OFFER DEADLINE :
30/09/2022 23:59:00 – Europe/Brussels
Universitat Rovira i Virgili (URV)
EU RESEARCH FRAMEWORK PROGRAMME:
HORIZON-MSCA-2021-DN-01-01 DEPARTMENT :
Department of Computer Engineering and Mathematics (DEIM)
Prof. Dr. Domenec Puig and Assoc. Prof. Dr. Hatem A. Rashwan, established at the Department of Computer Engineering and Mathematics – DEIM at Rovira I Virgili university, URV,Tarragona, Spain, are interested in receiving Expressions of Interest of potential doctorate candidates for the Marie Sklodowska – Curie Doctorate Network (MSCA-DN-2021) call.
The title of the proposed project: Determination of molecular subtypes of breast cancer using multimodal radiological imaging
The overarching goal of our project is to develop a new methodology to automate the classification of the different molecular subtypes of BC (i.e., Luminal A, Luminal B, Triple-negative and HR-/HER2-) from the analysis of radiological images (e.g., mammograms, MRI and ultrasound (traditional and elastography)), by the following steps: (1) segmentation of the tumour by means of a DL model (e.g., GAN); (2) obtaining fractal, morphological and kinetic textural characteristics of the segmented tumour regions in the previous step, which will be calculated using extractors of characteristics adapted to the visual patterns present in the digital images, as well as the features extracted by the DL model; (3) studying the correlation between the tumour shape and margins predicted and molecular subtypes of BC, which will be compared to the pioneer clinical studies; (4) developing an explainable DL model based on CNN for trustworthy classification of molecular subtypes of breast cancer, (5) investigating the correlation between the molecular subtypes and the risk to breast cancer relapse, and (6) finally validating the results of the proposed system in the hospital of Sant Joan de Reus Spain (associated partner), with whom the candidate is regularly interacting, via screening radiological images for the entire population of Catalunya between 2005 and 2015. We will use our previous work for breast tumour segmentation and shape classification in mammograms using generative adversarial and convolutional neural networks as a baseline of this thesis to achieve more accurate and reliable results and to use more different radiological images. Our hypothesis will be corroborated on INbreast (115 cases), DDSM (1168 cases) and private in-house (from HUSJR) (300 cases) datasets.
For BosomShield, we are looking for a doctorate candidate will have the following responsibilities:
- She/he will collaborate with diverse teams of scientists and engineers to build an advanced system for BosomShield.
- She/he will design and develop cutting edge methods based on brittle computer vision, machine learning algorithms and deep learning (CNN, RNN, Transformers,….) algorithms.
- She/he will help advance R&D by finding problems, implementing elegant solutions, and building tools that enable the team to move forward and to measure progress.
We are looking for talented and innovative self-motivated young scientists, strongly committed to high quality frontier and multi-disciplinary research and able to add new insights to the existing URV core expertise.
URV as Hosting Institution located at Scientific Campus of Sescelades, Tarragona, Spain, has all the technical and scientific facilities for carry out this project.
The PhD students will be working in the IRCV research group with the following persons:
Prof. Dr. Domenec Puig (the head of the group): link profile, and Assoc. Prof Dr. Hatem A. Rashwan: link profile, who are all expert in medical imaging and medical image analysis.
The Universitat Rovira i Virgili (URV) was created in 1991 by the Parliament of Catalonia from the already existing university faculties and schools. From the very first day, its aim has been very clear: to place knowledge at the service of society so as to contribute to the social and economic development of its environment, which has gradually transformed over time. Social and cultural changes have opened the doors to a new framework in which our students and future workers are obliged to interact in Europe. At the URV we train professionals under the precepts of European harmonization, a key factor for opening the doors to a world of work without frontiers. And we do so by providing a full range of educational possibilities with more than 40 undergraduate courses and 50 master's degrees (many of which are interuniversity), an extensive doctoral program and a flexible lifelong learning program so that professionals can constantly update their knowledge and improve their skills. All in all, our courses are being enjoyed by over 15,000 students. The data show that the URV is not only one of the leading universities in Catalonia but also one of the leading universities in the European area for the quality of its teaching, its commitment to continuous training and the excellence of its research, development and innovation. The URV is currently ranked as the 76th World University under 50 years (Times Higher Education Ranking 2019). Intelligent Robotics and Computer Vision Group (IRCV) is concerned with the development of innovative solutions in several areas of computer vision through the application of advanced computing techniques. The IRCV group is part of the Intelligent Technologies for Advanced Knowledge Acquisition research group recognised as a consolidated research group by the Government of Catalonia. The main research lines of IRCV are: 1) Deep learning and machine learning models for computer vision-based applications, 2) 2D and 3D image processing and analysis techniques: Range Image Processing, and Classification, Image segmentation, etc. 3) Computational techniques to model and visualize three-dimensional geometric objects. 4) Edge-cutting, world-class research on medical image analysis. 5) Planners to solve automated robotic tasks.
IRCV is a research group has all the equipment needed for the development of this project. The doctorate network will take advantage of the latest generation workstations for the simulations and programming of the algorithms, while all images will be provided by contacts in the Hospital of Reus (radiotherapy section).
At the attempted deadline for the submission of the proposals (30/09/2022):
- Early Stage Researcher:
- Knowledge of deep learning concepts and experience with deep learning environments (eg.: TensorFlow, PyTorch, etc).
- Excellent practical software engineering ability, particularly Python and C/C++.
- Knowledge of medical image analysis and working with image data.
- Masters degree is highly recommended.
- Collaborative spirit.
- Nationality: Any.
- Mobility: The researcher must not have resided or carried out his/her main activity (work, studies, etc.) in the country of the host organization for more than 12 months in the 3 years immediately prior to the deadline for submission of proposals (a relaxed rule for Career restarting and Reintegration).
- Must be fluent in English (both written and spoken).
Researchers willing to apply should check that they fulfil the eligibility criteria and then send an expression of interest, consisting of:
HOW TO APPLY
- Scanned copy of identity card, resident's card or passport currently in force.
- Curriculum Vitae (Any research career gaps and/or unconventional paths should be clearly explained so that this can be fairly assessed by the evaluators; if you are a forcibly displaced researcher, please explain your situation in the CV; if you have been residing in Country in the last 3 years please provide the exact duration and motives of your stay and be prepared to provide the documentation proving it during the redress phase if required by the Project Manager). We strongly recommend you to use the Europass CV template.
- Scanned copy of the certificate of the official academic qualification or proof of payment of the fees for the issuance of the certificate that allows the holder to access the doctoral studies. Students who hold Master degrees should present the scanned copies of their master's degrees. Students who are registered in an official university master's course that allows them to access the doctoral programme during the 2021/2022 academic year must present a scanned copy of their master's course registration form.
- Scanned copy of academic transcript of the qualification equivalent to a bachelor's degree.
- Scanned copy of academic transcript of the master's degree. Candidates who have not completed their Master's degrees must send their provisional academic transcript*.
- Two signed and scanned reference letters. We will not contact the referees on your behalf.
- A motivation letter, explaining his expertise and how the candidate is suited for the position she/he applies for.
- Expressions of interest must be submitted to your account through https://bosomshield.eu/.
- Researchers willing must apply to maximum two positions of the aforementioned 10 positions.
- DCs will be pre-selected on the basis of internal evaluation.
- Candidates will be informed of the results of the pre-selection two weeks after the deadline.
- Interview between the highest ranked candidates of the pre-selection will be organed by the supervisors to select the final candidate.