# SUFFICIENT: A scan-specific unsupervised deep learning framework for high-resolution 3D isotropic fetal brain MRI reconstruction

arXiv: https://arxiv.org/abs/2505.17472 · HTML: https://mlsanity.com/paper/2505.17472/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 46 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 21 of 21)

- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [VoxelMorph: A Learning Framework for Deformable Medical Image Registration](https://mlsanity.com/paper/1809.05231/) (2018)
- [Understanding the Limitations of CNN-based Absolute Camera Pose Regression](https://mlsanity.com/paper/1903.07504/) (2019)
- [TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning](https://mlsanity.com/paper/2003.04696/) (2020)
- [A Deep Learning Framework for Unsupervised Affine and Deformable Image Registration](https://mlsanity.com/paper/1809.06130/) (2018)
- [Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks](https://mlsanity.com/paper/1810.03982/) (2018)
- [Efficient and Accurate MRI Super-Resolution using a Generative Adversarial Network and 3D Multi-Level Densely Connected Network](https://mlsanity.com/paper/1803.01417/) (2018)
- [A Bayesian Perspective on the Deep Image Prior](https://mlsanity.com/paper/1904.07457/) (2019)
- [Enhanced generative adversarial network for 3D brain MRI super-resolution](https://mlsanity.com/paper/1907.04835/) (2019)
- [Channel Splitting Network for Single MR Image Super-Resolution](https://mlsanity.com/paper/1810.06453/) (2018)
- [SVoRT: Iterative Transformer for Slice-to-Volume Registration in Fetal Brain MRI](https://mlsanity.com/paper/2206.10802/) (2022)
- [Slice-to-volume medical image registration: a survey](https://mlsanity.com/paper/1702.01636/) (2017)
- [3D Reconstruction in Canonical Co-ordinate Space from Arbitrarily Oriented 2D Images](https://mlsanity.com/paper/1709.06341/) (2017)
- [Real-Time Automatic Fetal Brain Extraction in Fetal MRI by Deep Learning](https://mlsanity.com/paper/1710.09338/) (2017)
- [Deep MR Brain Image Super-Resolution Using Spatio-Structural Priors](https://mlsanity.com/paper/1909.04572/) (2019)
- [Predicting Slice-to-Volume Transformation in Presence of Arbitrary Subject Motion](https://mlsanity.com/paper/1702.08891/) (2017)
- [Context-Sensitive Super-Resolution for Fast Fetal Magnetic Resonance Imaging](https://mlsanity.com/paper/1703.00035/) (2017)
- [Deep Predictive Motion Tracking in Magnetic Resonance Imaging: Application to Fetal Imaging](https://mlsanity.com/paper/1909.11625/) (2019)
- [PVR: Patch-to-Volume Reconstruction for Large Area Motion Correction of Fetal MRI](https://mlsanity.com/paper/1611.07289/) (2016)
- [AFFIRM: Affinity Fusion-based Framework for Iteratively Random Motion correction of multi-slice fetal brain MRI](https://mlsanity.com/paper/2205.05851/) (2022)

## Abstract (arXiv)

High-quality 3D fetal brain MRI reconstruction from motion-corrupted 2D slices is crucial for clinical diagnosis. Reliable slice-to-volume registration (SVR)-based motion correction and super-resolution reconstruction (SRR) methods are essential. Deep learning (DL) has demonstrated potential in enhancing SVR and SRR when compared to conventional methods. However, it requires large-scale external training datasets, which are difficult to obtain for clinical fetal MRI. To address this issue, we propose an unsupervised iterative SVR-SRR framework for isotropic HR volume reconstruction. Specifically, SVR is formulated as a function mapping a 2D slice and a 3D target volume to a rigid transformation matrix, which aligns the slice to the underlying location in the target volume. The function is parameterized by a convolutional neural network, which is trained by minimizing the difference between the volume slicing at the predicted position and the input slice. In SRR, a decoding network embedded within a deep image prior framework is incorporated with a comprehensive image degradation model to produce the high-resolution (HR) volume. The deep image prior framework offers a local consistency prior to guide the reconstruction of HR volumes. By performing a forward degradation model, the HR volume is optimized by minimizing loss between predicted slices and the observed slices. Comprehensive experiments conducted on large-magnitude motion-corrupted simulation data and clinical data demonstrate the superior performance of the proposed framework over state-of-the-art fetal brain reconstruction frameworks.