Miloš Vrhovec

Sensitivity of a deep-learning-based breast cancer risk prediction model

Žan Klaneček, Yao‐Kuan Wang, Tobias Wagner, Lesley Cockmartin et autres

Abstract Objective. When it comes to the implementation of deep-learning based breast cancer risk (BCR) prediction models in clinical settings, it is important to be aware that these models could be sensitive to various factors, especially those arising from the acquisition process. …

si, be, us (code pays fourni par la source)

Impact of pectoral muscle removal on deep-learning-based breast cancer risk prediction

Žan Klaneček, Yao‐Kuan Wang, Tobias Wagner, Lesley Cockmartin et autres

Abstract Objective. State-of-the-art breast cancer risk (BCR) prediction models have been originally trained on mammograms with pectoral muscle (PM) included. This study investigated whether excluding PM during training/fine-tuning improves the model’s BCR discrimination performance, calibration, and robustness. Approach. First, the Original deep …

si, be, us (code pays fourni par la source)

Longitudinal interpretability of deep learning based breast cancer risk prediction

Žan Klaneček, Yao‐Kuan Wang, Tobias Wagner, Lesley Cockmartin et autres

Abstract Objective. Deep-learning-based models have achieved state-of-the-art breast cancer risk (BCR) prediction performance. However, these models are highly complex, and the underlying mechanisms of BCR prediction are not fully understood. Key questions include whether these models can detect breast morphologic changes that …

si, be, us (code pays fourni par la source)

Longitudinal interpretability of deep learning-based breast cancer risk prediction model: comparison of different attribution methods

Žan Klaneček, Yao K. Wang, Tobias Wagner, Lesley Cockmartin et autres

When developing Deep Learning models intended for clinical applications, understanding which part of the input contributed the most to the final decision is crucial. Our study brings interpretability to a Breast Cancer Risk (BCR) prediction by exploring whether the model relies on …

si, be, us (code pays fourni par la source)

Breast cancer risk assessment and risk distribution in 3,491 Slovenian women invited for screening at the age of 50; a population-based cross-sectional study

Katja Jarm, Vesna Zadnik, Mojca Birk, Miloš Vrhovec et autres

BACKGROUND: The evidence shows that risk-based strategy could be implemented to avoid unnecessary harm in mammography screening for breast cancer (BC) using age-only criterium. Our study aimed at identifying the uptake of Slovenian women to the BC risk assessment invitation and assessing …

si (code pays fourni par la source)

Uncertainty estimation for deep learning-based pectoral muscle segmentation via Monte Carlo dropout

Žan Klaneček, Tobias Wagner, Yao‐Kuan Wang, Lesley Cockmartin et autres

Abstract Objective . Deep Learning models are often susceptible to failures after deployment. Knowing when your model is producing inadequate predictions is crucial. In this work, we investigate the utility of Monte Carlo (MC) dropout and the efficacy of the proposed uncertainty …

si, be, us (code pays fourni par la source)

Communicating breast cancer screening during covid-19 pandemic - a Slovenian experience

Vesna Škrbec, Katja Jarm, Kristijana Hertl, Miloš Vrhovec et autres

si (code pays fourni par la source)

Multi-layered measures for mitigating effects of COVID-19 pandemic on national breast cancer screening programme.

Miloš Vrhovec, Katja Jarm, Kristijana Hertl, Vesna Škrbec et autres

e22501 Background: The beginning of the COVID-19 pandemic caused a major disturbance in the operation of breast cancer screening programmes worldwide with delays in screening examinations. The 2021 Dutch study Effects of cancer screening restart strategies after COVID-19 disruption describes 4 strategies …

si (code pays fourni par la source)

A study on the impact of parameter settings on the biological reproducibility and sensitivity of extracted radiomic features from full field digital mammography images

Žan Klaneček, Tobias Wagner, Yao-Kuan Wang, Lesley Cockmartin et autres

Aim: To develop and subsequently perform a systematic study on the impact of parameter settings on the biological reproducibility and sensitivity of extracted radiomic features from Full Field Digital Mammography (FFDM) images for the task of Breast Cancer Risk assessment. Methods: Cranio-caudal …

si, be, us (code pays fourni par la source)

Can functional cardiac age be predicted from the ECG in a normal healthy population

Vito Starc, M. Leban, Petra Šinigoj, Miloš Vrhovec et autres

We hypothesized that in a normal healthy population changes in several ECG parameters together might reliably characterize the functional age of the heart. Data from 377 healthy subjects (209 men, 168 women, aged 4 to 75 years) were included in the study. …

si, us (code pays fourni par la source)

Can Functional Cardiac Age be Predicted from ECG in a Normal Healthy Population

Todd T. Schlegel, Vito Starc, Manja Leban, Petra Šinigoj et autres

In a normal healthy population, we desired to determine the most age-dependent conventional and advanced ECG parameters. We hypothesized that changes in several ECG parameters might correlate with age and together reliably characterize the functional age of the heart. Methods: An initial …

us, si (code pays fourni par la source)