Les commentaires sont clos.

HYPOCHIR: Hyperspectral for precise and optimized orthopedic surgery

24 Octobre 2023

Catégorie : Post-doctorant

The subject of this post-doctorate is led by L@bISEN and is part of the HYPOCHIR project in collaboration with LaTIM (Laboratoire de traitement de l'information médicale), a joint research unit (UMR1101) involving Inserm, Université de Bretagne Occidentale (UBO), IMT Atlantique and CHRU de Brest. The aim of this project is to develop an innovative hyperspectral imaging-assisted mapping approach for real-time orthopedic planning.

Position Profile:

  • Affiliated Institution: Yncréa Ouest, a private higher education institution of general interest (EESPIG), under contract with the Ministry of Higher Education and Research.
  • Research Unit: L@bISEN.
  • Research Team: LSL (Light – Scatter – Learning).
  • Workplace: Brest campus.
  • Contract Duration: 2 years or 18 months.
  • Salary: 35k / year depending on experience.
  • Opportunity to participate in teaching activities at Yncréa Ouest

The candidate should have:

• Ph.D. in computer science, data science, machine learning, or a related field.

  • The candidate must have spent at least 18 months outside France from May 1, 2020 and the start of the project (a person from abroad is fully eligible for this position).
  • Strong programming skills, especially in Python and deep learning frameworks like TensorFlow or PyTorch.
  • Deep understanding of deep neural networks, machine learning for image segmentation.
  • Ability to work independently and creatively solve problems.
  • Excellent oral and written communication skills, with the ability to present research results clearly and concisely.
  • Prior experience in hyperspectral imaging would be a significant asset.
  • Motivated and passionate about the medical field.

To apply:

Please submit the following documents:

Application deadline: December 31, 2023.


Application Context:

The aim of the HYPOCHIR project is to explore the use of hyperspectral imaging to improve the precision of orthopedic surgery. Currently, RGB imaging has limitations in terms of visualization and identification of anatomical structures and surgical instruments. To overcome these limitations, hyperspectral imaging offers the possibility of obtaining detailed information over a wide range of wavelengths, enabling the unique spectral signatures of tissues and objects to be captured.



The main objective of this project is to develop a fast and efficient approach to hyperspectral image segmentation to automatically differentiate and identify various anatomical structures and surgical instruments. By leveraging the distinctive spectral characteristics of each element, it will be possible to accurately map the operating room, thereby facilitating preoperative planning, intraoperative navigation, and real-time assistance during orthopedic surgical procedures.

Experiments will be conducted on anatomical objects with well-defined physical characteristics to validate the effectiveness of the proposed segmentation methods. The primary goal of the HYPOCHIR project is to enhance the accuracy and safety of orthopedic surgical procedures by harnessing the advantages of hyperspectral imaging for operating room mapping. Through automatic segmentation based on spectral signatures, the project aims to optimize outcomes in the field of orthopedics. By providing improved surgical precision, HYPOCHIR will contribute to enhancing practices in orthopedic surgery and optimizing results for the patients involved.


Keywords: Hyperspectral imaging, orthopedic surgery, Image segmentation, deep learning, preoperative planning, Intraoperative navigation, Real-time assistance.


  • Working on an innovative research project that explores the use of hyperspectral imaging to enhance real-time orthopedic surgery.
  • The opportunity to work and collaborate with experts in medical imaging, image processing, and orthopedic surgery within a multidisciplinary team.
  • Contributing to the improvement of surgical precision in orthopedics, which can have a positive impact on patient outcomes.
  • Access to cutting-edge resources, including a snapshot hyperspectral camera, software tools, computing infrastructure, and an experimental operating room.
  • Opportunities for publication in reputable conferences and journals.
  • Competitive compensation and attractive benefits package.

References :

(1)Nadine Abdallah Saab, Marianne Al Hayek, Catherine Baskiotis, Nesma Settouti, Olga Assainova, Mohammed El Amine Bechar, Chafiaa Hamitouche, Marwa El Bouz, "Contribution of hyperspectral imaging in interventional environment: application to orthopedic surgery," Proc. SPIE 12519, Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imaging XXIX , 125190S (13 June 2023);

(2)Seidlitz, Silvia / Sellner, Jan / Odenthal, Jan / Özdemir, Berkin / Studier-Fischer, Alexander / Knödler, Samuel / Ayala, Leonardo / Adler, Tim J. / Kenngott, Hannes G. / Tizabi, Minu / Wagner, Martin / Nickel, Felix / Müller-Stich, Beat P. / Maier-Hein, Lena. “Robust deep learning-based semantic organ segmentation in hyperspectral images”. 2022. Medical Image Analysis , Vol. 80. p. 102488.

(3)Guolan Lu, Baowei Fei, "Medical hyperspectral imaging: a review," J. Biomed. Opt. 19(1) 010901 (20 January 2014)

(4)Koprowski, R., Olczyk, P. Segmentation in dermatological hyperspectral images: dedicated methods. BioMed Eng OnLine 15, 97 (2016). Zhan, Y. Uwamoto and Y. -W. Chen, "HyperUNet for Medical Hyperspectral Image Segmentation on a Choledochal Database," 2022 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, USA, 2022, pp. 1-5, doi: 10.1109/ICCE53296.2022.9730171