Diffusion Models for Medical Anomaly Detection

By Julia Wolleb, Florentin Bieder, Robin Sandkühler, Philippe C. Cattin. International Conference on Medical Image Computing and Computer-Assisted Intervention, 2022

417 citations recorded by the source corpus.

In medical applications, weakly supervised anomaly detection methods are of great interest, as only image-level annotations are required for training. Current anomaly detection methods mainly rely on generative adversarial networks or autoencoder models. Those models are often complicated to train or have difficulties to preserve fine details in the image. We present a novel weakly supervised anomaly detection method based on denoising diffusion implicit models. We combine the deterministic iterative noising and denoising scheme with classifier guidance for image-to-image translation between diseased and healthy subjects. Our method generates very detailed anomaly maps without the need for a complex training procedure. We evaluate our method on the BRATS2020 dataset for brain tumor detection and the CheXpert dataset for detecting pleural effusions.

View Paper: https://www.semanticscholar.org/paper/dc21d8ee24038e99ddfd0fe88b263e0eabc54337

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

A Survey on Generative Diffusion Models (2022, methodology): “It typically requires an additional classiﬁer with a UNet Encoder architecture to generate condition gradients for speciﬁc labels, which can be text, categorical, binary, or extracted features [12], [27], [28], [49], [50], [51], [52], [53], [54], [55].”
Unsupervised Medical Image Translation With Adversarial Diffusion Models (2022, methodology): “Since the training and validation subjects in the pelvic dataset did not carry any implants, the trained models learned to associate dark regions in T 1 -weighted MR images with regular tissues that elicit low signal such as outer bone layers [51].”
Diffusion models in medical imaging: A comprehensive survey (2022, methodology): “• Generalization to other types of noise distributions [69] • Facilitating diffusion process via implicit guidance [70] • Acceleration improvement using trainingfree DDIM sampling [71, 16] • Guiding diffusion process via classifier guidance [16] • Conditional DDPMs [63, 49, 53, 66, 146, 74] • Genera”
Diffusion Models in Vision: A Survey (2022, methodology): “Even if we found some works studying anomaly detection in medical images [44], [45], [46], this task could also be explored in other domains, such as video surveillance or industrial inspection.”