# MetaSSL: A General Heterogeneous Loss for Semi-Supervised Medical Image Segmentation

arXiv: https://arxiv.org/abs/2509.01144 · HTML: https://mlsanity.com/paper/2509.01144/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 52 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Builds on (most cited first, 30 of 36)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation](https://mlsanity.com/paper/1907.07034/) (2019)
- [Semi-Supervised Semantic Segmentation with Cross-Consistency Training](https://mlsanity.com/paper/2003.09005/) (2020)
- [Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks](https://mlsanity.com/paper/1807.07356/) (2018)
- [FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning](https://mlsanity.com/paper/2205.07246/) (2022)
- [Tversky loss function for image segmentation using 3D fully convolutional deep networks](https://mlsanity.com/paper/1706.05721/) (2017)
- [Semi-supervised Medical Image Segmentation through Dual-task Consistency](https://mlsanity.com/paper/2009.04448/) (2020)
- [R-Drop: Regularized Dropout for Neural Networks](https://mlsanity.com/paper/2106.14448/) (2021)
- [Boundary loss for highly unbalanced segmentation](https://mlsanity.com/paper/1812.07032/) (2018)
- [ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2106.05095/) (2021)
- [Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2305.00673/) (2023)
- [Mutual Consistency Learning for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2109.09960/) (2021)
- [Deep Learning for Medical Image Processing: Overview, Challenges and Future](https://mlsanity.com/paper/1704.06825/) (2017)
- [Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformer](https://mlsanity.com/paper/2112.04894/) (2021)
- [Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation](https://mlsanity.com/paper/2006.16806/) (2020)
- [Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation](https://mlsanity.com/paper/2107.11279/) (2021)
- [Inconsistency-aware Uncertainty Estimation for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2110.08762/) (2021)
- [Deep Co-Training for Semi-Supervised Image Segmentation](https://mlsanity.com/paper/1903.11233/) (2019)
- [UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2205.10334/) (2022)
- [Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective](https://mlsanity.com/paper/2302.01735/) (2023)
- [3D Segmentation with Exponential Logarithmic Loss for Highly Unbalanced Object Sizes](https://mlsanity.com/paper/1809.00076/) (2018)
- [Adaptive Bidirectional Displacement for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2405.00378/) (2024)
- [Automatic Segmentation of Vestibular Schwannoma from T2-Weighted MRI by Deep Spatial Attention with Hardness-Weighted Loss](https://mlsanity.com/paper/1906.03906/) (2019)

## Built on by (most cited first, 6 of 6)

- [PathCo-LatticE: Pathology-Constrained Lattice-Of Experts Framework for Fully-supervised Few-Shot Cardiac MRI Segmentation](https://mlsanity.com/paper/2512.09779/) (2025)
- [Weakly Supervised Patch Annotation for Improved Screening of Diabetic Retinopathy](https://mlsanity.com/paper/2603.03991/) (2026)
- [SynerMedGen: Synergizing Medical Multimodal Understanding with Generation via Task Alignment](https://mlsanity.com/paper/2605.08724/) (2026)
- [OFD-Net: Teacher-Free Reliable Semi-supervised Medical Image Segmentation with Orthogonal Feature Disentanglement Net of Foreground-Background](https://mlsanity.com/paper/2607.16705/) (2026)
- [Robust Activation Map Rectification for Weakly Supervised Volumetric Segmentation: Temporal Coherence as a Free Lunch](https://mlsanity.com/paper/2607.19877/) (2026)
- [SAUF-Net: Structure--Appearance Representation Learning with Uncertainty Feedback for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2609.02247/) (2026)

## Abstract (arXiv)

Semi-Supervised Learning (SSL) is important for reducing the annotation cost for medical image segmentation models. State-of-the-art SSL methods such as Mean Teacher, FixMatch and Cross Pseudo Supervision (CPS) are mainly based on consistency regularization or pseudo-label supervision between a reference prediction and a supervised prediction. Despite the effectiveness, they have overlooked the potential noise in the labeled data, and mainly focus on strategies to generate the reference prediction, while ignoring the heterogeneous values of different unlabeled pixels. We argue that effectively mining the rich information contained by the two predictions in the loss function, instead of the specific strategy to obtain a reference prediction, is more essential for SSL, and propose a universal framework MetaSSL based on a spatially heterogeneous loss that assigns different weights to pixels by simultaneously leveraging the uncertainty and consistency information between the reference and supervised predictions. Specifically, we split the predictions on unlabeled data into four regions with decreasing weights in the loss: Unanimous and Confident (UC), Unanimous and Suspicious (US), Discrepant and Confident (DC), and Discrepant and Suspicious (DS), where an adaptive threshold is proposed to distinguish confident predictions from suspicious ones. The heterogeneous loss is also applied to labeled images for robust learning considering the potential annotation noise. Our method is plug-and-play and general to most existing SSL methods. The experimental results showed that it improved the segmentation performance significantly when integrated with existing SSL frameworks on different datasets. Code is available at https://github.com/HiLab-git/MetaSSL.