arXiv subjects

Lorenzo Pettinari

Publications and source records attributed to Lorenzo Pettinari.

8 recordsLinked to original sources

arXiv2026

AlignUS: MRI-Guided Ultrasound Representation Learning for ALS Classification from Tongue Images

Amyotrophic lateral sclerosis (ALS) is a progressive neurodegenerative disease in which early assessment remains challenging, particularly in low-resource settings where MRI is often unavailable. High-resolution ultrasound (HRUS) of the tongue offers a portable and low-cost alternative for evaluating bulbar involvement, but learning reliable diagnostic models is limited by small datasets and the difficulty of extracting robust representations from ultrasound alone. We propose AlignUS, a cross-modal knowledge distillation framework that transfers anatomical knowledge from MRI to a HRUS-based classifier while requiring only HRUS at inference time. The model combines classification loss, supervised contrastive learning, and feature-level distillation to align HRUS representations with MRI embeddings. AlignUS achieves a patient-level balanced accuracy of 0.958, macro-F1 of 0.963, and ROC-AUC of 0.990, aggregated across four patient-level cross-validation folds, with consistent improvements over HRUS baselines and cross-modal alternatives. These results demonstrate that MRI-derived supervision can substantially improve ultrasound-based ALS assessment while preserving low-cost, inference-time independence from MRI.

cs.CV↗

arXiv2026

SA-Profile: Automated Sulcus Angle Profiling from Super-Resolution MRI

Trochlear dysplasia (TD) is an abnormality of the femoral trochlea associated with anterior knee pain and patellar instability. The sulcus angle (SA) is used to assess trochlear morphology, but it is typically measured on a single axial MR slice with no clear guidance on which to select, making it sensitive to slice selection and landmark placement. We propose an automatic framework for continuous SA profiling from super-resolved MR volumes. Clinically acquired axial, coronal, and sagittal MR scans are combined using implicit neural representations to reconstruct a high-resolution volume. SA measurements are computed across the trochlear region using two landmark detection U-Net models. The approach was evaluated on the public fastMRI dataset and a small in-house cohort of patients with TD. Compared with conventional manual single-slice SA measurements, the proposed automated method yielded a mean absolute error of 11.6$^\circ$ while providing continuous characterization of trochlear morphology. Population-level analysis demonstrated distinct mean SA profiles between the public cohort and the in-house TD cohort, highlighting the potential of profile-based assessment to characterize TD. By reducing reliance on a single manually selected axial slice, the proposed framework extends conventional SA assessment to a continuous profile-based description of trochlear morphology without additional imaging, while remaining conceptually linked to current clinical assessment. Further validation is required. The code is available: https://github.com/wehrlimi/SA_Profile.

cs.CV↗

arXiv2026

End2Reg: Learning Task-Specific Segmentation for Markerless Registration in Spine Surgery

Intraoperative navigation in spine surgery demands millimeter-level accuracy. Currently, this is achieved through radiation-intensive intraoperative imaging and bone-anchored markers that are invasive and disrupt surgical workflow. Markerless RGB-D registration methods offer a promising alternative. However, existing approaches rely on weak segmentation labels to isolate relevant anatomical structures, potentially propagating errors through the registration process. We present End2Reg, an end-to-end deep learning framework that jointly optimizes segmentation and registration, eliminating the need for segmentation labels and manual steps. The network learns task-specific segmentation masks optimized for registration, guided solely by the registration objective without explicit segmentation supervision. End2Reg achieves state-of-the-art performance on ex- and in-vivo benchmarks, reducing median Target Registration Error by 32% and mean Root Mean Square Error by 61%, while maintaining robust performance under partial occlusions. Ablation results confirm that end-to-end optimization significantly improves registration accuracy. Overall, End2Reg advances towards fully automatic, markerless intraoperative navigation. Code and interactive visualizations are available at: https://lorenzopettinari.github.io/end-2-reg/.

cs.CV↗

arXiv2026

Subcriticality at High Temperatures in Spin Lattice Systems

We provide new sufficient conditions for subcriticality of classical and quantum spin lattice systems, formulated in terms of the uniqueness of Kubo-Martin-Schwinger (KMS) states. This is achieved by exploiting a non-commutative analog of the Kirkwood-Salzburg equations together with a novel decomposition of local observables. In contrast to standard approaches \cite{Bratteli_Robinson_97,Frohlich_Ueltschi_2015}, our condition is uniform with respect to the dimension of the single-site Hilbert space. Moreover, unlike the results of \cite{Drago_Pettinari_Van_de_Ven_2025}, which required control over the growth of the derivatives of the interaction potentials, our result only involves estimating the natural $C^*$-norm of these potentials. This substantially enlarges the class of interactions for which the theorems apply and provides better lower bounds on the subcritical inverse temperature.

math-ph↗

arXiv2026

Coupling of the continuum and semiclassical limit. Part I: convergence of eigenvalues

We analyze the semiclassical $d$-dimensional Schrödinger operator in the continuum $ \frac{1}{2} Δ+ λ_N^2 V$ discretized on a mesh with spacing proportional to $1/N$. The semi-classical parameter $λ_N$ is chosen as $λ_N = N^{1 - γ}$, with $γ\in (-1,1)$, which ensures that $N$ governs both the semiclassical and continuum limit simultaneously. We prove that all eigenvalues of the discrete operator converge to those of the continuum, as $λ_N\to\infty$. Beyond this semi-classical domain, in the case of the harmonic oscillator, we further discuss the spectral asymptotics for $γ\in \mathbb{R} \setminus (-1,1)$, thereby fully characterizing the eigenvalue behavior across all possible values of $γ\in\mathbb{R}$.

math-ph↗

arXiv2026

Damping of phonons in Bose gas at low temperatures

We consider homogeneous Bose gas in a large cubic box with periodic boundary conditions interacting with a small potential with a positive Fourier transform. We compute the imaginary part of the phononic excitation spectrum in the lowest order of perturbation theory in thermodynamic limit at low temperatures and low momentum. Our analysis is based on perturbation theory of the standard Liouvillean. We use two approaches: the first, motivated by the standard representation of operator algebras, examines resonances near zero; the second analyzes the 2-point correlation function in the energy-momentum space.

math-ph↗

arXiv2025

On classical aspects of Bose-Einstein condensation

Berezin and Weyl quantization are renown procedures for mapping, commutative Poisson algebras of observables to their non-commutative, quantum counterparts. The latter is famous for its use on Weyl algebras, while the former is more appropriate for continuous functions decaying at infinity. In this work, we define a variant of the Berezin quantization map, which acts on the classical Weyl algebra $\mathcal{W}(E,0)$ and constitutes a positive \textit{strict deformation quantization}. This construction provides a natural framework to compare classical and quantum thermal equilibrium states of a Bose gas through the computation of their semi-classical limit. To this end, we first introduce a purely algebraic notion of KMS states for the classical Weyl algebra and establish that, in finite volume, there exists a unique such state, which can be interpreted as the Fourier transform of a Gibbs measure on a Hilbert space. We then construct a new class of classical KMS states that realize representations of the canonical commutation relations with infinite local density. These states arise as the semi-classical high-density limit of the quantum equilibrium states originally studied by Araki and Woods \cite{Araki_Woods_63}. A key feature of our approach is that it preserves the macroscopic ground-state occupation of the Bose gas in the classical regime. Finally, we demonstrate that the infinite-volume classical states can be obtained as thermodynamic limits of finite-volume Gibbs states.

math-ph↗

arXiv2025

Classical and quantum KMS states on spin lattice systems

We study the classical and quantum KMS conditions within the context of spin lattice systems. Specifically, we define a strict deformation quantization (SDQ) for a $\mathbb{S}^2$-valued spin lattice system over $\mathbb{Z}^d$ generalizing the renown Berezin SDQ for a single sphere. This allows to promote a classical dynamics on the algebra of classical observables to a quantum dynamics on the algebra of quantum observables. We then compare the notion of classical and quantum thermal equilibrium by showing that any weak*-limit point of a sequence of quantum KMS states fulfils the classical KMS condition. In short, this proves that the semiclassical limit of quantum thermal states describes classical thermal equilibrium, strenghtening the physical interpretation of the classical KMS condition. Finally we provide two sufficient conditions ensuring uniqueness of classical and quantum KMS states: The latter are based on an version of the Kirkwood-Salzburg equations adapted to the system of interest. As a consequence we identify a mild condition which ensures uniqueness of classical KMS states and of quantum KMS states for the quantized dynamics for a common sufficiently high temperature.

math-ph↗