Xuhua Ren1, Lei Xiang1, Dong Nie2, Yeqin Shao3, Huan Zhang4, Dinggang Shen2,5, Qian Wang1. 1. School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200030, China. 2. Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, 27599, USA. 3. Nantong University, Nantong, Jiangsu, 226019, China. 4. Department of Radiology, Ruijin Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China. 5. Department of Brain and Cognitive Engineering, Korea University, Seoul, 02841, Korea.
Abstract
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.
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.
Authors: Patrik F Raudaschl; Paolo Zaffino; Gregory C Sharp; Maria Francesca Spadea; Antong Chen; Benoit M Dawant; Thomas Albrecht; Tobias Gass; Christoph Langguth; Marcel Lüthi; Florian Jung; Oliver Knapp; Stefan Wesarg; Richard Mannion-Haworth; Mike Bowes; Annaliese Ashman; Gwenael Guillard; Alan Brett; Graham Vincent; Mauricio Orbes-Arteaga; David Cárdenas-Peña; German Castellanos-Dominguez; Nava Aghdasi; Yangming Li; Angelique Berens; Kris Moe; Blake Hannaford; Rainer Schubert; Karl D Fritscher Journal: Med Phys Date: 2017-04-21 Impact factor: 4.071
Authors: Xiaofeng Yang; Ning Wu; Guanghui Cheng; Zhengyang Zhou; David S Yu; Jonathan J Beitler; Walter J Curran; Tian Liu Journal: Int J Radiat Oncol Biol Phys Date: 2014-10-13 Impact factor: 7.038
Authors: Tri Huynh; Yaozong Gao; Jiayin Kang; Li Wang; Pei Zhang; Jun Lian; Dinggang Shen Journal: IEEE Trans Med Imaging Date: 2015-07-28 Impact factor: 10.048
Authors: Elias Tappeiner; Samuel Pröll; Markus Hönig; Patrick F Raudaschl; Paolo Zaffino; Maria F Spadea; Gregory C Sharp; Rainer Schubert; Karl Fritscher Journal: Int J Comput Assist Radiol Surg Date: 2019-03-07 Impact factor: 2.924