Learning Robust Medical Image Segmentation with Inductive Bias

Shrajan Bhandary, Dejan Kuhn, Zahra Babaiee, Tobias Fechter, Anca Grosu, Radu Grosu

Keywords: 3D Medical Image Segmentation, Inductive Bias, Small-sized dataset, Out-of-distribution

Abstract: Despite the success of transformer-based and convolutional neural networks in 3D medical image segmentation, current architectures exhibit limited generalisation on small datasets and under distribution shifts, especially when high-quality examples are scarce for specific structures. We introduce IB-nnU-Nets, a family of U-Net variants augmented with inductively biased filters inspired by vertebrate visual processing. Starting from a 3D U-Net backbone, we insert two 3D residual components into the second encoder block that implement on- and off-centre-surround convolutions with fixed, pre-computed weights and act as complementary edge detectors. Across multiple organ and tumour segmentation tasks, we show that equipping state-of-the-art 3D U-Nets with an IB block improves accuracy and robustness, with the strongest gains in small-data and out-of-distribution settings. The framework and trained IB-nnU-Net models are publicly available.

Primary Subject Area: Segmentation

Secondary Subject Area: Learning with Noisy Labels and Limited Data

Registration Requirement: Yes

Reproducibility: https://github.com/Shrajan/nnUNet/tree/master/documentation/third_party_additions/network_architecture

Visa & Travel: Yes

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Submission Number: 311