IB-U-Nets: Improving medical image segmentation tasks with 3D Inductive Biased kernels
This work addresses the challenge of robust medical image segmentation for limited datasets, which is critical for clinical applications, though it appears incremental as it builds upon the existing U-Net architecture.
The paper tackled the problem of 3D medical image segmentation by introducing IB-U-Nets, a novel architecture with inductive bias, which improved robustness and accuracy, especially on small datasets, as demonstrated through comparisons with state-of-the-art 3D U-Nets on multiple modalities and organs.
Despite the success of convolutional neural networks for 3D medical-image segmentation, the architectures currently used are still not robust enough to the protocols of different scanners, and the variety of image properties they produce. Moreover, access to large-scale datasets with annotated regions of interest is scarce, and obtaining good results is thus difficult. To overcome these challenges, we introduce IB-U-Nets, a novel architecture with inductive bias, inspired by the visual processing in vertebrates. With the 3D U-Net as the base, we add two 3D residual components to the second encoder blocks. They provide an inductive bias, helping U-Nets to segment anatomical structures from 3D images with increased robustness and accuracy. We compared IB-U-Nets with state-of-the-art 3D U-Nets on multiple modalities and organs, such as the prostate and spleen, using the same training and testing pipeline, including data processing, augmentation and cross-validation. Our results demonstrate the superior robustness and accuracy of IB-U-Nets, especially on small datasets, as is typically the case in medical-image analysis. IB-U-Nets source code and models are publicly available.