SegRap 2023 Banner
Join

DataSet

Description

SegRap 2023 Dataset will consist of CT images collected by Siemens CT scanners with the following scanning conditions: bulb voltage, 120 kV; current, 300 mA; scan thickness, 3.0 mm; resolution, 1024 × 1024 or 512 × 512; injected contrast agent, iohexol (volume, 60~80 mL; rate, 2 mL/s; without delay). The dataset consists of clinically required contrast and non-contrast head and neck CT images from patients with nasopharyngeal cancer before treatment. 

Training data will consist of CT images from 120 nasopharynx cancer patients with a corresponding label map that was manually segmented into 45 OARs and 2 GTVs: Brain, Brainstem, Chiasm, Cochlea left, Cochlea right, Esophagus, Eustachian tube left, Eustachian tube right, Eye left, Eye right, Hippocampus left, Hippocampus right, Internal auditory canal left, Internal auditory canal right, Larynx, Larynx glottic, Larynx supraglottic, Lens left, Lens right, Mandible left, Mandible right, Mastoid left, Mastoid right, Middle Ear left, Middle ear right, Optic nerve left, Optic nerve right, Oral cavity, Parotid left, Parotid right, Pharynx, Pituitary, Spinal cord, Submandibular left, Submandibular right, Temporal lobe left, Temporal lobe right, Thyroid, Temporomandibular joint left, Temporomandibular joint right, Trachea, Tympanic cavity left, Tympanic cavity right, Vestibular semicircular canal left, Vestibular semicircular canal right, Gross Target Volume of nasopharynx (GTVnx, also named GTVp), and Gross Target Volume of lymph node (GTVnd). 

Note: All organs were annotated individually by oncologists using MIM Software and ITKSNAP, the annotation of each organ was also stored individually. Based on the above annotation flow, (1) some pixels (in the region of some neighbour organs) may be annotated with multiple types (which means some organs' annotations have some overlapped pixels.); (2) some organs are the sub-part of other organs (Hippocampus left and Hippocampus located in the Brain). We split the 45 OARs into 58 subparts (link), which can be merged into 45 OARs using a fixed strategy. For the validation and testing sets, we will refine annotation carefully again to avoid the (1) problem. Validation and testing data will consist of CT images from 20 and 60 nasopharynx cancer patients, respectively. The expected output from your algorithm should be a set of label maps.

Download

The training set with labels and the validation set without labels can be downloaded without any additional requirements, Google-Drive, Pan.Baidu, the unzipped password is segrap2023@uestc

Reference

[1] Luo, X., Fu, J., Zhong, Y., Liu, S., Han, B., Astaraki, M., Bendazzoli, S., Toma-Dasu, I., Ye, Y., Chen, Z. and Xia, Y., 2023. SegRap2023: A Benchmark of Organs-at-Risk and Gross Tumor Volume Segmentation for Radiotherapy Planning of Nasopharyngeal Carcinoma. arXiv preprint arXiv:2312.09576.
or
@article{luo2023segrap2023,
title={SegRap2023: A Benchmark of Organs-at-Risk and Gross Tumor Volume Segmentation for Radiotherapy Planning of Nasopharyngeal Carcinoma}, author={Luo, Xiangde and Fu, Jia and Zhong, Yunxin and Liu, Shuolin and Han, Bing and Astaraki, Mehdi and Bendazzoli, Simone and Toma-Dasu, Iuliana and Ye, Yiwen and Chen, Ziyang and others}, journal={arXiv preprint arXiv:2312.09576}, year={2023} }

The SegRap 2023 data from the Sichuan Cancer Hospital & Institute, Sichuan Cancer Center has been provided only for the purpose of the SegRap 2023 challenge and thus the sharing stopped after the submission deadline on July 10, 2023 (12:00 AM GMT).

In order to download the data:

  1. Download the training set from GoogleOne or BaiduNetDisk (code: 2023)
  2. Download the EndUserAgreement-SegRap2023 file and fill in and print this page for signature, then scan it.
  3. Send the signed and scanned file to xiangde.luo@std.uestc.edu.cn to get the password of the zipped training set.

Note: We just handle the real-name email and your email suffix must match your affiliation. Please rename the signed-and-scanned file to EndUserAgreement-SegRap2023-*Your-Name *(like EndUserAgreement-SegRap2023-Xiangde-Luo.pdf, just PDF format is allowed). We will send the password to each participant within two days.