Scientific Discovery by Generating Counterfactuals Using Image Translation

Narayanaswamy, Arunachalam; Venugopalan, Subhashini; Webster, Dale R.; Peng, Lily; Corrado, Gregory S.; Ruamviboonsuk, Paisan; Bavishi, Pinal; Brenner, Michael P.; Varadarajan, Avinash V.

doi:10.1007/978-3-030-59710-8_27

Cited by 22 publications

(21 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This iterative image transformation enhances subtle image features exploited by DNNs. In a previous work, exaggerated images were used to discover a novel symptom of diabetic macular edema (Narayanaswamy et al, 2020 ). Inspired by these previous works, we next used CAG in counterfactual exaggeration to detect subtle features of brain activations exploited by the DNN classifier ( Figure 6A ).…”

Section: Resultsmentioning

confidence: 99%

Counterfactual Explanation of Brain Activity Classifiers Using Image-To-Image Transfer by Generative Adversarial Network

Matsui

Taki

Pham

et al. 2022

Front. Neuroinform.

View full text Add to dashboard Cite

Deep neural networks (DNNs) can accurately decode task-related information from brain activations. However, because of the non-linearity of DNNs, it is generally difficult to explain how and why they assign certain behavioral tasks to given brain activations, either correctly or incorrectly. One of the promising approaches for explaining such a black-box system is counterfactual explanation. In this framework, the behavior of a black-box system is explained by comparing real data and realistic synthetic data that are specifically generated such that the black-box system outputs an unreal outcome. The explanation of the system's decision can be explained by directly comparing the real and synthetic data. Recently, by taking advantage of advances in DNN-based image-to-image translation, several studies successfully applied counterfactual explanation to image domains. In principle, the same approach could be used in functional magnetic resonance imaging (fMRI) data. Because fMRI datasets often contain multiple classes (e.g., multiple behavioral tasks), the image-to-image transformation applicable to counterfactual explanation needs to learn mapping among multiple classes simultaneously. Recently, a new generative neural network (StarGAN) that enables image-to-image transformation among multiple classes has been developed. By adapting StarGAN with some modifications, here, we introduce a novel generative DNN (counterfactual activation generator, CAG) that can provide counterfactual explanations for DNN-based classifiers of brain activations. Importantly, CAG can simultaneously handle image transformation among all the seven classes in a publicly available fMRI dataset. Thus, CAG could provide a counterfactual explanation of DNN-based multiclass classifiers of brain activations. Furthermore, iterative applications of CAG were able to enhance and extract subtle spatial brain activity patterns that affected the classifier's decisions. Together, these results demonstrate that the counterfactual explanation based on image-to-image transformation would be a promising approach to understand and extend the current application of DNNs in fMRI analyses.

show abstract

Section: Resultsmentioning

confidence: 99%

Counterfactual Explanation of Brain Activity Classifiers Using Image-To-Image Transfer by Generative Adversarial Network

Matsui

Taki

Pham

et al. 2022

Front. Neuroinform.

View full text Add to dashboard Cite

show abstract

“…(1) We evaluated our model on the three desiderata of valid explanations, defined in the method section. We compared our counterfactual explanations with closest existing methods such as xGEM [54] and CycleGAN [37], [38]. We considered the following three evaluation metrics: Fréchet Inception Distance (FID) score to assess visual quality, counterfactual validity (CV) score to quantify compatibility with the classifier, and foreign object preservation (FOP) score to evaluate the retention of patient-specific information in the explanations.…”

Section: Methodsmentioning

confidence: 99%

Explaining the Black-box Smoothly- A Counterfactual Approach

Singla¹,

Pollack²,

Wallace³

et al. 2021

Preprint

View full text Add to dashboard Cite

We propose a BlackBox Counterfactual Explainer that is explicitly developed for medical imaging applications. Classical approaches (e.g., saliency maps) assessing feature importance do not explain how and why variations in a particular anatomical region are relevant to the outcome, which is crucial for transparent decision making in healthcare application. Our framework explains the outcome by gradually exaggerating the semantic effect of the given outcome label. Given a query input to a classifier, Generative Adversarial Networks produce a progressive set of perturbations to the query image that gradually changes the posterior probability from its original class to its negation. We design the loss function to ensure that essential and potentially relevant details, such as support devices, are preserved in the counterfactually generated images. We provide an extensive evaluation of different classification tasks on the chest X-Ray images. Our experiments show that a counterfactually generated visual explanation is consistent with the disease's clinical relevant measurements, both quantitatively and qualitatively.

show abstract

“…This method was validated on knee osteoarthritis severity prediction on X-ray images and tumor detection on histology images of metastatic lymph nodes. Narayanaswamy et al [96] used unsupervised image-to-image translation using CycleGAN [168] to generate counterfactual explanations. Translation between the two classes was applied successively to amplify the differences.…”

Section: Counterfactual Explanationmentioning

confidence: 99%

Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods

Salahuddin¹,

Woodruff²,

Chatterjee³

et al. 2021

Preprint

View full text Add to dashboard Cite

Artificial Intelligence (AI) has emerged as a useful aid in numerous clinical applications for diagnosis and treatment decisions. Deep neural networks have shown same or better performance than clinicians in many tasks owing to the rapid increase in the available data and computational power. In order to conform to the principles of trustworthy AI, it is essential that the AI system be transparent, robust, fair and ensure accountability. Current deep neural solutions are referred to as black-boxes due to a lack of understanding of the specifics concerning the decision making process. Therefore, there is a need to ensure interpretability of deep neural networks before they can be incorporated in the routine clinical workflow. In this narrative review, we utilized systematic keyword searches and domain expertise to identify nine different types of interpretability methods that have been used for understanding deep learning models for medical image analysis applications based on the type of generated explanations and technical similarities. Furthermore, we report the progress made towards evaluating the explanations produced by various interpretability methods. Finally we discuss limitations, provide guidelines for using interpretability methods and future directions concerning the interpretability of deep neural networks for medical imaging analysis.

show abstract

Scientific Discovery by Generating Counterfactuals Using Image Translation

Cited by 22 publications

References 19 publications

Counterfactual Explanation of Brain Activity Classifiers Using Image-To-Image Transfer by Generative Adversarial Network

Counterfactual Explanation of Brain Activity Classifiers Using Image-To-Image Transfer by Generative Adversarial Network

Explaining the Black-box Smoothly- A Counterfactual Approach

Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods

Contact Info

Product

Resources

About