SteGANomaly: Inhibiting CycleGAN Steganography for Unsupervised Anomaly Detection in Brain MRI

Baur, Christoph; Graf, R.; Wiestler, Benedikt; Albarqouni, Shadi; Navab, Nassir

doi:10.1007/978-3-030-59713-9_69

Cited by 32 publications

(32 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notable methods along this line include SVD-RND (22), CutPaste (23), CSI (24), SSD (25), PANDA (26), and MSC (27). UAD has also been applied to medical imaging (28) across many domains, including X-ray (29,30), CT (31,32), MRI (33)(34)(35), and endoscopy (36) datasets.…”

Section: Related Studymentioning

confidence: 99%

Pediatric Otoscopy Video Screening With Shift Contrastive Anomaly Detection

Wang

Tamhane

Santos

et al. 2022

Front. Digit. Health

View full text Add to dashboard Cite

Ear related concerns and symptoms represent the leading indication for seeking pediatric healthcare attention. Despite the high incidence of such encounters, the diagnostic process of commonly encountered diseases of the middle and external presents a significant challenge. Much of this challenge stems from the lack of cost effective diagnostic testing, which necessitates the presence or absence of ear pathology to be determined clinically. Research has, however, demonstrated considerable variation among clinicians in their ability to accurately diagnose and consequently manage ear pathology. With recent advances in computer vision and machine learning, there is an increasing interest in helping clinicians to accurately diagnose middle and external ear pathology with computer-aided systems. It has been shown that AI has the capacity to analyze a single clinical image captured during the examination of the ear canal and eardrum from which it can determine the likelihood of a pathognomonic pattern for a specific diagnosis being present. The capture of such an image can, however, be challenging especially to inexperienced clinicians. To help mitigate this technical challenge, we have developed and tested a method using video sequences. The videos were collected using a commercially available otoscope smartphone attachment in an urban, tertiary-care pediatric emergency department. We present a two stage method that first, identifies valid frames by detecting and extracting ear drum patches from the video sequence, and second, performs the proposed shift contrastive anomaly detection (SCAD) to flag the otoscopy video sequences as normal or abnormal. Our method achieves an AUROC of 88.0% on the patient level and also outperforms the average of a group of 25 clinicians in a comparative study, which is the largest of such published to date. We conclude that the presented method achieves a promising first step toward the automated analysis of otoscopy video.

show abstract

Section: Related Studymentioning

confidence: 99%

Pediatric Otoscopy Video Screening With Shift Contrastive Anomaly Detection

Wang

Tamhane

Santos

et al. 2022

Front. Digit. Health

View full text Add to dashboard Cite

show abstract

“…Notable methods along this line include SVD-RND [22], CutPaste [23], CSI [24], SSD [25] and MSC [26]. UAD has also been applied to medical imaging [27] across many domains, including Xray [28], [29], CT [30], [31], MRI [32], [33], [34] and endoscopy [35] datasets.…”

Section: Related Workmentioning

confidence: 99%

Otoscopy video screening with deep anomaly detection

Wang

Tamhane

Rzasa

et al. 2021

Medical Imaging 2021: Computer-Aided Diagnosis

View full text Add to dashboard Cite

“…Unsupervised Anomaly Segmentation. Unsupervised anomaly segmentation aims at identifying abnormal pixels on test images, containing, for example, lesions on medical images [7,10], defects in industrial images [9,23,36] or abnormal events in videos [1,30]. A main body of the literature has explored unsupervised deep (generative) representation learning to learn the distribution from normal data.…”

Section: Related Workmentioning

confidence: 99%

“…A common strategy for unsupervised anomaly segmentation is to model the distribution of normal images, for which generative models, such as generative adversarial networks (GANs) [2,7,30,32,33,35] and variational auto-encoders (VAEs) [10,11,27,31,39] have been widely employed. To achieve this, input images are compared to their reconstructed normal counterparts, which are recovered from the learned distribution, and anomalies are identified from the reconstruction error.…”

mentioning

confidence: 99%

Looking at the whole picture: constrained unsupervised anomaly segmentation

Silva-Rodríguez¹,

Naranjo²,

Dolz³

2021

Preprint

View full text Add to dashboard Cite

Current unsupervised anomaly localization approaches rely on generative models to learn the distribution of normal images, which is later used to identify potential anomalous regions derived from errors on the reconstructed images. However, a main limitation of nearly all prior literature is the need of employing anomalous images to set a class-specific threshold to locate the anomalies. This limits their usability in realistic scenarios, where only normal data is typically accessible. Despite this major drawback, only a handful of works have addressed this limitation, by integrating supervision on attention maps during training. In this work, we propose a novel formulation that does not require accessing images with abnormalities to define the threshold. Furthermore, and in contrast to very recent work, the proposed constraint is formulated in a more principled manner, leveraging well-known knowledge in constrained optimization. In particular, the equality constraint on the attention maps in prior work is replaced by an inequality constraint, which allows more flexibility. In addition, to address the limitations of penalty-based functions we employ an extension of the popular log-barrier methods to handle the constraint. Comprehensive experiments on the popular BRATS'19 dataset demonstrate that the proposed approach substantially outperforms relevant literature, establishing new state-of-the-art results for unsupervised lesion segmentation. IntroductionUnder the supervised learning paradigm, deep learning models have achieved astonishing performance in a wide range of applications. Nevertheless, a main limitation of these models is the large amount of labeled data required for training. Obtaining such curated labeled datasets is a cumbersome process prone to subjectivity, which makes access to sufficient training data difficult in practice. This problem is further magnified in the context of medical image segmentation, where labeling involves assigning a category to each image pixel

show abstract

SteGANomaly: Inhibiting CycleGAN Steganography for Unsupervised Anomaly Detection in Brain MRI

Cited by 32 publications

References 14 publications

Pediatric Otoscopy Video Screening With Shift Contrastive Anomaly Detection

Pediatric Otoscopy Video Screening With Shift Contrastive Anomaly Detection

Otoscopy video screening with deep anomaly detection

Looking at the whole picture: constrained unsupervised anomaly segmentation

Contact Info

Product

Resources

About