GERD

Point, Detect, Count: Multi-Task Medical Image Understanding with Instruction-Tuned Vision-Language Models

We investigate fine-tuning Vision-Language Models (VLMs) for multi-task medical image understanding, focusing on detection, localization, and counting of findings in medical images. Our objective is to evaluate whether instruction-tuned VLMs can simultaneously improve these tasks, with the goal of enhancing diagnostic accuracy and efficiency. Using MedMultiPoints, a multimodal dataset with annot...

SAMA-UNet: Enhancing Medical Image Segmentation with Self-Adaptive Mamba-Like Attention and Causal-Resonance Learning

Medical image segmentation plays an important role in various clinical applications, but existing models often struggle with the computational inefficiencies and challenges posed by complex medical data. State Space Sequence Models (SSMs) have demonstrated promise in modeling long-range dependencies with linear computational complexity, yet their application in medical image segmentation remains...

EndoVLA: Dual-Phase Vision-Language-Action Model for Autonomous Tracking in Endoscopy

In endoscopic procedures, autonomous tracking of abnormal regions and following circumferential cutting markers can significantly reduce the cogniti...

Application of deep learning models in the pathological classification and staging of esophageal cancer: A focus on Wave-Vision Transformer.

BACKGROUND: Esophageal cancer is the sixth most common cancer worldwide, with a high mortality rate. Early prognosis of esophageal abnormalities can i...

Characterization of subepithelial tumors of upper gastrointestinal tract by endoscopic ultrasound.

In this article we comment on the paper by Xu describing retrospective data on endoscopic treatment outcome of esophageal gastrointestinal stromal tu...

PRS-Med: Position Reasoning Segmentation with Vision-Language Model in Medical Imaging

Recent advancements in prompt-based medical image segmentation have enabled clinicians to identify tumors using simple input like bounding boxes or ...

VitaGraph: Building a Knowledge Graph for Biologically Relevant Learning Tasks

The intrinsic complexity of human biology presents ongoing challenges to scientific understanding. Researchers collaborate across disciplines to exp...

Informed, but Not Always Improved: Challenging the Benefit of Background Knowledge in GNNs

In complex and low-data domains such as biomedical research, incorporating background knowledge (BK) graphs, such as protein-protein interaction (PP...

Advances in gastrointestinal endoscopy: A comprehensive review of innovations in cancer diagnosis and management.

The field of gastroenterology has experienced revolutionary advances over the past years, as flexible endoscopes have become widely accessible. In add...

GNN-Suite: a Graph Neural Network Benchmarking Framework for Biomedical Informatics

We present GNN-Suite, a robust modular framework for constructing and benchmarking Graph Neural Network (GNN) architectures in computational biology...

Multi-contrast laser endoscopy for in vivo gastrointestinal imaging

White light endoscopy is the clinical gold standard for detecting diseases in the gastrointestinal tract. Most applications involve identifying visu...

Investigating the Genetic Links Between Immune Cell Profiles and Bladder Cancer: A Multidisciplinary Bioinformatics Approach.

: Bladder cancer (BC) is a common malignancy in the urinary system, with an increasing incidence rate. Immune cell infiltration within the tumor micro...

Research status and progress of deep learning in automatic esophageal cancer detection.

Esophageal cancer (EC), a common malignant tumor of the digestive tract, requires early diagnosis and timely treatment to improve patient prognosis. A...

A multi-objective evolutionary algorithm for detecting protein complexes in PPI networks using gene ontology.

Detecting protein complexes is crucial in computational biology for understanding cellular mechanisms and facilitating drug discovery. Evolutionary al...

VIGIL: Vision-Language Guided Multiple Instance Learning Framework for Ulcerative Colitis Histological Healing Prediction

Objective: Ulcerative colitis (UC), characterized by chronic inflammation with alternating remission-relapse cycles, requires precise histological h...

Transcriptomic Profiling of Hypoxia-Adaptive Responses in Tibetan Goat Fibroblasts.

The Tibetan goat () exhibits remarkable adaptations to high-altitude hypoxia, yet the molecular mechanisms remain unclear. This study integrates RNA-s...

Unraveling the molecular mechanisms of paclitaxel in high-grade serous ovarian cancer through network pharmacology.

High-grade serous ovarian cancer (HGSOC) is the most common and aggressive subtype of epithelial ovarian cancer, often diagnosed at advanced stages wi...

Risk factors and predictive models for post-operative moderate-to-severe mitral regurgitation following transcatheter aortic valve replacement: a machine learning approach.

BACKGROUND: Post-operative moderate-to-severe mitral regurgitation (MR) following transcatheter aortic valve replacement (TAVR) is associated with poo...

Exploring the potential biomarkers and potential causality of Ménière disease based on bioinformatics and machine learning.

Meniere disease (MD) is a common inner ear disorder closely related to immune abnormalities, but research on the characteristic genes between MD and i...

Automated vision-based assistance tools in bronchoscopy: stenosis severity estimation

Purpose: Subglottic stenosis refers to the narrowing of the subglottis, the airway between the vocal cords and the trachea. Its severity is typicall...