Your browser doesn't support javascript.
loading
Children Are Not Small Adults: Addressing Limited Generalizability of an Adult Deep Learning CT Organ Segmentation Model to the Pediatric Population.
Chatterjee, Devina; Kanhere, Adway; Doo, Florence X; Zhao, Jerry; Chan, Andrew; Welsh, Alexander; Kulkarni, Pranav; Trang, Annie; Parekh, Vishwa S; Yi, Paul H.
Afiliación
  • Chatterjee D; Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, USA.
  • Kanhere A; Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, USA.
  • Doo FX; Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, USA.
  • Zhao J; Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, USA.
  • Chan A; Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, USA.
  • Welsh A; Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, USA.
  • Kulkarni P; Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, USA.
  • Trang A; Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, USA.
  • Parekh VS; Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, USA.
  • Yi PH; Department of Diagnostic Imaging, St. Jude Children's Research Hospital, 262 Danny Thomas Place, Memphis, 38105 TN, USA. paul.yi@stjude.org.
J Imaging Inform Med ; 2024 Sep 19.
Article en En | MEDLINE | ID: mdl-39299957
ABSTRACT
Deep learning (DL) tools developed on adult data sets may not generalize well to pediatric patients, posing potential safety risks. We evaluated the performance of TotalSegmentator, a state-of-the-art adult-trained CT organ segmentation model, on a subset of organs in a pediatric CT dataset and explored optimization strategies to improve pediatric segmentation performance. TotalSegmentator was retrospectively evaluated on abdominal CT scans from an external adult dataset (n = 300) and an external pediatric data set (n = 359). Generalizability was quantified by comparing Dice scores between adult and pediatric external data sets using Mann-Whitney U tests. Two DL optimization approaches were then evaluated (1) 3D nnU-Net model trained on only pediatric data, and (2) an adult nnU-Net model fine-tuned on the pediatric cases. Our results show TotalSegmentator had significantly lower overall mean Dice scores on pediatric vs. adult CT scans (0.73 vs. 0.81, P < .001) demonstrating limited generalizability to pediatric CT scans. Stratified by organ, there was lower mean pediatric Dice score for four organs (P < .001, all) right and left adrenal glands (right adrenal, 0.41 [0.39-0.43] vs. 0.69 [0.66-0.71]; left adrenal, 0.35 [0.32-0.37] vs. 0.68 [0.65-0.71]); duodenum (0.47 [0.45-0.49] vs. 0.67 [0.64-0.69]); and pancreas (0.73 [0.72-0.74] vs. 0.79 [0.77-0.81]). Performance on pediatric CT scans improved by developing pediatric-specific models and fine-tuning an adult-trained model on pediatric images where both methods significantly improved segmentation accuracy over TotalSegmentator for all organs, especially for smaller anatomical structures (e.g., > 0.2 higher mean Dice for adrenal glands; P < .001).
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: J Imaging Inform Med Año: 2024 Tipo del documento: Article País de afiliación: Estados Unidos Pais de publicación: Suiza
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: J Imaging Inform Med Año: 2024 Tipo del documento: Article País de afiliación: Estados Unidos Pais de publicación: Suiza