Ia-Sante |

Retrieving similar cases for clinical decision support in the context of revascularization of lower limbs

Mon, 01 Sep 2025 00:00:00 +0000

New Method CMR-Guided Endomyocardial Biopsy in Suspicion Context of Isolated Cardiac Sarcoidosis

Sun, 01 Sep 2024 00:00:00 +0000

Toward Decision Support System for Lower Limb Endovascular Revascularization

Mon, 01 Jan 2024 00:00:00 +0000

Segmentation of cardiac infarction in delayed-enhancement MRI using probability map and transformers-based neural networks

Fri, 01 Dec 2023 00:00:00 +0000

Transformers-Based Neural Network for Cardiac Infarction Segmentation in Delayed-Enhancement MRI

Mon, 16 Oct 2023 00:00:00 +0000

User-centered design for the development of a patient monitoring software for peripheral arterial disease

Sun, 01 Oct 2023 00:00:00 +0000

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.

Light Random Regression Forests for automatic multi-organ localization in CT images

Tue, 18 Apr 2017 00:00:00 +0000

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

Fully Automatic Organ Localization in Medical Images Using Improved Random Regression Forests

Wed, 01 Jan 2014 00:00:00 +0000

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)