Radoslav Beňuš

Dr. Radoslav Beňuš

orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 November 2021 in Healthcare
Verified
Journal Article
Open access
PDF file
Andrej ThurzoAndrej Thurzo
Andrej Thurzo
HKHelena Kosnáčová
Helena Kosnáčová
VKVeronika Kurilova
Veronika Kurilova
SKSilvester Kosmeľ
Silvester Kosmeľ
RBRadoslav Beňuš
Radoslav Beňuš
IVIvan Varga
Ivan Varga
Three-dimensional convolutional neural networks (3D CNN) of artificial intelligence (AI) are potent in image processing and recognition using deep learning to perform generative and descriptive tasks. Compared to its predecessor, the advantage of CNN is that it automatically detects the important features without any human supervision. 3D CNN is used to extract features in three dimensions where input is a 3D volume or a sequence of 2D pictures, e.g., slices in a cone-beam computer tomography scan (CBCT). The main aim was to bridge interdisciplinary cooperation between forensic medical experts and deep learning engineers, emphasizing activating clinical forensic experts in the field with possibly basic knowledge of advanced artificial intelligence techniques with interest in its implementation in their efforts to advance forensic research further. This paper introduces a novel workflow of 3D CNN analysis of full-head CBCT scans. Authors explore the current and design customized 3D CNN application methods for particular forensic research in five perspectives: (1) sex determination, (2) biological age estimation, (3) 3D cephalometric landmark annotation, (4) growth vectors prediction, (5) facial soft-tissue estimation from the skull and vice versa. In conclusion, 3D CNN application can be a watershed moment in forensic medicine, leading to unprecedented improvement of forensic analysis workflows based on 3D neural networks.

25 July 2025 in Bratislava Medical Journal
Verified
Journal Article
Open access
PDF file
DFDarina Falbová
Darina Falbová
SSSimona Sulis
Simona Sulis
POPaulína Oravská
Paulína Oravská
AHAlexandra Hozakova
Alexandra Hozakova
PUPetra Švábová / Uhrová
Petra Švábová / Uhrová
LVLenka Vorobeľová
Lenka Vorobeľová
Purpose: Normal weight obesity (NWO) is a phenotype characterised by a normal body mass index (BMI) combined with excessive body fat percentage, which poses health risks that cannot be detected by conventional BMI assessment. This study investigated the prevalence of NWO in young adults and examined associations with body composition parameters and lifestyle factors. Methods: The sample comprised 833 Slovaks, men and women, aged 18–30 years (21.69 ± 2.49). Body composition was determined using InBody 770. NWO was defined as a body fat percentage of > 28% in women and > 20% in men with a BMI of ≤ 25 kg/m2. Lifestyle factors, assessed using a WHO-validated questionnaire, were analysed using binary logistic regression to identify predictors of NWO. Results: The prevalence of NWO was significantly higher in women (31.5%) than in men (19.0%; p = 0.003). In both sexes, individuals with NWO had significantly higher visceral fat area and lower lean body mass in specific body segments than normal weight (NW) counterparts. In addition, men in the NWO group had also a significantly lower phase angle (p = 0.017). In terms of lifestyle, we found that participants who did not eat breakfast regularly had a significantly higher risk of developing NWO. Participants with the highest physical activity (> 3 times per week) showed the strongest association with NW. Conclusion: NWO is relatively common in young adults, and is associated with higher visceral fat area and lower lean body mass despite a normal BMI. These findings emphasise the importance of looking beyond BMI when assessing health risks in young adults.

28 January 2023 in International journal of legal medicine
Verified
Journal Article
Closed access
PDF file
PUPetra Švábová / Uhrová
Petra Švábová / Uhrová
RBRadoslav Beňuš
Radoslav Beňuš
MCMária Chovancová
Mária Chovancová
AVAdriana Vojtušová
Adriana Vojtušová
MNMiroslav Novotný
Miroslav Novotný
Andrej ThurzoAndrej Thurzo
Andrej Thurzo

18 July 2024 in Diagnostics
Verified
Journal Article
Open access
PDF file
PUPetra Švábová / Uhrová
Petra Švábová / Uhrová
MSMichal Soták
Michal Soták
BGBranislav Galis
Branislav Galis
PKPatrícia Kroupová
Patrícia Kroupová
Lucia BundováLucia Bundová
Lucia Bundová
RBRadoslav Beňuš
Radoslav Beňuš
As results may vary depending on the method of examination, this paper analyzes methods of age estimation based on the maturation index of third molars (I3M) and Kohler’s developmental stages in living individuals. A total of 1475 orthopantomograms were analyzed. The results showed that the development of third molars tended to be more advanced in males than in females. Regression equations that included the value of the developmental stage of the left third molar most accurately predicted chronologic age in males and females. Using the I3M method, there were no statistically significant bilateral differences between the mandibular right and left third molars. Overall, 82.92% of males and only 72.82% of females were correctly classified with the cut-off value (0.08) for the left mandibular third molar index. In addition, 81.97% of individuals were correctly classified as minors and adults using the Kohler method, while only 78.62% of individuals were correctly classified as minors and adults using the I3M method. Based on the misclassification of minors as adults, both methods should be used with caution and overestimation of age should be considered, especially for those close to 18 years of age.

20 August 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SSSimona Sulis
Simona Sulis
DFDarina Falbová
Darina Falbová
RBRadoslav Beňuš
Radoslav Beňuš
PUPetra Švábová / Uhrová
Petra Švábová / Uhrová
AHAlexandra Hozakova
Alexandra Hozakova
LVLenka Vorobeľová
Lenka Vorobeľová
Background: This study aimed to investigate the association between body composition (BC) specific parameters such as fat mass (FM) and lean body mass (LBM) and bone quality in obese and non-obese young Slovak adults (18–30 years) using bioelectrical impedance analysis and quantitative ultrasound while considering the factors of sex and obesity status; Methods: BC was evaluated using bioelectrical impedance analysis (InBody 770) and bone quality by the speed of sound (SOS) in radius using QUS (Sunlight MiniOmni) in 774 young Slovak young adults aged 18–30 years, categorized by sex and obesity status (body fat %, PBF, ≥28% for men and ≥20% for women); Results: In non-obese individuals, radial SOS correlated positively with FM parameters. Significant positive correlations with LBM, including skeletal muscle mass (SMM), were observed in non-obese men but not in women. Conversely, SOS correlated negatively with FM parameters in obese individuals, significantly only in women. The correlation of SOS with LBM in obese individuals was insignificant in both sexes. Age, visceral FM, FM in the arm, and vitamin D intake were identified as the main predictors of radial SOS in young adults, except in obese men. Conclusions: Findings indicate FM benefits bone tissue in non-obese individuals, while excessive adiposity deteriorates bone quality in obese individuals, necessitating tailored evaluations and interventions based on sex, obesity status, and specific predictors.

15 January 2025 in American Journal of Human Biology
Verified
Journal Article
Closed access
DFDarina Falbová
Darina Falbová
PUPetra Švábová / Uhrová
Petra Švábová / Uhrová
RBRadoslav Beňuš
Radoslav Beňuš
AHAlexandra Hozakova
Alexandra Hozakova
SSSimona Sulis
Simona Sulis
LVLenka Vorobeľová
Lenka Vorobeľová