Where to Look Matters: Rethinking Sub-Volume Sampling in 3D Medical Self-supervised Learning

Key points

• However, random cropping implicitly treats all spatial regions as equally worth observing, despite anatomical priors and spatial redundancy that make regions inherently unequal in their value for representation learning.1
• To this end, we first show through controlled crop-quality manipulations that better sub-volumes lead to better downstream transfer, revealing the observation policy as an overlooked bottleneck in 3D medical SSL.1
• We propose \method, a plug-and-play framework that replaces random cropping with an offline coarse-to-fine probe bank guided by anatomy-awareness, informativeness, and diversity.1
• We instantiate \method as a lightweight \lite variant using geometric and image-statistical cues, and a diagnostic \feat variant using frozen visual features, to examine whether lightweight volume-intrinsic priors suffice or richer semantic cues reliably provide additional value.1

Sources (1)

• [1]Where to Look Matters: Rethinking Sub-Volume Sampling in 3D Medical Self-supervised Learning
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 05:51 PM

  Self-supervised learning on 3D medical images commonly relies on random sub-volume sampling during pretraining.

  However, random cropping implicitly treats all spatial regions as equally worth observing, despite anatomical priors and spatial redundancy that make regions inherently unequal in their value for representation learning.

Extractive summary: sentences quoted from the sources.