# Gifsplanation via Latent Shift: A Simple Autoencoder Approach to Counterfactual Generation for Chest X-rays

arXiv: https://arxiv.org/abs/2102.09475 · HTML: https://mlsanity.com/paper/2102.09475/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 35 references that are in the map.
- First posted on arXiv 18 Feb 2021.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs](https://mlsanity.com/paper/1901.07042/) (2019)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [Confounding variables can degrade generalization performance of radiological deep learning models](https://mlsanity.com/paper/1807.00431/) (2018)
- [PadChest: A large chest x-ray image dataset with multi-label annotated reports](https://mlsanity.com/paper/1901.07441/) (2019)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [Distribution Matching Losses Can Hallucinate Features in Medical Image Translation](https://mlsanity.com/paper/1805.08841/) (2018)
- [Explanation by Progressive Exaggeration](https://mlsanity.com/paper/1911.00483/) (2019)
- [On the limits of cross-domain generalization in automated X-ray prediction](https://mlsanity.com/paper/2002.02497/) (2020)
- [Weakly Supervised Lesion Localization With Probabilistic-CAM Pooling](https://mlsanity.com/paper/2005.14480/) (2020)
- [Using StyleGAN for Visual Interpretability of Deep Learning Models on Medical Images](https://mlsanity.com/paper/2101.07563/) (2021)
- [Assessing the (Un)Trustworthiness of Saliency Maps for Localizing Abnormalities in Medical Imaging](https://mlsanity.com/paper/2008.02766/) (2020)
- [xGEMs: Generating Examplars to Explain Black-Box Models](https://mlsanity.com/paper/1806.08867/) (2018)
- [Assessing the validity of saliency maps for abnormality localization in medical imaging](https://mlsanity.com/paper/2006.00063/) (2020)

## Built on by (most cited first, 2 of 2)

- [Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods](https://mlsanity.com/paper/2111.02398/) (2021)
- [Counterfactual Image Synthesis for Discovery of Personalized Predictive Image Markers](https://mlsanity.com/paper/2208.02311/) (2022)

## Abstract (arXiv)

Motivation: Traditional image attribution methods struggle to satisfactorily explain predictions of neural networks. Prediction explanation is important, especially in medical imaging, for avoiding the unintended consequences of deploying AI systems when false positive predictions can impact patient care. Thus, there is a pressing need to develop improved models for model explainability and introspection. Specific problem: A new approach is to transform input images to increase or decrease features which cause the prediction. However, current approaches are difficult to implement as they are monolithic or rely on GANs. These hurdles prevent wide adoption. Our approach: Given an arbitrary classifier, we propose a simple autoencoder and gradient update (Latent Shift) that can transform the latent representation of a specific input image to exaggerate or curtail the features used for prediction. We use this method to study chest X-ray classifiers and evaluate their performance. We conduct a reader study with two radiologists assessing 240 chest X-ray predictions to identify which ones are false positives (half are) using traditional attribution maps or our proposed method. Results: We found low overlap with ground truth pathology masks for models with reasonably high accuracy. However, the results from our reader study indicate that these models are generally looking at the correct features. We also found that the Latent Shift explanation allows a user to have more confidence in true positive predictions compared to traditional approaches (0.15±0.95 in a 5 point scale with p=0.01) with only a small increase in false positive predictions (0.04±1.06 with p=0.57). Accompanying webpage: https://mlmed.org/gifsplanation Source code: https://github.com/mlmed/gifsplanation