Publications by Omar Carpentiero

Accurate registration of Intraoral Scans (IOS) with Cone-Beam Computed Tomography (CBCT) enables integration of dental crown surfaces with the tooth roots and the surrounding alveolar bone. However, IOS-CBCT registration remains challenging because of limited anatomical overlap, cross-modal differences, and unreliable correspondences. Task 2 of the MICCAI STS 2026 Challenge formulates this setting as a semi-supervised rigid registration problem, in which IOS meshes must be aligned with their corresponding CBCT volumes. For this task, we propose a landmark-driven coarse-to-fine framework in which modality-specific networks predict corresponding dental landmarks from the IOS mesh and CBCT volume. A confidence-weighted RANSAC-Kabsch procedure estimates a robust initial transformation, later refined using point-to-plane Iterative Closest Point. On the challenge validation set, the method achieved a Mean Translation Error of 4.988 mm and a Mean Rotation Error of 1.421°, ranking first on the registration leaderboard at the time of evaluation. The code is available on GitHub: https://github.com/AImageLab-zip/L2L-Registration

Large-scale benchmarks such as BraTS have driven progress in brain tumor segmentation, but they provide only masks with limited access to the clinical semantics found in radiology reports. We introduce ReportX, a paired resource of 257 clinical reports aligned to BraTS-GLI-2023 subjects, structured into a rich set of qualitative and quantitative attributes. Qualitative fields are curated by clinicians, while quantitative descriptors are automatically derived via atlas-based localization and geometric computations. We compare our annotation schema to existing report-augmented datasets and show that ReportX provides substantially broader coverage of clinically relevant factors. To exploit this supervision, we encode reports using biomedical language models and incorporate their embeddings as auxiliary semantic guidance for 3D tumor segmentation during training. Experimental results demonstrate that the proposed vision-text alignment improves segmentation performance on standard BraTS metrics, with clinically curated reports providing more consistent improvements than automatically generated or less-structured counterparts. We publicly release the dataset (https://ditto.ing.unimore.it/reportx) and the source code (https://github.com/AImageLab-zip/ReportX).

The synthesis of missing MRI modalities has emerged as a critical solution to address incomplete multi-parametric imaging in brain tumor diagnosis and treatment planning. While recent advances in generative models, especially GANs and diffusion-based approaches, have demonstrated promising results in cross-modality MRI generation, challenges remain in preserving anatomical fidelity and minimizing synthesis artifacts. In this work, we build upon the Hybrid Fusion GAN (\hfgan) framework, introducing several enhancements aimed at improving synthesis quality and generalization across tumor types. Specifically, we incorporate z-score normalization, optimize network components for faster and more stable training, and extend the pipeline to support multi-view generation across various brain tumor categories, including gliomas, metastases, and meningiomas. Our approach focuses on refining 2D slice-based generation to ensure intra-slice coherence and reduce intensity inconsistencies, ultimately supporting more accurate and robust tumor segmentation in scenarios with missing imaging modalities. Our source code is available at https://github.com/AImageLab-zip/BraSyn25.