Assessing the Trustworthiness of Saliency Maps for Localizing Abnormalities in Medical Imaging

Abstract

PURPOSE: To evaluate the trustworthiness of saliency maps for abnormality localization in medical imaging. MATERIALS AND METHODS: reproducibility. Their performances versus baseline methods and localization network architectures were compared, using area under the precision-recall curve (AUPRC) and structural similarity index measure (SSIM) as metrics. RESULTS: <.005). Five and two saliency methods (of eight) failed the model randomization test on the segmentation and detection datasets, respectively, suggesting that these methods are not sensitive to changes in model parameters. The repeatability and reproducibility of the majority of the saliency methods were worse than localization networks for both the segmentation and detection datasets. CONCLUSION: Technology Assessment, Technical Aspects, Feature Detection, Convolutional Neural Network (CNN) Supplemental material is available for this article. © RSNA, 2021.

Ähnliche Arbeiten