{"id":5813,"date":"2023-09-04T03:39:49","date_gmt":"2023-09-04T03:39:49","guid":{"rendered":"https:\/\/cm.vastapps.dev\/tcia-analysis-result\/aren0532-tumor-annotations\/"},"modified":"2023-09-13T12:12:10","modified_gmt":"2023-09-13T12:12:10","slug":"aren0532-tumor-annotations","status":"publish","type":"tcia_analysis_result","link":"https:\/\/cm.vastapps.dev\/tcia-analysis-result\/aren0532-tumor-annotations\/","title":{"rendered":"AREN0532-TUMOR-ANNOTATIONS"},"featured_media":0,"template":"","cancer_types":["Wilms Tumor"],"citations":[4842,2925],"full_export":"

Summary<\/h1>

This dataset contains image annotations derived from the NCI Clinical Trial "Vincristine, Dactinomycin, and Doxorubicin With or Without Radiation Therapy or Observation Only in Treating Younger Patients Who Are Undergoing Surgery for Newly Diagnosed Stage I, Stage II, or Stage III Wilms' Tumor (AREN0532)<\/a><\/span>\u201d.\u00a0 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.<\/span><\/span><\/span><\/span><\/p>

Annotation Protocol<\/h3>

For each patient, every DICOM Study and DICOM Series was reviewed to identify and annotate the clinically relevant time points and sequences. I<\/span>n a typical patient the following annotation rules were followed:<\/span><\/p>

  1. The primary renal tumor(s) were annotated on post-contrast axial series. <\/span>Normal renal parenchyma were excluded.\u00a0<\/span><\/li>
  2. 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.\u00a0 RECIST 1.1 principles were generally be followed for lesion annotation, however, if <5 lesions measuring >1 cm were present, then smaller lesions were annotated, again up to 2 lesions per organ or 5 lesions per patient scan. Bone lesions were included if other lesions were not present.\u00a0<\/span><\/li>
  3. Lesions were labeled separately.<\/span><\/li>
  4. Seed points were automatically generated but were reviewed by a radiologist.<\/span><\/li>
  5. To ensure a high standard of accuracy and data quality, each annotation was reviewed by a secondary reader.<\/span><\/li><\/ol>

    At each time point:<\/span><\/p>

    1. A seed point (kernel) was created for each segmented structure. The seed points for each segmentation are provided in a separate DICOM RTSS file.\u00a0<\/span><\/li>
    2. SNOM<\/span>ED-CT \u201cAnatomic Region Sequence\u201d and \u201cSegmented Property Category Code Sequence\u201d and codes were inserted for all segmented structures.<\/span><\/li>
    3. Imaging time point codes were inserted to help identify each annotation in the context of the clinical trial assessment protocol.\u00a0<\/span>
      1. \u201cClinical Trial Time Point ID\u201d was used to encode time point type using one of the following strings as applicable: \u201cpre-dose\u201d or \u201cpost-chemotherapy\u201d<\/span><\/li>
      2. Content Item in \u201cAcquisition Context Sequence\u201d was added containing "Time Point Type" using Concept Code Sequence (0040,A168) selected from:<\/span>
        1. (255235001, SCT, \u201cPre-dose\u201d)<\/span><\/li>
        2. (262502001, SCT, "Post-chemotherapy")<\/span><\/li><\/ol><\/li><\/ol><\/li><\/ol>

          We believe that these are the most clinically useful annotations for radiologists as well as for future researchers. The selected sequences inform whether there is residual or recurrent tumor and assess response to therapy. <\/span><\/p>

          Important supplementary information and sample code<\/h3>
          1. A spreadsheet containing key details about the annotations is available in the\u00a0<\/span>Data Access<\/strong>\u00a0section below.<\/li>
          2. A\u00a0Jupyter notebook demonstrating how to use the\u00a0NBIA Data Retriever Command-Line Interface<\/a>\u00a0<\/span>application and the\u00a0<\/span>REST API (with authentication)<\/a>\u00a0to access these data can be found in the\u00a0Additional Resources<\/strong>\u00a0section below.<\/li><\/ol>

            <\/p>