# SingleStrip: learning skull-stripping from a single labeled example

arXiv: https://arxiv.org/abs/2508.10464 · HTML: https://mlsanity.com/paper/2508.10464/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 32 references that are in the map.
- First posted on arXiv 14 Aug 2025.

## Builds on (most cited first, 19 of 19)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Semi-Supervised Semantic Segmentation with Cross-Consistency Training](https://mlsanity.com/paper/2003.09005/) (2020)
- [Rethinking Pre-training and Self-training](https://mlsanity.com/paper/2006.06882/) (2020)
- [Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation](https://mlsanity.com/paper/1908.10454/) (2019)
- [SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining](https://mlsanity.com/paper/2107.09559/) (2021)
- [ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2106.05095/) (2021)
- [Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis](https://mlsanity.com/paper/1804.06353/) (2018)
- [SynthStrip: Skull-Stripping for Any Brain Image](https://mlsanity.com/paper/2203.09974/) (2022)
- [Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation](https://mlsanity.com/paper/2006.16806/) (2020)
- [Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysis](https://mlsanity.com/paper/2210.03736/) (2022)
- [A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction](https://mlsanity.com/paper/2207.01223/) (2022)
- [Real-time Prediction of Segmentation Quality](https://mlsanity.com/paper/1806.06244/) (2018)
- [Boosting Skull-Stripping Performance for Pediatric Brain Images](https://mlsanity.com/paper/2402.16634/) (2024)
- [Efficient Model Monitoring for Quality Control in Cardiac Image Segmentation](https://mlsanity.com/paper/2104.05533/) (2021)
- [Domain-randomized deep learning for neuroimage analysis](https://mlsanity.com/paper/2507.13458/) (2025)
- [SegQC: a segmentation network-based framework for multi-metric segmentation quality control and segmentation error detection in volumetric medical images](https://mlsanity.com/paper/2411.07601/) (2024)
- [Test-time augmentation-based active learning and self-training for label-efficient segmentation](https://mlsanity.com/paper/2308.10727/) (2023)
- [QANet -- Quality Assurance Network for Image Segmentation](https://mlsanity.com/paper/1904.08503/) (2019)

## Built on by (most cited first, 1 of 1)

- [Deep infant brain segmentation from multi-contrast MRI](https://mlsanity.com/paper/2512.05114/) (2025)

## Abstract (arXiv)

Deep learning segmentation relies heavily on labeled data, but manual labeling is laborious and time-consuming, especially for volumetric images such as brain magnetic resonance imaging (MRI). While recent domain-randomization techniques alleviate the dependency on labeled data by synthesizing diverse training images from label maps, they offer limited anatomical variability when very few label maps are available. Semi-supervised self-training addresses label scarcity by iteratively incorporating model predictions into the training set, enabling networks to learn from unlabeled data. In this work, we combine domain randomization with self-training to train three-dimensional skull-stripping networks using as little as a single labeled example. First, we automatically bin voxel intensities, yielding labels we use to synthesize images for training an initial skull-stripping model. Second, we train a convolutional autoencoder (AE) on the labeled example and use its reconstruction error to assess the quality of brain masks predicted for unlabeled data. Third, we select the top-ranking pseudo-labels to fine-tune the network, achieving skull-stripping performance on out-of-distribution data that approaches models trained with more labeled images. We compare AE-based ranking to consistency-based ranking under test-time augmentation, finding that the AE approach yields a stronger correlation with segmentation accuracy. Our results highlight the potential of combining domain randomization and AE-based quality control to enable effective semi-supervised segmentation from extremely limited labeled data. This strategy may ease the labeling burden that slows progress in studies involving new anatomical structures or emerging imaging techniques.