Causality-Driven One-Shot Learning for Prostate Cancer Grading from MRI
This addresses the problem of limited labeled data for medical image classification, particularly for prostate cancer grading, though it appears incremental as it builds on existing meta-learning and causality concepts.
The paper tackles prostate cancer grading from MRI in low-data scenarios by developing a causality-driven one-shot learning method that extracts cause-effect relationships between image features. The approach shows enhanced ability to discern relevant information and yields more reliable and interpretable predictions on a publicly available prostate MRI dataset.
In this paper, we present a novel method to automatically classify medical images that learns and leverages weak causal signals in the image. Our framework consists of a convolutional neural network backbone and a causality-extractor module that extracts cause-effect relationships between feature maps that can inform the model on the appearance of a feature in one place of the image, given the presence of another feature within some other place of the image. To evaluate the effectiveness of our approach in low-data scenarios, we train our causality-driven architecture in a One-shot learning scheme, where we propose a new meta-learning procedure entailing meta-training and meta-testing tasks that are designed using related classes but at different levels of granularity. We conduct binary and multi-class classification experiments on a publicly available dataset of prostate MRI images. To validate the effectiveness of the proposed causality-driven module, we perform an ablation study and conduct qualitative assessments using class activation maps to highlight regions strongly influencing the network's decision-making process. Our findings show that causal relationships among features play a crucial role in enhancing the model's ability to discern relevant information and yielding more reliable and interpretable predictions. This would make it a promising approach for medical image classification tasks.