Self-supervised multi-scale cropping and simple masked attentive predicting for lung CT-scan anomaly detection

W Li, GH Liu, H Fan, Z Li… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Anomaly detection has been widely explored by training an out-of-distribution detector with
only normal data for medical images. However, detecting local and subtle irregularities …

Enhancing Reconstruction-Based Out-of-Distribution Detection in Brain MRI with Model and Metric Ensembles

E Huijben, S Amirrajab, JPW Pluim - arXiv preprint arXiv:2412.17586, 2024 - arxiv.org
Out-of-distribution (OOD) detection is crucial for safely deploying automated medical image
analysis systems, as abnormal patterns in images could hamper their performance …

Image-Conditioned Diffusion Models for Medical Anomaly Detection

M Baugh, H Reynaud, SN Marimont… - … on Uncertainty for Safe …, 2024 - Springer
Generating pseudo-healthy reconstructions of images is an effective way to detect
anomalies, as identifying the differences between the reconstruction and the original can …

Harder synthetic anomalies to improve OoD detection in Medical Images

SN Marimont, G Tarroni - arXiv preprint arXiv:2308.01412, 2023 - arxiv.org
Our method builds upon previous Medical Out-of-Distribution (MOOD) challenge winners
that empirically show that synthetic local anomalies generated copying/interpolating foreign …