Working at Amsterdam UMC

PhD Artificial Intelligence based detection and prediction of esophageal cancer

Can you improve diagnosis and treatment of esophageal cancer precursor lesions with multi-parameter analysis and integrated risk stratification using Artificial Intelligence?
PhD Artificial Intelligence based detection and prediction of esophageal cancer
Questions?
Apply now
  • Hours: 36 uur per week
  • Division: Laboratories
  • Contract type: fixed-term
  • Salary: € 2.570 - € 3.271
  • React until: 31 January 2022
Apply now Apply within 8 day(s)
The project

Esophageal carcinoma (EAC) is diagnosed at a late stage and has a poor prognosis. A dramatic increase in incidence of EAC is observed during the last decades. EAC can be prevented if precursor lesions are detected and treated in time. Barrett’s esophagus (BE) is the only known precursor lesion, and can progress through a sequence of initially benign, to in a later stage malignant tissue alterations. Pathology diagnosis is key for optimal patient management, but histopathology tissue analysis is subjective and results in unacceptable variation in patient outcome. In addition, no test that identifies patients that progress to cancer exists to date. Clearly, there is an urgent need for precise and objective diagnostic tools.

The goal of this project is to improve diagnosis and treatment of people with precursor lesions of esophageal cancer by integrating histopathology image analysis with biomarkers and clinical parameters using AI. We aim to develop an automated AI-based expert-histopathology classifier that supports clinical decision making; and use AI to move from one-dimensional analysis to a multi-parameter risk-stratification pipeline for optimal patient management.

In this project, we will develop state-of-the-art AI-based algorithms to analyze and characterize the spatial-temporal distribution of histological and biomarker data in one system. Here spatial refers to local tissue characteristics observed in histopathology imaging data and the temporal aspect is addressed by following patients over time. The to-be-developed algorithms will allow to relate histopathology imaging data to disease progression and enable the discovery of novel biomarkers that can support clinical decision making. Eventually, this will lead to better personalized management of patients, reduced burden on health professionals and health system budget, and better quality of life for patients with Barrett’s esophagus.

This project is a collaboration between the qurAI group, the Computational Pathology Lab AUMC and the Amsterdam Machine Learning Lab (AMLab). It is supported by funding from the Dutch “Maag-Lever-Darm-Stichting” and has a running time of 42 months.

Question about this vacancy?
Tanja Hart Tanja Hart +31621603178 Recruitment adviseur
About your role

As a PhD-candidate, you will be responsible for developing and evaluating the best possible AI system for automated expert-diagnosis of patients with precursor lesions of esophageal adenocarcinom (EAC) and to identify those patients at high risk to progress to cancer.

The challenge is two-fold. Firstly, you will develop an AI system that has a diagnostic performance on-par with expert pathologists. This system will be developed and trained using gradings provided by expert pathologists. Secondly, the intent is to push the quality of grading and risk assessment beyond what can currently be achieved based on our current understanding of disease development. The route to achieving this is via the development of new AI techniques for biomarker discovery and quantification; Using clinical and histological time-series you will develop spatial and temporal pathology tissue system signature and train longitudinal progression models. Finally, you will validate these algorithms in independent cases to ensure the devised AI-algorithms' applicability in clinical practice.

You will:

  • research AI-based clinical decision-making, by developing new deep learning solutions for the detection and progression prediction of patients with precursor lesion of esophageal cancer
  • publish and present your work in journals and international conferences;
  • be an active part of the qurAI, AMLab and Computational pathology group and their activities;
  • assist in educational activities and supervision of bachelor and master students.

About you
  • A Master’s degree (or equivalent) in Artificial Intelligence, Computer Science, Medicine, Mathematics, Engineering or a related subject
  • Previously demonstrated interest in artificial intelligence and medical data analysis, in the form of coursework, projects and academic publications, and an affinity with medical topics
  • Excellent programming skills, particularly in Python and ML-related libraries
  • High motivation in pursuing academic research in a multidisciplinary setting of medical imaging, Pathology and AI.
  • Goal-oriented, independent and proactive.
  • Fluency in English, both written and spoken.
Our offer
  • A jump start to your career in research work.
  • All te space for you to contribute shaping the care of tomorrow.
  • Working on large-scale and research project, with motivated colleagues from all over the world.
  • We offer a contract for a year (12 months) with the intention to be extended with 2,5 years for the total project duration of 3,5 years (possible extension if sufficient funding is availble).
  • The base salary does not include holiday pay (8%) and a year-end bonus (8.3%). 
  • In addition to excellent accessibility by public transport, AMC also has a sufficient number of parking spaces for employees.
  • Pension is accrued at Be Frank. 
About your workplace

You will be embedded in the qurAI group, an interfaculty, multidisciplinary group between the Institute of Informatics of the University of Amsterdam (Science Park) and the Department of Biomedical Engineering and Physics of the Amsterdam University Medical Center (AUMC) and work on both locations. We focus on the development, validation and clinical integration of AI solutions for data analysis challenges in healthcare. The group aims at designing and enabling socially responsible AI innovations in healthcare.

You will work under the supervision of Prof. Clarisa Sánchez from the qurAI, assistant Prof. Erik Bekkers and his group at Amsterdam Machine Learning Lab (AMLab) and dr. Sybren Meijer from the Computational Pathology Lab AUMC. There are weekly research meetings and journal clubs and various ways to develop yourself as an independent researcher. Furthermore, as we aim to develop clinical relevant AI algorithms, the department of gastro-enterology (AUMC) is also closely involved.

https://qurai.amsterdam/

https://amlab.science.uva.nl/

http://barrettpathology.com/

What to expect
A job in our beautiful capital
Working for the most preferred employer in healthcare (intermediair 2021)
All colleagues have the same goal: contributing to tomorrow's care
We care not only for our patients, but also for you
Cooperation is characterised by mutual trust and interest in one another
We are constantly innovating, so you must be able to deal with change
Parking is limited at location VUmc, but by public transport you can get to the door
A full agenda, because our staff association organises many fun activities
Meet your colleagues Watch video’s of your future colleagues
Amsterdam UMC
Tulp
Verpleegkundige visie
Let’s meet!

For questions or more information about this position or the research, please contact:

Prof. Dr. Clarisa Sánchez Gutiérrez via  c.i.sanchezgutierrez@uva.nl, qurAI, Amsterdam
Asst. prof. Erik Bekkers via e.j.bekkers@uva.nl, AMLab, Amsterdam.
Dr. Sybren Meijer s.l.meijer@amsterdamumc.nl, Department of Pathology Amsterdam UMC.

For more information about the application process, please contact Tanja Hart, Advisor Recruitment and Selection, via T: 06-21603178 or E: t.hart@amsterdamumc.nl.

A reference check, screening and hiring test may be part of the procedure. Read here whether this also applies to you. 

In case of equal suitability, internal candidates will be given priority over external candidates.

Acquisition in response to this vacancy is not appreciated.