MADGAN: unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction

Abstract

Background Unsupervised learning can discover various unseen abnormalities, relying on large-scale unannotated medical images of healthy subjects. Towards this, unsupervised methods reconstruct a 2D/3D single medical image to detect outliers either in the learned feature space or from high reconstruction loss. However, without considering continuity between multiple adjacent slices, they cannot directly discriminate diseases composed of the accumulation of subtle anatomical anomalies, such as Alzheimer’s disease (AD). Moreover, no study has shown how unsupervised anomaly detection is associated with either disease stages, various (i.e., more than two types of) diseases, or multi-sequence magnetic resonance imaging (MRI) scans. Results We propose unsupervised medical anomaly detection generative adversarial network (MADGAN), a novel two-step method using GAN-based multiple adjacent brain MRI slice reconstruction to detect brain anomalies at different stages on multi-sequence structural MRI: (Reconstruction) Wasserstein loss with Gradient Penalty + 100 $$\ell _1$$ ℓ 1 loss—trained on 3 healthy brain axial MRI slices to reconstruct the next 3 ones—reconstructs unseen healthy/abnormal scans; (Diagnosis) Average $$\ell _2$$ ℓ 2 loss per scan discriminates them, comparing the ground truth/reconstructed slices. For training, we use two different datasets composed of 1133 healthy T1-weighted (T1) and 135 healthy contrast-enhanced T1 (T1c) brain MRI scans for detecting AD and brain metastases/various diseases, respectively. Our self-attention MADGAN can detect AD on T1 scans at a very early stage, mild cognitive impairment (MCI), with area under the curve (AUC) 0.727, and AD at a late stage with AUC 0.894, while detecting brain metastases on T1c scans with AUC 0.921. Conclusions Similar to physicians’ way of performing a diagnosis, using massive healthy training data, our first multiple MRI slice reconstruction approach, MADGAN, can reliably predict the next 3 slices from the previous 3 ones only for unseen healthy images. As the first unsupervised various disease diagnosis, MADGAN can reliably detect the accumulation of subtle anatomical anomalies and hyper-intense enhancing lesions, such as (especially late-stage) AD and brain metastases on multi-sequence MRI scans.

Usefulness of a Metal Artifact Reduction Algorithm in Digital Tomosynthesis Using a Combination of Hybrid Generative Adversarial Networks

“…Recently, some works studied GAN applications with and without MAR [ 40 , 41 ]. These studies applied GAN technology to the reconstructed image to improve the accuracy of the tomographic image in the in-plane and longitudinal directions.…”

Brain Tumor Detection and Classification on MR Images by a Deep Wavelet Auto-Encoder Model

“…Han [40] proposed an unsupervised medical anomaly network model to detect unsupervised medical anomalies (MADGAN). A new two-step method that uses GANbased multiple contiguous MRI slice reconstruction to detect brain abnormalities at different stages on multi-structured MRI: (reconstruction) Wasserstein loss with graded penalty + 100, 1 loss − 1.…”

Using Convolutional Encoder Networks to Determine the Optimal Magnetic Resonance Image for the Automatic Segmentation of Multiple Sclerosis

“…It is a conditional GAN which uses MRIs such as FLAIR and T1 contrast images in place of noise vectors. Another example is the Medical Anomaly Detection GAN (MADGAN) [21], which also takes advantage of the aforementioned attention mechanism. Although this model is used for classification, a recent study has shown its very pertinent applications in both MRI reconstruction and lesion detection [21].…”