TY - GEN
T1 - Deep learning for multi-task medical image segmentation in multiple modalities
AU - Moeskops, Pim
AU - Wolterink, Jelmer M.
AU - van der Velden, Bas H.M.
AU - Gilhuijs, Kenneth G.A.
AU - Leiner, Tim
AU - Viergever, Max A.
AU - Išgum, Ivana
N1 - Conference code: 19
PY - 2016/1/1
Y1 - 2016/1/1
N2 - Automatic segmentation of medical images is an important task for many clinical applications. In practice,a wide range of anatomical structures are visualised using different imaging modalities. In this paper,we investigate whether a single convolutional neural network (CNN) can be trained to perform different segmentation tasks. A single CNN is trained to segment six tissues in MR brain images,the pectoral muscle in MR breast images,and the coronary arteries in cardiac CTA. The CNN therefore learns to identify the imaging modality,the visualised anatomical structures,and the tissue classes. For each of the three tasks (brain MRI,breast MRI and cardiac CTA),this combined training procedure resulted in a segmentation performance equivalent to that of a CNN trained specifically for that task,demonstrating the high capacity of CNN architectures. Hence,a single system could be used in clinical practice to automatically perform diverse segmentation tasks without task-specific training.
AB - Automatic segmentation of medical images is an important task for many clinical applications. In practice,a wide range of anatomical structures are visualised using different imaging modalities. In this paper,we investigate whether a single convolutional neural network (CNN) can be trained to perform different segmentation tasks. A single CNN is trained to segment six tissues in MR brain images,the pectoral muscle in MR breast images,and the coronary arteries in cardiac CTA. The CNN therefore learns to identify the imaging modality,the visualised anatomical structures,and the tissue classes. For each of the three tasks (brain MRI,breast MRI and cardiac CTA),this combined training procedure resulted in a segmentation performance equivalent to that of a CNN trained specifically for that task,demonstrating the high capacity of CNN architectures. Hence,a single system could be used in clinical practice to automatically perform diverse segmentation tasks without task-specific training.
KW - Brain MRI
KW - Breast MRI
KW - Cardiac CTA
KW - Convolutional neural networks
KW - Deep learning
KW - Medical image segmentation
UR - http://www.scopus.com/inward/record.url?scp=84996503302&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-46723-8_55
DO - 10.1007/978-3-319-46723-8_55
M3 - Conference contribution
AN - SCOPUS:84996503302
SN - 978-3-319-46722-1
VL - II
T3 - Lecture Notes in Computer Science
SP - 478
EP - 486
BT - Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016
A2 - Unal, Gozde
A2 - Ourselin, Sebastian
A2 - Joskowicz, Leo
A2 - Sabuncu, Mert R.
A2 - Wells, William
PB - Springer
CY - Cham
T2 - 19th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2016
Y2 - 17 October 2016 through 21 October 2016
ER -