# Trainable Joint Bilateral Filters for Enhanced Prediction Stability in Low-dose CT

arXiv: https://arxiv.org/abs/2207.07368 · HTML: https://mlsanity.com/paper/2207.07368/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 38 references that are in the map.
- First posted on arXiv 15 Jul 2022.

## Builds on (most cited first, 13 of 13)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)](https://mlsanity.com/paper/1702.00288/) (2017)
- [On instabilities of deep learning in image reconstruction - Does AI come at a cost?](https://mlsanity.com/paper/1902.05300/) (2019)
- [Fast End-to-End Trainable Guided Filter](https://mlsanity.com/paper/1803.05619/) (2018)
- [Quadratic Autoencoder (Q-AE) for Low-dose CT Denoising](https://mlsanity.com/paper/1901.05593/) (2019)
- [Learning with Known Operators reduces Maximum Training Error Bounds](https://mlsanity.com/paper/1907.01992/) (2019)
- [Superpixel Convolutional Networks using Bilateral Inceptions](https://mlsanity.com/paper/1511.06739/) (2015)
- [Noise Conscious Training of Non Local Neural Network powered by Self Attentive Spectral Normalized Markovian Patch GAN for Low Dose CT Denoising](https://mlsanity.com/paper/2011.05684/) (2020)
- [Ultra Low-Parameter Denoising: Trainable Bilateral Filter Layers in Computed Tomography](https://mlsanity.com/paper/2201.10345/) (2022)
- [Precision Learning: Towards Use of Known Operators in Neural Networks](https://mlsanity.com/paper/1712.00374/) (2017)
- [JBFnet -- Low Dose CT Denoising by Trainable Joint Bilateral Filtering](https://mlsanity.com/paper/2007.04754/) (2020)
- [Limited Parameter Denoising for Low-dose X-ray Computed Tomography Using Deep Reinforcement Learning](https://mlsanity.com/paper/2203.14794/) (2022)
- [Low Dose CT Denoising via Joint Bilateral Filtering and Intelligent Parameter Optimization](https://mlsanity.com/paper/2007.04768/) (2020)

## Built on by (most cited first, 5 of 5)

- [Beyond the LUMIR challenge: The pathway to foundational registration models](https://mlsanity.com/paper/2505.24160/) (2025)
- [On the Benefit of Dual-domain Denoising in a Self-supervised Low-dose CT Setting](https://mlsanity.com/paper/2211.01111/) (2022)
- [Noise2Contrast: Multi-Contrast Fusion Enables Self-Supervised Tomographic Image Denoising](https://mlsanity.com/paper/2212.04832/) (2022)
- [Physics-Informed Learning for Time-Resolved Angiographic Contrast Agent Concentration Reconstruction](https://mlsanity.com/paper/2403.01993/) (2024)
- [Large Scale Unsupervised Brain MRI Image Registration Solution for Learn2Reg 2024](https://mlsanity.com/paper/2409.00917/) (2024)

## Abstract (arXiv)

Low-dose computed tomography (CT) denoising algorithms aim to enable reduced patient dose in routine CT acquisitions while maintaining high image quality. Recently, deep learning~(DL)-based methods were introduced, outperforming conventional denoising algorithms on this task due to their high model capacity. However, for the transition of DL-based denoising to clinical practice, these data-driven approaches must generalize robustly beyond the seen training data. We, therefore, propose a hybrid denoising approach consisting of a set of trainable joint bilateral filters (JBFs) combined with a convolutional DL-based denoising network to predict the guidance image. Our proposed denoising pipeline combines the high model capacity enabled by DL-based feature extraction with the reliability of the conventional JBF. The pipeline's ability to generalize is demonstrated by training on abdomen CT scans without metal implants and testing on abdomen scans with metal implants as well as on head CT data. When embedding two well-established DL-based denoisers (RED-CNN/QAE) in our pipeline, the denoising performance is improved by 10,%/82,% (RMSE) and 3,%/81,% (PSNR) in regions containing metal and by 6,%/78,% (RMSE) and 2,%/4,% (PSNR) on head CT data, compared to the respective vanilla model. Concluding, the proposed trainable JBFs limit the error bound of deep neural networks to facilitate the applicability of DL-based denoisers in low-dose CT pipelines.