# ResDynUNet++: A nested U-Net with residual dynamic convolution blocks for dual-spectral CT

arXiv: https://arxiv.org/abs/2512.16140 · HTML: https://mlsanity.com/paper/2512.16140/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 34 references that are in the map.
- First posted on arXiv 18 Dec 2025.

## Builds on (most cited first, 14 of 14)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [Deep Convolutional Neural Network for Inverse Problems in Imaging](https://mlsanity.com/paper/1611.03679/) (2016)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)
- [Dynamic Filter Networks](https://mlsanity.com/paper/1605.09673/) (2016)
- [CondConv: Conditionally Parameterized Convolutions for Efficient Inference](https://mlsanity.com/paper/1904.04971/) (2019)
- [Learned Primal-dual Reconstruction](https://mlsanity.com/paper/1707.06474/) (2017)
- [Solving ill-posed inverse problems using iterative deep neural networks](https://mlsanity.com/paper/1704.04058/) (2017)
- [ViTGAN: Training GANs with Vision Transformers](https://mlsanity.com/paper/2107.04589/) (2021)
- [A Comprehensive Review of U-Net and Its Variants: Advances and Applications in Medical Image Segmentation](https://mlsanity.com/paper/2502.06895/) (2025)
- [An Extended Primal-Dual Algorithm Framework for Nonconvex Problems with Application to Nonlinear Imaging](https://mlsanity.com/paper/2109.07174/) (2021)

## Abstract (arXiv)

We propose a hybrid reconstruction framework for dual-spectral CT (DSCT) that integrates iterative methods with deep learning models. The reconstruction process consists of two complementary components: a knowledge-driven module and a data-driven module. In the knowledge-driven phase, we employ the oblique projection modification technique (OPMT) to reconstruct an intermediate solution of the basis material images from the projection data. We select OPMT for this role because of its fast convergence, which allows it to rapidly generate an intermediate solution that successfully achieves basis material decomposition. Subsequently, in the data-driven phase, we introduce a novel neural network, ResDynUNet++, to refine this intermediate solution. The ResDynUNet++ is built upon a UNet++ backbone by replacing standard convolutions with residual dynamic convolution blocks, which combine the adaptive, input-specific feature extraction of dynamic convolution with the stable training of residual connections. This architecture is designed to address challenges like channel imbalance and near-interface large artifacts in DSCT, producing clean and accurate final solutions. Extensive experiments on both synthetic phantoms and real clinical datasets validate the efficacy and superior performance of the proposed method.