Latest AI and machine learning research in universal precautions for healthcare professionals.
Segmentation models such as Segment Anything Model (SAM) and SAM2 achieve strong prompt-driven zero-shot performance. However, their training on natural images limits domain transfer to medical data. Consequently, accurate segmentation typically requires extensive fine-tuning and expert-designed prompts. We propose DiffuSAM, a diffusion-based adaptation of SAM2 for prompt-free medical image segmen...
Large diffusion transformers (DiTs) follow global editing instructions well but consistently leak local edits into unrelated regions, because joint-attention architectures offer no explicit channel telling the network where to apply the edit. We introduce REDEdit, a co-trained, instruction- and region-aware adapter framework that retrofits a frozen DiT into a precise local editor without modifying...
Tuberculosis (TB) is prevalent in Uganda and overlaps with a high rate of HIV/TB coinfection. While nearly all hospital-based TB cases in Kampala, the...
Background: Radiographic detection of caries lesions adjacent to restorations is challenging due to limitations of two-dimensional imaging and difficu...
This study developed a large language model (LLM)-based solution to identify people at HIV risk using electronic health records. We transformed struct...
Predicting which receptor a phage binds to from genome sequence alone has remained an intractable challenge, principally because the experimental phen...
Panoramic radiography is a fundamental diagnostic tool in dentistry, offering a comprehensive view of the entire dentition with minimal radiation expo...
Background: Datasets related to infectious diseases are essential for public health decision-making, yet their reuse remains limited by persistent bar...
Instance-level object segmentation across disparate egocentric and exocentric views is a fundamental challenge in visual understanding, critical for a...
We address the challenge of synthetic-to-real transfer in forestry perception where real data have only coarse Tree labels while synthetic data provid...
Style transfer aims to render a content image with the visual characteristics of a reference style while preserving its underlying semantic layout and...
Digital breast tomosynthesis (DBT) is now the standard of care for breast cancer screening in the USA. Accurate segmentation of fibroglandular tissue ...
Visual Foundation Models (VFMs) such as the Segment Anything Model (SAM) have significantly advanced broad use of image segmentation. However, SAM and...
Generative object compositing methods have shown remarkable ability to seamlessly insert objects into scenes. However, when applied to real-world cata...
Existing defect/anomaly generation methods often rely on few-shot learning, which overfits to specific defect categories due to the lack of large-scal...
Referring Expression Segmentation (RES) aims to segment image regions described by natural-language expressions, serving as a bridge between vision an...
For applications including facial identification, forensic analysis, photographic improvement, and medical imaging diagnostics, facial image deblurrin...
We introduce region-specific image refinement as a dedicated problem setting: given an input image and a user-specified region (e.g., a scribble mask ...
We present Moondream Segmentation, a referring image segmentation extension of Moondream 3, a vision-language model. Given an image and a referring ex...
Data heterogeneity hinders clinical deployment of medical image analysis models, and generative data augmentation helps mitigate this issue. However, ...