TY - JOUR
T1 - ConvNet-Based Localization of Anatomical Structures in 3-D Medical Images
AU - de Vos, Bob D.
AU - Wolterink, Jelmer M.
AU - de Jong, Pim A.
AU - Leiner, Tim
AU - Viergever, Max A.
AU - Isgum, Ivana
PY - 2017
Y1 - 2017
N2 - Localization of anatomical structures is a prerequisite for many tasks in a medical image analysis. We propose a method for automatic localization of one or more anatomical structures in 3-D medical images through detection of their presence in 2-D image slices using a convolutional neural network (ConvNet). A single ConvNet is trained to detect the presence of the anatomical structure of interest in axial, coronal, and sagittal slices extracted from a 3-D image. To allow the ConvNet to analyze slices of different sizes, spatial pyramid pooling is applied. After detection, 3-D bounding boxes are created by combining the output of the ConvNet in all slices. In the experiments, 200 chest CT, 100 cardiac CT angiography (CTA), and 100 abdomen CT scans were used. The heart, ascending aorta, aortic arch, and descending aorta were localized in chest CT scans, the left cardiac ventricle in cardiac CTA scans, and the liver in abdomen CT scans. Localization was evaluated using the distances between automatically and manually defined reference bounding box centroids and walls. The best results were achieved in the localization of structures with clearly defined boundaries (e.g., aortic arch) and the worst when the structure boundary was not clearly visible (e.g., liver). The method was more robust and accurate in localization multiple structures.
AB - Localization of anatomical structures is a prerequisite for many tasks in a medical image analysis. We propose a method for automatic localization of one or more anatomical structures in 3-D medical images through detection of their presence in 2-D image slices using a convolutional neural network (ConvNet). A single ConvNet is trained to detect the presence of the anatomical structure of interest in axial, coronal, and sagittal slices extracted from a 3-D image. To allow the ConvNet to analyze slices of different sizes, spatial pyramid pooling is applied. After detection, 3-D bounding boxes are created by combining the output of the ConvNet in all slices. In the experiments, 200 chest CT, 100 cardiac CT angiography (CTA), and 100 abdomen CT scans were used. The heart, ascending aorta, aortic arch, and descending aorta were localized in chest CT scans, the left cardiac ventricle in cardiac CTA scans, and the liver in abdomen CT scans. Localization was evaluated using the distances between automatically and manually defined reference bounding box centroids and walls. The best results were achieved in the localization of structures with clearly defined boundaries (e.g., aortic arch) and the worst when the structure boundary was not clearly visible (e.g., liver). The method was more robust and accurate in localization multiple structures.
UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85028374522&origin=inward
UR - https://www.ncbi.nlm.nih.gov/pubmed/28252392
U2 - https://doi.org/10.1109/TMI.2017.2673121
DO - https://doi.org/10.1109/TMI.2017.2673121
M3 - Article
C2 - 28252392
SN - 0278-0062
VL - 36
SP - 1470
EP - 1481
JO - IEEE Transactions on Medical Imaging
JF - IEEE Transactions on Medical Imaging
IS - 7
ER -