DeScarGAN: Disease-Specific Anomaly Detection with Weak Supervision

Wolleb, Julia; Sandkühler, Robin; Cattin, Philippe C.

doi:10.1007/978-3-030-59719-1_2

Cited by 19 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, some papers also show semi-supervised methods outperforming Constraint Programming using 3 constraints fully supervised methods. These outperforming methods are based on classical feature extraction followed by multipleinstance learning (MIL) based models [49], through adaptations to GANs [27] (using skip-connections and weightsharing subnetworks) and through the adaptation of AEs to the SegAE model [32] (using pairs of T1-w, T2-w and FLAIR data for improved anomaly detection). For this improvement in comparison to fully supervised models, Khosla et al [32] reason that fully supervised methods systematically either under or overestimate lesion volumes (when segmenting lesions), while their proposed method was reported to be free of this bias.…”

Section: Resultsmentioning

confidence: 99%

Anomaly Detection in Medical Imaging -- A Mini Review

Tschuchnig,

Gadermayr

2021

Preprint

View full text Add to dashboard Cite

The increasing digitization of medical imaging enables machine learning based improvements in detecting, visualizing and segmenting lesions, easing the workload for medical experts. However, supervised machine learning requires reliable labelled data, which is is often difficult or impossible to collect or at least time consuming and thereby costly. Therefore methods requiring only partly labeled data (semi-supervised) or no labeling at all (unsupervised methods) have been applied more regularly. Anomaly detection is one possible methodology that is able to leverage semi-supervised and unsupervised methods to handle medical imaging tasks like classification and segmentation. This paper uses a semi-exhaustive literature review of relevant anomaly detection papers in medical imaging to cluster into applications, highlight important results, establish lessons learned and give further advice on how to approach anomaly detection in medical imaging. The qualitative analysis is based on google scholar and 4 different search terms, resulting in 120 different analysed papers. The main results showed that the current research is mostly motivated by reducing the need for labelled data. Also, the successful and substantial amount of research in the brain MRI domain shows the potential for applications in further domains like OCT and chest X-ray.

show abstract

Section: Resultsmentioning

confidence: 99%

Anomaly Detection in Medical Imaging -- A Mini Review

Tschuchnig,

Gadermayr

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…This aims to enhance visual similarity with the original image. DeScarGAN [23] adopts this loss function in its own GAN architecture and has outperformed Fixed-point GAN in their case study for Chest X-Ray pathology identification and localisation.…”

Section: Related Workmentioning

confidence: 99%

Contrastive Counterfactual Visual Explanations With Overdetermination

White¹,

Ngan²,

Phelan³

et al. 2021

Preprint

View full text Add to dashboard Cite

A novel explainable AI method called CLEAR Image is introduced in this paper. CLEAR Image is based on the view that a satisfactory explanation should be contrastive, counterfactual and measurable. CLEAR Image explains an image's classification probability by contrasting the image with a corresponding image generated automatically via adversarial learning. This enables both salient segmentation and perturbations that faithfully determine each segment's importance. CLEAR Image was successfully applied to a medical imaging case study where it outperformed methods such as Grad-CAM and LIME by an average of 27% using a novel pointing game metric. CLEAR Image excels in identifying cases of 'causal overdetermination' where there are multiple patches in an image, any one of which is sufficient by itself to cause the classification probability to be close to one.

show abstract

“…There are not many unsupervised anomaly detection baselines available for direct comparison due to three reasons: (i) no publicly released code [25,72,74,81], (ii) requiring weak/strong manual annotation [56,68,75,84], and (iii) relying on additional information from other modalities [17,46]. Therefore, we considered six major baselines for direct comparison: MemAE [13]-a Memory Matrix based method, Ganomaly [1]-a GAN-based method, f-AnoGAN [57]-the current state of the art for medical imaging, and CutPaste [37], PANDA [52], M-KD [56]the most recent unsupervised anomaly detection methods.…”

Section: Baselines and Metricsmentioning

confidence: 99%

In-painting Radiography Images for Unsupervised Anomaly Detection

Xiang¹,

Liu²,

Yuille³

et al. 2021

Preprint

View full text Add to dashboard Cite

We propose space-aware memory queues for in-painting and detecting anomalies from radiography images (abbreviated as SQUID). Radiography imaging protocols focus on particular body regions, therefore producing images of great similarity and yielding recurrent anatomical structures across patients. To exploit this structured information, our SQUID consists of a new Memory Queue and a novel in-painting block in the feature space. We show that SQUID can taxonomize the ingrained anatomical structures into recurrent patterns; and in the inference, SQUID can identify anomalies (unseen/modified patterns) in the image. SQUID surpasses the state of the art in unsupervised anomaly detection by over 5 points on two chest X-ray benchmark datasets. Additionally, we have created a new dataset (Dig-itAnatomy), which synthesizes the spatial correlation and consistent shape in chest anatomy. We hope DigitAnatomy can prompt the development, evaluation, and interpretability of anomaly detection methods, particularly for radiography imaging. Code and dataset will be made available.

show abstract

DeScarGAN: Disease-Specific Anomaly Detection with Weak Supervision

Cited by 19 publications

References 16 publications

Anomaly Detection in Medical Imaging -- A Mini Review

Anomaly Detection in Medical Imaging -- A Mini Review

Contrastive Counterfactual Visual Explanations With Overdetermination

In-painting Radiography Images for Unsupervised Anomaly Detection

Contact Info

Product

Resources

About