Influence of uncertainty estimation techniques on false-positive reduction in liver lesion detection
This work addresses false positives in medical imaging for liver lesion detection, which is critical for accurate diagnosis, but it is incremental as it builds on existing uncertainty estimation methods.
The study tackled false-positive predictions in liver lesion detection from medical images by evaluating uncertainty estimation techniques and shape-based features in a post-processing step, resulting in improved F1-scores across two datasets (abdominal MR and CT images).
Deep learning techniques show success in detecting objects in medical images, but still suffer from false-positive predictions that may hinder accurate diagnosis. The estimated uncertainty of the neural network output has been used to flag incorrect predictions. We study the role played by features computed from neural network uncertainty estimates and shape-based features computed from binary predictions in reducing false positives in liver lesion detection by developing a classification-based post-processing step for different uncertainty estimation methods. We demonstrate an improvement in the lesion detection performance of the neural network (with respect to F1-score) for all uncertainty estimation methods on two datasets, comprising abdominal MR and CT images, respectively. We show that features computed from neural network uncertainty estimates tend not to contribute much toward reducing false positives. Our results show that factors like class imbalance (true over false positive ratio) and shape-based features extracted from uncertainty maps play an important role in distinguishing false positive from true positive predictions. Our code can be found at https://github.com/ishaanb92/FPCPipeline.