University of Cambridge > > Computational and Systems Biology > Replacing pathologists with next generation diagnostics: use of artificial intelligence to analyse image and DNA sequencing data

Replacing pathologists with next generation diagnostics: use of artificial intelligence to analyse image and DNA sequencing data

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact .

Abstract: To date, tissue-based diagnostics have been inherently subjective. To make the process more robust, we are developing an artificial intelligence solution based on microscopic image analysis. Ultimately, we wish to combine this with a molecular analysis that measures immune responses in the same tissue, to provide a completely novel, holistic approach able to predict diagnosis and/ or prognosis in a wide range of conditions mediated or modulated by the immune system. In this exciting project, we will develop an advanced mathematical classification of a relatively heterogeneous disease.

The model we will use is that of coeliac disease (CD), a relatively common condition, caused by a damaging immune response to the small intestine, with effects ranging from no symptoms, through anaemia to severe intestinal symptoms, and with complications including bone thinning, infertility and, rarely, lymphoma and duodenal cancer. Assessing whether a patient has CD relies primarily on “gold standard” duodenal biopsy examination by a pathologist, an unavoidably subjective process with poor inter-observer concordance (up to 25% cases) and a suspicion that a significant number of cases are missed. Furthermore, some biopsies appear to show a disease continuum from normal to severe.

We will discuss image analysis work undertaken on a subset of our cohort of carefully clinicopathologically annotated, high resolution digitised images of 500 duodenal biopsy samples (250 coeliac disease; 200 normal; 50 equivocal). We will also explain some of our future image analysis plans. Finally we will consider how we might undertake a combined integrative analysis of digital images, together with a novel molecular analysis of the activity of the immune system, the algorithm for which was developed in the Soilleux laboratory. We believe that the algorithms generated during this project hold great promise in a broad range of areas, including diagnostics. There is relatively little work on joint analysis of sequence and imaging data and the machine learning methodologies we develop will ultimately be useful for a range of immune-modulated disease.

This talk is part of the Computational and Systems Biology series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity