Unlocking Robust Segmentation Across All Age Groups via Continual Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929321688432640 |
|---|---|
| author | Liu, Chih-Ying Valanarasu, Jeya Maria Jose Gonzalez, Camila Langlotz, Curtis Ng, Andrew Gatidis, Sergios |
| author_facet | Liu, Chih-Ying Valanarasu, Jeya Maria Jose Gonzalez, Camila Langlotz, Curtis Ng, Andrew Gatidis, Sergios |
| contents | Most deep learning models in medical imaging are trained on adult data with unclear performance on pediatric images. In this work, we aim to address this challenge in the context of automated anatomy segmentation in whole-body Computed Tomography (CT). We evaluate the performance of CT organ segmentation algorithms trained on adult data when applied to pediatric CT volumes and identify substantial age-dependent underperformance. We subsequently propose and evaluate strategies, including data augmentation and continual learning approaches, to achieve good segmentation accuracy across all age groups. Our best-performing model, trained using continual learning, achieves high segmentation accuracy on both adult and pediatric data (Dice scores of 0.90 and 0.84 respectively). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_13185 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unlocking Robust Segmentation Across All Age Groups via Continual Learning Liu, Chih-Ying Valanarasu, Jeya Maria Jose Gonzalez, Camila Langlotz, Curtis Ng, Andrew Gatidis, Sergios Image and Video Processing Computer Vision and Pattern Recognition Most deep learning models in medical imaging are trained on adult data with unclear performance on pediatric images. In this work, we aim to address this challenge in the context of automated anatomy segmentation in whole-body Computed Tomography (CT). We evaluate the performance of CT organ segmentation algorithms trained on adult data when applied to pediatric CT volumes and identify substantial age-dependent underperformance. We subsequently propose and evaluate strategies, including data augmentation and continual learning approaches, to achieve good segmentation accuracy across all age groups. Our best-performing model, trained using continual learning, achieves high segmentation accuracy on both adult and pediatric data (Dice scores of 0.90 and 0.84 respectively). |
| title | Unlocking Robust Segmentation Across All Age Groups via Continual Learning |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.13185 |