Benchmarking the Influence of Pre-training on Explanation Performance in MR Image Classification

Abstract

Convolutional Neural Networks (CNNs) are frequently and successfully used in medical prediction tasks. They are often used in combination with transfer learning, leading to improved performance when training data for the task are scarce. The resulting models are highly complex and typically do not provide any insight into their predictive mechanisms, motivating the field of "explainable" artificial intelligence (XAI). However, previous studies have rarely quantitatively evaluated the "explanation performance" of XAI methods against ground-truth data, and transfer learning and its influence on objective measures of explanation performance has not been investigated. Here, we propose a benchmark dataset that allows for quantifying explanation performance in a realistic magnetic resonance imaging (MRI) classification task. We employ this benchmark to understand the influence of transfer learning on the quality of explanations. Experimental results show that popular XAI methods applied to the same underlying model differ vastly in performance, even when considering only correctly classified examples. We further observe that explanation performance strongly depends on the task used for pre-training and the number of CNN layers pre-trained. These results hold after correcting for a substantial correlation between explanation and classification performance.

Under review

References in corpus (11)

• Axiomatic Attribution for Deep Networks
• Striving for Simplicity: The All Convolutional Net
• Learning Important Features Through Propagating Activation Differences
• Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey
• Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAI
• Transfer Learning in Magnetic Resonance Brain Imaging: a Systematic Review
• Benchmarking Deep Learning Interpretability in Time Series Predictions
• Benchmarking Attribution Methods with Relative Feature Importance
• OpenXAI: Towards a Transparent Evaluation of Model Explanations
• Theoretical Behavior of XAI Methods in the Presence of Suppressor Variables
• XAI-TRIS: Non-linear image benchmarks to quantify false positive post-hoc attribution of feature importance

Cited by in corpus (1)

• GECOBench: A Gender-Controlled Text Dataset and Benchmark for Quantifying Biases in Explanations