Diffusion Models for Medical Anomaly Detection

Abstract

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.

Diffusion Models for Medical Image Analysis: A Comprehensive Survey

“…To date, diffusion models have been found to be useful in a wide variety of areas, ranging from generative modeling tasks such as image generation [23], image super-resolution [24], image inpainting [25] to discriminative tasks such as image segmentation [26], classification [27], and anomaly detection [28]. Recently, the medical imaging community has witnessed exponential growth in the number of diffusion-based techniques (see Figure 4).…”

“…Wolleb et al [28] introduce a weakly supervised learning method based on Denoising Diffusion Implicit Models (DDIMs) [72] for medical anomaly detection. Given an input image of a healthy or diseased subject, image-to-image translation first performs such that the objective is to translate the input image into the healthy one.…”

“…Moreover, BrainGen [39] produces realistic examples of brain scans, which are conditioned on meta-data such as age, gender, ventricular volume, and brain volume relative to intracranial volume. In addition, the use of a classifier and implicit guidance methods in [28] and [54] have been investigated thoroughly. In this way, the distribution is shifted in a manner that is more likely to reach the expected outcome.…”

“…• Generalization to other types of noise distributions [53] • Facilitating diffusion process via implicit guidance [54] • Acceleration improvement using trainingfree DDIM sampling [55,28] • Guiding diffusion process via classifier guidance [28] • Conditional DDPMs [46,32,36,50,135,57] • Generating synthetic segmentation datasets [43,44] • Cross-modality translation [34] • Multi-modal conversion [32,34] • Exploiting K-space parameter-free guidance [38] • Accelerate MC sampling using coarse-tofine sampling [38] • Adversarial learning in the reverse diffusion process [39,34] • 3D reconstruction from 2D images [50] • Conditioning on medical meta-data [48] • Using LDM to enhance the training and sampling efficiency [48,59] • DDPMs for histopathology images [49] • 3D medical image generation [51] • Using deformation fields for medical image generation [134,52] • DDPMs in skin image adversarial attacks [56] Noise Conditioned Score Networks (NCSNs) 1 CSGM-MRI-Langevin [96] 2 Self-Score [41] In this algorithm [61], creating samples requires solving the Langevin dynamics equation. However, this equation mandates the solution of the gradient of the log density w.r.t.…”

SHAPR predicts 3D cell shapes from 2D microscopic images

“…Denoising diffusion probabilistic models were further improved in their loss function by architecture changes and by classifier guidance during sampling, leading to improved image quality of the predictions [12,3]. While most diffusion models are applied in the natural image domain, Wolleb et al have used them for segmentation of MRI images [22] and anomaly detection [21] in multimodal brain images, showing their applicability in the medical domain for segmentation of 2D MRI images. We propose a diffusion model, hereafter called DIffusion based Shape PRediction, DISPR for predicting 3D single cell shapes that are realistic reconstructions of 2D microscopy images.…”