Holistic image analysis comprises interdependent subtasks such as segmentation, detection, and recognition of relevant objects. Here, we propose BiomedParse, a biomedical foundation model for imaging ...

Abstract: Federated learning empowers the privacy-preserving training of a global model in decentralized medical scenarios ... to integrate personalization and clustering in medical image segmentation ...

We used Hodgkin Lymphoma (HL) with 18 F-fluorodeoxyglucose (FGD) PET/CT as an example and aimed to develop and validate a fully automated 3D segmentation model incorporating HL-specific intensity ...

The Masked Autoencoder (MAE) is an effective self-supervised learning strategy in computer vision 29: portions of the image are masked ... with the CNN network models DenseNet121 and ResNet50, trained ...

[2025/06/06] 🎉 We release the inference code and checkpoints of StyleAR integrate with depth control. [2025/05/27] 🎉 We release the inference code and checkpoints. [2025/05/27] 🎉 We release the ...

rough edge segmentation, and false and even missed detections caused by the light, shadow, and other factors. To address these issues, we propose a visual state-space (VSS) model called GLVMamba, ...