Related papers: Bilateral Asymmetry Guided Counterfactual Generati…

Counterfactual examples for an input -- perturbations that change specific features but not others -- have been shown to be useful for evaluating bias of machine learning models, e.g., against specific demographic groups. However,…

With the ongoing rise of machine learning, the need for methods for explaining decisions made by artificial intelligence systems is becoming a more and more important topic. Especially for image classification tasks, many state-of-the-art…

Data scarcity and class imbalance are two fundamental challenges in many machine learning applications to healthcare. Breast cancer classification in mammography exemplifies these challenges, with a malignancy rate of around 0.5% in a…

A machine learning model, under the influence of observed or unobserved confounders in the training data, can learn spurious correlations and fail to generalize when deployed. For image classifiers, augmenting a training dataset using…

We propose a new generative adversarial architecture to mitigate imbalance data problem for the task of medical image semantic segmentation where the majority of pixels belong to a healthy region and few belong to lesion or non-health…

Mammogram inspection in search of breast tumors is a tough assignment that radiologists must carry out frequently. Therefore, image analysis methods are needed for the detection and delineation of breast masses, which portray crucial…

Foundation models trained on web-scraped datasets propagate societal biases to downstream tasks. While counterfactual generation enables bias analysis, existing methods introduce artifacts by modifying contextual elements like clothing and…

Recent works show that Generative Adversarial Networks (GANs) can be successfully applied to chest X-ray data augmentation for lung disease recognition. However, the implausible and distorted pathology features generated from the less than…

We present a novel framework for explainable labeling and interpretation of medical images. Medical images require specialized professionals for interpretation, and are explained (typically) via elaborate textual reports. Different from…

Neural Image Classifiers are effective but inherently hard to interpret and susceptible to adversarial attacks. Solutions to both problems exist, among others, in the form of counterfactual examples generation to enhance explainability or…

We propose a novel approach to mitigate biases in computer vision models by utilizing counterfactual generation and fine-tuning. While counterfactuals have been used to analyze and address biases in DNN models, the counterfactuals…

Supervised deep learning relies on the assumption that enough training data is available, which presents a problem for its application to several fields, like medical imaging. On the example of a binary image classification task (breast…

Despite their high accuracies, modern complex image classifiers cannot be trusted for sensitive tasks due to their unknown decision-making process and potential biases. Counterfactual explanations are very effective in providing…

Reducing the requirement for densely annotated masks in medical image segmentation is important due to cost constraints. In this paper, we consider the problem of inferring pixel-level predictions of brain lesions by only using image-level…

Counterfactuals can explain classification decisions of neural networks in a human interpretable way. We propose a simple but effective method to generate such counterfactuals. More specifically, we perform a suitable diffeomorphic…

Ascription of an image gives insights into the objects that influence the classification of the whole image or its pixels towards a specific category. These insights help radiologists to visualize deformities in medical imaging. Most of the…

Explaining decisions of black-box classifiers is paramount in sensitive domains such as medical imaging since clinicians confidence is necessary for adoption. Various explanation approaches have been proposed, among which perturbation based…

There exists an apparent negative correlation between performance and interpretability of deep learning models. In an effort to reduce this negative correlation, we propose a Born Identity Network (BIN), which is a post-hoc approach for…

Neural networks are prone to learning shortcuts -- they often model simple correlations, ignoring more complex ones that potentially generalize better. Prior works on image classification show that instead of learning a connection to object…

Deep learning models in medical imaging often fail when deployed in new clinical environments due to distribution shifts in demographics, scanner hardware, or acquisition protocols. A central challenge is underspecification, where models…