Identification of features in benign breast disease biopsies that predict breast cancer risk

Identification of features in benign breast disease biopsies that predict breast cancer risk

Reimbursement

This is an AI for Health MSc project. Students are eligible to receive a monthly reimbursement of €500,- for a period of six months. For more information please read the requirements.

Clinical Problem

Millions of women undergo breast biopsies (i.e., tissue sampling) each year to determine whether a suspicious lesion found on a mammogram (e.g., calcifications, a mass or density) or on physical examination represents breast cancer (BC). Although 75% of breast biopsies show benign breast disease (BBD), which is reassuring, women with BBD experience a 1.5- to four-fold increased risk of future development of BC compared with women not diagnosed with BBD. To better identify women that would benefit from intensified monitoring, improved prediction of BC risk is urgently needed.

Project goal

Convolutional neural networks to characterize tissue composition of biopsies and assess the morphology of normal breast lobules (which are the source of BBD) have been developed and reported in several publications (PMC9275035; PMC8770616; PMID: 35503494). The goals of this project include: - characterization of morphologic features of the BBD biopsies - establishing approaches for predicting BC risk.

Data

Mayo Clinic (Rochester, US) has established a cohort of 5,499 women biopsied for BBD between 2002-2013, including 360 who developed an incident DCIS or invasive BC. Microscopic slides of all biopsies have been thoroughly reviewed and analyzed and digital images of a subset have been incorporated into a case-cohort, which includes all biopsies preceding BC and a random subset of biopsies (~900 total women).

Results

Thesis, source code, documentation; the algorithm will be made publically available as a Docker container on https://grand-challenge.org/.

Embedding

The student will be supervised by a research member of the Diagnostic Image Analysis Group and Computational Pathology Group whose research is dedicated to analyses of histopathological slides with deep learning techniques. We have a strong collaboration with pathology experts in the field of cancer grading. The student will have access to a large GPU cluster.

Requirements

  • Students with a major in computer science, biomedical engineering, artificial intelligence, physics, or a related area in the final stage of master level studies are invited to apply.
  • Affinity with programming in Python
  • Interest in deep learning and medical image analysis

Information

People

Witali Aswolinskiy

Witali Aswolinskiy

Postdoctoral Researcher

 Mark Sherman

Mark Sherman