Medsam
PulseAugur coverage of Medsam — every cluster mentioning Medsam across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
BruNet framework achieves state-of-the-art bruise segmentation
Researchers have developed BruNet, a novel framework for segmenting bruises in medical images, addressing the challenges of limited data and variable appearance. This framework utilizes a ViT-based visual encoder, such …
-
New framework improves AI polyp segmentation reliability
Researchers have developed a new framework called Referee-Based Quality Estimation (RBQE) to improve the reliability of polyp segmentation models used in real-time colonoscopies. RBQE measures the agreement between a pr…
-
DeferredSeg framework enhances medical image segmentation with human-AI collaboration
Researchers have developed DeferredSeg, a novel framework designed to improve the trustworthiness of medical image segmentation by incorporating a human-AI collaboration system. This system dynamically routes pixels to …
-
New AI agent MediSkill-Evo improves clinical diagnosis and evidence grounding
Researchers have developed MediSkill-Evo, a novel clinical agent designed to improve diagnostic accuracy and evidence-based decision-making in healthcare interactions. This system enhances an agent's ability to gather e…
-
MedSAM adaptation can hurt out-of-distribution performance, study finds
A new research paper explores how adapting foundation models like MedSAM for medical image segmentation can inadvertently harm their performance on out-of-distribution (OOD) data. The study tested six adaptation strateg…
-
VesselBridge3D framework adapts foundation models for low-data 3D vessel segmentation
Researchers have developed VesselBridge3D, a new framework designed to improve 3D vessel segmentation in medical imaging, particularly in low-data scenarios. This framework adapts existing foundation models, such as DIN…
-
MedSAM enables zero-shot prostate segmentation in micro-ultrasound
Researchers have developed a novel zero-shot pipeline using the MedSAM foundation model to segment prostate boundaries in high-frequency micro-ultrasound images. This method aims to improve early detection of prostate c…
-
New adaptive prompting framework improves multi-organ ultrasound segmentation
Researchers have developed BAP-MOS, a novel framework for multi-organ ultrasound segmentation that addresses challenges with adjacent structures and localized boundary errors. The system employs an adaptive prompting st…
-
AI model uses Vision Transformer for laryngeal cancer screening
Researchers have developed a new AI model using a Vision Transformer and attention mechanisms to analyze NBI endoscopy images for laryngeal cancer screening. This model demonstrates good classification performance with …
-
New framework ConceptSMILE audits trustworthiness of AI concept explanations
Researchers have developed ConceptSMILE, a new model-agnostic framework designed to audit the trustworthiness of concept-based explanations in artificial intelligence. This framework extends existing perturbation-based …
-
New framework combats medical MLLM hallucinations with evidence injection
Researchers have developed a novel, training-free framework to enhance the trustworthiness of medical multimodal large language models (MLLMs). This system, called Synergistic Perception-Reasoning Governance, addresses …
-
New AI framework translates radiologist speech to MRI tumor segmentation
Researchers have developed LoGSAM, a novel framework designed for parameter-efficient segmentation of brain tumors in MRI scans. This system transforms radiologist dictations into text prompts that guide foundation mode…
-
New method enhances medical image segmentation for skin lesions
Researchers have developed PEFT-MedSAM, a parameter-efficient fine-tuning method for the Medical Segment Anything Model (MedSAM) to improve the segmentation of skin lesions in dermoscopic images. This technique freezes …
-
New AI framework segments eye glands without costly masks
Researchers have developed TopoPult-SSL, a novel two-stage framework for segmenting meibomian glands across different clinical imaging devices. The first stage adapts existing models using weak clinical priors like eyel…
-
New AI models enhance medical image segmentation accuracy
Researchers have developed two new approaches to improve medical image segmentation. One method enhances the MedSAM model by adding a lightweight box predictor, which uses a single click to estimate a bounding box, impr…
-
Medical AI Evolves: Agents Automate Workflows, Models Grasp Complex Reasoning
Recent research presented at CVPR 2026 indicates a shift in medical AI from simple image recognition to more complex tasks like workflow optimization and cross-modal reasoning. Studies are exploring AI agents that can a…
-
New Transformer Model Enhances Medical Image Segmentation
Researchers have developed SMAFormer, a new Transformer-based architecture designed to improve medical image segmentation, particularly for small and irregularly shaped tumors. This model integrates multiple attention m…
-
New benchmark tests medical AI model robustness
Researchers have introduced MedFM-Robust, a new benchmark designed to evaluate the reliability of medical foundation models. This benchmark assesses both vision-language models, such as LLaVA-Med and GPT-4o, and segment…
-
MedCore framework prunes MedSAM for clinical use
Researchers have developed MedCore, a new framework designed to prune large medical image segmentation models like MedSAM. This method focuses on preserving critical structures and boundary fidelity, which are essential…
-
CRC-SAM framework enables multi-modal colorectal cancer segmentation
Researchers have developed CRC-SAM, a novel framework for segmenting colorectal cancer across multiple imaging types including CT, colonoscopy, and histology. This system builds upon the MedSAM model and utilizes low-ra…