News

[Nature Communications] Large-scale generative tumor synthesis in computed tomography images for improving tumor recognition

A new study from HKUST Smart Lab introduces FreeTumor, a Generative AI (GAI) model for tumor synthesis that is now published in Nature Communications.

Last updated on 2025/12/11

[TPAMI] Large-Scale 3D Medical Image Pre-training with Geometric Context Priors

HKUST Smart Lab is proud to announce the publication of our latest work, a foundation model for 3D medical image analysis that is now published in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).

Last updated on 2025/12/03

[Press Release] SmartLab Introduces SmartPath: An AI Pathology Platform Transforming End-to-End Cancer Care

SmartLab unveils SmartPath, an AI-powered pathology system that transforms cancer care workflows through accurate diagnosis, subtyping, biomarker quantification, treatment response assessment, and prognostic follow-up.

Last updated on 2025/10/20

[EClinicalMedicine] Multi-task Deep Learning System achieves accurate identification and prognosis prediction of triple-negative breast cancer

A collaborative team has developed a multi-task deep learning system capable of identifying and predicting prognosis of triple-negative breast cancer based on H&E WSIs, improving both accuracy and efficiency in clinical workflows.

Last updated on 2025/10/10

[EClinicalMedicine] Multi-task Deep Learning System Enhances Integrated Non-invasive MRI Diagnosis of Nine Knee Abnormalities

A collaborative team has developed a multi-task deep learning system capable of diagnosing nine common knee abnormalities on MRI, improving both accuracy and efficiency in clinical workflows.

Last updated on 2025/09/29