
MonoPCC: Photometric-invariant Cycle Constraint for Monocular Depth Estimation of Endoscopic Images
Zhiwei Wang, Ying Zhou, Shiquan He +6
Photometric constraint is indispensable for self-supervised monocular depth estimation. It involves warping a source image onto a target view using estimated depth&pose, and then m…
MonoBox: Tightness-free Box-supervised Polyp Segmentation using Monotonicity Constraint
Qiang Hu, Zhenyu Yi, Ying Zhou +4
We propose MonoBox, an innovative box-supervised segmentation method constrained by monotonicity to liberate its training from the user-unfriendly box-tightness assumption. In cont…
IBoxCLA: Towards Robust Box-supervised Segmentation of Polyp via Improved Box-dice and Contrastive Latent-anchors
Qiang Hu, Ying Chen, Hongkuan Shi +2
Box-supervised polyp segmentation attracts increasing attention for its cost-effective potential. Existing solutions often rely on learning-free methods or pretrained models to lab…