AI-enabled in silico immunohistochemical characterization for Alzheimer's disease

Bryan He, Syed Bukhari, Edward Fox, Abubakar Abid, Jeanne Shen, Claudia Kawas, Maria Corrada, Thomas Montine, James Zou

Research output: Contribution to journalArticlepeer-review

Abstract

We develop a deep learning approach, in silico immunohistochemistry (IHC), which takes routinely collected histochemical-stained samples as input and computationally generates virtual IHC slide images. We apply in silico IHC to Alzheimer's disease samples, where several hallmark changes are conventionally identified using IHC staining across many regions of the brain. In silico IHC computationally identifies neurofibrillary tangles, β-amyloid plaques, and neuritic plaques at a high spatial resolution directly from the histochemical images, with areas under the receiver operating characteristic curve of between 0.88 and 0.92. In silico IHC learns to identify subtle cellular morphologies associated with these lesions and can generate in silico IHC slides that capture key features of the actual IHC.

Original languageEnglish (US)
Article number100191
JournalCell Reports Methods
Volume2
Issue number4
DOIs
StatePublished - Apr 25 2022
Externally publishedYes

Keywords

  • Alzheimer's disease
  • amyloid plaque
  • deep learning
  • immunohistochemistry
  • machine learning
  • neuritic plaque
  • neurofibrillary tangle

ASJC Scopus subject areas

  • Biochemistry
  • Biotechnology
  • Biochemistry, Genetics and Molecular Biology (miscellaneous)
  • Genetics
  • Computer Science Applications
  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'AI-enabled in silico immunohistochemical characterization for Alzheimer's disease'. Together they form a unique fingerprint.

Cite this