HaN‐Seg: The head and neck organ‐at‐risk CT and MR segmentation dataset

Abstract

For the cancer in the head and neck (HaN), radiotherapy (RT) represents an important treatment modality. Segmentation of organs-at-risk (OARs) is the starting point of RT planning,however,existing approaches are focused on either computed tomography (CT) or magnetic resonance (MR) images, while multimodal segmentation has not been thoroughly explored yet. We present a dataset of CT and MR images of the same patients with curated reference HaN OAR segmentations for an objective evaluation of segmentation methods. Acquisition and validation methods:The cohort consists of HaN images of 56 patients that underwent both CT and T1-weighted MR imaging for imageguided RT. For each patient, reference segmentations of up to 30 OARs were obtained by experts performing manual pixel-wise image annotation. By maintaining the distribution of patient age and gender, and annotation type, the patients were randomly split into training Set 1 (42 cases or 75%) and test Set 2 (14 cases or 25%). Baseline auto-segmentation results are also provided by training the publicly available deep nnU-Net architecture on Set 1, and evaluating its performance on Set 2. Data format and usage notes: The data are publicly available through an openaccess repository under the name HaN-Seg: The Head and Neck Organ-at-Risk CT & MR Segmentation Dataset. Images and reference segmentations are stored in the NRRD file format, where the OAR filenames correspond to the nomenclature recommended by the American Association of Physicists in Medicine,and OAR and demographics information is stored in separate commaseparated value files. Potential applications: The HaN-Seg: The Head and Neck Organ-at-Risk CT & MR Segmentation Challenge is launched in parallel with the dataset release to promote the development of automated techniques for OAR segmentation in the HaN. Other potential applications include out-of -challenge algorithm development and benchmarking, as well as external validation of the developed algorithms.

vOARiability: Interobserver and intermodality variability analysis in OAR contouring from head and neck CT and MR images

“…15,16 The baseline auto-segmentation experiments and results, performed and obtained for the images used in this study, 53 indicate that there is still room for improvements that can be leveraged by applying custom solutions, for example, tailored CT and MR modality feature fusion module techniques. 54 Our study is not without limitations. First, although observers were asked to mimic clinical practice, contouring was performed retrospectively and the observers were aware that their results would not be used for RT planning.Second,there were only two contour sets available for each CT and MR image, and normally more contours would be required, preferably from multiple institutions,for a more reliable variability analysis.Finally, the variability analysis was performed by comparing the obtained contours, but preferably a consensus in the form of ground truth contours would represent a better comparison reference.…”

“…[13][14][15][16] On the other hand, automated contouring (i.e., automated segmentation, auto-segmentation) performed by computerassisted algorithms 17 has witnessed a revival with the introduction and integration of artificial intelligence approaches, such as deep learning, [18][19][20][21][22][23][24][25][26] which has outperformed the previously established atlas-based auto-segmentation. 27 As a result, computational challenges were organized to evaluate the quality of auto-segmentation results, 28 and several datasets were made publicly available for benchmarking different auto-segmentation methodologies 20,[28][29][30][31] and evaluating their clinical acceptability. 32 However, even with sophisticated auto-segmentation approaches, manual contouring is still the method of choice for evaluating and benchmarking the performance of the developed algorithms.…”

“…The MR modality has been long recognized as valuable for contouring OARs in the HaN region, [45][46][47][48] however, to the best of our knowledge, the accuracy and consistency of the resulting OAR contours have not been yet objectively evaluated. In this study, we therefore analyze the interobserver and intermodality variability of manual contouring of up to 31 OARs in the HaN region, performed by observers with different level of experience from CT and MR images of the same patients.Besides providing valuable insights to the levels of both interobserver and intermodality variability from the perspective of manual OAR contouring, the obtained results can be also viewed as a baseline for an objective evaluation of methods for auto-segmentation of OARs in the HaN region, 31 which have been rapidly evolving during the past decade due to the integration of artificial intelligence, and received a considerable boost in performance due to the advances in deep learning. [18][19][20][21][22][23][24][25][26] F I G U R E 1 Example of a CT (top row) and MR (bottom row) image of the same patient from the devised cohort, displayed in mid-axial (left), mid-coronal (middle), and mid-sagittal (right) cross-sections.…”

“…In this study, we therefore analyze the interobserver and intermodality variability of manual contouring of up to 31 OARs in the HaN region, performed by observers with different level of experience from CT and MR images of the same patients. Besides providing valuable insights to the levels of both interobserver and intermodality variability from the perspective of manual OAR contouring, the obtained results can be also viewed as a baseline for an objective evaluation of methods for auto‐segmentation of OARs in the HaN region, 31 which have been rapidly evolving during the past decade due to the integration of artificial intelligence, and received a considerable boost in performance due to the advances in deep learning 18–26 …”

Essential parameters needed for a U-Net-based segmentation of individual bones on planning CT images in the head and neck region using limited datasets for radiotherapy application

“…Furthermore, we compared the prediction capability of our best experimental scenario to benchmark segmentation tools. Finally, our model was evaluated using cohorts from the HaN-Seg challenge 2023 (Podobnik et al 2023) to quantify how our model generalizes to patients acquired using different protocols and acquisition parameters.…”