Sidaty el Hadramy

Sidaty El Hadramy, Nazim Haouchine, Michael Wehrli et al.

This paper presents NOIR, a framework that reframes core medical imaging tasks as operator learning between continuous function spaces, challenging the prevailing paradigm of discrete grid-based deep learning. Instead of operating on fixed pixel or voxel grids, NOIR embeds discrete medical signals into shared Implicit Neural Representations and learns a Neural Operator that maps between their latent modulations, enabling resolution-independent function-to-function transformations. We evaluate NOIR across multiple 2D and 3D downstream tasks, including segmentation, shape completion, image-to-image translation, and image synthesis, on several public datasets such as Shenzhen, OASIS-4, SkullBreak, fastMRI, as well as an in-house clinical dataset. It achieves competitive performance at native resolution while demonstrating strong robustness to unseen discretizations, and empirically satisfies key theoretical properties of neural operators. The project page is available here: https://github.com/Sidaty1/NOIR-io.

Karl-Philippe Beaudet, Yordanka Velikova, Sidaty El Hadramy et al.

Purpose: Laparoscopic ultrasound (LUS) enhances the safety of liver surgery by visualizing intrahepatic vessels in real-time. Still, vessel identification remains difficult due to probe constraints, complex vascular structure, and tissue deformation. This work aims to enable real-time, patient-specific vessel identification that remains robust under deformation through deformable ultrasound augmentation. Methods: Preoperative CT vessel annotations are used to generate synthetic ultrasound data via optimized physics-based rendering, coupled with domain adaptation to intraoperative ultrasound. The rendering is trained end-to-end for vessel identification and patient-specificity, eliminating the need for preoperative ultrasound. A deformation-aware augmentation simulates realistic intraoperative motion and tissue deformation within the rendering pipeline. Results: In abdominal phantom and limited clinical feasibility experiments (single-case clinical evaluation), the framework achieved real-time intrahepatic vessel-branch identification, maintaining performance under new patient poses. Conclusion: The framework enables real-time vessel identification without preoperative ultrasound and supports technical feasibility, but multi-patient validation is still needed for generalizability and clinical feasibility.

Lorenzo Pettinari, Sidaty El Hadramy, Michael Wehrli et al.

Purpose: Intraoperative navigation in spine surgery demands millimeter-level accuracy. Current systems based on intraoperative radiographic imaging and bone-anchored markers are invasive, radiation-intensive and workflow disruptive. Recent markerless RGB-D registration methods offer a promising alternative, but existing approaches rely on weak segmentation labels to isolate relevant anatomical structures, which can propagate errors throughout registration. Methods: We present End2Reg an end-to-end deep learning framework that jointly optimizes segmentation and registration, eliminating the need for weak segmentation labels and manual steps. The network learns segmentation masks specifically optimized for registration, guided solely by the registration objective without direct segmentation supervision. Results: The proposed framework achieves state-of-the-art performance on ex- and in-vivo benchmarks, reducing median Target Registration Error by 32% to 1.83mm and mean Root Mean Square Error by 45% to 3.95mm, respectively. An ablation study confirms that end-to-end optimization significantly improves registration accuracy. Conclusion: The presented end-to-end RGB-D registration pipeline removes dependency on weak labels and manual steps, advancing towards fully automatic, markerless intraoperative navigation. Code and interactive visualizations are available at: https://lorenzopettinari.github.io/end-2-reg/.

Vincent Ochs, Florentin Bieder, Sidaty el Hadramy et al.

Tabular data builds the basis for a wide range of applications, yet real-world datasets are frequently incomplete due to collection errors, privacy restrictions, or sensor failures. As missing values degrade the performance or hinder the applicability of downstream models, and while simple imputing strategies tend to introduce bias or distort the underlying data distribution, we require imputers that provide high-quality imputations, are robust across dataset sizes and yield fast inference. We therefore introduce TabINR, an auto-decoder based Implicit Neural Representation (INR) framework that models tables as neural functions. Building on recent advances in generalizable INRs, we introduce learnable row and feature embeddings that effectively deal with the discrete structure of tabular data and can be inferred from partial observations, enabling instance adaptive imputations without modifying the trained model. We evaluate our framework across a diverse range of twelve real-world datasets and multiple missingness mechanisms, demonstrating consistently strong imputation accuracy, mostly matching or outperforming classical (KNN, MICE, MissForest) and deep learning based models (GAIN, ReMasker), with the clearest gains on high-dimensional datasets.

Karl-Philippe Beaudet, Sidaty El Hadramy, Philippe C Cattin et al.

Intraoperative ultrasound images are inherently challenging to interpret in liver surgery due to the limited field of view and complex anatomical structures. Bridging the gap between preoperative and intraoperative data is crucial for effective surgical guidance. 3D IntraVascular UltraSound (IVUS) offers a potential solution by enabling the reconstruction of the entire organ, which facilitates registration between preoperative computed tomography (CT) scans and intraoperative IVUS images. In this work, we propose an optimization-based calibration method using a 3D-printed phantom for accurate 3D Intravascular Ultrasound volume reconstruction. Our approach ensures precise alignment of tracked IVUS data with preoperative CT images, improving intraoperative navigation. We validated our method using in vivo swine liver images, achieving a calibration error from 0.88 to 1.80 mm and a registration error from 3.40 to 5.71 mm between the 3D IVUS data and the corresponding CT scan. Our method provides a reliable and accurate means of calibration and volume reconstruction. It can be used to register intraoperative ultrasound images with preoperative CT images in the context of liver surgery, and enhance intraoperative guidance.

Michael Wehrli, Alicia Durrer, Paul Friedrich et al.

To treat Trochlear Dysplasia (TD), current approaches rely mainly on low-resolution clinical Magnetic Resonance (MR) scans and surgical intuition. The surgeries are planned based on surgeons experience, have limited adoption of minimally invasive techniques, and lead to inconsistent outcomes. We propose a pipeline that generates super-resolved, patient-specific 3D pseudo-healthy target morphologies from conventional clinical MR scans. First, we compute an isotropic super-resolved MR volume using an Implicit Neural Representation (INR). Next, we segment femur, tibia, patella, and fibula with a multi-label custom-trained network. Finally, we train a Wavelet Diffusion Model (WDM) to generate pseudo-healthy target morphologies of the trochlear region. In contrast to prior work producing pseudo-healthy low-resolution 3D MR images, our approach enables the generation of sub-millimeter resolved 3D shapes compatible for pre- and intraoperative use. These can serve as preoperative blueprints for reshaping the femoral groove while preserving the native patella articulation. Furthermore, and in contrast to other work, we do not require a CT for our pipeline - reducing the amount of radiation. We evaluated our approach on 25 TD patients and could show that our target morphologies significantly improve the sulcus angle (SA) and trochlear groove depth (TGD). The code and interactive visualization are available at https://wehrlimi.github.io/sr-3d-planning/.

Sidaty El Hadramy, Oumeymah Cherkaoui, Philippe C. Cattin

Regularization is essential in deformable image registration (DIR) to ensure that the estimated Deformation Vector Field (DVF) remains smooth, physically plausible, and anatomically consistent. However, fine-tuning regularization parameters in learning-based DIR frameworks is computationally expensive, often requiring multiple training iterations. To address this, we propose cIDI, a novel DIR framework based on Implicit Neural Representations (INRs) that conditions the registration process on regularization hyperparameters. Unlike conventional methods that require retraining for each regularization hyperparameter setting, cIDIR is trained over a prior distribution of these hyperparameters, then optimized over the regularization hyperparameters by using the segmentations masks as an observation. Additionally, cIDIR models a continuous and differentiable DVF, enabling seamless integration of advanced regularization techniques via automatic differentiation. Evaluated on the DIR-LAB dataset, $\operatorname{cIDIR}$ achieves high accuracy and robustness across the dataset.