Skip to search formSkip to main contentSkip to account menu

Topicwise Separable Sentence Retrieval for Medical Report Generation

Experiments demonstrate that Teaser surpasses state-of-the-art models, while also validating its capability to effectively represent rare topics and establish more dependable correspondences between queries and topics.
PubMed (opens in a new tab)

MedRG: Medical Report Grounding with Multi-modal Large Language Model

A novel framework, Medical Report Grounding (MedRG), an end-to-end solution for utilizing a multi-modal Large Language Model to predict key phrase by incorporating a unique token, BOX, into the vocabulary to serve as an embedding for unlocking detection capabilities.
arXiv (opens in a new tab)

Training-free image style alignment for self-adapting domain shift on handheld ultrasound devices

The proposed TISA can directly infer handheld device images without extra training and is suited for clinical applications and shows that TISA performs better and more stably in medical detection and segmentation tasks for handheld device data.
arXiv (opens in a new tab)

Training-free image style alignment for domain shift on handheld ultrasound devices.

The Training-free Image Style Alignment (TISA) is proposed to align the style of handheld device data to those of standard devices, and eliminates the demand for source data, and can transform the image style while preserving spatial context during testing.
PubMed (opens in a new tab)

Reliable Source Approximation: Source-Free Unsupervised Domain Adaptation for Vestibular Schwannoma MRI Segmentation

Reliable Source Approximation is proposed, which can generate source-like and structure-preserved images from the target domain for updating model parameters and adapting domain shifts and is validated on vestibular schwannoma segmentation across multi-modality MRI.
arXiv (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)