NMNikolett Marton

Nikolett Marton

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Nikolett Marton has a total of 61 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Photon-counting detector CT in trauma imaging: Evidence, clinical applications, and future perspectives

    by Soomin Rho, András István Vigh, Nikolett Marton

    Computed tomography (CT) is the primary imaging modality for the rapid assessment of trauma patients, where timely and accurate diagnosis is essential for guiding management and improving outcomes. Photon-counting detector CT (PCD-CT) represents the most significant technological advance in CT in recent decades, overcoming key limitations of conventional energy-integrating detector systems through direct photon conversion and spectral discrimination. This narrative review critically synthesizes the current evidence on PCD-CT in trauma imaging, highlighting its technical principles, clinical applications, limitations, and future perspectives. Available data demonstrate that PCD-CT provides ultra-high spatial resolution, comprehensive spectral imaging, reduced beam-hardening and metal artifacts, and improved radiation- and contrast-dose efficiency compared with conventional CT. These advantages facilitate more accurate assessment of osseous injuries, vascular trauma, active hemorrhage, pulmonary and bowel injuries, occult fractures, and periprosthetic complications, while enabling advanced tissue characterization through material decomposition techniques. However, much of the available evidence is derived from small clinical cohorts, non-trauma populations, or studies extrapolated from dual-energy CT. Moreover, PCD-CT does not replace magnetic resonance imaging for soft-tissue or bone marrow evaluation, and its broader implementation remains constrained by cost, limited scanner availability, and workflow considerations. Large prospective multicenter trauma studies are needed to determine whether the technical advantages of PCD-CT translate into improved diagnostic accuracy, clinical decision-making, workflow efficiency, and ultimately patient outcomes.

  • Open Access

    A fotonszámláló CT-technológia szerepe a pulmonalis kórképek kimutatásában

    by Mátyás Rédei, Kriszta Beáta Gurza, Pál Maurovich-Horvat, Nikolett Marton

    A mellkasi komputertomográfia a pulmonalis betegségek diagnosztikájának alapvető képalkotó módszere. A hagyományos, energiaintegráló detektorral működő rendszerek azonban fizikai korlátokkal rendelkeznek: a térbeli felbontás limitált, az elektronikus zaj jelenléte, valamint a kis dózisú vizsgálatok során romló képminőség egyes klinikai helyzetekben csökkentheti a diagnosztikus pontosságot. A fotonszámláló detektoros komputertomográfia új technológiai megközelítést képvisel, amely az egyes röntgenfotonok egyedi detektálásán és energiaszint szerinti osztályozásán alapul. Ennek köszönhetően javul a dózishatékonyság, csökken a képzaj, nő a térbeli felbontás, és egyetlen adatgyűjtésből spektrális információ is nyerhető. A jelen összefoglaló célja a fotonszámláló detektoros komputertomográfia szerepének áttekintése a pulmonalis képalkotásban. A rendelkezésre álló irodalmi adatok alapján a technológia különösen előnyös a kis méretű pulmonalis nodulusok, a subsolid és tejüveghomályos elváltozások, valamint az interstitialis tüdőbetegségek finom morfológiai jeleinek megjelenítésében. Emellett részletesebb ábrázolást tesz lehetővé infektív, vascularis és traumás eredetű eltérések esetén is. A spektrális képalkotás – beleértve a virtuális monoenergetikus rekonstrukciókat és a jódtérképeket – kiegészítő funkcionális információt nyújthat a perfúziós viszonyokról, a szöveti karakterizálásról és a terápiás válasz megítéléséről. A módszer intervenciós alkalmazások során szintén ígéretes, mivel javíthatja a célzott eltérések és a beavatkozó eszközök környezetének megítélését. Összességében a fotonszámláló detektoros komputertomográfia jelentős technológiai előrelépést képvisel a tüdőképalkotásban. Széles körű elterjedését jelenleg még korlátozza a hozzáférhetőség, a költségek, valamint az eltérő rendszerek közötti összehasonlíthatóság kérdése. A jelenlegi adatok alapján azonban várható, hogy a módszer a jövőben egyre meghatározóbb szerepet tölt be a pulmonalis diagnosztikában. Orv Hetil. 2026; 167(30): 1186–1198.

  • Open Access

    Current state-of-the-art imaging of gout – A narrative review

    by Maral Shokri, Janos Norbert Gyebnar, Akos Menyhart, Peter Vince Balint, Nikolett Marton

    Gout, which frequently manifests as excruciating flare-ups and gradual joint deterioration, is still the most prevalent type of crystal-induced arthritis. Despite the fact that the disease's well-known characteristics are hyperuricemia and the deposition of monosodium urate crystals, precise diagnosis can still be difficult, particularly in instances that resemble other arthritides or lack typical biochemical results. Imaging has become essential for tracking gout activity and response to treatment, in addition to detecting the condition. Advanced modalities like dual-energy computed tomography, photon-counting detector computed tomography, and magnetic resonance imaging have joined conventional radiography and ultrasonography over the past years. Applications of artificial intelligence have started to assist in picture interpretation and diagnosis accuracy in more recent times. In this review article, we focus on how imaging has changed in the treatment of gout, analyze the benefits and disadvantages of each modality, and hypothesize how new technologies can influence clinical practice in the future.


  • Open Access

    Osteopathia striata with cranial sclerosis: A rare case of a young male patient

    by Borbala Zsofia Liptak, Viktor Molnar, Maria Judit Molnar, Nikolett Marton

    Osteopathia striata with cranial sclerosis is a skeletal dysplasia that presents a variety of clinical symptoms along with typical radiological characteristics. While there are a number of distinct skeletal dysplasias to take into account when making a differential diagnosis for osteopathia striata with cranial sclerosis, none of them exhibit the simultaneous calvarial thickening and longitudinal striations of the long bones as the aforementioned disease. Here we report a rare case of a 25-year-old male patient who suffered from cranial nerve deficiencies due to encroachment of the neural canals by sclerosis with involvement of the optic and acoustic nerves. This paper demonstrates the process of investigating a rare progressive genetic disease and highlights the differential diagnostic considerations. This case teaches us the radiological characteristics of osteopathia striata with cranial sclerosis and displays current imaging techniques. The article also summarizes the diseases with cranial sclerosis and sclerotic metaphyseal striations.

  • Open Access

    The AI implementation gap in trauma radiography: standalone versus discretionary AI-integrated fracture detection

    by Anna Gurabi, Sirus S. Hosseini-Begtary, Peter Hegedus, Andor Viktor Gal, Pal Maurovich-Horvat, Nikolett Marton

    Objective: In emergency trauma care, artificial intelligence (AI) may aid fracture detection on radiographs, potentially reducing radiologists’ workload. We evaluated the role of deep learning-based decision-support software in the reporting of trauma cases. Materials and methods: We retrospectively analyzed 2317 trauma radiographs acquired at a single center: 1,174 images obtained from November 1 to 16, 2023, without access to the AI tool during reporting, and 1,143 images from February 1 to 13, 2024, with discretionary use of the AI output during reporting. The AI software output was compared with final radiology reports, with ground truth established by a musculoskeletal radiologist with 9 years’ experience. Accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated at both the fracture and patient levels. Results: The dataset included 1,914 patients with 1,188 acute fractures (621 in November, 567 in February). At the fracture level, standalone AI achieved 90.7% accuracy, 87.8% sensitivity, 94.0% specificity, 94.3% PPV, and 87.2% NPV in November, 94.1%, 93.5%, 94.6%, 94.5%, and 93.6% in February, respectively. Non-AI-assisted radiologists reached 92.4%, 89.0%, 96.2%, 96.3%, and 88.7%, AI-assisted radiologists 93.4%, 90.0%, 96.7%, 96.4%, and 90.7%, respectively. At the patient level, AI’s overall performance reached up to 96.5% accuracy and 95.6% sensitivity. Discrepancies between AI and radiologists occurred in 326 cases, often related to anatomical variants such as accessory ossicles. Conclusion: Standalone AI demonstrated near-expert accuracy and sensitivity in fracture detection at both fracture and patient levels. PPV increased with AI support, indicating more accurate detection of actual fractures. Relevance statement: By examining discretionary real-world use of AI in trauma radiography, this study shows that clinical benefit is not guaranteed by algorithmic performance alone, as optional AI integration does not consistently improve radiologist sensitivity, underscoring a critical implementation gap in practice. Key Points: Standalone AI achieves near-expert fracture detection performance in trauma radiography. Discretionary AI use does not consistently improve radiologist sensitivity. AI use reduces discrepancies, suggesting improved diagnostic consistency. Clinical benefit of AI depends on real-world implementation strategy.

  • Open Access

    Optimizing contrast timing in photon-counting detector CT for the assessment of peripheral arthritis

    by Akos Horvath, Rita Csercsik, Janos Norbert Gyebnar, Daniel Sandor Veres, Pal Maurovich-Horvat, Akos Menyhart, Viktoria Gyergyoi, Peter Vince Balint, Nikolett Marton

    Objective: Photon-counting detector CT (PCD-CT) allows for iodine mapping of inflamed tissues in peripheral immune-mediated arthritis, supporting diagnosis and disease activity assessment. This study aims to identify the optimal timing for image acquisition after intravenous iodinated contrast administration to maximize enhancement and contrast with surrounding tissues. Methods: High-resolution PCD-CT scans of bilateral wrist–hand regions were obtained from 26 patients with peripheral arthritis, both native and post-contrast (1 ml/kg intravenous iodinated contrast at 2.5 ml/sec flow) at 120-, 180-, and 240-s delay phases. Iodine maps were constructed from spectral data. Phases were compared based on densities and iodine concentrations measured in synovial, tenosynovial, and periungual tissues, with muscle, fat, and vessels as controls. We used descriptive statistics and mixed-effects linear regression inferential models for the comparisons. Synovitis and tenosynovitis were verified by ultrasound measurements. Results: No significant differences (p > 0.05) were found in iodine concentration or density across the 120-, 180-, and 240-s post-contrast phases in inflamed synovial, tenosynovial, and periungual soft tissues. Inflamed tissues showed significant and consistent differences in iodine concentration from muscle and fat (p < 0.0001) across all phases, while the greatest differentiation from vessels was in the 120-s phase. The effective dose was identical across all post-contrast phases (0.028 ± 0.0035 mSv). Conclusion: Iodine uptake in inflamed tissues was identical across all three post-contrast phases. However, the 120-s phase offered the highest contrast between inflammation and surrounding vascular structures while minimizing scan time, supporting its use for standardized follow-up imaging.


  • Open Access

    Advancements and initial experiences in AI-Assisted X-ray based fracture diagnosis: A narrative review

    by Sirus S. Hosseini-Begtary, Anna Gurabi, Peter Hegedus, Nikolett Marton

    This review explores the advancements in artificial intelligence for radiograph fracture diagnosis, emphasizing technological developments and inherent limitations. Artificial intelligence improves diagnostic accuracy and manages workflow efficiency. The review categorizes artificial intelligence applications in fracture diagnosis into four primary tasks: recognition, classification, detection, and localization. The most popular performance metrics, such as diagnostic accuracy, precision, sensitivity, specificity, and area under the curve analysis, are used to compare artificial intelligence systems with traditional radiological methods and are explained as serving as a guide. Each task and performance metric is illustrated with practical examples and success stories from recent literature, offering insights into the strengths and weaknesses of various artificial intelligence approaches, such as support vector machines, convolutional neural networks, and generative adversarial networks. We also incorporate case analyses, underscoring the potential and limitations of artificial intelligence in fracture detection. In particular, challenges were posed by external factors such as casts and anatomical complexities. Future directions are explored, emphasizing human-artificial intelligence collaboration and the development of more advanced, transparent artificial intelligence systems alongside parallel evolving ethical considerations and regulatory frameworks. This review aims to equip clinicians with the knowledge to understand and utilize artificial intelligence technologies effectively in their practice.


  • Open Access

    Photon-counting computed tomography in the assessment of rheumatoid arthritis-associated interstitial lung disease: an initial experience

    by Nikolett Marton, Janos Gyebnar, Kinga Fritsch, Judit Majnik, Gyorgy Nagy, Judit Simon, Veronika MülLer, Adam Domonkos Tarnoki, David Laszlo Tarnoki, Pal Maurovich-Horvat

    Interstitial lung disease (ILD) accounts for a significant proportion of mortality and morbidity in patients with rheumatoid arthritis (RA). The aim of this cross-sectional study is to evaluate the performance of novel photon-counting detector computed tomography (PCD-CT) in the detection of pulmonary parenchymal involvement. Sixty-one patients with RA without a previous definitive diagnosis of ILD underwent high-resolution (HR) (0.4 mm slice thickness) and ultra-high-resolution (UHR) (0.2 mm slice thickness) PCDCT examination. The extent of interstitial abnormalities [ground-glass opacity (GGO), reticulation, bronchiectasis, and honeycombing] were scored in each lobe using a Likert-type scale. Total ILD scores were calculated as the sum of scores from all lobes. Reticulation and bronchiectasis scores were higher in the UHR measurements taken compared with the HR protocol [median (quartile 1, quartile 3): 2 (0, 3.5) vs. 0 (0, 3), P < 0.001 and 2 (0, 2) vs. 0 (0, 2), P < 0.001, respectively]; however, GGO and honeycombing scores did not differ [2 (2, 4) vs. 2 (2, 4), P = 0.944 and 0 (0, 0) vs. 0 (0, 0), P = 0.641, respectively]. Total ILD scores from both HR and UHR scans showed a mild negative correlation in diffusion capacity for carbon monoxide (HR: r = -0.297, P = 0.034; UHR: r = -0.294, P = 0.036). The pattern of lung parenchymal involvement did not differ significantly between the two protocols. The HR protocol had significantly lower volume CT dose index [0.67 (0.69, 1.06) mGy], total dose length product [29 (24.48, 33.2) mGy*cm] compared with UHR scans [8.18 (6.80, 9.23) mGy, P < 0.001 and 250 (218, 305) mGy*cm, P < 0.001]. UHR PCD-CT provides more detailed information on ILD in patients with RA than low-dose HR PCDCT. HR PCD-CT image acquisition with a low effective radiation dose may serve as a valuable, low-radiation screening tool in the selection of patients for further, higher-dose UHR PCD-CT screening.


  • Open Access

    Impact of Medium-Sized Extracellular Vesicles on the Transduction Efficiency of Adeno-Associated Viruses in Neuronal and Primary Astrocyte Cell Cultures

    by Orsolya Tünde Kovács, Eszter Soltész-Katona, Nikolett Marton, Eszter Baricza, László Hunyady, Gábor Turu, György Nagy

    (1) Adeno-associated viruses (AAV) are safe and efficient gene therapy vectors with promising results in the treatment of several diseases. Extracellular vesicles (EV) are phospholipid bilayer-surrounded structures carrying several types of lipids, proteins, and nucleic acids with the ability to cross biological barriers. EV-associated AAVs might serve as new and efficient gene therapy vectors considering that they carry the benefits of both AAVs and EVs. (2) We tested vesicle-associated AAVs and vesicles mixed with AAVs on two major cell types of the central nervous system: a neural cell line (N2A) and primary astrocyte cells. (3) In contrast to previously published in vivo observations, the extracellular vesicle packaging did not improve but, in the case of primary astrocyte cells, even inhibited the infection capacity of the AAV particles. The observed effect was not due to the inhibitory effects of the vesicles themselves, since mixing the AAVs with extracellular vesicles did not change the effectiveness. (4) Our results suggest that improvement of the in vivo efficacy of the EV-associated AAV particles is not due to the enhanced interaction between the AAV and the target cells, but most likely to the improved delivery of the AAVs through tissue barriers and to the shielding of AAVs from neutralizing antibodies.


  • Transarticular epithelioid hemangioma of the ankle—a case of a rare vascular neoplasm

    by Nikolett Marton, Irma Ramos-Oliver, Alfredo Gimeno Cajal, Matías de Albert, Rosa Dominguez Oronoz

    Epithelioid hemangioma of the bone is a rare kind of vascular neoplasm posing a diagnostic challenge because of its ability to mimic malignant tumors. We report a case of a fast-growing, talofibular joint–involving epithelioid hemangioma, which was suspectedly initiated by vascular damage due to trauma and arthroscopy. The ankle mass appeared as a lytic lesion on the CT images and as a T1 hypo-, T2 mildly hyperintense, lobulated structure on the MRI scans. The contrast enhancement pattern was typical to vascular neoplasms. Histologically the lesion consisted of well-formed vessels lined with epithelioid cells with a slightly atypical nuclear morphology, inflammation with a significant number of eosinophils, and low mitotic rate. Immunohistochemistry analysis showed the presence of vascular markers but no rearrangements characteristic of soft tissue sarcomas were registered by the next-generation sequencing. The surgical treatment was curative. The report presents current imaging methods and summarizes the imaging findings of transarticular spreading tumors. The paper also highlights that for the differential diagnosis of vascular tumors showing signs of aggressivity, the pathological analysis is inevitable. Correct diagnosis of the epithelioid hemangioma is essential, as the treatment of more malignant entities is substantially different. An added value of the report is that to the best of our knowledge, a transarticular spreading epithelioid hemangioma of the ankle has never been described before.