Objectives: Brain segmentation of infant magnetic resonance (MR) images is vitally important for studying typical and atypical brain development. The infant brain undergoes many changes throughout the first years of postnatal life, making tissue segmentation difficult for most existing algorithms. Here we introduce a deep neural network BIBSNet ( B aby and I nfant B rain S egmentation Neural Net work), an open-source, community-driven model for robust and generalizable brain segmentation leveraging data augmentation and a large sample size of manually annotated images.
Experimental design: Included in model training and testing were MR brain images from 90 participants with an age range of 0-8 months (median age 4.6 months). Using the BOBs repository of manually annotated real images along with synthetic segmentation images produced using SynthSeg, the model was trained using a 10-fold procedure. Model performance of segmentations was assessed by comparing BIBSNet, joint label fusion (JLF) inferred segmentation to ground truth segmentations using Dice Similarity Coefficient (DSC). Additionally, MR data along with the FreeSurfer compatible segmentations were processed with the DCAN labs infant-ABCD-BIDS processing pipeline from ground truth, JLF, and BIBSNet to further assess model performance on derivative data, including cortical thickness, resting state connectivity and brain region volumes.
Principal observations: BIBSNet segmentations outperforms JLF across all regions based on DSC comparisons. Additionally, with processed derived metrics, BIBSNet segmentations outperforms JLF segmentations across nearly all metrics.
Conclusions: BIBSNet segmentation shows marked improvement over JLF across all age groups analyzed. The BIBSNet model is 600x faster compared to JLF, produces FreeSurfer-compatible segmentation labels, and can be easily included in other processing pipelines. BIBSNet provides a viable alternative for segmenting the brain in the earliest stages of development.