# Deep Slice Interpolation for Reducing Through-Plane Anisotropy and Noise in Head CT

arXiv: https://arxiv.org/abs/2606.09953 · HTML: https://mlsanity.com/paper/2606.09953/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 41 references that are in the map.
- First posted on arXiv 8 Jun 2026.

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

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)](https://mlsanity.com/paper/1702.00288/) (2017)
- [Real-Time Intermediate Flow Estimation for Video Frame Interpolation](https://mlsanity.com/paper/2011.06294/) (2020)
- [FILM: Frame Interpolation for Large Motion](https://mlsanity.com/paper/2202.04901/) (2022)
- [AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation](https://mlsanity.com/paper/1907.10244/) (2019)
- [Understanding metric-related pitfalls in image analysis validation](https://mlsanity.com/paper/2302.01790/) (2023)
- [Brain MRI Super Resolution Using 3D Deep Densely Connected Neural Networks](https://mlsanity.com/paper/1801.02728/) (2018)
- [SAINT: Spatially Aware Interpolation NeTwork for Medical Slice Synthesis](https://mlsanity.com/paper/2001.00704/) (2020)
- [Data-Efficient Unsupervised Interpolation Without Any Intermediate Frame for 4D Medical Images](https://mlsanity.com/paper/2404.01464/) (2024)
- [I3Net: Inter-Intra-slice Interpolation Network for Medical Slice Synthesis](https://mlsanity.com/paper/2405.02857/) (2024)

## Abstract (arXiv)

Head computed tomography (CT) typically uses sub-millimeter in-plane resolution but 2-5 mm through-plane spacing, creating substantial anisotropy that degrades multiplanar reconstructions, volumetric measurements such as hematoma volume estimation, and downstream algorithms that assume near-isotropic voxels. We present a deep learning system that synthesizes intermediate CT slices from pairs of neighboring axial slices, halving the effective through-plane spacing. The system improves three-dimensional visualization while simultaneously producing inherently denoised outputs, yielding two complementary benefits from a single inference pass. To build a reliable system, we systematically evaluate pixel-wise losses, namely mean squared error (MSE) and mean absolute error (L1); structural-similarity losses, namely the structural similarity index (SSIM) and its multi-scale variant (MS-SSIM); and hybrid combinations. On a held-out test set, all converged models outperform classical interpolation baselines and pretrained video frame interpolation methods (RIFE, FILM) on all structural measures, with MS-SSIM+L1 offering the strongest balanced profile. We also document training instability in SSIM-family losses and identify partial remedies: the standard numerical fixes eliminate the dominant failure mode but leave residual divergence at smaller batch sizes. All results are reported with patient-level bootstrap confidence intervals and paired statistical tests. As an illustration, we apply the system to an out-of-distribution head CT series from Hospital Universitario Virgen del Roc'io: the model synthesizes intermediate slices and exhibits on the real slices the implicit-denoising signature predicted by our theoretical analysis, supporting in a single external case that interpolation quality and implicit denoising are not confined to the training distribution.