TY - JOUR
T1 - Multi atlas based segmentation
T2 - Should we prefer the best atlas group over the group of best atlases?
AU - Zaffino, Paolo
AU - Ciardo, Delia
AU - Raudaschl, Patrik
AU - Fritscher, Karl
AU - Ricotti, Rosalinda
AU - Alterio, Daniela
AU - Marvaso, Giulia
AU - Fodor, Cristiana
AU - Baroni, Guido
AU - Amato, Francesco
AU - Orecchia, Roberto
AU - Jereczek-Fossa, Barbara Alicja
AU - Sharp, Gregory C.
AU - Spadea, Maria Francesca
PY - 2018/6/19
Y1 - 2018/6/19
N2 - Multi atlas based segmentation (MABS) uses a database of atlas images, and an atlas selection process is used to choose an atlas subset for registration and voting. In the current state of the art, atlases are chosen according to a similarity criterion between the target subject and each atlas in the database. In this paper, we propose a new concept for atlas selection that relies on selecting the best performing group of atlases rather than the group of highest scoring individual atlases. Experiments were performed using CT images of 50 patients, with contours of brainstem and parotid glands. The dataset was randomly split into two groups: 20 volumes were used as an atlas database and 30 served as target subjects for testing. Classic oracle selection, where atlases are chosen by the highest dice similarity coefficient (DSC) with the target, was performed. This was compared to oracle group selection, where all the combinations of atlas subgroups were considered and scored by computing DSC with the target subject. Subsequently, convolutional neural networks were designed to predict the best group of atlases. The results were also compared with the selection strategy based on normalized mutual information (NMI). Oracle group was proven to be significantly better than classic oracle selection (p < 10-5). Atlas group selection led to a median ± interquartile DSC of 0.740 ± 0.084, 0.718 ± 0.086 and 0.670 ± 0.097 for brainstem and left/right parotid glands respectively, outperforming NMI selection 0.676 ± 0.113, 0.632 ± 0.104 and 0.606 ± 0.118 (p < 0.001) as well as classic oracle selection. The implemented methodology is a proof of principle that selecting the atlases by considering the performance of the entire group of atlases instead of each single atlas leads to higher segmentation accuracy, being even better then current oracle strategy. This finding opens a new discussion about the most appropriate atlas selection criterion for MABS.
AB - Multi atlas based segmentation (MABS) uses a database of atlas images, and an atlas selection process is used to choose an atlas subset for registration and voting. In the current state of the art, atlases are chosen according to a similarity criterion between the target subject and each atlas in the database. In this paper, we propose a new concept for atlas selection that relies on selecting the best performing group of atlases rather than the group of highest scoring individual atlases. Experiments were performed using CT images of 50 patients, with contours of brainstem and parotid glands. The dataset was randomly split into two groups: 20 volumes were used as an atlas database and 30 served as target subjects for testing. Classic oracle selection, where atlases are chosen by the highest dice similarity coefficient (DSC) with the target, was performed. This was compared to oracle group selection, where all the combinations of atlas subgroups were considered and scored by computing DSC with the target subject. Subsequently, convolutional neural networks were designed to predict the best group of atlases. The results were also compared with the selection strategy based on normalized mutual information (NMI). Oracle group was proven to be significantly better than classic oracle selection (p < 10-5). Atlas group selection led to a median ± interquartile DSC of 0.740 ± 0.084, 0.718 ± 0.086 and 0.670 ± 0.097 for brainstem and left/right parotid glands respectively, outperforming NMI selection 0.676 ± 0.113, 0.632 ± 0.104 and 0.606 ± 0.118 (p < 0.001) as well as classic oracle selection. The implemented methodology is a proof of principle that selecting the atlases by considering the performance of the entire group of atlases instead of each single atlas leads to higher segmentation accuracy, being even better then current oracle strategy. This finding opens a new discussion about the most appropriate atlas selection criterion for MABS.
KW - atlas selection
KW - convolutional neural network
KW - medical image segmentation
KW - multi atlas based segmentation
KW - oracle selection
UR - http://www.scopus.com/inward/record.url?scp=85049364652&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85049364652&partnerID=8YFLogxK
U2 - 10.1088/1361-6560/aac712
DO - 10.1088/1361-6560/aac712
M3 - Article
AN - SCOPUS:85049364652
VL - 63
JO - Physics in Medicine and Biology
JF - Physics in Medicine and Biology
SN - 0031-9155
IS - 12
M1 - 12NT01
ER -