Sara Cammarota

Dottorandi

sara.cammarota@hotmail.it

+39 06 72596008

Biografia

Sara è una studentessa del Programma Nazionale di Dottorato in Intelligenza Artificiale presso la Sezione di Fisica Medica di Tor Vergata.

Ha conseguito la laurea triennale in Fisica presso l’Università La Sapienza di Roma, dove ha sviluppato una tesi sull’uso dei fotomoltiplicatori al silicio nella tomografia a emissione di positroni. Successivamente ha conseguito un master in Data Science, concentrandosi su Topological Deep Learning e Semantic Communications.

I suoi interessi di ricerca si concentrano in particolare sulle reti neurali a grafo e sull’apprendimento profondo topologico, in particolare su come le architetture neurali informate dalla topologia possano elaborare dati biologici complessi e strutturati e fornire informazioni utili.

Last 5 articles (Scopus)

opensearch:totalResults = 318
opensearch:startIndex = 0
opensearch:itemsPerPage = 25
@role = request
@searchTerms = AU-ID(6602297547)
@startPage = 0

@_fa = true
@ref = self
@href = https://api.elsevier.com/content/search/scopus?start=0&count=25&query=AU-ID%286602297547%29&apiKey=6ae70c855c11cca26b94ca23c22dcbcf
@type = application/json

@_fa = true
@ref = first
@href = https://api.elsevier.com/content/search/scopus?start=0&count=25&query=AU-ID%286602297547%29&apiKey=6ae70c855c11cca26b94ca23c22dcbcf
@type = application/json

@_fa = true
@ref = next
@href = https://api.elsevier.com/content/search/scopus?start=25&count=25&query=AU-ID%286602297547%29&apiKey=6ae70c855c11cca26b94ca23c22dcbcf
@type = application/json

@_fa = true
@ref = last
@href = https://api.elsevier.com/content/search/scopus?start=293&count=25&query=AU-ID%286602297547%29&apiKey=6ae70c855c11cca26b94ca23c22dcbcf
@type = application/json


inizio

@_fa = true

@_fa = true
@ref = self
@href = https://api.elsevier.com/content/abstract/scopus_id/105014517393

@_fa = true
@ref = author-affiliation
@href = https://api.elsevier.com/content/abstract/scopus_id/105014517393?field=author,affiliation

@_fa = true
@ref = scopus
@href = https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=105014517393&origin=inward

@_fa = true
@ref = scopus-citedby
@href = https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=105014517393&origin=inward

@_fa = true
@ref = full-text
@href = https://api.elsevier.com/content/article/eid/1-s2.0-S1566253525007225

Towards neural foundation models for vision: Aligning EEG, MEG, and fMRI representations for decoding, encoding, and modality conversion; Information Fusion; February 2026; DOI: 10.1016/j.inffus.2025.103650
prism:url = https://api.elsevier.com/content/abstract/scopus_id/105014517393
dc:identifier = SCOPUS_ID:105014517393
eid = 2-s2.0-105014517393
dc:creator = Ferrante M.
prism:publicationName = Information Fusion
prism:issn = 15662535
prism:eIssn =
prism:volume = 126
prism:issueIdentifier =
prism:pageRange =
prism:coverDate = 2026-02-01
prism:coverDisplayDate = February 2026
prism:doi = 10.1016/j.inffus.2025.103650
citedby-count = 0

@_fa = true
affilname = Università degli Studi di Roma "Tor Vergata"
affiliation-city = Rome
affiliation-country = Italy

pubmed-id =
prism:aggregationType = Journal
subtype = ar
subtypeDescription = Article
article-number = 103650
source-id = 26099
openaccess = 1
openaccessFlag = true
value:

$ = all

$ = publisherhybridgold

value:

$ = All Open Access

$ = Hybrid Gold

prism:isbn:

@_fa =
$ =

pii = S1566253525007225

inizio

@_fa = true

@_fa = true
@ref = self
@href = https://api.elsevier.com/content/abstract/scopus_id/105028987504

@_fa = true
@ref = author-affiliation
@href = https://api.elsevier.com/content/abstract/scopus_id/105028987504?field=author,affiliation

@_fa = true
@ref = scopus
@href = https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=105028987504&origin=inward

@_fa = true
@ref = scopus-citedby
@href = https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=105028987504&origin=inward

Beam angle optimization for radiotherapy using LLMs via reinforcement-learning inspired iterative refinement; Medical Physics; February 2026; DOI: 10.1002/mp.70258
prism:url = https://api.elsevier.com/content/abstract/scopus_id/105028987504
dc:identifier = SCOPUS_ID:105028987504
eid = 2-s2.0-105028987504
dc:creator = Cammarota S.
prism:publicationName = Medical Physics
prism:issn = 00942405
prism:eIssn = 24734209
prism:volume = 53
prism:issueIdentifier = 2
prism:pageRange =
prism:coverDate = 2026-02-01
prism:coverDisplayDate = February 2026
prism:doi = 10.1002/mp.70258
citedby-count = 0

@_fa = true
affilname = Università degli Studi di Roma "Tor Vergata"
affiliation-city = Rome
affiliation-country = Italy

pubmed-id = 41612144
prism:aggregationType = Journal
subtype = ar
subtypeDescription = Article
article-number = e70258
source-id = 17871
openaccess = 0
openaccessFlag = false
value:

$ =

value:

$ =

prism:isbn:

@_fa =
$ =

pii =

inizio

@_fa = true

@_fa = true
@ref = self
@href = https://api.elsevier.com/content/abstract/scopus_id/105029463551

@_fa = true
@ref = author-affiliation
@href = https://api.elsevier.com/content/abstract/scopus_id/105029463551?field=author,affiliation

@_fa = true
@ref = scopus
@href = https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=105029463551&origin=inward

@_fa = true
@ref = scopus-citedby
@href = https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=105029463551&origin=inward

Choroid Plexus Enlargement in Multiple Sclerosis Correlates with Cortical and Phase Rim Lesions on 7T MRI and Predicts Progression Independent of Relapse Activity; American Journal of Neuroradiology; 1 February 2026; DOI: 10.3174/ajnr.A8983
prism:url = https://api.elsevier.com/content/abstract/scopus_id/105029463551
dc:identifier = SCOPUS_ID:105029463551
eid = 2-s2.0-105029463551
dc:creator = Barbuti E.
prism:publicationName = American Journal of Neuroradiology
prism:issn = 01956108
prism:eIssn = 1936959X
prism:volume = 47
prism:issueIdentifier = 2
prism:pageRange = 557-565
prism:coverDate = 2026-02-01
prism:coverDisplayDate = 1 February 2026
prism:doi = 10.3174/ajnr.A8983
citedby-count = 1

@_fa = true
affilname = Sapienza Università di Roma
affiliation-city = Rome
affiliation-country = Italy

@_fa = true
affilname = Massachusetts General Hospital
affiliation-city = Boston
affiliation-country = United States

pubmed-id = 40854683
prism:aggregationType = Journal
subtype = ar
subtypeDescription = Article
article-number =
source-id = 20028
openaccess = 1
openaccessFlag = true
value:

$ = all

$ = publisherhybridgold

value:

$ = All Open Access

$ = Hybrid Gold

prism:isbn:

@_fa =
$ =

pii =

inizio

@_fa = true

@_fa = true
@ref = self
@href = https://api.elsevier.com/content/abstract/scopus_id/105027200597

@_fa = true
@ref = author-affiliation
@href = https://api.elsevier.com/content/abstract/scopus_id/105027200597?field=author,affiliation

@_fa = true
@ref = scopus
@href = https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=105027200597&origin=inward

@_fa = true
@ref = scopus-citedby
@href = https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=105027200597&origin=inward

Training Neural Networks by Optimizing Neuron Positions; Lecture Notes in Computer Science; 2026; DOI: 10.1007/978-3-032-07448-5_23
prism:url = https://api.elsevier.com/content/abstract/scopus_id/105027200597
dc:identifier = SCOPUS_ID:105027200597
eid = 2-s2.0-105027200597
dc:creator = Erb L.
prism:publicationName = Lecture Notes in Computer Science
prism:issn = 03029743
prism:eIssn = 16113349
prism:volume = 15582 LNCS
prism:issueIdentifier =
prism:pageRange = 269-280
prism:coverDate = 2026-01-01
prism:coverDisplayDate = 2026
prism:doi = 10.1007/978-3-032-07448-5_23
citedby-count = 0

@_fa = true
affilname = Karlsruher Institut für Technologie
affiliation-city = Karlsruhe
affiliation-country = Germany

@_fa = true
affilname = FZI Forschungszentrum Informatik
affiliation-city = Karlsruhe
affiliation-country = Germany

pubmed-id =
prism:aggregationType = Book Series
subtype = cp
subtypeDescription = Conference Paper
article-number =
source-id = 25674
openaccess = 0
openaccessFlag = false
value:

$ =

value:

$ =

prism:isbn:

@_fa = true
$ = [9783032074478]

pii =

inizio

@_fa = true

@_fa = true
@ref = self
@href = https://api.elsevier.com/content/abstract/scopus_id/105023212114

@_fa = true
@ref = author-affiliation
@href = https://api.elsevier.com/content/abstract/scopus_id/105023212114?field=author,affiliation

@_fa = true
@ref = scopus
@href = https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=105023212114&origin=inward

@_fa = true
@ref = scopus-citedby
@href = https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=105023212114&origin=inward

Reconstructing music perception from brain activity using a prior guided diffusion model; Scientific Reports; December 2025; DOI: 10.1038/s41598-025-26095-w
prism:url = https://api.elsevier.com/content/abstract/scopus_id/105023212114
dc:identifier = SCOPUS_ID:105023212114
eid = 2-s2.0-105023212114
dc:creator = Ciferri M.
prism:publicationName = Scientific Reports
prism:issn =
prism:eIssn = 20452322
prism:volume = 15
prism:issueIdentifier = 1
prism:pageRange =
prism:coverDate = 2025-12-01
prism:coverDisplayDate = December 2025
prism:doi = 10.1038/s41598-025-26095-w
citedby-count = 0

@_fa = true
affilname = Università degli Studi di Roma "Tor Vergata"
affiliation-city = Rome
affiliation-country = Italy

pubmed-id = 41298548
prism:aggregationType = Journal
subtype = ar
subtypeDescription = Article
article-number = 42108
source-id = 21100200805
openaccess = 1
openaccessFlag = true
value:

$ = all

$ = publisherfullgold

$ = repository

$ = repositoryam

value:

$ = All Open Access

$ = Gold

$ = Green

prism:isbn:

@_fa =
$ =

pii =

Ultimi 5 articoli (PubMed)

  • Beam angle optimization for radiotherapy using LLMs via reinforcement-learning inspired iterative refinement
    on 29 Gennaio 2026

    CONCLUSIONS: This study demonstrates that general-purpose LLMs, operating without specialized model training or fine-tuning, can effectively serve as intelligent agents for automated radiotherapy TP, specifically addressing the BAO problem. This flexible and scalable framework has the potential to enhance clinical decision-making workflows in radiotherapy. Future research directions include exploring more comprehensive and clinically nuanced reward functions and extending the methodology to...

  • Towards Intelligent Agents for Radiotherapy: Integrating Exploration-Exploitation with Foundation Models
    on 3 Dicembre 2025

    This study proposes an automated approach to radiotherapy treatment planning by integrating a reinforcement-learning-style iterative framework with a multimodal Large Language Model (LLM). We specifically investigate the problem of Beam Angle Optimization, a high-dimensional and non-convex subproblem of Treatment Planning. Our system employs GPT-4V to select candidate beam angles and analyze three-dimensional dose distributions generated by Monte Carlo simulations within the MatRAD environment....

  • Antiretroviral Adherence and Use of Antihypertensives, Statins, and Antidiabetics Among Elderly People with HIV: A 5-Year Real-World Study in Southern Italy
    on 27 Settembre 2025

    Modern antiretroviral therapy (ART) has transformed HIV into a chronic, manageable condition. This retrospective analysis of administrative data from Apulia (Southern Italy) covering 2018-2023 evaluated demographic changes, ART regimen trends, adherence, and the use of antihypertensives, statins, and antidiabetics among people with HIV (PWH). Temporal trends were assessed using compound annual growth rate (CAGR). ART adherence was measured as proportion of days covered (PDC), categorized as...

  • Lactose Breath Test: Possible Strategies to Optimize Test Performance, Accuracy, and Clinical Impact
    on 26 Ottobre 2024

    Lactose malabsorption (LM) refers to the incomplete absorption of lactose in the small intestine, resulting in the arrival of ingested lactose in the colon, which can give rise to symptoms defined as lactose intolerance (LI). The lactose breath test (LBT), thanks to its low cost, availability, and noninvasiveness, is the most used diagnostic method. However, the LBT is a tedious tool, requiring prolonged involvement of patients, qualified staff, and infrastructure, of which the most...

  • Rifaximin Use, Adherence and Persistence in Patients with Hepatic Encephalopathy: A Real-World Study in the South of Italy
    on 14 Luglio 2023

    Real-world data on the therapeutic management of hepatic encephalopathy (HE) patients are limited. The aim of this study was to evaluate the HE medications prescribed in an Italian cohort of HE patients post-discharge and to assess the real-world rifaximin adherence and persistence over 1 year. An observation retrospective study was conducted using data retrieved from outpatient pharmaceutical databases and hospital discharge records of the Campania region. For all subjects hospitalized for HE...