20/11/2020
Logo of Marie Skłodowska-Curie Actions

PhD position 11 – MSCA COFUND, AI4theSciences (PSL, France) - “3DMorphEmbryo”

This job offer has expired


  • ORGANISATION/COMPANY
    Université PSL
  • RESEARCH FIELD
    EngineeringComputer engineering
  • RESEARCHER PROFILE
    First Stage Researcher (R1)
  • APPLICATION DEADLINE
    26/02/2021 23:00 - Europe/Brussels
  • LOCATION
    France › Paris
  • TYPE OF CONTRACT
    Temporary
  • JOB STATUS
    Full-time
  • HOURS PER WEEK
    35
  • OFFER STARTING DATE
    01/09/2021
  • EU RESEARCH FRAMEWORK PROGRAMME
    H2020 / Marie Skłodowska-Curie Actions COFUND
  • REFERENCE NUMBER
    AI4theSciences-PhD-11
  • MARIE CURIE GRANT AGREEMENT NUMBER
    945304

OFFER DESCRIPTION

“Artificial intelligence for the Sciences” (AI4theSciences) is an innovative, interdisciplinary and intersectoral PhD programme, led by Université Paris Sciences et Lettres (PSL) and co-funded by the European Commission. Supported by the European innovation and research programme Horizon 2020-Marie Sklodowska-Curie Actions, AI4theSciences is uniquely shaped to train a new generation of researchers at the highest academic level in their main discipline (Physics, Engineering, Biology, Human and Social Sciences) and master the latest technologies in Artificial Intelligence and Machine Learning which apply in their own field.

26 doctoral students will join the PSL university's doctoral schools in 2 academic cohorts to carry out work on subjects suggested and defined by PSL's scientific community. The 2020 call will offer up to 15 PhD positions on 24 PhD research projects. The candidates will be recruited through HR processes of high standard, based on transparency, equal opportunities and excellence.

 

Description of the PhD subject: “3DMorphEmbryo - AI-assisted reconstruction of 3D human embryo morphology from 2D medical images to improve the prediction of its development potential”

 

Context - Motivation

Faced by about 10 % of couples worldwide, infertility is a global public health issue (World Health Organization). One critical step for clinical success of in vitro fertilization technologies (IVF) lies in the choice of the embryo(s) having the greatest potential to implant and further develop. Since a few years, this selection has been improved with the advent of medical incubators equipped with embedded time-lapse microscopes (Embryoscope® or Geri®). Providing records of the first 6 days of pre-implantation development, these incubators have opened a new avenue for the assessment of embryo quality, through the analysis, by experts and/or automatized methods, of embryo morphokinetics (morphology and kinetics of development). Such approach has now proven its superiority, and is just starting to leverage the power of deep learning to gain in efficiency and objectivity. One strong limitation of current time-lapse devices is the impossibility to visualize the embryomorphology in 3D with the imaging techniques implemented (bright/dark-field for Geri® or Hoffman modulation contrast for Embryoscope®). While a dozen of focal planes are recorded over the embryo, only the brightest is generally picked for further morphokinetic analysis. Yet, the embryo is transparent, which allows medical doctors to distinguish by eye the shape and arrangement of cells and potential issues, which lets envision the possibility to numerically reconstruct the 3D morphology of embryos from 2D images. In computer vision a novel and active field works on the 3D reconstruction of objects morphology from 2D pictures using deep convolutional networks and generative models, showing promising results. To our knowledge such approach has not yet been adapted to biological/medical images, although deep learning has already proved its superiority in bio(medical) image classification, segmentation, registration or restoration. Another largely unexplored avenue for the improvement of embryo selection is the systematic combined analysis of morphokinetic features with health data (age, disease, sperm, hormones,etc...) and incubation characteristics (O2/CO2 ratio, temperature etc...). Finally, whether more recent light microscopy techniques may provide intrinsic advantages for human embryo 3D morphology reconstruction remains undocumented.

 

Scientific Objectives, Methodology & Expected results

The project will leverage deep (convolutional) neural networks to achieve three main aims:

  1. To develop an algorithm in order to reconstruct the 3D morphology of human embryo from 2D confocal images of bright/dark-field and modulation contrast type and to evaluate the potential of quantitative phase imaging techniques to improve such reconstruction.
  2. To design computational methods to fully automatize from time-lapse videos the detection and quantitative characterization of relevant morphokinetic events in human embryo development.
  3. To improve the medical assessment of embryo implantation potential by combining the statistical analysis of morphokinetic features with clinical pregnancy outcome, but also patient health and embryo incubation data.

 

To develop and train a deep learning algorithm for 3D reconstruction (aim 1), the project will take advantage of large datasets currently collected by Dr. H. Turlier for various early transparent embryos (mouse,marine,worms...), through established collaborations with biologists. Early embryos are indeed routinely imaged simultaneously with bright-field (or phase contrast) and 3D fluorescent settings. The algorithm will then be tested and fine-tuned on human embryo data of similar type (3D fluorescent + bright-field) currently generated through an ongoing collaboration. The algorithm will finally be evaluated on 2D medical images of human embryos by medical embryologists. The potential of alternative imaging methods for improved 3D reconstruction, such as quantitative phase microscopy developed by the team of Prof. G. Popescu, will further be assessed during a mobility period in the USA.

In parallel, convolutional and recurrent neural network architectures will be developed directly for 2D medical images to quantify relevant morphologic and kinetic features of human embryo development: celldivision, compaction,cavitation (aim 2). This part will rely on the expertise in embryomorphogenesis of the team of Dr. H. Turlier, and in particular, its unique capacity to perform 3D simulations of early embryo development and to generate artificial images from such simulations, an advantage that may prove to be decisive to develop efficient algorithms to characterize morphogenetic events. These novel methods for morphokinetic characterization assisted by artificial intelligence will be evaluated with regard to traditional morphokinetic grading methods.

For the last part (aim 3), a pipeline based on multimodal machine learning approaches will be developed to improve the prediction of pregnancy outcome through a combined statistical analysis of various data: morphokinetic features (extracted or raw images), embryologist’s expert grading of the embryo potential, patient health data (age, weight, diseases, infertility factors etc...), the IVF procedure (with or without intracytoplasmic sperm injection, hormonal dosage, sperm characteristics, number of attempts...), and the pregnancy outcome when available. As the pregnancy outcome is not known for all imaged embryos, both supervised and unsupervised learning approaches will be considered. A particular attention will be paid to the model explainability, by working closely with embryologists and medical doctors from the Cochin Paris hospital, in order to build a computation tool aiming at helping them on their clinical decisions, while not replacing their expert’s appreciation.

 

The student will quickly acquire strong knowledge in early mammalian embryo development thanks to the expertise of H. Turlier on embryo morphogenesis and through a close collaboration with the reproductive medicine department of the Cochin Paris hospital. The co-supervision by Dr. B. Stanciulescu, expert in computer vision and machine learning, will ensure a rapid and efficient implementation of state-of-the-art machine learning techniques for this project. Finally, the international partnership with Prof. G. Popescu will provide precious knowledge on optical imaging techniques, their advantages and drawbacks.

 

International mobility

The PhD student will spend a mobility period of a few months (4 to 6 months) in the Quantitative Light Imaging Laboratory (Light ECE, Beckman Institute for Advanced Science and Technology, University of Illinois), headed by Prof. G. Popescu, that develops novel light microscopy techniques. The objective will be to evaluate the potential of quantitative phase imaging to improve AI-assisted retrieval of 3D transparent embryo morphology from 2D images, in the context of early embryo development but also more generally for somatic cells and small tissues.

 

Thesis supervision

Hervé Turlier and Bogdan Stanciulescu

 

PSL

Created in 2012, Université PSL is aiming at developing interdisciplinary training programmes and science projects of excellence within its members. Its 140 laboratories and 2,900 researchers carry out high-level disciplinary research, both fundamental and applied, fostering a strong interdisciplinary approach. The scope of Université PSL covers all areas of knowledge and creation (Sciences, Humanities and Social Science, Engineering, the Arts). Its eleven component schools gather 17,000 students and have won more than 200 ERC. PSL has been ranked 36th in the 2020 Shanghai ranking (ARWU).

More Information

Benefits

  • Opportunity to conduct academic research in a top 100 university in the world.
  • High-quality doctoral training rewarded by a PhD degree, prepared within Collège de France - PSL and delivered by PSL.
  • Access to cutting-edge infrastructures for research & innovation.
  • Appointment for a period of 36 months (job contract delivered by the involved component school of PSL) based on a salary of 3100 € gross employer (including employer tax) per month or approximately a 2228 € gross salary per month.
  • Job contract under the French labour legislation in force, respecting health and safety, and social security: 35 hours per week contract, 25 days of annual leave per year (“congés annuels”). Eventual complementary activities may be accepted or proposed by the co-supervisors (maximum of 64h/year for teaching, 32 day/year for specific missions).
  • Short stay(s) or secondment in France or abroad are expected.
  • An international environment supported by the adherence to the European Charter & Code.
  • Access to AI training package, with a strong interdisciplinary focus, together with a Career development Plan.

Eligibility criteria

  • Applicants must have a Master’s degree (or be in the process of obtaining one) or have a University degree equivalent to a European Master’s (5-year duration) to be eligible at the time of the deadline of the relative call.
  • There is no nationality or age criteria, but applicants must not have resided or carried out their main activity (work, studies, etc.) in France for more than 12 months in the 3 years immediately before the deadline of the call (MSCA Mobility rule).
  • Applicants must declare to be available to start the programme on schedule.

For submitting your online application, go to: https://www.psl.eu/recherche/grands-projets-de-recherche/projets-europee...

 

The online application should contain the following documents:

  • English translated transcripts from the Master’s degree (or equivalent 5-year degree). A copy of the Master’s degree or a certificate of achievement will be required later on for the final registration.
  • International curriculum vitae and a cover letter explaining the reasons that lead him/her to prepare a PhD, why he/she applies to this offer and his/her professional project (guidelines will be given to the applicants in order to help him/her in the writing of his/her letter).
  • Two academic reference letters.
  • A statement duly signed on the mobility rules, availability, and conflicts of interest.

The applicants can only apply to one PhD project among the available ones. Multiple applications of one candidate will automatically make all his/her applications ineligible.

Selection process

The applications will be analysed by the Management Team for eligibility and completeness. Afterwards, the applications will be reviewed by the Selection Committee. In the pre-selection round (March-April 2021), applicants will be rated using a scoring system based on 3 criteria (academic excellence, experience, motivation, and qualities). A shortlist of qualified applicants will be interviewed during the selection round (June 2021) to further assess their qualifications and skills according to the predefined selection criteria.

All information regarding the applications (criteria, composition of the Selection Committee, requirements) can be found on the website of the programme, in greater detail.

 

The selection and recruitment processes of the PhD student will be in accordance with the European Charter for Researchers and Code of Conduct of the Recruitment of Researchers. The recruitment process will be open, transparent, impartial, equitable, and merit based. There will be no discrimination based on race, gender, sexual orientation, religion of belief, disability, or age.

Additional comments

The Centre for Interdisciplinary Research in Biology (CIRB) is a CNRS/INSERM laboratory located in Collège de France - PSL, one of the most prestigious research and education institution in France, which is associated to Université Paris Sciences et Lettres (PSL). The laboratory is composed of 18 independent research teams interested in various thematics, ranging from cell and developmental biology, neuroscience to cancer and cardio-vascularbiology. Its strength and originality are to bring together physicists, mathematicians and biologists to investigate fundamental and applied biological problems from complementary expertise. Interdisciplinary is at the core of the research strategy of the laboratory, which is in perfect line with the diverse scientific environment of Collège de France and with the education and training strategy of PSL.

 

Collège de France - PSL is a public higher education institution, which is unique in France and has no equivalent abroad. Since the 16th century, Collège de France - PSL has had a two-fold mission: to be a forum for cutting-edge research and teaching in every field of literature, science and the arts. Collège de France - PSL was founded by Francis I in 1530. Today, 50 professors are working alongside several hundred researchers, engineers, technicians and administrative staff. The chairs cover a huge range of disciplines ranging from Mathematics to the study of major civilizations, and include Physics, Chemistry, Biology and Medicine, Philosophy and Literature, the Social Sciences and Economics, Prehistory, Archaeology and History, and many more. Several of the chairs are temporary chairs which promote emerging fields and a multidisciplinary approach. From the very outset, the basic premise that chairs are not permanent has underpinned the creative energy of this academic community. Therefore, when incumbents retire, new appointments are made on the basis of the very latest scientific developments. New members are elected by the Assembly of Professors. There is no specific academic rank stipulated for nominees; the only relevant factors are the significance and originality of their work. The possibility of modifying chairs is a principle which avoids the rigidity of fixed academic disciplines. Collège de France - PSL is therefore permanently adapting to developments in the sciences and remains a focal point for the scientific community.

Web site for additional job details

Required Research Experiences

  • RESEARCH FIELD
    MathematicsApplied mathematics
  • YEARS OF RESEARCH EXPERIENCE
    1 - 4

Offer Requirements

  • REQUIRED EDUCATION LEVEL
    Mathematics: Master Degree or equivalent
  • REQUIRED LANGUAGES
    ENGLISH: Excellent

Skills/Qualifications

  • Strong scientific background in either Applied Mathematics, Computer Science or (theoretical) Physics.
  • Proficiency in Python programming is required.
  • Competences in computer vision, C++ and/or machine learning are highly desirable, although not required.
  • Previous research experience at the crossroads of biology or medicine will be considered very favorably.

Specific Requirements

  • The student should have spent less than 12 months in France prior to March 2021 to be eligible. He will however have the opportunity to perform a research internship as an assistant engineer in the laboratory from July 2021, before the start of his PhD program in September 2021.

Work location(s)
1 position(s) available at
Centre for Interdisciplinary Research in Biology, Collège de France - PSL
France
Paris
75005
11, place Marcelin Berthelot

EURAXESS offer ID: 579218

Disclaimer:

The responsibility for the jobs published on this website, including the job description, lies entirely with the publishing institutions. The application is handled uniquely by the employer, who is also fully responsible for the recruitment and selection processes.

 

Please contact support@euraxess.org if you wish to download all jobs in XML.