NCI Data Jamboree (Project Abstract Submission): Submission #54

serial: '54'
sid: '189168'
uuid: 0a2df779-5b64-4d31-8077-5266df612d92
uri: /nci/datajamboree/abstractsubmission
created: '1785181531'
completed: '1785182175'
changed: '1785182175'
in_draft: '0'
current_page: ''
remote_addr: 10.208.24.192
uid: '0'
langcode: en
webform_id: nci_data_jamboree_abstracts
entity_type: node
entity_id: '2272'
locked: '0'
sticky: '0'
notes: ''
metatag: meta
data:
  list_of_additional_authors:
    - add_author_letters: Ph.D.
      affiliation: 'Oak Ridge National Laboratory'
      first_name: Xi
      last_name: Zhang
    - add_author_letters: Ph.D.
      affiliation: 'Oak Ridge National Laboratory'
      first_name: Ankita
      last_name: Paul
    - add_author_letters: Ph.D.
      affiliation: 'Oak Ridge National Laboratory'
      first_name: Ethan
      last_name: Seefried
  category: 'Employing statistical, computational, and informatics tools, algorithms, and methods to integrate or analyze data'
  degree_s_: Ph.D.
  email: chandrashekm@ornl.gov
  first_name: Mayanka
  keywords_abstracts: 'whole-slide imaging; foundation-model embeddings; '
  last_name: 'Chandra Shekar'
  middle_initial: ''
  organization: 'Oak Ridge National Laboratory'
  organization_address:
    address: ''
    address_2: ''
    city: Knoxville
    country: ''
    postal_code: ''
    state_province: ''
  summary: |
    Pediatric cancers are rare and morphologically heterogeneous, making it difficult to develop robust whole-slide image classification models. RADIANCE is a pathology data project that creates reusable foundation-model embeddings and links them to patch coordinates, slide and specimen identifiers, model provenance, and available clinical metadata.
    During the 3-days, we will evaluate whether embeddings contain sufficient information for pediatric cancer classification. Using whole-slide images from the CCDI MCI, we will select a cohort with suitable diagnostic labels and train a model to classify cancer or histologic subtypes. We will first establish a baseline that treats patch embeddings as an unordered collection. We will then evaluate a hierarchical approach that incorporates patch locations and relationships among neighboring tissue regions. The primary technical question is whether spatially organized aggregation improves classification compared with conventional non-spatial aggregation.
    This project is relevant to the broader cancer data community because generating foundation-model embeddings from whole-slide images is computationally expensive. Evaluating reusable embeddings for a concrete downstream task will help determine whether they can support multiple studies without repeatedly processing the source images. We also intend to share the resulting vector database as a resource for the community to use in whole-slide image downstream tasks. The workflow may also provide a template for classification, cohort discovery, case retrieval, and other pathology applications.
    The work will require expertise in computational pathology, pediatric cancer, machine learning, and data engineering. Expected tools include Python, PyTorch, pathology foundation-model embeddings, the Milvus vector database for embedding storage and retrieval, and GPU-enabled computing on OLCF’s Frontier supercomputing platform for model training and evaluation. We have assembled a ready-to-go team from Oak Ridge National Laboratory.  
    Mayanka ChandraShekar (in-person), Ethan Seefried (in-person), Xi Zhang (online), Ankita Paul (online)
  title: 'Research Scientist'
  ttile: 'Hierarchical, Spatially Aware Whole-Slide Image Classification for Pediatric Cancer Using RADIANCE'