TY - GEN
T1 - Automated Segmentation of the Hippocampus in Pediatric Imaging
AU - Rouhi, Rahimeh
AU - Tanedo, Jeffrey
AU - Wei, Iris Miao
AU - Valder, Malia
AU - Zanjal, Shreyash
AU - Gajawelli, Niharika
AU - Nelson, Marvin
AU - Deoni, Sean
AU - Wang, Yalin
AU - Linguraru, Marius George
AU - Lepore, Natasha
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - The infant hippocampus plays a pivotal role in early brain development and is linked to cognitive and memory functions. Accurate delineation of the hippocampus is essential for studying normal brain development and detecting early abnormalities associated with various neurodevelopmental disorders. In this paper, different deep neural network models were trained for 3D-automatic segmentation of the hippocampus based on cross-validation on a cohort of T1-Weighted (T1W) images acquired from 100 subjects with ground truth. The models were tested on another image cohort of 86 subjects without ground truth. Ensembling the single-trained models during cross-validation resulted in the final segmentation. Among all the trained networks, nnUNet and SegResNet achieved the best average Dice Similarity Coefficient (DSC)=0.82±0.01 and 95th Hausdorff Distance (95HD)=2.45±1.10 mm, respectively, in 5-fold cross-validation. We presented a comprehensive comparison between different architectures in terms of their generalizability and effectiveness, suggesting the potential for developing on-the-fly automated segmentation of the hippocampus in pediatric MRI.
AB - The infant hippocampus plays a pivotal role in early brain development and is linked to cognitive and memory functions. Accurate delineation of the hippocampus is essential for studying normal brain development and detecting early abnormalities associated with various neurodevelopmental disorders. In this paper, different deep neural network models were trained for 3D-automatic segmentation of the hippocampus based on cross-validation on a cohort of T1-Weighted (T1W) images acquired from 100 subjects with ground truth. The models were tested on another image cohort of 86 subjects without ground truth. Ensembling the single-trained models during cross-validation resulted in the final segmentation. Among all the trained networks, nnUNet and SegResNet achieved the best average Dice Similarity Coefficient (DSC)=0.82±0.01 and 95th Hausdorff Distance (95HD)=2.45±1.10 mm, respectively, in 5-fold cross-validation. We presented a comprehensive comparison between different architectures in terms of their generalizability and effectiveness, suggesting the potential for developing on-the-fly automated segmentation of the hippocampus in pediatric MRI.
KW - Brain development
KW - deep learning
KW - hippocampus segmentation
KW - pediatric imaging
UR - http://www.scopus.com/inward/record.url?scp=85183463326&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85183463326&partnerID=8YFLogxK
U2 - 10.1109/SIPAIM56729.2023.10373495
DO - 10.1109/SIPAIM56729.2023.10373495
M3 - Conference contribution
AN - SCOPUS:85183463326
T3 - Proceedings of the 19th International Symposium on Medical Information Processing and Analysis, SIPAIM 2023
BT - Proceedings of the 19th International Symposium on Medical Information Processing and Analysis, SIPAIM 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 19th International Symposium on Medical Information Processing and Analysis, SIPAIM 2023
Y2 - 15 November 2023 through 17 November 2023
ER -