LymphAtlas- A Unified Multimodal Lymphoma Imaging Repository Delivering AI-Enhanced Diagnostic Insight

The Co-Seg++ framework has been introduced to enhance medical image segmentation by allowing semantic and instance segmentation tasks to mutually improve each other. This innovative approach utilizes a spatio-sequential prompt encoder and a multi-task collaborative decoder to better capture relationships in medical images, addressing the challenges of segmenting complex anatomical structures and tumor environments.

A new method for Positron Emission Tomography (PET) image reconstruction has been proposed, utilizing diffusion models to enhance image quality while addressing challenges such as tracer-specific contrast variability and high computational demands. This approach employs an anatomical prior-guided framework that alternates between diffusion sampling and model fine-tuning, resulting in improved image reconstruction from various PET tracers.

A novel hybrid framework has been introduced for precise liver tumor segmentation in CT scans, combining an attention-enhanced U-Net with handcrafted radiomics and voxel-wise 3D CNN refinement. This approach aims to improve the accuracy and efficiency of tumor delineation, addressing challenges such as low contrast and blurred boundaries in imaging.

A new weakly supervised method for the segmentation of vertebral metastases in CT scans has been introduced, utilizing a Diffusion Autoencoder to enhance classification accuracy without requiring detailed lesion masks. This innovative approach leverages voxel-level healthy/malignant labels to identify malignant regions effectively.