Deep Learning Auto-Segmentation Network for Pediatric Computed Tomography Data Sets: Can We Extrapolate From Adults?
Details
Publication Year 2024-07-15,Volume 119,Issue #4,Page 1297-1306
Journal Title
International Journal of Radiation Oncology, Biology, Physics
Publication Type
Research article
Abstract
PURPOSE: Artificial intelligence (AI)-based auto-segmentation models hold promise for enhanced efficiency and consistency in organ contouring for adaptive radiation therapy and radiation therapy planning. However, their performance on pediatric computed tomography (CT) data and cross-scanner compatibility remain unclear. This study aimed to evaluate the performance of AI-based auto-segmentation models trained on adult CT data when applied to pediatric data sets and explore the improvement in performance gained by including pediatric training data. It also examined their ability to accurately segment CT data acquired from different scanners. METHODS AND MATERIALS: Using the nnU-Net framework, segmentation models were trained on data sets of adult, pediatric, and combined CT scans for 7 pelvic/thoracic organs. Each model was trained on 290 to 300 cases per category and organ. Training data sets included a combination of clinical data and several open repositories. The study incorporated a database of 459 pediatric (0-16 years) CT scans and 950 adults (>18 years), ensuring all scans had human expert ground-truth contours of the selected organs. Performance was evaluated based on Dice similarity coefficients (DSC) of the model-generated contours. RESULTS: AI models trained exclusively on adult data underperformed on pediatric data, especially for the 0 to 2 age group: mean DSC was below 0.5 for the bladder and spleen. The addition of pediatric training data demonstrated significant improvement for all age groups, achieving a mean DSC of above 0.85 for all organs in every age group. Larger organs like the liver and kidneys maintained consistent performance for all models across age groups. No significant difference emerged in the cross-scanner performance evaluation, suggesting robust cross-scanner generalization. CONCLUSIONS: For optimal segmentation across age groups, it is important to include pediatric data in the training of segmentation models. The successful cross-scanner generalization also supports the real-world clinical applicability of these AI models. This study emphasizes the significance of data set diversity in training robust AI systems for medical image interpretation tasks.
Publisher
Elsevier
Keywords
Humans; *Deep Learning; Child; *Tomography, X-Ray Computed; Child, Preschool; Infant; Adolescent; Adult; Infant, Newborn; Spleen/diagnostic imaging; Datasets as Topic; Urinary Bladder/diagnostic imaging; Liver/diagnostic imaging; Pelvis/diagnostic imaging; Male; Kidney/diagnostic imaging; Female; Age Factors; Middle Aged
Department(s)
Physical Sciences
Terms of Use/Rights Notice
Refer to copyright notice on published article.


Creation Date: 2024-08-06 05:34:03
Last Modified: 2024-08-06 05:34:17

© 2024 The Walter and Eliza Hall Institute of Medical Research. Access to this website is subject to our Privacy Policy and Terms of Use

An error has occurred. This application may no longer respond until reloaded. Reload 🗙