# ParseCaps: An Interpretable Parsing Capsule Network for Medical Image Diagnosis

arXiv: https://arxiv.org/abs/2411.01564 · HTML: https://mlsanity.com/paper/2411.01564/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 75 references that are in the map.
- First posted on arXiv 3 Nov 2024.

## Builds on (most cited first, 24 of 24)

- [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)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [Axial Attention in Multidimensional Transformers](https://mlsanity.com/paper/1912.12180/) (2019)
- [Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation](https://mlsanity.com/paper/2003.07853/) (2020)
- [Adaptively Sparse Transformers](https://mlsanity.com/paper/1909.00015/) (2019)
- [XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations](https://mlsanity.com/paper/2103.10663/) (2021)
- [DeepCaps: Going Deeper with Capsule Networks](https://mlsanity.com/paper/1904.09546/) (2019)
- [Coherent Concept-based Explanations in Medical Image and Its Application to Skin Lesion Diagnosis](https://mlsanity.com/paper/2304.04579/) (2023)
- [Brain Tumor Type Classification via Capsule Networks](https://mlsanity.com/paper/1802.10200/) (2018)
- [The Doctor Just Won't Accept That!](https://mlsanity.com/paper/1711.08037/) (2017)
- [Attention routing between capsules](https://mlsanity.com/paper/1907.01750/) (2019)
- [TreeCaps: Tree-Based Capsule Networks for Source Code Processing](https://mlsanity.com/paper/2009.09777/) (2020)
- [Comprehensible Convolutional Neural Networks via Guided Concept Learning](https://mlsanity.com/paper/2101.03919/) (2021)
- [HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network](https://mlsanity.com/paper/2203.10699/) (2022)
- [OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning](https://mlsanity.com/paper/2403.13351/) (2024)
- [Vanishing Activations: A Symptom of Deep Capsule Networks](https://mlsanity.com/paper/2305.11178/) (2023)

## Built on by (most cited first, 1 of 1)

- [MSPCaps: A Multi-Scale Patchify Capsule Network with Cross-Agreement Routing for Visual Recognition](https://mlsanity.com/paper/2508.16922/) (2025)

## Abstract (arXiv)

Deep learning has excelled in medical image classification, but its clinical application is limited by poor interpretability. Capsule networks, known for encoding hierarchical relationships and spatial features, show potential in addressing this issue. Nevertheless, traditional capsule networks often underperform due to their shallow structures, and deeper variants lack hierarchical architectures, thereby compromising interpretability. This paper introduces a novel capsule network, ParseCaps, which utilizes the sparse axial attention routing and parse convolutional capsule layer to form a parse-tree-like structure, enhancing both depth and interpretability. Firstly, sparse axial attention routing optimizes connections between child and parent capsules, as well as emphasizes the weight distribution across instantiation parameters of parent capsules. Secondly, the parse convolutional capsule layer generates capsule predictions aligning with the parse tree. Finally, based on the loss design that is effective whether concept ground truth exists or not, ParseCaps advances interpretability by associating each dimension of the global capsule with a comprehensible concept, thereby facilitating clinician trust and understanding of the model's classification results. Experimental results on CE-MRI, PH2, and Derm7pt datasets show that ParseCaps not only outperforms other capsule network variants in classification accuracy, redundancy reduction and robustness, but also provides interpretable explanations, regardless of the availability of concept labels.