Searcharxiv⌕ Search

arXiv subjects

Nicola Fusco

Publications and source records attributed to Nicola Fusco.

At least 19 recordsLinked to original sources
arXiv2026

A deep learning framework for efficient pathology image analysis

Artificial intelligence (AI) has transformed digital pathology by enabling biomarker prediction from high-resolution whole-slide images (WSIs). However, current methods are computationally inefficient, processing thousands of redundant tiles per WSI and requiring complex aggregator models. We introduce EAGLE (Efficient Approach for Guided Local Examination), a deep learning framework that emulates pathologists by selectively analyzing informative regions. EAGLE incorporates two foundation models: CHIEF for efficient tile selection and Virchow2 for extracting high-quality features. Benchmarking was conducted against leading slide- and tile-level foundation models across 43 tasks from nine cancer types, spanning morphology, biomarker prediction, treatment response and prognosis. EAGLE outperformed state-of-the-art patch aggregation methods by up to 23% and achieved the highest AUROC overall. It processed a slide in 2.27 seconds, reducing computational time by more than 99% compared to existing models. This efficiency enables real-time workflows, allows rapid review of the exact tiles used for each prediction, and reduces dependence on high-performance computing, making AI-powered pathology more accessible. By reliably identifying meaningful regions and minimizing artifacts, EAGLE provides robust and auditable outputs, supported by systematic negative controls and attention concentration analyses. Its unified embedding enables rapid slide searches, integration into multi-omics pipelines and emerging clinical foundation models.

cs.CV↗
arXiv2025

Stability for the Surface Diffusion Flow

We study the global existence and stability of surface diffusion flow (the normal velocity is given by the Laplacian of the mean curvature) of smooth boundaries of subsets of the $n$--dimensional flat torus. More precisely, we show that if a smooth set is ``close enough'' to a strictly stable critical set for the Area functional under a volume constraint, then the surface diffusion flow of its boundary hypersurface exists for all time and asymptotically converges to the boundary of a ``translated'' of the critical set. This result was obtained in dimension $n=3$ by Acerbi, Fusco, Julin and Morini (extending previous results for spheres of Escher, Mayer and Simonett and Elliott and Garcke in dimension $n=2$). Our work generalizes such conclusion to any dimension $n\in\mathbb N$. For sake of clarity, we show all the details in dimension $n=4$ and we list the necessary modifications to the quantities involved in the proof in the general $n$--dimensional case, in the last section.

math.AP↗
arXiv2025

The isoperimetric inequality for the capillary energy outside convex cylinders

We study the isoperimetric problem for capillary surfaces with a general contact angle $θ\in (0, π)$, outside convex infinite cylinders with arbitrary two-dimensional convex section. We prove that the capillary energy of any surface supported on any such convex cylinder is strictly larger than that of a spherical cap with the same volume and the same contact angle on a flat support, unless the surface is itself a spherical cap resting on a facet of the cylinder. In this class of convex sets, our result extends for the first time the well-known Choe-Ghomi-Ritoré relative isoperimetric inequality, corresponding to the case $θ= π/2$, to general angles.

math.AP↗
arXiv2025

Consistency for the surface diffusion flat flow in three dimensions

We investigate the flat flow solution for the surface diffusion equation via the discrete minimizing movements scheme proposed by Cahn and Taylor. We prove that in dimension three the scheme converges to the unique smooth solution of the equation, provided that the initial set is sufficiently regular.

math.AP↗
arXiv2024

PD-L1 Classification of Weakly-Labeled Whole Slide Images of Breast Cancer

Specific and effective breast cancer therapy relies on the accurate quantification of PD-L1 positivity in tumors, which appears in the form of brown stainings in high resolution whole slide images (WSIs). However, the retrieval and extensive labeling of PD-L1 stained WSIs is a time-consuming and challenging task for pathologists, resulting in low reproducibility, especially for borderline images. This study aims to develop and compare models able to classify PD-L1 positivity of breast cancer samples based on WSI analysis, relying only on WSI-level labels. The task consists of two phases: identifying regions of interest (ROI) and classifying tumors as PD-L1 positive or negative. For the latter, two model categories were developed, with different feature extraction methodologies. The first encodes images based on the colour distance from a base color. The second uses a convolutional autoencoder to obtain embeddings of WSI tiles, and aggregates them into a WSI-level embedding. For both model types, features are fed into downstream ML classifiers. Two datasets from different clinical centers were used in two different training configurations: (1) training on one dataset and testing on the other; (2) combining the datasets. We also tested the performance with or without human preprocessing to remove brown artefacts Colour distance based models achieve the best performances on testing configuration (1) with artefact removal, while autoencoder-based models are superior in the remaining cases, which are prone to greater data variability.

cs.CE↗
arXiv2023

Rigidity and large volume residues in exterior isoperimetry for convex sets

A comparison theorem by Choe, Ghomi and Ritoré states that the exterior isoperimetric profile $I_\mathcal{C}$ of any convex body $\mathcal{C}$ in $\mathbb{R}^N$ lies above that of any half-space $H$. We characterize convex bodies such that $I_\mathcal{C}\equiv I_H$ in terms of a notion of "maximal affine dimension at infinity'', briefly called the asymptotic dimension $d^*(\mathcal{C})$ of $\mathcal{C}$. More precisely, we show that $I_\mathcal{C}\equiv I_H$ if and only if $d^*(\mathcal{C})\ge N-1$. We also show that if $d^*(\mathcal{C})\le N-2$, then, for large volumes, $I_\mathcal{C}$ is asymptotic to the isoperimetric profile of $\mathbb{R}^N$. We then estimate, in terms of $d^*(\mathcal{C})$-dependent power laws, the order as $v\to\infty$ of the difference between $I_\mathcal{C}$ and the isoperimetric profile of $\mathbb{R}^N$.

math.DG↗
arXiv2023

A remark on a conjecture on the symmetric Gaussian Problem

In this paper we study the functional given by the integral of the mean curvature of a convex set with Gaussian weight with Gaussian volume constraint. It was conjectured that the ball centered at the origin is the only minimizer of such a functional for certain value of the mass. We give a positive answer in dimension two while in higher dimension the situation is different. In fact, for small value of mass the ball centered at the origin is a local minimizer while for large values the ball is a maximizer among convex sets with uniform bound on the curvature.

math.AP↗
arXiv2022

Some weighted isoperimetric inequalities in quantitative form

In this paper we study two different weighted isoperimetric inequalities. In the first part of the paper we prove a sharp stability result for the isoperimetric inequality with a log-convex weight. In the second part we analize the behavior of a negative power weight for the perimeter thus providing a complete picture of the isoperimetric problem in this context.

math.AP↗
arXiv2022

Regularity of capillarity droplets with obstacle

In this paper we study the regularity properties of $Λ$-minimizers of the capillarity energy in a half space with the wet part constrained to be confined inside a given planar region. Applications to a model for nanowire growth are also provided.

math.AP↗
arXiv2022

Isoperimetry and stability properties of balls with respect to nonlocal energies

We obtain a sharp quantitative isoperimetric inequality for nonlocal $s$-perimeters, uniform with respect to $s$ bounded away from $0$. This allows us to address local and global minimality properties of balls with respect to the volume-constrained minimization of a free energy consisting of a nonlocal $s$-perimeter plus a non-local repulsive interaction term. In the particular case $s =1$ the $s$-perimeter coincides with the classical perimeter, and our results improve the ones of Knüpfer and Muratov concerning minimality of balls of small volume in isoperimetric problems with a competition between perimeter and a nonlocal potential term. More precisely, their result is extended to its maximal range of validity concerning the type of nonlocal potentials considered, and is also generalized to the case where local perimeters are replaced by their nonlocal counterparts.

math.AP↗
arXiv2020

Minimality of balls in the small volume regime for a general Gamow type functional

We consider functionals given by the sum of the perimeter and the double integral of some kernel $g:\mathbb R^N\times\mathbb R^N\to \mathbb R^+$, multiplied by a "mass parameter" $\varepsilon$. We show that, whenever $g$ is admissible, radial and decreasing, the unique minimizer of this functional among sets of given volume is the ball as soon as $\varepsilon\ll 1$.

math.AP↗
arXiv2020

Stationary sets and asymptotic behavior of the mean curvature flow with forcing in the plane

We consider the flat flow solutions of the mean curvature equation with a forcing term in the plane. We prove that for every constant forcing term the stationary sets are given by a finite union of disks with equal radii and disjoint closures. On the other hand for every bounded forcing term tangent disks are never stationary. Finally in the case of an asymptotically constant forcing term we show that the only possible long time limit sets are given by disjoint unions of disks with equal radii and possibly tangent.

math.AP↗
arXiv2019

Sharp stability for the Riesz potential

In this paper we show the stability of the ball as maximizer of the Riesz potential among sets of given volume. The stability is proved with sharp exponent $1/2$, and is valid for any dimension $N\geq 2$ and any power $1<α<N$.

math.FA↗
arXiv2018

The surface diffusion flow with elasticity in three dimensions

We establish short-time existence of a smooth solution to the surface diffusion equation with an elastic term and without an additional curvature regularization in three space dimensions. We also prove the asymptotic stability of strictly stable stationary sets.

math.AP↗
arXiv2018

The $Γ$-limit of traveling waves in the FitzHugh-Nagumo system

Patterns and waves are basic and important phenomena that govern the dynamics of physical and biological systems. A common theme in investigating such systems is to identify the intrinsic factors responsible for such self-organization. The $Γ$-convergence is a well-known technique applicable to variational formulation in studying the concentration phenomena of stable patterns. A geometric variational functional associated with the $Γ$-limit of standing waves of FitzHugh-Nagumo system has recently been built. This article studies the $Γ$-limit of traveling waves. To the best of our knowledge, this is the first attempt to expand the scope of applicability of $Γ$-convergence to cover non-stationary problems.

math.AP↗