Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery

Schlegl, Thomas; Seeböck, Philipp; Waldstein, Sebastian M.; Schmidt‐Erfurth, Ursula; Langs, Georg

doi:10.1007/978-3-319-59050-9_12

Cited by 1,958 publications

(1,561 citation statements)

References 15 publications

Supporting

Mentioning

1,551

Contrasting

Unclassified

Order By: Relevance

“…Second, being able to generate instances, or even instances that are as close as possible to an observation, provides means to study the difference of examples to a class. This is relevant in medicine, where the discovery and study of anomalies that are potentially linked to disease is relevant Schlegl et al ().…”

Section: General Approaches Of Explainable Ai Modelsmentioning

confidence: 99%

Causability and explainability of artificial intelligence in medicine

Holzinger

Langs

Denk

et al. 2019

WIREs Data Min & Knowl

Self Cite

953

571

View full text Add to dashboard Cite

Explainable artificial intelligence (AI) is attracting much interest in medicine. Technically, the problem of explainability is as old as AI itself and classic AI represented comprehensible retraceable approaches. However, their weakness was in dealing with uncertainties of the real world. Through the introduction of probabilistic learning, applications became increasingly successful, but increasingly opaque. Explainable AI deals with the implementation of transparency and traceability of statistical black‐box machine learning methods, particularly deep learning (DL). We argue that there is a need to go beyond explainable AI. To reach a level of explainable medicine we need causability. In the same way that usability encompasses measurements for the quality of use, causability encompasses measurements for the quality of explanations. In this article, we provide some necessary definitions to discriminate between explainability and causability as well as a use‐case of DL interpretation and of human explanation in histopathology. The main contribution of this article is the notion of causability, which is differentiated from explainability in that causability is a property of a person, while explainability is a property of a system This article is categorized under: Fundamental Concepts of Data and Knowledge > Human Centricity and User Interaction

show abstract

Section: General Approaches Of Explainable Ai Modelsmentioning

confidence: 99%

Causability and explainability of artificial intelligence in medicine

Holzinger

Langs

Denk

et al. 2019

WIREs Data Min & Knowl

Self Cite

953

571

View full text Add to dashboard Cite

show abstract

“…Furthermore, with the increasing use of digital pathology in clinical practice 29 , generative models can be used for various digital image processing applications 30 , 31 , 32 and applied to forms of semi-supervised learning such as anomaly detection. 33 Our use of two data sets demonstrates the breadth of input images that can be incorporated into our pipeline. The survey of images from GANs trained on TCGA slides was designed to be a straightforward classification task of five distinct cancer types, while the differentiation of the five histotypes of ovarian carcinoma is a challenging morphologic classification task for general pathologists, yet has evolved to become highly reproducible amongst experts.…”

Section: Discussionmentioning

confidence: 99%

Synthesis of diagnostic quality cancer pathology images

Peng

Farnell

et al. 2020

Preprint

View full text Add to dashboard Cite

Keyboards: cancer, pathology, deep learning, artificial intelligence, quality assurance, education Link to the demo website: http://gan.aimlab.ca/ 1 ABSTRACT Deep learning-based computer vision methods have recently made remarkable breakthroughs in the analysis and classification of cancer pathology images. However, there has been relatively little investigation of the utility of deep neural networks to synthesize medical images. In this study, we evaluated the efficacy of generative adversarial networks (GANs) to synthesize high resolution pathology images of ten histological types of cancer, including five cancer types from The Cancer Genome Atlas (TCGA) and the five major histological subtypes of ovarian carcinoma. The quality of these images was assessed using a comprehensive survey of board-certified pathologists (n = 9) and pathology trainees (n = 6). Our results show that the real and synthetic images are classified by histotype with comparable accuracies, and the synthetic images are visually indistinguishable from real images. Furthermore, we trained deep convolutional neural networks (CNNs) to diagnose the different cancer types and determined that the synthetic images perform as well as additional real images when used to supplement a small training set. These findings have important applications in proficiency testing of medical practitioners and quality assurance in clinical laboratories. Furthermore, training of computer-aided diagnostic systems can benefit from synthetic images where labeled datasets are limited (e.g., rare cancers). We have created a publicly available website where clinicians and researchers can attempt questions from the image survey at http://gan.aimlab.ca/ .

show abstract

“…Several deep‐learning–based models have been recently suggested for unsupervised abnormality detection. Schlegl et al . used generative adversarial network (GAN) to detect abnormalities.…”

Section: Discussionmentioning

confidence: 99%

“…1,2,14 Several deep-learning-based models have been recently suggested for unsupervised abnormality detection. Schlegl et al 24 used generative adversarial network (GAN) to detect abnormalities. In the training phase, they trained a GAN to map random samples from a latent space to the normal data.…”

Section: Discussionmentioning

confidence: 99%

Unsupervised abnormality detection through mixed structure regularization (MSR) in deep sparse autoencoders

2019

View full text Add to dashboard Cite

Purpose The purpose of this study is to introduce and evaluate the mixed structure regularization (MSR) approach for a deep sparse autoencoder aimed at unsupervised abnormality detection in medical images. Unsupervised abnormality detection based on identifying outliers using deep sparse autoencoders is a very appealing approach for computer‐aided detection systems as it requires only healthy data for training rather than expert annotated abnormality. However, regularization is required to avoid overfitting of the network to the training data. Methods We used coronary computed tomography angiography (CCTA) datasets of 90 subjects with expert annotated centerlines. We segmented coronary lumen and wall using an automatic algorithm with manual corrections where required. We defined normal coronary cross section as cross sections with a ratio between lumen and wall areas larger than 0.8. We divided the datasets into training, validation, and testing groups in a tenfold cross‐validation scheme. We trained a deep sparse overcomplete autoencoder model for normality modeling with random structure and noise augmentation. We assessed the performance of our deep sparse autoencoder with MSR without denoising (SAE‐MSR) and with denoising (SDAE‐MSR) in comparison to deep sparse autoencoder (SAE), and deep sparse denoising autoencoder (SDAE) models in the task of detecting coronary artery disease from CCTA data on the test group. Results The SDAE‐MSR achieved the best aggregated area under the curve (AUC) with a 20% improvement and the best aggregated Average Precision (AP) with a 30% improvement upon the SAE and SDAE (AUC: 0.78 to 0.94, AP: 0.66 to 0.86) in distinguishing between coronary cross sections with mild stenosis (stenosis grade < 0.3) and coronary cross sections with severe stenosis (stenosis grade > 0.7). The improvements were statistically significant (Mann–Whitney U‐test, P < 0.001). Similarly, The SDAE‐MSR achieved the best aggregated AUC (AP) with an 18% (18%) improvement upon the SAE and SDAE (AUC: 0.71 to 0.84, AP: 0.68 to 0.80). The improvements were statistically significant (Mann–Whitney U‐test, P < 0.05). Conclusion Deep sparse autoencoders with MSR in addition to explicit sparsity regularization term and stochastic corruption of the input data with Gaussian noise have the potential to improve unsupervised abnormality detection using deep‐learning compared to common deep autoencoders.

show abstract

Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery

Cited by 1,958 publications

References 15 publications

Causability and explainability of artificial intelligence in medicine

Causability and explainability of artificial intelligence in medicine

Synthesis of diagnostic quality cancer pathology images

Unsupervised abnormality detection through mixed structure regularization (MSR) in deep sparse autoencoders

Contact Info

Product

Resources

About