TY - JOUR
T1 - Interleaved 3D-CNNs for joint segmentation of small-volume structures in head and neck CT images
AU - Ren, Xuhua
AU - Xiang, Lei
AU - Nie, Dong
AU - Shao, Yeqin
AU - Zhang, Huan
AU - Shen, Dinggang
AU - Wang, Qian
N1 - Funding Information:
This research was supported by the grants from National Natural Science Foundation of China (61473190, 81471733, 61671255), National Key R&D Program of China (2017YFC0107600), Science and Technology Commission of Shanghai Municipality (16511101100, 16410722400).
Publisher Copyright:
© 2018 American Association of Physicists in Medicine
PY - 2018/5
Y1 - 2018/5
N2 - Purpose: Accurate 3D image segmentation is a crucial step in radiation therapy planning of head and neck tumors. These segmentation results are currently obtained by manual outlining of tissues, which is a tedious and time-consuming procedure. Automatic segmentation provides an alternative solution, which, however, is often difficult for small tissues (i.e., chiasm and optic nerves in head and neck CT images) because of their small volumes and highly diverse appearance/shape information. In this work, we propose to interleave multiple 3D Convolutional Neural Networks (3D-CNNs) to attain automatic segmentation of small tissues in head and neck CT images. Method: A 3D-CNN was designed to segment each structure of interest. To make full use of the image appearance information, multiscale patches are extracted to describe the center voxel under consideration and then input to the CNN architecture. Next, as neighboring tissues are often highly related in the physiological and anatomical perspectives, we interleave the CNNs designated for the individual tissues. In this way, the tentative segmentation result of a specific tissue can contribute to refine the segmentations of other neighboring tissues. Finally, as more CNNs are interleaved and cascaded, a complex network of CNNs can be derived, such that all tissues can be jointly segmented and iteratively refined. Result: Our method was validated on a set of 48 CT images, obtained from the Medical Image Computing and Computer Assisted Intervention (MICCAI) Challenge 2015. The Dice coefficient (DC) and the 95% Hausdorff Distance (95HD) are computed to measure the accuracy of the segmentation results. The proposed method achieves higher segmentation accuracy (with the average DC: 0.58 ± 0.17 for optic chiasm, and 0.71 ± 0.08 for optic nerve; 95HD: 2.81 ± 1.56 mm for optic chiasm, and 2.23 ± 0.90 mm for optic nerve) than the MICCAI challenge winner (with the average DC: 0.38 for optic chiasm, and 0.68 for optic nerve; 95HD: 3.48 for optic chiasm, and 2.48 for optic nerve). Conclusion: An accurate and automatic segmentation method has been proposed for small tissues in head and neck CT images, which is important for the planning of radiotherapy.
AB - Purpose: Accurate 3D image segmentation is a crucial step in radiation therapy planning of head and neck tumors. These segmentation results are currently obtained by manual outlining of tissues, which is a tedious and time-consuming procedure. Automatic segmentation provides an alternative solution, which, however, is often difficult for small tissues (i.e., chiasm and optic nerves in head and neck CT images) because of their small volumes and highly diverse appearance/shape information. In this work, we propose to interleave multiple 3D Convolutional Neural Networks (3D-CNNs) to attain automatic segmentation of small tissues in head and neck CT images. Method: A 3D-CNN was designed to segment each structure of interest. To make full use of the image appearance information, multiscale patches are extracted to describe the center voxel under consideration and then input to the CNN architecture. Next, as neighboring tissues are often highly related in the physiological and anatomical perspectives, we interleave the CNNs designated for the individual tissues. In this way, the tentative segmentation result of a specific tissue can contribute to refine the segmentations of other neighboring tissues. Finally, as more CNNs are interleaved and cascaded, a complex network of CNNs can be derived, such that all tissues can be jointly segmented and iteratively refined. Result: Our method was validated on a set of 48 CT images, obtained from the Medical Image Computing and Computer Assisted Intervention (MICCAI) Challenge 2015. The Dice coefficient (DC) and the 95% Hausdorff Distance (95HD) are computed to measure the accuracy of the segmentation results. The proposed method achieves higher segmentation accuracy (with the average DC: 0.58 ± 0.17 for optic chiasm, and 0.71 ± 0.08 for optic nerve; 95HD: 2.81 ± 1.56 mm for optic chiasm, and 2.23 ± 0.90 mm for optic nerve) than the MICCAI challenge winner (with the average DC: 0.38 for optic chiasm, and 0.68 for optic nerve; 95HD: 3.48 for optic chiasm, and 2.48 for optic nerve). Conclusion: An accurate and automatic segmentation method has been proposed for small tissues in head and neck CT images, which is important for the planning of radiotherapy.
KW - 3D convolution neural network
KW - image segmentation
KW - treatment planning
UR - http://www.scopus.com/inward/record.url?scp=85044227753&partnerID=8YFLogxK
U2 - 10.1002/mp.12837
DO - 10.1002/mp.12837
M3 - Article
C2 - 29480928
AN - SCOPUS:85044227753
SN - 0094-2405
VL - 45
SP - 2063
EP - 2075
JO - Medical Physics
JF - Medical Physics
IS - 5
ER -