Annotations for ACRIN-HNSCC-FDG-PET-CT Collection

This dataset contains image annotations derived from the NCI Clinical Trial "<a href="https://doi.org/10.7937/K9/TCIA.2016.JQEJZZNG">ACRIN-HNSCC-FDG-PET-CT (ACRIN 6685)</a>”.  This dataset was generated as part of an NCI project to augment TCIA datasets with annotations that will improve their value for cancer researchers and AI developers.<h3><strong>Annotation Protocol</strong></h3>For each patient, all scans were reviewed to identify and annotate the clinically relevant time points and sequences/series. Scans were initially annotated by an international team of radiologists holding MBBS degrees or higher, which were then reviewed by US-based board-certified radiologists to ensure accuracy. In a typical patient all available time points were annotated. The following annotation rules were followed:<ol><li>PERCIST criteria was followed for PET imaging. Specifically, the lesions estimated to have the most elevated SUVmax were annotated.</li><li>RECIST 1.1 was otherwise generally followed for MR and CT imaging. A maximum of 5 lesions were annotated per patient scan (timepoint); no more than 2 per organ. The same 5 lesions were annotated at each time point. Lymph nodes were annotated if >1 cm in short axis. Other lesions were annotated if >1 cm. If the primary lesion is < 1 cm, it was still annotated.</li><li>Three-dimensional segmentations of lesions were created in the axial plane. If no axial plane was available, lesions were annotated in the coronal plane.</li><li>MRIs were annotated using the T1-weighted axial post contrast sequence, fat saturated if available.</li><li>CTs were annotated using the axial post contrast series. If not available, the non contrast series were annotated.</li><li>PET/CTs were annotated on the CT and attenuation corrected PET images.</li><li>If the post contrast CT was performed the same day as the PET/CT, the non contrast CT portion of the PET/CT was not annotated.</li><li>Lesions were labeled separately.</li><li>The volume of each annotated lesion was calculated and reported in cubic centimeters [cc] in the Annotation Metadata CSV.</li><li>Seed points were automatically generated, but reviewed by a radiologist.</li><li>A “negative” annotation was created for any exam without findings.</li></ol>At each time point:<ol><li>A seed point (kernel) was created for each segmented structure. The seed points for each segmentation are provided in a separate DICOM RTSTRUCT file.</li><li>SNOMED-CT “Anatomic Region Sequence” and “Segmented Property Category Code Sequence” and codes were inserted for all segmented structures.</li><li>“Tracking ID” and “Tracking UID” tags were inserted for each segmented structure to enable longitudinal lesion tracking.</li><li>Imaging time point codes were inserted to help identify each annotation in the context of the clinical trial assessment protocol.<ol><li>“Clinical Trial Time Point ID” was used to encode time point type using one of the following strings as applicable: “pre-dose” or “post-chemotherapy”.</li><li>Content Item in “Acquisition Context Sequence” was added containing "Time Point Type" using Concept Code Sequence (0040,A168) selected from:<ol><li>(255235001, SCT, “Pre-dose”) (in this trial, both the CT/MRI and PET/CT, while being different timepoints, are pre-treatment)</li></ol></li></ol></li></ol><h3>Important supplementary information and sample code</h3><ol><li>A spreadsheet containing key details about the annotations is available in the <strong>Data Access</strong> section below.</li><li>A Jupyter notebook demonstrating how to use the <a href="https://wiki.cancerimagingarchive.net/display/NBIA/NBIA+Data+Retriever+Command-Line+Interface+Guide">NBIA Data Retriever Command-Line Interface</a> application and the <a href="https://wiki.cancerimagingarchive.net/display/Public/NBIA+Search+with+Authentication+REST+API+Guide">REST API</a> to access these data can be found in the <strong>Additional Resources</strong> section below.</li></ol>

本数据集收录了源自美国国家癌症研究所临床试验（ACRIN Clinical Trial <a href="https://doi.org/10.7937/K9/TCIA.2016.JQEJZZNG">ACRIN-HNSCC-FDG-PET-CT (ACRIN 6685)</a>”的图像标注。该数据集的生成旨在作为国家癌症研究所（NCI）项目的一部分，以增强TCIA数据集的标注，从而提升其对于癌症研究人员和人工智能开发者的价值。以下为标注协议的详细说明：

对于每位患者，所有扫描均经审查以识别并标注临床相关的时间点及序列/系列。初期的标注由持有MBBS学位或以上资格的国际放射科医生团队完成，随后由美国认证的放射科医生进行复核以确保准确性。在典型患者中，所有可用的时点均进行了标注。遵循以下标注规则：

1. 对于正电子发射断层扫描（PET）成像，遵循PERCIST标准。具体而言，标注了SUVmax值最高的病变。
2. 对于磁共振成像（MRI）和计算机断层扫描（CT）成像，一般遵循RECIST 1.1标准。每位患者扫描（时点）最多标注5个病变，每个器官不超过2个。每个时点标注相同的5个病变。若淋巴结短轴直径大于1厘米，则进行标注。其他病变若直径大于1厘米，亦进行标注。若原发灶直径小于1厘米，仍需进行标注。
3. 在轴向平面上创建了病变的三维分割。若无轴向平面可用，则在冠状平面上进行标注。
4. 若可用，使用T1加权轴位对比增强序列对MRI进行标注，若不可用，则使用脂肪饱和序列。
5. 使用轴位对比增强序列对CT进行标注。若不可用，则标注非对比增强序列。
6. 在CT和衰减校正的PET图像上进行PET/CT的标注。
7. 若对比增强CT与PET/CT在同一天进行，则PET/CT的非对比增强部分不进行标注。
8. 对病变进行单独标注。
9. 计算并报告每个标注病变的体积，单位为立方厘米[cc]，详见标注元数据CSV文件。
10. 自动生成种子点，但需由放射科医生进行复核。
11. 对于无发现结果的任何检查，创建“阴性”标注。

在每个时点：
1. 为每个分割结构创建一个种子点（内核）。每个分割的种子点以单独的DICOM RTSTRUCT文件提供。
2. 插入SNOMED-CT“解剖区域序列”和“分割属性类别代码序列”及代码，涵盖所有分割结构。
3. 为每个分割结构插入“跟踪ID”和“跟踪UID”标签，以实现纵向病变跟踪。
4. 插入成像时间点代码，以帮助在临床试验评估协议的背景下识别每个标注。
- 使用“临床试验时间点ID”对时间点类型进行编码，采用以下字符串之一：'pre-dose'或'post-chemotherapy'。
- 在“采集上下文序列”中添加“时间点类型”，使用概念代码序列（0040,A168）选择，如下所示：
- (255235001, SCT, “Pre-dose”）（在本试验中，CT/MRI和PET/CT虽为不同时间点，但均为治疗前）。

重要补充信息和示例代码：
1. 包含标注关键细节的电子表格可在下方的“数据访问”部分找到。
2. 展示如何使用NBIA数据检索命令行界面应用和REST API访问这些数据的Jupyter笔记本可在下方的“附加资源”部分找到。