# Information Bottleneck Attribution for Visual Explanations of Diagnosis and Prognosis

arXiv: https://arxiv.org/abs/2104.02869 · HTML: https://mlsanity.com/paper/2104.02869/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 22 references that are in the map.
- First posted on arXiv 7 Apr 2021.

## Builds on (most cited first, 9 of 9)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [ResNeSt: Split-Attention Networks](https://mlsanity.com/paper/2004.08955/) (2020)
- [Tell Me Where to Look: Guided Attention Inference Network](https://mlsanity.com/paper/1802.10171/) (2018)
- [Restricting the Flow: Information Bottlenecks for Attribution](https://mlsanity.com/paper/2001.00396/) (2020)
- [MosMedData: Chest CT Scans With COVID-19 Related Findings Dataset](https://mlsanity.com/paper/2005.06465/) (2020)
- [Testing the robustness of attribution methods for convolutional neural networks in MRI-based Alzheimer's disease classification](https://mlsanity.com/paper/1909.08856/) (2019)
- [Deep neural network or dermatologist?](https://mlsanity.com/paper/1908.06612/) (2019)
- [A novel multiple instance learning framework for COVID-19 severity assessment via data augmentation and self-supervised learning](https://mlsanity.com/paper/2102.03837/) (2021)
- [Weakly Supervised Object Detection with 2D and 3D Regression Neural Networks](https://mlsanity.com/paper/1906.01891/) (2019)

## Built on by (most cited first, 4 of 4)

- [Explainable Transformer Prototypes for Medical Diagnoses](https://mlsanity.com/paper/2403.06961/) (2024)
- [Extending Information Bottleneck Attribution to Video Sequences](https://mlsanity.com/paper/2501.16889/) (2025)
- [Cyst-X: A Multi-Center MRI Benchmark and Federated Learning Framework for Malignancy-Risk Stratification of Pancreatic Cystic Neoplasm](https://mlsanity.com/paper/2507.22017/) (2025)
- [Mortality Prediction of Pulmonary Embolism Patients with Deep Learning and XGBoost](https://mlsanity.com/paper/2411.18063/) (2024)

## Abstract (arXiv)

Visual explanation methods have an important role in the prognosis of the patients where the annotated data is limited or unavailable. There have been several attempts to use gradient-based attribution methods to localize pathology from medical scans without using segmentation labels. This research direction has been impeded by the lack of robustness and reliability. These methods are highly sensitive to the network parameters. In this study, we introduce a robust visual explanation method to address this problem for medical applications. We provide an innovative visual explanation algorithm for general purpose and as an example application, we demonstrate its effectiveness for quantifying lesions in the lungs caused by the Covid-19 with high accuracy and robustness without using dense segmentation labels. This approach overcomes the drawbacks of commonly used Grad-CAM and its extended versions. The premise behind our proposed strategy is that the information flow is minimized while ensuring the classifier prediction stays similar. Our findings indicate that the bottleneck condition provides a more stable severity estimation than the similar attribution methods.