Related papers: Towards generating more interpretable counterfactu…

Concept-based explanations permit to understand the predictions of a deep neural network (DNN) through the lens of concepts specified by users. Existing methods assume that the examples illustrating a concept are mapped in a fixed direction…

Lack of explainability in artificial intelligence, specifically deep neural networks, remains a bottleneck for implementing models in practice. Popular techniques such as Gradient-weighted Class Activation Mapping (Grad-CAM) provide a…

Interpreting the inner workings of deep learning models is crucial for establishing trust and ensuring model safety. Concept-based explanations have emerged as a superior approach that is more interpretable than feature attribution…

Causal generative modelling is gaining interest in medical imaging due to its ability to answer interventional and counterfactual queries. Most work focuses on generating counterfactual images that look plausible, using auxiliary…

Concept Activation Vectors (CAVs) provide a powerful approach for interpreting deep neural networks by quantifying their sensitivity to human-defined concepts. However, when computed independently at different layers, CAVs often exhibit…

Counterfactual explanations enhance the interpretability of deep learning models in medical imaging, yet adapting them to 3D CT scans poses challenges due to volumetric complexity and resource demands. We extend the Latent Shift…

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…

Interpretability and small labelled datasets are key issues in the practical application of deep learning, particularly in areas such as medicine. In this paper, we present a semi-supervised technique that addresses both these issues by…

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…

Concept Bottleneck Models (CBMs) in medical imaging aim to improve model interpretability by predicting intermediate clinical concepts before final diagnoses. However, most existing CBMs treat concepts as discriminative predictors of…

Interpretability methods for image classification assess model trustworthiness by attempting to expose whether the model is systematically biased or attending to the same cues as a human would. Saliency methods for feature attribution…

Generative models such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) play an increasingly important role in medical image analysis. The latent spaces of these models often show semantically meaningful…

Segmenting anatomical structures in medical images plays an important role in the quantitative assessment of various diseases. However, accurate segmentation becomes significantly more challenging in the presence of disease. Disease…

Convolutional neural network (CNN) models for computer vision are powerful but lack explainability in their most basic form. This deficiency remains a key challenge when applying CNNs in important domains. Recent work on explanations…

Counterfactual medical image generation enables clinicians to explore clinical hypotheses, such as predicting disease progression, facilitating their decision-making. While existing methods can generate visually plausible images from…

To interpret deep learning models, one mainstream is to explore the learned concepts by networks. Testing with Concept Activation Vector (TCAV) presents a powerful tool to quantify the contribution of query concepts (represented by…

Counterfactual explanations (CEs) aim to enhance the interpretability of machine learning models by illustrating how alterations in input features would affect the resulting predictions. Common CE approaches require an additional model and…

Deep learning has advanced medical image classification, but interpretability challenges hinder its clinical adoption. This study enhances interpretability in Chest X-ray (CXR) classification by using concept bottleneck models (CBMs) and a…

Artificial intelligence is increasingly leveraged across various domains to automate decision-making processes that significantly impact human lives. In medical image analysis, deep learning models have demonstrated remarkable performance.…

As large language models (LLMs) are widely deployed across various domains, the ability to control their generated outputs has become more critical. This control involves aligning LLMs outputs with human values and ethical principles or…