Related Experiment Video
Updated: May 2, 2026
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
Deep Learning Models for Abdominal CT Organ Segmentation in Children: Development and Validation in Internal and
Elanchezhian Somasundaram1,2, Zachary Taylor1, Vinicius V Alves1
1Department of Radiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave, MLC 5033, Cincinnati, OH 45229.
Insights
Deep learning models for pediatric abdominal organ segmentation, utilizing transfer learning (TL) on public datasets and fine-tuning with institutional data, showed superior performance compared to native training and existing models. This advancement offers potential for improved pediatric imaging volumetry applications.
Area of Science:
- Medical image analysis
- Deep learning in radiology
- Pediatric CT segmentation
Background:
- Deep learning algorithms excel in adult abdominal organ segmentation.
- Validation of these algorithms in pediatric populations is limited.
- Pediatric CT examinations require specialized segmentation models.
Purpose of the Study:
- To develop and validate deep learning models for segmenting liver, spleen, and pancreas in pediatric CT scans.
- To compare the performance of different deep learning architectures and training strategies.
Main Methods:
- Retrospective analysis of 1731 CT examinations (483 pediatric, 1248 mixed pediatric/adult).
- Training and validation of SegResNet, DynUNet, and SwinUNETR models using native training (NT) and transfer learning (TL).
- Comparison with TotalSegmentator; performance evaluated using Dice Similarity Coefficient (DSC).
Main Results:
- Transfer learning (TL) models outperformed native training (NT) and TotalSegmentator on internal and public pediatric datasets.
- Segmentation performance was highest for the liver and spleen, followed by the pancreas.
- The DynUNet TL model demonstrated the best overall performance and was released as open-source.
Conclusions:
- Transfer learning models, fine-tuned on institutional pediatric data, significantly improve abdominal organ segmentation in children.
- The developed open-source model offers a valuable tool for pediatric imaging analysis.
- Segmentation accuracy varies by organ, with the pancreas being more challenging.
Abstract:
BACKGROUND. Deep learning abdominal organ segmentation algorithms have shown excellent results in adults; validation in children is sparse. OBJECTIVE. The purpose of this article is to develop and validate deep learning models for liver, spleen, and pancreas segmentation on pediatric CT examinations. METHODS. This retrospective study developed and validated deep learning models for liver, spleen, and pancreas segmentation using 1731 CT examinations (1504 training, 221 testing), derived from three internal institutional pediatric (age ≤ 18 years) datasets (n = 483) and three public datasets comprising pediatric and adult examinations with various pathologies (n = 1248). Three deep learning model architectures (SegResNet, DynUNet, and SwinUNETR) from the Medical Open Network for Artificial Intelligence (MONAI) framework underwent training using native training (NT), relying solely on institutional datasets, and transfer learning (TL), incorporating pretraining on public datasets. For comparison, TotalSegmentator, a publicly available segmentation model, was applied to test data without further training. Segmentation performance was evaluated using mean Dice similarity coefficient (DSC), with manual segmentations as reference. RESULTS. For internal pediatric data, the DSC for TotalSegmentator, NT models, and TL models for normal liver was 0.953, 0.964-0.965, and 0.965-0.966, respectively; for normal spleen, 0.914, 0.942-0.945, and 0.937-0.945; for normal pancreas, 0.733, 0.774-0.785, and 0.775-0.786; and for pancreas with pancreatitis, 0.703, 0.590-0.640, and 0.667-0.711. For public pediatric data, the DSC for TotalSegmentator, NT models, and TL models for liver was 0.952, 0.871-0.908, and 0.941-0.946, respectively; for spleen, 0.905, 0.771-0.827, and 0.897-0.926; and for pancreas, 0.700, 0.577-0.648, and 0.693-0.736. For public primarily adult data, the DSC for TotalSegmentator, NT models, and TL models for liver was 0.991, 0.633-0.750, and 0.926-0.952, respectively; for spleen, 0.983, 0.569-0.604, and 0.923-0.947; and for pancreas, 0.909, 0.148-0.241, and 0.699-0.775. The DynUNet TL model was selected as the best-performing NT or TL model considering DSC values across organs and test datasets and was made available as an open-source MONAI bundle (https://github.com/cchmc-dll/pediatric_abdominal_segmentation_bundle.git). CONCLUSION. TL models trained on heterogeneous public datasets and fine-tuned using institutional pediatric data outperformed internal NT models and Total-Segmentator across internal and external pediatric test data. Segmentation performance was better in liver and spleen than in pancreas. CLINICAL IMPACT. The selected model may be used for various volumetry applications in pediatric imaging.
