Premium
Segmentation of organs‐at‐risks in head and neck CT images using convolutional neural networks
Author(s) -
Ibragimov Bulat,
Xing Lei
Publication year - 2017
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1002/mp.12045
Subject(s) - voxel , artificial intelligence , computer science , convolutional neural network , segmentation , pattern recognition (psychology) , deep learning , image segmentation , artificial neural network , computer vision
Purpose Accurate segmentation of organs‐at‐risks ( OAR s) is the key step for efficient planning of radiation therapy for head and neck (HaN) cancer treatment. In the work, we proposed the first deep learning‐based algorithm, for segmentation of OAR s in HaN CT images, and compared its performance against state‐of‐the‐art automated segmentation algorithms, commercial software, and interobserver variability. Methods Convolutional neural networks ( CNN s)—a concept from the field of deep learning—were used to study consistent intensity patterns of OAR s from training CT images and to segment the OAR in a previously unseen test CT image. For CNN training, we extracted a representative number of positive intensity patches around voxels that belong to the OAR of interest in training CT images, and negative intensity patches around voxels that belong to the surrounding structures. These patches then passed through a sequence of CNN layers that captured local image features such as corners, end‐points, and edges, and combined them into more complex high‐order features that can efficiently describe the OAR . The trained network was applied to classify voxels in a region of interest in the test image where the corresponding OAR is expected to be located. We then smoothed the obtained classification results by using Markov random fields algorithm. We finally extracted the largest connected component of the smoothed voxels classified as the OAR by CNN , performed dilate–erode operations to remove cavities of the component, which resulted in segmentation of the OAR in the test image. Results The performance of CNN s was validated on segmentation of spinal cord, mandible, parotid glands, submandibular glands, larynx, pharynx, eye globes, optic nerves, and optic chiasm using 50 CT images. The obtained segmentation results varied from 37.4% Dice coefficient ( DSC ) for chiasm to 89.5% DSC for mandible. We also analyzed the performance of state‐of‐the‐art algorithms and commercial software reported in the literature, and observed that CNN s demonstrate similar or superior performance on segmentation of spinal cord, mandible, parotid glands, larynx, pharynx, eye globes, and optic nerves, but inferior performance on segmentation of submandibular glands and optic chiasm. Conclusion We concluded that convolution neural networks can accurately segment most of OAR s using a representative database of 50 HaN CT images. At the same time, inclusion of additional information, for example, MR images, may be beneficial to some OAR s with poorly visible boundaries.