Interleaved 3D-CNNs for joint segmentation of small-volume structures in head and neck CT images

Xuhua Ren, Lei Xiang, Dong Nie, Yeqin Shao, Huan Zhang, Dinggang Shen, Qian Wang

Research output: Contribution to journalArticlepeer-review

104 Citations (Scopus)


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.

Original languageEnglish
Pages (from-to)2063-2075
Number of pages13
JournalMedical physics
Issue number5
Publication statusPublished - 2018 May


  • 3D convolution neural network
  • image segmentation
  • treatment planning

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging


Dive into the research topics of 'Interleaved 3D-CNNs for joint segmentation of small-volume structures in head and neck CT images'. Together they form a unique fingerprint.

Cite this