# Generalizing Medical Image Representations via Quaternion Wavelet Networks

arXiv: https://arxiv.org/abs/2310.10224 · HTML: https://mlsanity.com/paper/2310.10224/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 71 references that are in the map.
- First posted on arXiv 16 Oct 2023.

## Builds on (most cited first, 27 of 27)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Kvasir-SEG: A Segmented Polyp Dataset](https://mlsanity.com/paper/1911.07069/) (2019)
- [UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation](https://mlsanity.com/paper/1912.05074/) (2019)
- [Deep Learning on a Data Diet: Finding Important Examples Early in Training](https://mlsanity.com/paper/2107.07075/) (2021)
- [Solving Inverse Problems in Medical Imaging with Score-Based Generative Models](https://mlsanity.com/paper/2111.08005/) (2021)
- [Diffusion Models for Medical Image Analysis: A Comprehensive Survey](https://mlsanity.com/paper/2211.07804/) (2022)
- [Models Genesis: Generic Autodidactic Models for 3D Medical Image Analysis](https://mlsanity.com/paper/1908.06912/) (2019)
- [End-to-end Training for Whole Image Breast Cancer Diagnosis using An All Convolutional Design](https://mlsanity.com/paper/1711.05775/) (2017)
- [Streaming convolutional neural networks for end-to-end learning with multi-megapixel images](https://mlsanity.com/paper/1911.04432/) (2019)
- [Follow My Eye: Using Gaze to Supervise Computer-Aided Diagnosis](https://mlsanity.com/paper/2204.02976/) (2022)
- [FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation](https://mlsanity.com/paper/2103.17235/) (2021)
- [Does Preprocessing Help Training Over-parameterized Neural Networks?](https://mlsanity.com/paper/2110.04622/) (2021)
- [Quaternion Convolutional Neural Networks for Heterogeneous Image Processing](https://mlsanity.com/paper/1811.02656/) (2018)
- [RelatIF: Identifying Explanatory Training Examples via Relative Influence](https://mlsanity.com/paper/2003.11630/) (2020)
- [Diagnose Like a Radiologist: Hybrid Neuro-Probabilistic Reasoning for Attribute-Based Medical Image Diagnosis](https://mlsanity.com/paper/2208.09282/) (2022)
- [Medical Image Captioning via Generative Pretrained Transformers](https://mlsanity.com/paper/2209.13983/) (2022)
- [Quaternion Generative Adversarial Networks](https://mlsanity.com/paper/2104.09630/) (2021)
- [Generalizable Medical Image Segmentation via Random Amplitude Mixup and Domain-Specific Image Restoration](https://mlsanity.com/paper/2208.03901/) (2022)
- [TarGAN: Target-Aware Generative Adversarial Networks for Multi-modality Medical Image Translation](https://mlsanity.com/paper/2105.08993/) (2021)
- [2-Step Sparse-View CT Reconstruction with a Domain-Specific Perceptual Network](https://mlsanity.com/paper/2012.04743/) (2020)
- [Predicting cognitive scores with graph neural networks through sample selection learning](https://mlsanity.com/paper/2106.09408/) (2021)
- [Attention-Map Augmentation for Hypercomplex Breast Cancer Classification](https://mlsanity.com/paper/2310.07633/) (2023)
- [Hypercomplex Image-to-Image Translation](https://mlsanity.com/paper/2205.02087/) (2022)
- [QSAM-Net: Rain streak removal by quaternion neural network with self-attention module](https://mlsanity.com/paper/2208.04346/) (2022)

## Built on by (most cited first, 6 of 6)

- [A Wavelet Diffusion GAN for Image Super-Resolution](https://mlsanity.com/paper/2410.17966/) (2024)
- [Towards Explaining Hypercomplex Neural Networks](https://mlsanity.com/paper/2403.17929/) (2024)
- [PHemoNet: A Multimodal Network for Physiological Signals](https://mlsanity.com/paper/2410.00010/) (2024)
- [Quaternion Wavelet-Conditioned Diffusion Models for Image Super-Resolution](https://mlsanity.com/paper/2505.00334/) (2025)
- [Lightweight Hypercomplex MRI Reconstruction: A Generalized Kronecker-Parameterized Approach](https://mlsanity.com/paper/2503.05063/) (2025)
- [An Automatic Detection Method for Hematoma Features in Placental Abruption Ultrasound Images Based on Few-Shot Learning](https://mlsanity.com/paper/2510.21495/) (2025)

## Abstract (arXiv)

Neural network generalizability is becoming a broad research field due to the increasing availability of datasets from different sources and for various tasks. This issue is even wider when processing medical data, where a lack of methodological standards causes large variations being provided by different imaging centers or acquired with various devices and cofactors. To overcome these limitations, we introduce a novel, generalizable, data- and task-agnostic framework able to extract salient features from medical images. The proposed quaternion wavelet network (QUAVE) can be easily integrated with any pre-existing medical image analysis or synthesis task, and it can be involved with real, quaternion, or hypercomplex-valued models, generalizing their adoption to single-channel data. QUAVE first extracts different sub-bands through the quaternion wavelet transform, resulting in both low-frequency/approximation bands and high-frequency/fine-grained features. Then, it weighs the most representative set of sub-bands to be involved as input to any other neural model for image processing, replacing standard data samples. We conduct an extensive experimental evaluation comprising different datasets, diverse image analysis, and synthesis tasks including reconstruction, segmentation, and modality translation. We also evaluate QUAVE in combination with both real and quaternion-valued models. Results demonstrate the effectiveness and the generalizability of the proposed framework that improves network performance while being flexible to be adopted in manifold scenarios and robust to domain shifts. The full code is available at: https://github.com/ispamm/QWT.