Les commentaires sont clos.

12-months postdoctoral position: medical image analysis

27 Février 2023

Catégorie : Post-doctorant

12 months Postdoctoral position, ARA region
Medical Image Analysis

Job definition

Research scientist: cine-MRI 3D segmentation of the left ventricle using Deep Learning guided by geometric parametric models

Job nature

Contract type: Researcher on a fixed-term contract
Job type: Information sciences: processing, hardware-software integrated systems

Lab: Institut Pascal UMR 6602 - UCA/CNRS
Head: Evelyne Gil
Supervisors: Laurent Sarry (Institut Pascal, PU UCA), Patrick Clarysse (CREATIS, DR CNRS)
Location: axe TGI, équipe CaVITI, Faculté de Médecine, BP 38, 63001, Clermont-Ferrand
Contact :,

The post-doc project concerns the development of segmentation tools for cine MRI images to facilitate the estimation of 3D myocardial function. Cine MRI has become the reference modality in terms of accuracy and reproducibility for the estimation of myocardial anatomical features (volume, mass, thickening...), as well as for global function (ventricular ejection fraction). In the context of the ANR 3DStrain project (2011-2015), we have proposed a new variational formalism for the estimation of the regional function (strain), consisting in computing a dense field of deformation at each point of the myocardium. However, this estimation remains dependent on the quality of the segmentation of the endocardial and epicardial walls, which we then managed using deformable B-spline models.
The semantic segmentation methods by Deep Learning have shown very good performances, both in 2D and 3D on this type of data. We have recently confirmed this by training 2D and 3D U-Net Deep Neural Network models on our own 3T cine MRI database of which about 200 endo and epicardial volumes of the left ventricle (LV) have been manually delineated (corresponding to more than 2000 slices). However, the standard models do not ensure an anatomically plausible segmentation, because they do not incorporate any geometric or topological shape constraints.

The main objective of the project is therefore to integrate a constraint in the form of geometric models into the Deep Learning framework. These models will have to make a compromise in terms of degrees of freedom to represent the anatomical variability of the myocardial walls, while sufficiently constraining the final prediction.
Another advantage of these models will be the ability to interactively correct the predicted segmentation. Indeed, the a posteriori correction of a segmentation performed at the pixel/voxel level remains very time consuming, in particular in dynamic imaging. If the prediction directly produces a parametric model that can be modified interactively, this facilitates the correction of the result.

The methodology consists in replacing the encoder/decoder structure of the semantic segmentation networks by an encoder/FCN structure allowing the regression of the parameters of the chosen geometric model. The geometric model, representing the endocardial or epicardial surface of the LV, must be locally deformable, which leads to B-spline contours in 2D and to tensor product B-spline surfaces in 3D. Rather than using the control points as parameters, we will study the possibility of replacing them by the nodal points which have the advantage of belonging to the contour or the surface and thus being more easily editable a posteriori. B-splines also have the advantage of being able to compute sampled points from parameters in a tensor formalism, compatible with frameworks such as TensorFlow or PyTorch in order to benefit from GPU or TPU hardware accelerations.
Because of the particular geometry of the LV, it is possible to simplify the model with a single B-spline of the radial distance to the major axis of the left ventricle, rather than considering one B-spline per coordinate. This simplified representation assumes the ability to normalize the orientation of the acquisitions around the major axis.
The activities of the recruited post-doc will follow an incremental approach of increasing complexity, with deliverables resulting from network learning and predicted segmentation on the same test basis at each step:

  1. Normalization of 2D and 3D images. In clinical practice, the point of insertion of the right ventricle on the left ventricle is used as angular reference. Both manual and automatic image reorientation by learning will be considered.
  2. Development of the 2D regression model for slice-by-slice segmentation. The main contribution lies in the loss function which will be significantly different from those usually used in semantic segmentation which compare the theoretical and predicted classifications. Indeed, it will consist of the distance between the predicted sampled contour and the ground truth contour, which is more meaningful than a surface measure.
  3. Development of the 3D regression model. The loss function will be identical to the 2D case, the main difficulty will be to build the B-spline surface model and to implement it in tensor form.
  4. In cine MRI, the different slices of the same volume are acquired on distinct apneas. This results in possible shifts between slices that create volume discontinuities. We will study the possibility of integrating a Spatial Transformer Network into the previous 3D network model, allowing the variability of the acquisitions to be learned in the form of a set of translations between slices.

Expected skills:
We are looking for a PhD in data analysis and machine learning with the following skills if possible:
* experience in Machine Learning and in particular in Deep Learning (classification and regression) - Applications to image analysis
* Python / C++ programming with experience in Machine Learning frameworks (TensorFlow / PyTorch)

Work environment:
The work will be carried out at the Institut Pascal ( on the site of the Faculty of Medicine of Clermont-Ferrand, in interaction with the MYRIAD team of the CREATIS laboratory. Several stays are planned in Lyon to materialize this collaboration between the two laboratories.

Contract duration: 12 months
Workload: full time
Hiring date: 1.5 months after acceptance of the application
Expected diploma: PhD
Desired experience: 1 to 4 years
Indicative salary: 2900€ gross / month
Founder: Labex PRIMES (