Segmentation of organs-at-risks in head and neck CT images using convolutional neural networks

By Bulat Ibragimov, Lei Xing. 2017

472 citations recorded by the source corpus.

Purpose: Accurate segmentation of organs‐at‐risks (OARs) 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 OARs 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 (CNNs)—a concept from the field of deep learning—were used to study consistent intensity patterns of OARs 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 CNNs 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 CNNs 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 OARs 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 OARs with poorly visible boundaries.

Subfields: Oral Surgery, Otorhinolaryngology, Radiation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Oral Surgery

In Otorhinolaryngology

Arvid Lundervold

In Radiation

Citations in the corpus

An overview of deep learning in medical imaging focusing on MRI (2018, background): “example acute ischemic lesion segmentation in DWI [262]; brain tumor segmentation [263]; segmentation of the striatum [264]; segmentation of organs-at-risks in head and neck CT images [265]; and fully automated segmentation of polycystic kidneys [266]; deformable segmentation of the prostate [267]; ”
Deep Reinforcement Learning for Automated Radiation Adaptation in Lung Cancer (2017, background): “while at the same time providing superior performance [7]-[8].”
Artificial intelligence and machine learning for medical imaging: A technology review. (2021, unknown): “Classification can be binary, like in determining whether a pathology is present or not in an image [25,27], involve multiple classes, as in determining a particular pathology among several labels [28 – 30], or concern not the whole image but each pixel, as done for image segmentation [31,32].”
Deep learning in medical imaging and radiation therapy. (2018, methodology): “76,83 Table I briefly summarizes published performance of DL methods in organ and substructure segmentation tasks using either Dice coefficient or Jaccard index, if given, as the performance metric.”
Modified U-Net (mU-Net) with Incorporation of Object-Dependent High Level Features for Improved Liver and Liver-Tumor Segmentation in CT Images (2019, methodology): “emerged and have been applied for liver [11]–[14], head and neck [15], [16], prostate [17], and brain [18], [19]”
Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy (2018, background): “Some of them use standard classiﬁcation networks on patches [30, 31, 32, 33] with tailored pre-and post-processing, while others also use U-Net based architectures [34, 35, 36].”