Self-Supervised Multi-Organ Segmentation in Pediatric Abdominal CT Based on Vision Foundation Models

To address the scarcity of annotated data for pediatric abdominal CT imaging and the insufficient generalization capability of existing models, we constructed a self-supervised pretraining architecture tailored for pediatric CT domain adaptation based on the visual foundation model DINOv3, and validated its performance in the task of pediatric abdominal multi-organ segmentation.

We built a general-purpose radiological visual representation using the large-scale adult CT dataset CT-3M, and introduced a Gram-anchoring mechanism that employs a frozen adult pretrained model as a structural teacher to guide domain alignment of local topological structures on unlabeled pediatric CT data. Combined with a multi-scale feature aggregation strategy and a lightweight Primus decoder, downstream segmentation tasks were evaluated on a public pediatric CT dataset. Based on case-wise paired results, we compared the mean Dice similarity coefficient (DSC) and mean intersection over union (IoU) between our model and the baseline nnU-Net using the Wilcoxon signed-rank test, and computed the relative performance improvements.

A total of 867 abdominal CT imaging cases were collected, constituting a pretraining dataset comprising 367 588 two-dimensional CT slices. On the public Pediatric-CT-SEG dataset (359 cases), our model achieved a mean DSC of (71.38±1.08)% and a mean IoU of (63.73±1.01)%, representing improvements of 3.22% and 3.59% over the baseline nnU-Net, respectively, with statistically significant differences (P < 0.05). Stable improvements in mean DSC were also observed for small-volume or boundary-ambiguous organs, including the duodenum (5.78%), pancreas (4.69%), left adrenal gland (2.89%), right adrenal gland (1.12%), and gallbladder (1.86%). Ablation experiments demonstrated that DSC improved by 1.44%, 3.66%, 5.78%, and 6.45% following adult pretraining, pediatric domain adaptation, high-resolution adaptation, and multi-scale feature aggregation, respectively.

The self-supervised pretraining framework proposed in this study effectively alleviates the domain shift between adult and pediatric abdominal CT images, significantly enhances segmentation accuracy for pediatric abdominal multi-organs-particularly small organs and structures with complex boundaries-and provides a reliable technical solution for intelligent pediatric imaging analysis in scenarios with limited annotated data.