# Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoders

arXiv: https://arxiv.org/abs/2203.10417 · HTML: https://mlsanity.com/paper/2203.10417/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 79 references that are in the map.
- First posted on arXiv 20 Mar 2022.

## Builds on (most cited first, 30 of 33)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [Understanding disentangling in β-VAE](https://mlsanity.com/paper/1804.03599/) (2018)
- [Variational Inference of Disentangled Latent Concepts from Unlabeled Observations](https://mlsanity.com/paper/1711.00848/) (2017)
- [Isolating Sources of Disentanglement in Variational Autoencoders](https://mlsanity.com/paper/1802.04942/) (2018)
- [Fader Networks: Manipulating Images by Sliding Attributes](https://mlsanity.com/paper/1706.00409/) (2017)
- [XRAI: Better Attributions Through Regions](https://mlsanity.com/paper/1906.02825/) (2019)
- [Towards Visually Explaining Variational Autoencoders](https://mlsanity.com/paper/1911.07389/) (2019)
- [Explainable deep learning models in medical image analysis](https://mlsanity.com/paper/2005.13799/) (2020)
- [Learning Deep Disentangled Embeddings with the F-Statistic Loss](https://mlsanity.com/paper/1802.05312/) (2018)
- [Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations](https://mlsanity.com/paper/1705.08841/) (2017)
- [Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods](https://mlsanity.com/paper/2111.02398/) (2021)
- [Guided Variational Autoencoder for Disentanglement Learning](https://mlsanity.com/paper/2004.01255/) (2020)
- [Assessing the (Un)Trustworthiness of Saliency Maps for Localizing Abnormalities in Medical Imaging](https://mlsanity.com/paper/2008.02766/) (2020)
- [Deep Learning in Alzheimer's disease: Diagnostic Classification and Prognostic Prediction using Neuroimaging Data](https://mlsanity.com/paper/1905.00931/) (2019)
- [Echocardiography Segmentation with Enforced Temporal Consistency](https://mlsanity.com/paper/2112.02102/) (2021)
- [Global and Local Interpretability for Cardiac MRI Classification](https://mlsanity.com/paper/1906.06188/) (2019)
- [Deep Learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge](https://mlsanity.com/paper/2108.04016/) (2021)
- [GLSR-VAE: Geodesic Latent Space Regularization for Variational AutoEncoder Architectures](https://mlsanity.com/paper/1707.04588/) (2017)
- [Explainable Anatomical Shape Analysis through Deep Hierarchical Generative Models](https://mlsanity.com/paper/1907.00058/) (2019)
- [Interpretable Deep Models for Cardiac Resynchronisation Therapy Response Prediction](https://mlsanity.com/paper/2006.13811/) (2020)
- [Fully automatic detection and segmentation of abdominal aortic thrombus in post-operative CTA images using deep convolutional neural networks](https://mlsanity.com/paper/1804.00304/) (2018)

## Built on by (most cited first, 17 of 17)

- [CLIP in Medical Imaging: A Survey](https://mlsanity.com/paper/2312.07353/) (2023)
- [SADIR: Shape-Aware Diffusion Models for 3D Image Reconstruction](https://mlsanity.com/paper/2309.03335/) (2023)
- [Inherently Interpretable Multi-Label Classification Using Class-Specific Counterfactuals](https://mlsanity.com/paper/2303.00500/) (2023)
- [FairSkin: Fair Diffusion for Skin Disease Image Generation](https://mlsanity.com/paper/2410.22551/) (2024)
- [Disentangling Hippocampal Shape Variations: A Study of Neurological Disorders Using Mesh Variational Autoencoder with Contrastive Learning](https://mlsanity.com/paper/2404.00785/) (2024)
- [Interpretable Representation Learning of Cardiac MRI via Attribute Regularization](https://mlsanity.com/paper/2406.08282/) (2024)
- [OWT: A Foundational Organ-Wise Tokenization Framework for Medical Imaging](https://mlsanity.com/paper/2505.04899/) (2025)
- [Attribute Regularized Soft Introspective VAE: Towards Cardiac Attribute Regularization Through MRI Domains](https://mlsanity.com/paper/2307.12618/) (2023)
- [Deep Learning Framework for Spleen Volume Estimation from 2D Cross-sectional Views](https://mlsanity.com/paper/2308.08038/) (2023)
- [Attribute Regularized Soft Introspective Variational Autoencoder for Interpretable Cardiac Disease Classification](https://mlsanity.com/paper/2312.08915/) (2023)
- [Advancing Generative Model Evaluation: A Novel Algorithm for Realistic Image Synthesis and Comparison in OCR System](https://mlsanity.com/paper/2402.17204/) (2024)
- [On the Road to Clarity: Exploring Explainable AI for World Models in a Driver Assistance System](https://mlsanity.com/paper/2404.17350/) (2024)
- [DeepSPV: A Deep Learning Pipeline for 3D Spleen Volume Estimation from 2D Ultrasound Images](https://mlsanity.com/paper/2411.11190/) (2024)
- [Flip Distribution Alignment VAE for Multi-Phase MRI Synthesis](https://mlsanity.com/paper/2510.02970/) (2025)
- [On the Joint Minimization of Regularization Loss Functions in Deep Variational Bayesian Methods for Attribute-Controlled Symbolic Music Generation](https://mlsanity.com/paper/2511.07118/) (2025)
- [PathoSyn: Imaging-Pathology MRI Synthesis via Disentangled Deviation Diffusion](https://mlsanity.com/paper/2512.23130/) (2025)
- [HUydra: Full-Range Lung CT Synthesis via Multiple HU Interval Generative Modelling](https://mlsanity.com/paper/2603.23041/) (2026)

## Abstract (arXiv)

Deep learning (DL) methods where interpretability is intrinsically considered as part of the model are required to better understand the relationship of clinical and imaging-based attributes with DL outcomes, thus facilitating their use in the reasoning behind medical decisions. Latent space representations built with variational autoencoders (VAE) do not ensure individual control of data attributes. Attribute-based methods enforcing attribute disentanglement have been proposed in the literature for classical computer vision tasks in benchmark data. In this paper, we propose a VAE approach, the Attri-VAE, that includes an attribute regularization term to associate clinical and medical imaging attributes with different regularized dimensions in the generated latent space, enabling a better-disentangled interpretation of the attributes. Furthermore, the generated attention maps explained the attribute encoding in the regularized latent space dimensions. Using the Attri-VAE approach we analyzed healthy and myocardial infarction patients with clinical, cardiac morphology, and radiomics attributes. The proposed model provided an excellent trade-off between reconstruction fidelity, disentanglement, and interpretability, outperforming state-of-the-art VAE approaches according to several quantitative metrics. The resulting latent space allowed the generation of realistic synthetic data in the trajectory between two distinct input samples or along a specific attribute dimension to better interpret changes between different cardiac conditions.