---
title: "Two-Fold Patch Perturbation for Efficient Self-Supervised Learning in 3D Medical Imaging"
authors:
  - "Tirthajit Baruah"
  - "Kabir Jamadar"
  - "Punit Rathore"
doi: "10.24963/ijcai.2026/740"
url: "https://ijcai.org/proceedings/2026/740"
pdf: "https://ijcai.org/proceedings/2026/0740.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "6654-6662"
track: "AI and Health"
keywords:
  - "Medical knowledge representation: Medical knowledge representation"
  - "Self-supervised learning: Self-supervised learning"
  - "Medical imaging: Medical imaging"
  - "Medical diagnosis: Medical diagnosis"
---

# Two-Fold Patch Perturbation for Efficient Self-Supervised Learning in 3D Medical Imaging

Tirthajit Baruah, Kabir Jamadar, Punit Rathore

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 6654-6662. DOI: [10.24963/ijcai.2026/740](https://doi.org/10.24963/ijcai.2026/740)

## Abstract

Self-supervised pre-training has become a key paradigm for reducing annotation costs in 3D medical imaging, yet many recent approaches rely on complex objectives or incur substantial computational overhead. We propose a simple and efficient self-supervised pre-training framework for 3D medical images based on a two-fold patch-wise perturbation strategy. The method applies Bernoulli patch masking and discrete rotations, and trains a shared encoder with a three-head objective for reconstruction, perturbation localization, and rotation prediction. This design encourages spatially aware and transferable representations while remaining computationally lightweight. Experiments across diverse segmentation and classification benchmarks, including modality-shift scenarios, demonstrate consistent improvements over general self-supervised baselines and competitive or superior performance compared to recent medical self-supervised methods, while requiring substantially less memory, computation, and training time than the state-of-the-art pre-training pipelines.