A Deep Learning Strategy to Integrate Karyometric Features with Underlying Molecular Pathways in Ovarian Cancer Initiation

Abstract

High-grade serous ovarian carcinoma is an aggressive cancer type that primarily affects postmenopausal women and usually originates in the fallopian tube cells. However, the exact process of how these cells transform into cancer isn't fully understood. The goal of the proposed project is to provide comprehensive biological information about the early steps in ovarian carcinogenesis that could be used as targets for ovarian cancer prevention. The biological information is gathered from tissue images, omics-based analyses, and processed by machine learning tools to be linked with outcomes data for in-depth biological and clinical interpretation and functional analyses in experimental models. The major project outcomes at this stage include single-cell karyotyping data from the fallopian tube epithelium and tools for distilling the data from histologic images.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 2023
Accession Number
AD1218604

Entities

People

  • Arkadiusz Gertych
  • Sandra Orsulic

Organizations

  • University of California Regents

Tags

DTIC Thesaurus Topics

  • Abdomen
  • Artificial Intelligence Software
  • Breast Cancer
  • Carcinoma
  • Cell Physiological Processes
  • Cells
  • Computational Science
  • Data Curation
  • Data Mining
  • Dimensionality Reduction
  • Information Science
  • Lymphocytes
  • Machine Learning
  • Medical Personnel
  • Neural Networks
  • Oncology
  • Supervised Machine Learning

Fields of Study

  • Biology

Readers

  • Neural Network Machine Learning.
  • Oncology and Biomarker-Based Cancer Detection.
  • Women's Health and Cancer Risk Research: African American Women and Pregnancy Outcomes.

Technology Areas

  • AI & ML