Pilotage-Projets |

REMI — Decision Support for Lower-Limb Endovascular Revascularization

Wed, 01 Sep 2021 00:00:00 +0000

How do you help a vascular surgeon choose the best revascularization strategy, when the success of a technique remains hard to predict? REMI explores one answer: learning from past cases — the way an experienced clinician does — but in a tooled, traceable and interpretable way.

The result, first

REMI (from the French Revascularisation Endovasculaire des Membres Inférieurs — Lower-Limb Endovascular Revascularization) is a clinical decision-support project I have coordinated since 2021, in close collaboration with the vascular surgery department of Grenoble Alpes University Hospital. Within a few years, it has made it possible to:

design and deploy in the clinic a user-centred data-collection software;
turn real clinical data — incomplete and heterogeneous — into a usable case base;
demonstrate the relevance of case-based reasoning to suggest, for a new patient, the strategies that succeeded in similar patients;
bring a doctoral thesis to completion (Margaux Roux, defended with distinction on 16 December 2025) and lead a multidisciplinary team funded by five successive grants.

This project consisted of taking a concrete clinical need, translating it into specifications, removing the technical and organizational roadblocks, and going all the way to a genuinely used prototype.

The clinical problem: a decision that is hard to anticipate

Peripheral Arterial Disease (PAD) of the lower limbs is an arterial condition whose main symptoms are pain and ischemic wounds. To avoid severe complications — amputation, death — revascularization aims to restore blood flow, either endovascularly (angioplasty, stenting) or through open surgery.

The problem: the probability of success or failure of a given technique remains hard to predict. The surgeon relies on decision trees, scores (WIfI) and, above all, on experience. To date, no tool fully helps them choose, for this patient, the most promising strategy.

Endovascular revascularization techniques: angioplasty and stenting (fig. 1.9, M. Roux thesis).

A method: case-based reasoning

Clinical decision-support systems traditionally fall into two families: statistical approaches, powerful but often poorly interpretable (“black boxes”), and expert-rule approaches, transparent but hard to scale.

REMI explores a middle path: Case-Based Reasoning (CBR). Its assumption — “similar problems have similar solutions” — translates, in the clinic, into: similar symptoms, treated with similar therapies, lead to similar outcomes. It is a learning method close to medical reasoning itself, and naturally more explainable: every recommendation rests on real cases that can be examined.

The CBR cycle unfolds in four steps (shown in the cover image): retrieve similar cases, reuse and adapt their solution, revise the outcome, then retain the new case to enrich the base.

From raw clinical data to a usable case base

This is often the most underestimated — and most structuring — step. The data available in electronic health records are incomplete, heterogeneous and designed for care, not for analysis. The project therefore had to:

model a “case”: a set of attributes describing the problem (severity, WIfI score, lesion anatomy, comorbidities) and a second set describing the surgical solution and its outcome;
explicitly handle missing data and attribute typing;
combine retrospective and prospective data, then develop a Python extraction-and-aggregation pipeline that transforms patient-centred data into a decision-support-oriented case base.

Class diagram of the data model implemented in the collection software (fig. 3.9, M. Roux thesis).

A user-centred prototype, deployed in the clinic

To collect high-quality prospective data, we designed a prototype software directly usable by clinicians, within their workflow. It automatically computes the WIfI score (and thus the amputation risk), models an operation as a sequence of surgical gestures applied to lesions, and automatically generates an operative report.

This is exactly the kind of deliverable I care about: a tool designed with and for its users, robust enough to leave the lab bench and enter clinical practice. Developing this application justified hiring a dedicated research engineer.

Interface of the prototype data-collection software (fig. 3.11, M. Roux thesis).

Demo video of the software, presented at the project’s first conference (in French).

Representing cases to compare them

Comparing two patients requires a sound similarity measure between cases. The project relies on an autoencoder: a neural network that learns to represent each case in a compact latent space, where geometric proximity reflects clinical similarity. Retrieval of relevant cases then takes place in that space.

Retrieval of similar cases in the learned latent space (fig. 4.4, M. Roux thesis).

Project leadership and funding

Started in 2021 with Prof. Rafaëlle Spear, the project gradually brought together three sites (TIMC in Grenoble, LTSI in Rennes, Grenoble Alpes University Hospital) and was supported by €284,450 raised from four funding sources.

Period	Project / scheme	Co-lead(s)	Funding obtained	Source	Amount
2021–2022	REMI-ORIA	Rafaëlle Spear	Equipment	EMERGENCE (TIMC laboratory)	€12,000
2022–2023	User-centered development for data collection in endovascular revascularization	Rafaëlle Spear & Alexandre Demeure	2 Master’s (M2) interns (Laure Chatenet & Clément Gasse)	MIAI@Grenoble Alpes (ANR-19-P3IA-0003)	€11,200
2024–2025	CAMI-assistant chair	Sandrine Voros	1 research engineer for one year (Romaric Ruga) + equipment	MIAI@Grenoble Alpes (ANR-19-P3IA-0003)	€66,056
2024–2026	Decision support — REMI	Rafaëlle Spear & Pascal Haigron	1 PhD student (Margaux Roux)	LabeX CAMI	€160,000
2026–2027	Clinical deployment and validation of an AI tool	Rafaëlle Spear	Thesis completion + 1 intern + software subcontracting	Fondation pour l’Avenir	€35,194
				Total	€284,450

Supervision and collaborations

Margaux Roux, PhD student — thesis “Decision support for lower-limb endovascular revascularization”, defended on 16 December 2025 (co-supervision at 33% with R. Spear and P. Haigron).
Laure Chatenet and Clément Gasse, Master’s (M2) interns.
Romaric Ruga, research engineer (finalizing the data-collection software).
Prof. Rafaëlle Spear (PU-PH, vascular surgery, Grenoble Alpes University Hospital) — clinical co-lead since the project’s inception.
Prof. Pascal Haigron (University of Rennes, LTSI) — thesis co-supervisor.
Sandrine Voros (TIMC) and Alexandre Demeure — co-leads on funding schemes.

Publications

2025. Roux Margaux, Spear Rafaëlle, Fouard Céline, Haigron Pascal — Retrieving similar cases for clinical decision support in the context of revascularization of lower limbs. International Journal of Medical Informatics, Vol 201, pp105931
2024. Roux Margaux, Spear Rafaëlle, Haigron Pascal, Demeure Alexandre, Fouard Céline — Toward Decision Support System for Lower Limb Endovascular Revascularization. 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
2023. Spear Rafaëlle, Fouard Céline, Demeure Alexandre, Gasse Clément, Chatenet Laure — User-centered design for the development of a patient monitoring software for peripheral arterial disease. Annals of Vascular Surgery

Together with , this project anchors my work in — with one constant requirement: interpretable methods, genuinely usable tools, and an ongoing dialogue with clinicians.

LPR: from a lab idea to a clinical prototype

Mon, 01 Jun 2020 00:00:00 +0000

Taking a medical robot from concept to first-in-human trials: TRL maturation, quality assurance, risk analysis and industrial spin-off.

The clinical gesture

Inserting a needle under image guidance is a common interventional-radiology procedure: for a biopsy or tumour ablation, the clinician acquires a volume image, plans a trajectory on one slice, then inserts the needle. The gesture is delicate — at the moment of insertion the radiologist has very few guidance tools and relies mostly on experience and on memorising the chosen slice. Under CT, checking the trajectory means repeated control images, hence radiation and back-and-forth; under MRI, the gesture becomes almost impossible to perform by hand inside the bore.

The LPR (Light Puncture Robot) addresses this: a lightweight robot placed directly on the patient to follow its motion as closely as possible, able to hold, position and insert the needle under the clinician’s control. It is compatible with both X-ray CT and MRI — therefore built entirely from non-ferromagnetic materials — and registers itself automatically in the image. The video below sums it up, from registration to needle positioning:

Climbing the TRLs

The real challenge with a medical device isn’t having the idea: it’s pushing it up the technology-readiness levels (TRL) until it can be tested on humans. Here is the path the LPR travelled, from concept (TRL 1) to clinical prototype (TRL 6):

The first steps were quick: observing the clinical procedure, the first design, the first prototype (the α prototype, already there when I joined the team). The real work started afterwards. Moving from TRL 4 to TRL 5 — from a lab-validated robot to one cleared for testing on humans — took far more than research: a redesign of the code under quality assurance, a full risk analysis, and outside expertise. We worked with our partner Axe Systems to manufacture the mechanical part under quality assurance, and with the clinical investigation centre (CIC-IT) of Grenoble Alpes University Hospital and the company SQI for risk analysis and quality-controlled development. This file secured clearance from the French medicines agency (ANSM) and let us build a protocol guaranteeing the robot’s safety for preclinical trials on healthy subjects in MRI, without needle insertion.

These trials mobilised, over two years, a ten-person team that I coordinated (3 from the CIC-IT, 3 from TIMC, 2 from Axe Systems, 2 from SQI).

Moving from TRL 4 to TRL 5 means rewriting the code under quality assurance, running a risk analysis, and making research, clinical and industry teams work together. That is exactly the work a company expects when it wants to turn a promising prototype into a credible device.

The next step — industrialisation — could no longer happen in the lab. So I led a start-up project built on the robot, supported by Grenoble’s tech-transfer office (SATT Linksium), first in maturation (2017) then in incubation (2018–2019). This phase produced two patents and two applications to the national BPI i-Lab innovation contest (2018 and 2019). The feedback was excellent — 17/20 on the technology dimension, 14.6/20 on the financial dimension, 14.8/20 overall — but the project was ultimately not funded. I recruited and supervised an engineer (Jérémy Lenfant) and then two successive co-founders for the business side (Bertrand Perrin, then Antoine Bourrier).

Project management: the funding

Beyond the technical side, the LPR was a long exercise in coordination at the research / clinical / industry interface, backed by a series of grants I secured and ran:

Project	Role	Funder / type	Partners	Period
Robacus	Coordinator	ANR TecSan — ANR-11-TECS-020-01	TIMC, LIRMM, Grenoble Alpes Univ. Hospital (CIC-IT, radiology), Axe Systems	2012–2015
LPROP	Coordinator	Carnot LSI Institute — pre-maturation	TIMC	2015–2016
Emergence (×2)	Coordinator	TIMC — internal (equipment & interns)	TIMC	2016–2017
LPR maturation	Coordinator	SATT Linksium	TIMC, Linksium	2017
LPR incubation	Coordinator	SATT Linksium	Linksium, co-founders	2018–2019

Behind the scenes: remote control of the robot

In collaboration with the LIRMM team (Montpellier), a partner in the Robacus project, we demonstrated real-time remote control of the robot through a force-feedback teleoperation interface — a step toward a gesture where the radiologist would drive insertion from the control room, without radiation exposure. This feasibility demo was not taken further, but it nicely illustrates the flexibility of the guidance software’s architecture, built on , the medical-application prototyping framework I co-develop: its modularity made it possible to reuse code from one prototype version to the next, rather than rewriting everything.

Skills brought to bear

Multi-partner project coordination (research · clinical · industry) · quality-assured and risk-analysed development of a medical device · running regulated preclinical trials on healthy subjects · TRL maturation of a software component, from concept to clinical prototype · industrial maturation and incubation (patent drafting, business plan, team recruitment) · modular, reusable software architecture for medical prototyping.

2022. Fouard Céline, Lenfant Jérémy, Ganesaratnam Gokularajah, Hungr Nikolaï — Connector for cables. US Patent
2018. Ghelfi Julien, Moreau-Gaudry Alexandre, Hungr Nikolaï, Fourd Céline, Veron Baptiste, Medici Maud, Chipon Émilie, Cinquin Philippe, Bricault Ivan — Evaluation of the needle positioning accuracy of a light puncture robot under MRI guidance: results of a clinical trial on healthy volunteers. Cardiovascular and interventional radiology, vol 41 no 9
2016. Hungr Nikolaï, Bricault Ivan, Cinquin Philippe, Fouard Céline — Design and validation of a CT-and MRI-guided robot for percutaneous needle procedures. IEEE transactions on robotics, vol 32 Issue 4
2014. Dorileo Ederson, Hungr Nikolaï, Zemiti Nabil, Fouard Céline, Poignet Philippe — A modular CT/MRI-guided teleoperation platform for robot assisted punctures planning. CARS 2014-28th International Congress and Exhibition on Computer Assisted Radiology and Surgery
2014. Dorileo Ederson, Zemiti Nabil, Poignet Philippe, Hungr Nikolaï, Bricault Ivan, Fouard Céline — Observations of Lightly Flexible Needle Deflection in 3D CT/MRI. Proceedings of Surgetica 2014
2011. Hungr Nikolaï, Fouard Céline, Robert Adeline, Bricault Ivan, Cinquin Philippe — Interventional radiology robot for CT and MRI guided percutaneous interventions. Proceedings of the 14th international conference on Medical image Ccomputing and Computer-Assisted Intervention (MICCAI)
2008. Zemiti Nabil, Bricault Ivan, Fouard Céline, Sanche Bénédicte, Cinquin Philippe — LPR: A CT and MR-compatible puncture robot to enhance accuracy and safety of image-guided interventions. IEEE/ASME Transactions on Mechatronics
2008. Bricault Ivan, Zemiti Nabil, Jouniaux Émilie, Fouard Céline, Taillant Élise, Dorandeu Frédéric, Cinquin Philippe — Light Puncture Robot for CT and MRI Interventions. IEEE Engineering in Medicine and Biology Magazine

Automatically locating organs in CT images

Fri, 30 Sep 2016 00:00:00 +0000

My first turn toward machine learning — taken, with this student, two years before the deep-learning boom.

In the continuation of the project, I co-supervised with Emmanuel Promayon the PhD of Prasad Samarakoon, defended on 30 September 2016 at Université Grenoble Alpes (funded by the French ANR TecSan project “Robacus”). This is the project that tipped me toward machine learning applied to medical imaging. We started two years before the rise of deep-learning segmentation: so we bet not on deep neural networks, but on decision-tree forests (random forests) — a clear-eyed choice for the time, and a formative one.

What this thesis really gave me was not one more method: it was an early familiarity with the strengths and the limits of learning-based approaches — first among them their surprising robustness.

The challenge: locating, not segmenting

To plan a puncture assisted by the LPR robot, one must first locate, in the CT scan, the target organs and those to avoid — a step still done by hand by the clinician, tedious and costly in expert time. Rather than aiming straight for full segmentation (delineating every contour), we tackled the more tractable and equally useful problem of localization: enclosing each organ in a bounding box, automatically.

The contribution

Beyond a thorough analysis of the method, the thesis produced two contributions of real practical reach:

the Light Random Regression Forests: a faster and far more memory-efficient model, at equivalent accuracy — and therefore easier to embed and deploy;
an automatic parametrization that removes settings previously fixed “by hand”, making the method more robust and more reproducible from one dataset to another.

The regression-forest pipeline: training-set preparation, preprocessing, training, then prediction (data in yellow, algorithmic steps in blue)

Robustness — and bias: the phantom-kidney story

One experiment remains, for me, the perfect illustration of what these methods really are. To learn to locate the kidneys, our training database — built from experts’ manual delineations (ours and those of the team’s PhD students) — contained only patients with two kidneys. During the testing phase, the radiologist handed us the image of a patient who had only one. The algorithm dutifully found… two bounding boxes, placing a “phantom kidney” exactly where statistics expected it.

Even then, we were alert to a truth that has lost none of its relevance: a model is only the reflection of the data it is shown. The quality and representativeness of the training set matter as much as the algorithm itself.

What this project represented

With the rise of deep learning, this forest-based localization strategy was later set aside — but it was decisive. It let me approach the machine-learning turn from the foundations, at a time when one still took the time to understand why a method works, what it guarantees, and where it fails. That perspective — robustness, generalization, vigilance about the data — is exactly what I bring today to medical-application prototyping.

Skills involved: doctoral co-supervision · machine learning applied to medical imaging · design of robust, automatic methods · building and critically assessing training datasets.

2017. Samarakoon Prasad N, Promayon Emmanuel, Fouard Céline — Light Random Regression Forests for automatic multi-organ localization in CT images. 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)
2014. Saramakoon Prasad, Promayon Emmanuel, Fouard Céline — Fully Automatic Organ Localization in Medical Images Using Improved Random Regression Forests. Proceedings of Surgetica 2014

CamiTK: a workshop for prototyping medical applications

Tue, 01 Nov 2011 00:00:00 +0000

From software to method — capitalizing on interdisciplinary know-how to move faster, from concept to validated prototype.

Designing an application for the operating room is never “just code.” It means getting medical images, sensors, biomechanical models — sometimes a robot — and above all specialists who don’t speak the same technical language, to work together. CamiTK is the tool I co-founded with Emmanuel Promayon so that this dialogue produces prototypes — fast, clean, and reusable. It is also the foundation of expertise I now draw on to help companies prototype medical applications.

The problem: interdisciplinarity is expensive

In computer-assisted medical interventions, every team shows up with its own world: its operating system, its language of choice, its libraries, its habits — and its level of maturity, from throwaway prototype to clinical-grade software. With each new project, the temptation is to rewrite everything. You reinvent the wheel, you lose months, and the know-how walks out the door when someone leaves the team.

For a company, this is exactly the pain point: how do you avoid starting from scratch with every innovation, while keeping the rigor that medical work demands?

The answer: a shared software foundation

With Emmanuel Promayon, we designed CamiTK as a modular workshop: a stable core that handles what is common to every project — 3D visualization, interaction, data and input/output management, abstraction of medical formats (DICOM, meshes…) — and around which each specialist plugs in their own domain extension, without touching the rest.

CamiTK’s building-block architecture: a shared core, an interface layer, and one extension per domain of expertise.

This architectural choice (a C++/Qt/VTK core, following component-based software engineering) delivers what a company looks for in a technical foundation. And since version 5, CamiTK also accepts Python extensions: you can prototype an idea in a few lines, then harden it in C++ once validated — exactly the right trade-off between exploration speed and production robustness.

In practice, the foundation provides:

Cross-platform — the same code runs on Linux, Windows and macOS.
Interoperability — the building blocks of one project are reused in the next.
Default behaviors — a specialist plugs in their algorithm and immediately gets a working application, without rewriting the interface.
Intellectual-property safeguards — each module keeps its own license; the open-source core coexists with proprietary extensions (as was the case for the confidential LPR modules).
Durability — the knowledge stays in the tool, not only in people’s heads.

Example of an application prototyped with CamiTK.

From software building block to method

CamiTK’s most valuable contribution is not the code: it is what its practice taught us. By guiding real projects all the way to technology transfer — first among them the — we generalized a methodology for maturing software building blocks for medical devices, aligned with the TRL (Technology Readiness Levels) scale.

Concretely: knowing what maturity level a prototype sits at, what it takes to reach the next one, and where to invest validation and software-quality effort so you don’t get stuck at the moment of industrial or clinical transfer. This is exactly the kind of course a company needs to hold when moving an idea from the lab to a product.

Over the projects, CamiTK thus became a dual methodological tool: to make disciplines collaborate, and to structure the climb up the TRL scale.

Adoption as proof

A method is only worth as much as its ability to outlive its authors. CamiTK has passed that test: released as open source, packaged in the official debian-med suite, adopted by internal and national projects, and — the most telling proof — still actively developed more than fifteen years after it began (version 6.0, with new tools such as DevStudio to create an extension in minutes).

A continuous adoption trajectory, from the lab to the open-source ecosystem.

This project also gave me the chance to coordinate and co-supervise a team of engineers — up to four at once — over several years: hiring, organizing development, code review, documentation, and nurturing a community of users.

What I take from it — and what I can bring

I founded and structured CamiTK; today, I use it daily as an expert. This dual standpoint — the one who designed the architecture and the one who uses it — lets me bring to a company:

a durable software architecture designed for reuse and cross-platform support;

a maturity-scaling (TRL) method proven on real technology transfers;

the ability to make very different profiles collaborate (clinical, research, engineering, industry) around a single prototype;

fine-grained intellectual-property management in an ecosystem mixing open source and proprietary building blocks;

the supervision of technical teams over the long term.

Publications

2013. Promayon Emmanuel, Fouard Céline, Deram Aurélien, Hungr Nikolaï, Luboz Vincent, Payan Yohan, Sarrazin Johan, Saubat Nicolas, Selmi Sonia Yuki, Voros Sandrine, Cinquin Philippe, Troccaz Jocelyne — Using CamiTK for Rapid Prototyping of Interactvie Computer Assisted Medical Intervention Applications. Proceedings of 35th Annual International Conference of the IEEE EMBS
2012. Fouard Céline, Deram Aurélien, Keraval Yannick, Promayon Emmanuel — CamiTK: a Modular Framework Integrating Visualization, Image Processing and Biomechanical Modeling. Soft Tissue Biomechanical Modeling for Computer Assisted Surgery

CamiTK is the thread that runs through all my projects, from the to : the conviction that a good medical prototype begins with good engineering — shared, and built to last.

Interventional cardiology

Mon, 01 Jan 0001 00:00:00 +0000

From clinical need to prototype: guiding the gesture at the heart of the cath lab.

Interventional cardiology is performed under imaging, yet the clinician must often act without directly seeing the target: the lesion to treat or to biopsy does not appear on the real-time image in the room. Carried out with Prof. Gilles Barone-Rochette (Grenoble Alpes University Hospital) and the LTSI laboratory in Rennes, this project pursues a single goal expressed through two clinical questions: to give the cardiologist reliable guidance, built from preoperative imaging and usable directly in the room.

The common thread: bouncing back when the data runs short

The project started with the guidance of cell therapy. The first clinical trial enrolled fewer patients than expected: the data needed for the next steps were not there. Rather than abandoning it, we redeployed the technical building blocks already developed (image segmentation, navigation) toward a related clinical need with more immediate value and a better-identified bottleneck: endomyocardial biopsy.

This pivot is, in itself, a deliverable: it illustrates the ability to de-risk a project, preserve the assets already built, and refocus the effort where the clinical value is highest — exactly the kind of trade-off a company expects when an R&D programme does not go as planned.

Sub-project 1 — Guiding post-infarction cell therapy

After a heart attack, some therapies consist in re-injecting cells into the myocardium. The whole challenge is precision: reaching the right areas, relying on information (the extent of fibrosis, the viable regions) that is only visible on preoperative imaging, not on the real-time image in the room.

Our approach: fuse multimodal imaging to transfer, during the intervention, the targets identified preoperatively. The core building block is the automatic segmentation of the myocardium and fibrosis on late gadolinium enhancement MRI (LGE-MRI), developed using deep learning as part of Erwan Lecesne’s PhD (co-supervised with the LTSI in Rennes), then integrated into to be presented to the clinician in the room.

Re-injecting cells in the right place: the precision of the gesture determines the therapy’s effectiveness.

CamiTK is a prototyping toolkit: it makes it possible to move quickly from concept to evaluated prototype, but its output is not meant to be a CE-marked medical device. This building block is therefore a proof of concept; its industrial transfer is currently under discussion with partners in the field.

Sub-project 2 — A map for endomyocardial biopsy

Three conditions — cardiac sarcoidosis, chronic myocarditis and arrhythmogenic cardiomyopathy — can present a similar clinical picture yet call for opposite treatments. To decide, a biopsy is needed… provided the sample is taken in the right place.

Endomyocardial biopsy: sampling a piece of cardiac tissue, where the lesion is located.

The state of the art leaves a real gap:

“blind” biopsy is poorly specific, because the fibrosis to target stays invisible during the gesture;
electro-anatomical guidance is long and, likewise, blind to fibrosis.

Our solution acts as a “GPS” for the biopsy catheter: it transfers the target identified on preoperative imaging onto the real-time image, to guide the sampling. Two design choices make it a solution built for adoption: it is hardware-independent (compatible with an existing room) and works on real-time fluoroscopy, with no complex fusion step. It directly reuses the segmentation building block from the first sub-project.

Diagram of the proposed guidance system for endomyocardial biopsy (published).

Current status: we are preparing the first clinical trials in the laboratory; industrial transfer will follow.

What this project demonstrates

Designing from a real clinical need, in close dialogue with practitioners, rather than around a technical feat.
Mastering medical image processing and AI, and putting them at the service of a precise, useful target.
Taking a prototype from the laboratory toward the clinic, with a clear awareness of maturity stages (TRL), the trial framework and CE marking.
Architecting for adoption: hardware independence, integration into a prototyping toolkit, reuse of building blocks.
Refocusing a project to preserve its value: agility and de-risking in the face of the unexpected.
Leading a multi-site collaboration (Grenoble–Rennes) and co-supervising a PhD.

Funding obtained

Funding	Amount	Purpose
Famtastic project (France Life Imaging)	€20,000	Kick-starting the collaboration with the LTSI (Rennes)
PUI (UGA)	€60,000	Maturing the prototype toward the first clinical trials
PhD funding (LabeX CAMI)	€170,000	Co-supervision of Erwan Lecesne’s PhD
Post-doctorate (LabeX CAMI)	€56,000	One year of post-doctoral engineering
Total	€306,000

Collaborations and supervision

Prof. Gilles Barone-Rochette — interventional cardiologist, Grenoble Alpes University Hospital: clinical partner of the project.
LTSI laboratory (Rennes) — Professor Mireille Garreau and Antoine Simon (associate professor): collaboration on cardiac image processing.
Erwan Lecesne’s PhD (2020–2024), co-supervised at 50% with Mireille Garreau (LTSI): multimodal image processing to improve post-infarction cell therapy.
Théophile Tiffet’s PhD — medical resident: echocardiography / SPECT calibration for interventional cardiology.

2024. Barone-Rochette Gilles, MD,, Erwan Lecesne, MSc,, Antoine Simon, PhD, Mireille Garreau, PhD,, Celine Fouard, PhD — New Method CMR-Guided Endomyocardial Biopsy in Suspicion Context of Isolated Cardiac Sarcoidosis. Circulation: Cardiovascular Imaging, vol 17, no 4
2023. Erwan Lecesne, Antoine Simon, Mireille Garreau, Barone-Rochette Gilles, Celine Fouard — Segmentation of cardiac infarction in delayed-enhancement MRI using probability map and transformers-based neural networks. Computer Methods and Programs in Biomedicine, vol 242
2023. Lecesne Erwan, Simon Antoine, Garreau Mireille, Barone-Rochette Gilles, Fouard Céline — Transformers-Based Neural Network for Cardiac Infarction Segmentation in Delayed-Enhancement MRI. 2023 IEEE Twelfth International Conference on Image Processing Theory, Tools and Applications (IPTA)

Pilotage-Projets |

REMI — Decision Support for Lower-Limb Endovascular Revascularization

The result, first

The clinical problem: a decision that is hard to anticipate

A method: case-based reasoning

From raw clinical data to a usable case base

A user-centred prototype, deployed in the clinic

Representing cases to compare them

Project leadership and funding

Supervision and collaborations

Publications

LPR: from a lab idea to a clinical prototype

The clinical gesture

Climbing the TRLs

Project management: the funding

Behind the scenes: remote control of the robot

Skills brought to bear

Related publications

Automatically locating organs in CT images

The challenge: locating, not segmenting

The contribution

Robustness — and bias: the phantom-kidney story

What this project represented

Related publications

CamiTK: a workshop for prototyping medical applications

The problem: interdisciplinarity is expensive

The answer: a shared software foundation

From software building block to method

Adoption as proof

What I take from it — and what I can bring

Publications

Interventional cardiology

The common thread: bouncing back when the data runs short

Sub-project 1 — Guiding post-infarction cell therapy

Sub-project 2 — A map for endomyocardial biopsy

What this project demonstrates

Funding obtained

Collaborations and supervision

Related publications