Auto‐segmentation of organs at risk for head and neck radiotherapy planning: From atlas‐based to deep learning methods

Abstract

Radiotherapy (RT) is one of the basic treatment modalities for cancer of the head and neck (H&N), which requires a precise spatial description of the target volumes and organs at risk (OARs) to deliver a highly conformal radiation dose to the tumor cells while sparing the healthy tissues. For this purpose, target volumes and OARs have to be delineated and segmented from medical images. As manual delineation is a tedious and time-consuming task subjected to intra/interobserver variability, computerized auto-segmentation has been developed as an alternative. The field of medical imaging and RT planning has experienced an increased interest in the past decade, with new emerging trends that shifted the field of H&N OAR auto-segmentation from atlas-based to deep learning-based approaches. In this review, we systematically analyzed 78 relevant publications on auto-segmentation of OARs in the H&N region from 2008 to date, and provided critical discussions and recommendations from various perspectives: image modalityboth computed tomography and magnetic resonance image modalities are being exploited, but the potential of the latter should be explored more in the future; OARthe spinal cord, brainstem, and major salivary glands are the most studied OARs, but additional experiments should be conducted for several less studied soft tissue structures; image databaseseveral image databases with the corresponding ground truth are currently available for methodology evaluation, but should be augmented with data from multiple observers and multiple institutions; methodologycurrent methods have shifted from atlas-based to deep learning autosegmentation, which is expected to become even more sophisticated; ground truthdelineation guidelines should be followed and participation of multiple experts from multiple institutions is recommended; performance metricsthe Dice coefficient as the standard volumetric overlap metrics should be accompanied with at least one distance metrics, and combined with clinical acceptability scores and risk assessments; segmentation performancethe best performing methods achieve clinically acceptable auto-segmentation for several OARs, however, the dosimetric impact should be also studied to provide clinically relevant endpoints for RT planning.

Review of Deep Learning Based Automatic Segmentation for Lung Cancer Radiotherapy

“…It can not only shorten the time needed to exploit the anatomy but also allow experts to devote time to optimize RT treatment planning so that the OARs could be less irradiated. In recent years, various image segmentation techniques have been proposed, resulting in more accurate and efficient image segmentation for clinical diagnosis and treatment (18)(19)(20)(21)(22)(23)(24).…”

A Preliminary Experience of Implementing Deep-Learning Based Auto-Segmentation in Head and Neck Cancer: A Study on Real-World Clinical Cases

“… The box plot results of auto-segmentation of OARs in HNC reported in terms of the Dice coefficient ( 22 ). The red mark dots are the Dice coefficient in our second phase training results.…”

“…The major evident advantage of DL-based autosegmentation is that it can systematically learn the adequate features, which was never possible with the naked eye for segmentation, from a large amount of a given training database. Then, the same features can be searched automatically in a validation set ( 22 ).…”

“…Second, it is extremely difficult to compare the segmentation performance between these state-of-the-art techniques directly, because they do not, in general, provide detailed statistical descriptions (e.g., image acquisition setups, image properties, manual delineation guidelines and patient cohorts) of the corresponding gold-standard. Furthermore, different performance metrics are often used in these studies for different OARs ( 22 ). As an emerging clinically relevant tool, therefore, adequate assessment methods that relate more directly to clinical judgment of contours are required.…”

Auto-segmentations by convolutional neural network in cervical and anorectal cancer with clinical structure sets as the ground truth

“…CNN-based methods have proven highly accurate for automated segmentation in magnetic resonance imaging (MRI) of the prostate, CT of the liver and bladder, and PET/CT images of skeletal structures [7] , [8] , [9] , [10] , [11] . Furthermore, in the field of radiation oncology, studies on head and neck cancer have adhered to the fact that correctly implemented AI techniques generates better efficiency and standardization of treatment for patients with head and neck cancer [12] , [13] , [14] . In the case of rectal cancer, a previous study evaluated the auto-segmentation of target volume and OAR, and showed varying segmentation accuracy based on the Dice similarity coefficient ranging from 61.8% (colon) to 93.4% (bladder) [15] .…”