Transcriptional intra-tumour heterogeneity predicted by deep learning in routine breast histopathology slides provides independent prognostic information.

Journal: European journal of cancer (Oxford, England : 1990)
Published Date: Jun 23, 2023

Abstract

BACKGROUND: Intra-tumour heterogeneity (ITH) causes diagnostic challenges and increases the risk for disease recurrence. Quantification of ITH is challenging and has not been demonstrated in large studies. It has previously been shown that deep learning can enable spatially resolved prediction of molecular phenotypes from digital histopathology whole slide images (WSIs). Here we propose a novel method (Deep-ITH) to predict and measure ITH, and we evaluate its prognostic performance in breast cancer.

Authors

  • Yinxi Wang
    Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden.
  • Maya Alsheh Ali
    Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden.
  • Johan Vallon-Christersson
    Division of Oncology, Department of Clinical Sciences Lund, Lund University, Lund, Sweden.
  • Keith Humphreys
    Department of Psychiatry, Stanford University, Stanford, California, United States of America.
  • Johan Hartman
    Department of Oncology/Pathology, Karolinska Institutet, Stockholm, Sweden; Department of Clinical Science and Education, Södersjukhuset, Karolinska Institutet, Stockholm, Sweden.
  • Mattias Rantalainen
    Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden.

Keywords

External Resources

Popular Topics
Recent Journals