Leveraging diffusion models for unsupervised out-of-distribution detection on image manifold.

Out-of-distribution (OOD) detection is crucial for enhancing the reliability of machine learning models when confronted with data that differ from their training distribution. In the image domain, we hypothesize that images inhabit manifolds defined by latent properties such as color, position, and shape. Leveraging this intuition, we propose a novel approach to OOD detection using a diffusion model to discern images that deviate from the in-domain distribution.

An alternative extension of telomeres related prognostic model to predict survival in lower grade glioma.

Objective: The alternative extension of the telomeres (ALT) mechanism is activated in lower grade glioma (LGG), but the role of the ALT mechanism has not been well discussed. The primary purpose was to demonstrate the significance of the ALT mechanism in prognosis estimation for LGG patients.

Method: Gene expression and clinical data of LGG patients were collected from the Chinese Glioma Genome Atlas (CGGA) and the Cancer Genome Atlas (TCGA) cohort, respectively.