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

• URL: http://arxiv.org/abs/2008.02766v2
• Date: Thu, 15 Jul 2021 02:39:22 GMT
• Title: Assessing the (Un)Trustworthiness of Saliency Maps for Localizing Abnormalities in Medical Imaging
• Authors: Nishanth Arun, Nathan Gaw, Praveer Singh, Ken Chang, Mehak Aggarwal, Bryan Chen, Katharina Hoebel, Sharut Gupta, Jay Patel, Mishka Gidwani, Julius Adebayo, Matthew D. Li, Jayashree Kalpathy-Cramer
• Abstract summary: Saliency maps have become a widely used method to make deep learning models more interpretable. They are increasingly being used in medical imaging to provide clinically plausible explanations. We show that all eight saliency map techniques fail at least one of the criteria and are, in most cases, less trustworthy when compared to the baselines.
• Score: 7.359736138662335
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Saliency maps have become a widely used method to make deep learning models more interpretable by providing post-hoc explanations of classifiers through identification of the most pertinent areas of the input medical image. They are increasingly being used in medical imaging to provide clinically plausible explanations for the decisions the neural network makes. However, the utility and robustness of these visualization maps has not yet been rigorously examined in the context of medical imaging. We posit that trustworthiness in this context requires 1) localization utility, 2) sensitivity to model weight randomization, 3) repeatability, and 4) reproducibility. Using the localization information available in two large public radiology datasets, we quantify the performance of eight commonly used saliency map approaches for the above criteria using area under the precision-recall curves (AUPRC) and structural similarity index (SSIM), comparing their performance to various baseline measures. Using our framework to quantify the trustworthiness of saliency maps, we show that all eight saliency map techniques fail at least one of the criteria and are, in most cases, less trustworthy when compared to the baselines. We suggest that their usage in the high-risk domain of medical imaging warrants additional scrutiny and recommend that detection or segmentation models be used if localization is the desired output of the network. Additionally, to promote reproducibility of our findings, we provide the code we used for all tests performed in this work at this link: https://github.com/QTIM-Lab/Assessing-Saliency-Maps.

Related papers

• A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis [48.84443450990355]
  Deep networks have achieved broad success in analyzing natural images, when applied to medical scans, they often fail in unexcepted situations. We investigate this challenge and focus on model sensitivity to domain shifts, such as data sampled from different hospitals or data confounded by demographic variables such as sex, race, etc, in the context of chest X-rays and skin lesion images. Taking inspiration from medical training, we propose giving deep networks a prior grounded in explicit medical knowledge communicated in natural language.
  arXiv  Detail & Related papers  (2024-05-23T17:55:02Z)
• Evaluation of importance estimators in deep learning classifiers for Computed Tomography [1.6710577107094642]
  Interpretability of deep neural networks often relies on estimating the importance of input features. Two versions of SmoothGrad topped the fidelity and ROC rankings, whereas both Integrated Gradients and SmoothGrad excelled in DSC evaluation. There was a critical discrepancy between model-centric (fidelity) and human-centric (ROC and DSC) evaluation.
  arXiv  Detail & Related papers  (2022-09-30T11:57:25Z)
• Preservation of High Frequency Content for Deep Learning-Based Medical Image Classification [74.84221280249876]
  An efficient analysis of large amounts of chest radiographs can aid physicians and radiologists. We propose a novel Discrete Wavelet Transform (DWT)-based method for the efficient identification and encoding of visual information.
  arXiv  Detail & Related papers  (2022-05-08T15:29:54Z)
• CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency [61.40511574314069]
  Backpropagation image saliency aims at explaining model predictions by estimating model-centric importance of individual pixels in the input. We propose CAMERAS, a technique to compute high-fidelity backpropagation saliency maps without requiring any external priors.
  arXiv  Detail & Related papers  (2021-06-20T08:20:56Z)
• Weakly-supervised High-resolution Segmentation of Mammography Images for Breast Cancer Diagnosis [17.936019428281586]
  In cancer diagnosis, interpretability can be achieved by localizing the region of the input image responsible for the output. We introduce a novel neural network architecture to perform weakly-supervised segmentation of high-resolution images. We apply this model to breast cancer diagnosis with screening mammography, and validate it on a large clinically-realistic dataset.
  arXiv  Detail & Related papers  (2021-06-13T17:25:21Z)
• Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization [59.5104563755095]
  We introduce a simple but effective approach to improve the generalization capability of deep neural networks in the field of medical imaging classification. Motivated by the observation that the domain variability of the medical images is to some extent compact, we propose to learn a representative feature space through variational encoding.
  arXiv  Detail & Related papers  (2020-09-27T12:30:30Z)
• Explainable Disease Classification via weakly-supervised segmentation [4.154485485415009]
  Deep learning approaches to Computer Aided Diagnosis (CAD) typically pose the problem as an image classification (Normal or Abnormal) problem. This paper examines this problem and proposes an approach which mimics the clinical practice of looking for evidence prior to diagnosis. The proposed solution is then adapted to Breast Cancer detection from mammographic images.
  arXiv  Detail & Related papers  (2020-08-24T09:00:30Z)
• Rethinking Localization Map: Towards Accurate Object Perception with Self-Enhancement Maps [78.2581910688094]
  This work introduces a novel self-enhancement method to harvest accurate object localization maps and object boundaries with only category labels as supervision. In particular, the proposed Self-Enhancement Maps achieve the state-of-the-art localization accuracy of 54.88% on ILSVRC.
  arXiv  Detail & Related papers  (2020-06-09T12:35:55Z)
• Assessing the validity of saliency maps for abnormality localization in medical imaging [6.299152745637685]
  Saliency maps have become a widely used method to assess which areas of the input image are most pertinent to the prediction of a trained neural network. In this work, we explored the credibility of the various existing saliency map methods on the RSNA Pneumonia dataset.
  arXiv  Detail & Related papers  (2020-05-29T20:17:26Z)
• Interpreting Medical Image Classifiers by Optimization Based Counterfactual Impact Analysis [2.512212190779389]
  We present a model saliency mapping framework tailored to medical imaging. We replace techniques with a strong neighborhood conditioned inpainting approach, which avoids implausible artefacts.
  arXiv  Detail & Related papers  (2020-04-03T14:59:08Z)
• Do Public Datasets Assure Unbiased Comparisons for Registration Evaluation? [96.53940048041248]
  We use the variogram to screen the manually annotated landmarks in two datasets used to benchmark registration in image-guided neurosurgeries. Using variograms, we identified potentially problematic cases and had them examined by experienced radiologists.
  arXiv  Detail & Related papers  (2020-03-20T20:04:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.