# SAR: Scale-Aware Restoration Learning for 3D Tumor Segmentation

arXiv: https://arxiv.org/abs/2010.06107 · HTML: https://mlsanity.com/paper/2010.06107/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Oct 2020.

## Built on by (most cited first, 8 of 8)

- [Data efficient deep learning for medical image analysis: A survey](https://mlsanity.com/paper/2310.06557/) (2023)
- [Keep Your Friends Close & Enemies Farther: Debiasing Contrastive Learning with Spatial Priors in 3D Radiology Images](https://mlsanity.com/paper/2211.08643/) (2022)
- [Self-supervised Tumor Segmentation through Layer Decomposition](https://mlsanity.com/paper/2109.03230/) (2021)
- [A Point in the Right Direction: Vector Prediction for Spatially-aware Self-supervised Volumetric Representation Learning](https://mlsanity.com/paper/2211.08533/) (2022)
- [A Survey of the Impact of Self-Supervised Pretraining for Diagnostic Tasks with Radiological Images](https://mlsanity.com/paper/2309.02555/) (2023)
- [Dive into Self-Supervised Learning for Medical Image Analysis: Data, Models and Tasks](https://mlsanity.com/paper/2209.12157/) (2022)
- [DMC-Net: Lightweight Dynamic Multi-Scale and Multi-Resolution Convolution Network for Pancreas Segmentation in CT Images](https://mlsanity.com/paper/2410.02129/) (2024)
- [Deep Learning Approaches for Medical Imaging Under Varying Degrees of Label Availability: A Comprehensive Survey](https://mlsanity.com/paper/2504.11588/) (2025)

## Abstract (arXiv)

Automatic and accurate tumor segmentation on medical images is in high demand to assist physicians with diagnosis and treatment. However, it is difficult to obtain massive amounts of annotated training data required by the deep-learning models as the manual delineation process is often tedious and expertise required. Although self-supervised learning (SSL) scheme has been widely adopted to address this problem, most SSL methods focus only on global structure information, ignoring the key distinguishing features of tumor regions: local intensity variation and large size distribution. In this paper, we propose Scale-Aware Restoration (SAR), a SSL method for 3D tumor segmentation. Specifically, a novel proxy task, i.e. scale discrimination, is formulated to pre-train the 3D neural network combined with the self-restoration task. Thus, the pre-trained model learns multi-level local representations through multi-scale inputs. Moreover, an adversarial learning module is further introduced to learn modality invariant representations from multiple unlabeled source datasets. We demonstrate the effectiveness of our methods on two downstream tasks: i) Brain tumor segmentation, ii) Pancreas tumor segmentation. Compared with the state-of-the-art 3D SSL methods, our proposed approach can significantly improve the segmentation accuracy. Besides, we analyze its advantages from multiple perspectives such as data efficiency, performance, and convergence speed.