Postdoc/PhD Positions in Computer Vision/Artificial Intelligence for Healthcare
Phd & PostDoc positions: Multi-modality Learning from Video & Text for Large Scale Surgical Video Analysis
Surgery is still not as safe as we would like it to be. Post-operative deaths account for 3 million deaths globally, making it the third greatest contributor to deaths in the world. The ambitious European ERC Consolidator project CompSURG aims to develop a novel computational methodology for analyzing intra-operative adverse events (IAEs) from surgical videos on a large scale. Currently, IAEs are under-reported, hindering their thorough analysis, the establishment of appropriate safety measures, and the development of intraoperative assistance systems to reduce their occurrence. Recent studies have shown that IAEs, while previously considered inconsequential, may in fact be indicative of serious complications and poor surgical outcomes.
Building on these findings, CompSURG proposes a radically new computational approach to improve intra-operative surgical safety, with a specific focus on automatic recognition and analysis of surgical activities and IAEs in endoscopic videos. We have several positions aimed at developing novel cutting-edge computer vision and machine learning techniques to model the intricate interactions between surgical tools and anatomy, examine activity patterns and variability on a large scale, and identify critical steps requiring safety measures. In particular, we will develop new methodologies relying on large language/video models, semantic graph modeling, self-supervised learning and representation learning from multi-modal video/text knowledge databases. The successful candidates will also have the opportunity to work closely with an international network of top-notch clinicians.
PhD & PostDoc: Federated Learning for Scaling-up Surgical Activity Analysis
Existing surgical activity recognition approaches are trained in a centralized manner: they require all the data to be stored on the same server. As institutions cannot easily share their data due to privacy concerns, current methods are often trained on limited datasets that are not representative of the surgical variability. Consequently, they do not generalize well to new clinical environments. A promising direction to address this issue is Federated Learning, in which a shared machine learning model is trained by aggregating locally-computed updates.
Theses positions are part of a new project focusing on designing and evaluating novel algorithms based on deep learning, semi-supervised learning and federated learning to analyze surgical activities from a distributed database of endoscopic videos. One example of major application will be the automated assessment of critical safety steps during surgery. To carry out this work, the successful candidates will have access to a unique database of videos stemming from several clinical institutions and also have the possibility to interact with highly motivated clinical partners. By developing privacy-preserving computer vision and machine learning methods, they will facilitate the deployment of AI in operating rooms.
PhD: Holistic Surgical Scene Analysis from Multi-modal Operating Room Data
The operating room is a high-tech environment in which surgical devices generate a lot of data about the underlying surgical activities. Our research group aims to use this large amount of multi-modal data from both cameras and surgical devices to develop an artificial intelligence system that can assist clinicians and staff in the surgical workflow.
The proposed project aims to develop novel approaches for analyzing complex minimally invasive surgical procedures using synchronized multi-modal data obtained from endoscopic and ceiling-mounted camera views and surgical equipment. These approaches will focus on building holistic surgical scene representations using spatio-temporal semantic scene graphs. The high-level knowledge embedded in the surgical scene graph representation will enable various downstream applications ranging from fine-grained surgical activity reporting and cognitive load assessment of the surgical staff to intra-operative decision support.
PostDoc: Quantitative Medical Imaging Biomarkers
This position will focus on developing novel medical image analysis methods based on deep learning to discover imaging biomarkers for CT/MR/US images with the objective to improve risk stratification and predict treatment success for liver diseases. The successful candidate will work in close collaboration with radiologists and biologists and also have the opportunity to mentor a growing team of PhD students working in developing new approaches for medical image segmentation and classification.
Requirements
For PhD students:
- Master in Computer Science or equivalent
- Strong Python programming skills
- Strong knowledge in computer vision and machine learning
- Proficiency in English (oral and written)
- Experience with Deep Learning is a plus
For postdoctoral fellows:
- PhD in Computer Science or equivalent
- Strong Python programming skills
- Strong knowledge and experience in computer vision, machine learning and deep learning
- Proficiency in English (oral and written)
- Publications in top-tier conferences/journals
Environment
The position is located in Strasbourg, France. Strasbourg is a lively, green and cosmopolitan city situated in the heart of Europe and is also home to the European parliament. The successful candidate will be hosted within a top-notch AI team located within the IHU institute for image-guided surgery. He/She will thereby have direct contact with clinicians, industrial partners and also have access to an exceptional international research environment offering state-of-the-art computing resources and unique clinical facilities.
Benefits
Cutting-edge research in an interdisciplinary and leading international research environment
Ability to work at the forefront of a rapidly growing field at the intersection of computer science, artificial intelligence and medicine
Development of real-world AI-based solutions for the operating room
To Apply
Starting dates for all position are flexible. The postdoctoral positions are renewable up to 3 years, offers a competitive salary commensurate with experience, and may lead to a permanent contract.
For PhD students:
Please send a long CV, motivation letter and academic transcripts to Nicolas Padoy.
For postdoctoral fellows:
Please send a long CV, motivation letter and list of publications to Nicolas Padoy.
Women are encouraged to apply.
Links
ICube laboratory
IHU MixSurg Institute
Laboratory of excellence CAMI
IRCAD Institute