Carole Frindel

Nima Hatami, Tae-Hee Cho, Laura Mechtouff et al.

Clinical outcome prediction plays an important role in stroke patient management. From a machine learning point-of-view, one of the main challenges is dealing with heterogeneous data at patient admission, i.e. the image data which are multidimensional and the clinical data which are scalars. In this paper, a multimodal convolutional neural network - long short-term memory (CNN-LSTM) based ensemble model is proposed. For each MR image module, a dedicated network provides preliminary prediction of the clinical outcome using the modified Rankin scale (mRS). The final mRS score is obtained by merging the preliminary probabilities of each module dedicated to a specific type of MR image weighted by the clinical metadata, here age or the National Institutes of Health Stroke Scale (NIHSS). The experimental results demonstrate that the proposed model surpasses the baselines and offers an original way to automatically encode the spatio-temporal context of MR images in a deep learning architecture. The highest AUC (0.77) was achieved for the proposed model with NIHSS.

Ezequiel de la Rosa, Ruisheng Su, Mauricio Reyes et al.

Accurate estimation of brain infarction (i.e., irreversibly damaged tissue) is critical for guiding treatment decisions in acute ischemic stroke. Reliable infarct prediction informs key clinical interventions, including the need for patient transfer to comprehensive stroke centers, the potential benefit of additional reperfusion attempts during mechanical thrombectomy, decisions regarding secondary neuroprotective treatments, and ultimately, prognosis of clinical outcomes. This work introduces the Ischemic Stroke Lesion Segmentation (ISLES) 2024 challenge, which focuses on the prediction of final infarct volumes from pre-interventional acute stroke imaging and clinical data. ISLES24 provides a comprehensive, multimodal setting where participants can leverage all clinically and practically available data, including full acute CT imaging, sub-acute follow-up MRI, and structured clinical information, across a train set of 150 cases. On the hidden test set of 98 cases, the top-performing model, a multimodal nnU-Net-based architecture, achieved a Dice score of 0.285 (+/- 0.213) and an absolute volume difference of 21.2 (+/- 37.2) mL, underlining the significant challenges posed by this task and the need for further advances in multimodal learning. This work makes two primary contributions: first, we establish a standardized, clinically realistic benchmark for post-treatment infarct prediction, enabling systematic evaluation of multimodal algorithmic strategies on a longitudinal stroke dataset; second, we analyze current methodological limitations and outline key research directions to guide the development of next-generation infarct prediction models.

Nima Hatami, Laura Mechtouff, David Rousseau et al.

Patient outcome prediction is critical in management of ischemic stroke. In this paper, a novel machine learning model is proposed for stroke outcome prediction using multimodal Magnetic Resonance Imaging (MRI). The proposed model consists of two serial levels of Autoencoders (AEs), where different AEs at level 1 are used for learning unimodal features from different MRI modalities and a AE at level 2 is used to combine the unimodal features into compressed multimodal features. The sequences of multimodal features of a given patient are then used by an LSTM network for predicting outcome score. The proposed AE2-LSTM model is proved to be an effective approach for better addressing the multimodality and volumetric nature of MRI data. Experimental results show that the proposed AE2-LSTM outperforms the existing state-of-the art models by achieving highest AUC=0.71 and lowest MAE=0.34.

Morgane des Ligneris, Nathan Painchaud, Allan Serva et al.

Pulmonary embolism, the obstruction of a pulmonary artery by a blood clot, is one of the leading causes of acute cardiovascular syndrome. In clinical practice, therapeutic decisions after diagnosis via computed tomography pulmonary angiography rely on risk stratification, which categorizes 30-day mortality risk into three categories. This stratification depends on the right-to-left ventricular diameter ratio and blood levels of two cardiac enzymes. However, blood biomarkers are not always available in emergency settings, and manual calculation of established severity scores - such as Qanadli and Mastora - is time-consuming and rarely performed in clinical routine practice. This study introduces an automated pipeline that models a directed graph representation of the pulmonary arterial tree, labeling its hierarchical structure and characterizing pulmonary embolism. The pipeline derives image-based biomarkers, including local artery-level features (morphological information, hierarchical position, clot volume, and resulting obstruction) and global patient-level biomarkers such as automatically calculated severity scores (Qanadli and Mastora) and the total embolic volume distribution by lobes and hierarchical levels. Using artificial-intelligence-generated binary masks of arteries, emboli, lungs, and lobes, it creates a patient digital twin of the arterial structure. Validation of the pipeline through comparison to an existing pipeline, anatomical expectations, and manual severity score calculations demonstrates the pipeline's ability to automatically generate anatomically accurate digital twins and severity scores with strong agreement. This supports the potential of these image-derived biomarkers to automatically provide rapid, precise information on thrombotic burden and spatial clot distribution.

Ezequiel de la Rosa, Mauricio Reyes, Sook-Lei Liew et al.

Diffusion-weighted MRI (DWI) is essential for stroke diagnosis, treatment decisions, and prognosis. However, image and disease variability hinder the development of generalizable AI algorithms with clinical value. We address this gap by presenting a novel ensemble algorithm derived from the 2022 Ischemic Stroke Lesion Segmentation (ISLES) challenge. ISLES'22 provided 400 patient scans with ischemic stroke from various medical centers, facilitating the development of a wide range of cutting-edge segmentation algorithms by the research community. Through collaboration with leading teams, we combined top-performing algorithms into an ensemble model that overcomes the limitations of individual solutions. Our ensemble model achieved superior ischemic lesion detection and segmentation accuracy on our internal test set compared to individual algorithms. This accuracy generalized well across diverse image and disease variables. Furthermore, the model excelled in extracting clinical biomarkers. Notably, in a Turing-like test, neuroradiologists consistently preferred the algorithm's segmentations over manual expert efforts, highlighting increased comprehensiveness and precision. Validation using a real-world external dataset (N=1686) confirmed the model's generalizability. The algorithm's outputs also demonstrated strong correlations with clinical scores (admission NIHSS and 90-day mRS) on par with or exceeding expert-derived results, underlining its clinical relevance. This study offers two key findings. First, we present an ensemble algorithm (https://github.com/Tabrisrei/ISLES22_Ensemble) that detects and segments ischemic stroke lesions on DWI across diverse scenarios on par with expert (neuro)radiologists. Second, we show the potential for biomedical challenge outputs to extend beyond the challenge's initial objectives, demonstrating their real-world clinical applicability.

Guillaume Garret, Antoine Vacavant, Carole Frindel

Vascular segmentation represents a crucial clinical task, yet its automation remains challenging. Because of the recent strides in deep learning, vesselness filters, which can significantly aid the learning process, have been overlooked. This study introduces an innovative filter fusion method crafted to amplify the effectiveness of vessel segmentation models. Our investigation seeks to establish the merits of a filter-based learning approach through a comparative analysis. Specifically, we contrast the performance of a U-Net model trained on CT images with an identical U-Net configuration trained on vesselness hyper-volumes using matching parameters. Our findings, based on two vascular datasets, highlight improved segmentations, especially for small vessels, when the model's learning is exposed to vessel-enhanced inputs.

Guillaume Garret, Antoine Vacavant, Carole Frindel

Deep learning models have achieved impressive performance in medical image segmentation, yet their black-box nature limits clinical adoption. In vascular applications, trustworthy segmentation should rely on both local image cues and global anatomical structures, such as vessel connectivity or branching. However, the extent to which models leverage such global context remains unclear. We present a novel explainability pipeline for 3D vessel segmentation, combining gradient-based attribution with graph-guided point selection and a blob-based analysis of Saliency maps. Using vascular graphs extracted from ground truth, we define anatomically meaningful points of interest (POIs) and assess the contribution of input voxels via Saliency maps. These are analyzed at both global and local scales using a custom blob detector. Applied to IRCAD and Bullitt datasets, our analysis shows that model decisions are dominated by highly localized attribution blobs centered near POIs. Attribution features show little correlation with vessel-level properties such as thickness, tubularity, or connectivity -- suggesting limited use of global anatomical reasoning. Our results underline the importance of structured explainability tools and highlight the current limitations of segmentation models in capturing global vascular context.

Méghane Decroocq, Carole Frindel, Pierre Rougé et al.

Computational fluid dynamics (CFD) simulation provides valuable information on blood flow from the vascular geometry. However, it requires extracting precise models of arteries from low-resolution medical images, which remains challenging. Centerline-based representation is widely used to model large vascular networks with small vessels, as it encodes both the geometric and topological information and facilitates manual editing. In this work, we propose an automatic method to generate a structured hexahedral mesh suitable for CFD directly from centerlines. We addressed both the modeling and meshing tasks. We proposed a vessel model based on penalized splines to overcome the limitations inherent to the centerline representation, such as noise and sparsity. The bifurcations are reconstructed using a parametric model based on the anatomy that we extended to planar n-furcations. Finally, we developed a method to produce a volume mesh with structured, hexahedral, and flow-oriented cells from the proposed vascular network model. The proposed method offers better robustness to the common defects of centerlines and increases the mesh quality compared to state-of-the-art methods. As it relies on centerlines alone, it can be applied to edit the vascular model effortlessly to study the impact of vascular geometry and topology on hemodynamics. We demonstrate the efficiency of our method by entirely meshing a dataset of 60 cerebral vascular networks. 92% of the vessels and 83% of the bifurcations were meshed without defects needing manual intervention, despite the challenging aspect of the input data. The source code is released publicly.

Théo Jourdan, Antoine Boutet, Carole Frindel

Federated Learning (FL) is a collaborative scheme to train a learning model across multiple participants without sharing data. While FL is a clear step forward towards enforcing users' privacy, different inference attacks have been developed. In this paper, we quantify the utility and privacy trade-off of a FL scheme using private personalized layers. While this scheme has been proposed as local adaptation to improve the accuracy of the model through local personalization, it has also the advantage to minimize the information about the model exchanged with the server. However, the privacy of such a scheme has never been quantified. Our evaluations using motion sensor dataset show that personalized layers speed up the convergence of the model and slightly improve the accuracy for all users compared to a standard FL scheme while better preventing both attribute and membership inferences compared to a FL scheme using local differential privacy.

Claude Rosin Ngueveu, Antoine Boutet, Carole Frindel et al.

With the widespread adoption of the quantified self movement, an increasing number of users rely on mobile applications to monitor their physical activity through their smartphones. Granting to applications a direct access to sensor data expose users to privacy risks. Indeed, usually these motion sensor data are transmitted to analytics applications hosted on the cloud leveraging machine learning models to provide feedback on their health to users. However, nothing prevents the service provider to infer private and sensitive information about a user such as health or demographic attributes.In this paper, we present DySan, a privacy-preserving framework to sanitize motion sensor data against unwanted sensitive inferences (i.e., improving privacy) while limiting the loss of accuracy on the physical activity monitoring (i.e., maintaining data utility). To ensure a good trade-off between utility and privacy, DySan leverages on the framework of Generative Adversarial Network (GAN) to sanitize the sensor data. More precisely, by learning in a competitive manner several networks, DySan is able to build models that sanitize motion data against inferences on a specified sensitive attribute (e.g., gender) while maintaining a high accuracy on activity recognition. In addition, DySan dynamically selects the sanitizing model which maximize the privacy according to the incoming data. Experiments conducted on real datasets demonstrate that DySan can drasticallylimit the gender inference to 47% while only reducing the accuracy of activity recognition by 3%.