Semantic-consistent diffusion model for unsupervised traumatic brain injury detection and segmentation from computed tomography images.

Journal: Medical physics
Published Date: Apr 9, 2025

Abstract

BACKGROUND: Unsupervised traumatic brain injury (TBI) lesion detection aims to identify and segment abnormal regions, such as cerebral edema and hemorrhages, using only healthy training data. Recent advancements in generative models have achieved success in unsupervised anomaly detection by transforming abnormal patterns into normal counterparts. However, current mask-free image generators often fail to maintain semantic consistency of anatomical structures during the restoration process. This limitation negatively impacts residual-based anomaly detection, particularly in cases where structural deformations occur due to the mass effect of TBI lesions.

Authors

  • Diya Sun
    Peking University People's Hospital, Institute for Artificial Intelligence, Key Laboratory of Trauma Treatment and Neural Regeneration, Peking University, Beijing, China.
  • Yuru Pei
    School of Intelligence Science and Technology, Key Laboratory of Machine Perception (MOE), State Key Laboratory of General Artificial Intelligence, Peking University, Beijing, China.
  • Liyi Ying
    School of Mathematics, Statistics and Mechanic, Beijing University of Technology, Beijing, China.
  • Tianbing Wang
    Peking University People's Hospital, Institute for Artificial Intelligence, Key Laboratory of Trauma Treatment and Neural Regeneration, Peking University, Beijing, China.

Keywords

External Resources

Popular Topics
Recent Journals