Image-conditioned Diffusion Models for Medical Anomaly Detection

Matthew Baugh, Hadrien Reynaud, Sergio Naval Marimont, Sarah Cechnicka, Johanna Paula Müller, Giacomo Tarroni, Bernhard Kainz

Keywords: Anomaly detection, self-supervised, diffusion model

Abstract: Generating pseudo-healthy reconstructions of images is an effective way to detect anomalies, as identifying the differences between the reconstruction and the original can localise arbitrary anomalies whilst also providing interpretability for an observer by displaying what the image 'should' look like. All existing reconstruction-based methods have a common shortcoming; they assume that models trained on purely normal data are incapable of reproducing pathologies yet also able to fully maintain healthy tissue. These implicit assumptions often fail, with models either not recovering normal regions or reproducing both the normal and abnormal features. We rectify this issue using image-conditioned diffusion models. Our model takes the input image as conditioning and is explicitly trained to correct synthetic anomalies introduced into healthy images, ensuring that it removes anomalies at test time. This conditioning allows the model to attend to the entire image without any loss of information, enabling it to replicate healthy regions with high fidelity. We evaluate our method across four datasets and define a new state-of-the-art performance for residual-based anomaly detection. Code is available as an anonymous repository until the conference https://anonymous.4open.science/r/image-conditioned-diffusion-model-AD-A323 .

Submission Number: 11