Deep learning is revolutionizing various scientific fields, with medical applications at the forefront. One key focus is automating image segmentation, a process crucial in many clinical services. However, medical images are often ambiguous and challenging even for experts. To address this, reliable models need to quantify their uncertainty, allowing physicians to understand the model’s confidence in its segmentation. This paper explores how the performance and uncertainty of a model are influenced by the number of annotations per input sample. We examine the effects of both single and multiple manual annotations on various deep learning architectures. To tackle this question, we employ three widely recognized deep learning architectures and evaluate them across four publicly available datasets. Furthermore, we explore the effects of dropout rates on Monte Carlo models by examining uncertainty models with dropout rates of 20%, 40%, 60%, and 80%. Subsequently, we evaluate the models using various measurement metrics. The findings reveal that the influence of multiple annotations varies significantly depending on the datasets. Additionally, we observe that the dropout rate has minimal or no impact on the model’s performance unless there is a substantial loss of training data, primarily evident in the 80% dropout rate scenario.

Social media is internet-based technology and an electronic form of communication that facilitates sharing of ideas, documents, and personal information. Twitter is a microblogging platform and is the most effective social service for posting microblogs and likings, commenting, sharing, and communicating with others. The problem we are shedding light on in this paper is the misuse of bots on Twitter. The purpose of bots is to automate specific repetitive tasks instead of human interaction. However, bots are misused to influence people’s minds by spreading rumors and conspiracy related to controversial topics. In this paper, we initiate a new benchmark created on a 1.5M Twitter profile. We train different supervised machine learning on our benchmark to detect bots on Twitter. In addition to increasing benchmark scalability, various autofeature selections are utilized to identify the most influential features and remove the less influential ones. Furthermore, over-under-sampling is applied to reduce the imbalance effect on the benchmark. Finally, our benchmark compared with other stateof-the-art benchmarks and achieved a 6% higher area under the curve than other datasets in the case of generalization, improving the model performance by at least 2% by applying over-/undersampling.

Social media is internet-based technology and an electronic form of communication that facilitates sharing of ideas, documents, and personal information. Twitter is a microblogging platform and is the most effective social service for posting microblogs and likings, commenting, sharing, and communicating with others. The problem we are shedding light on in this paper is the misuse of bots on Twitter. The purpose of bots is to automate specific repetitive tasks instead of human interaction. However, bots are misused to influence people’s minds by spreading rumors and conspiracy related to controversial topics. In this paper, we initiate a new benchmark created on a 1.5M Twitter profile. We train different supervised machine learning on our benchmark to detect bots on Twitter. In addition to increasing benchmark scalability, various autofeature selections are utilized to identify the most influential features and remove the less influential ones. Furthermore, over-under-sampling is applied to reduce the imbalance effect on the benchmark. Finally, our benchmark compared with other stateof-the-art benchmarks and achieved a 6% higher area under the curve than other datasets in the case of generalization, improving the model performance by at least 2% by applying over-/undersampling.

Reliable uncertainty quantification is essential for deploying image segmentation models in systems where inter-rater variability among experts is significant and must be accounted for to ensure dependable performance. A key unresolved question is whether multiple annotations per case are required during training to obtain robust uncertainty estimates. In this work, we provide analytical and empirical evidence addressing this issue. Using nine diverse publicly available datasets and the nnU-Net framework extended with Ensemble, Bayesian, Probabilistic, and Hierarchical Probabilistic models, we systematically compare training with single- versus multi-annotator annotations. Uncertainty was assessed using two complementary approaches: probability maps and disagreement-as-class. Performance was measured with established metrics, including A-Dice, GED, and Dice. Results show that ensemble-based probability map approaches consistently outperform other methods and achieve comparable performance under both single- and multi-annotation settings. In contrast, for the disagreement-as-class approach multi-annotation setting provides significant advantages over a single-annotation setting for capturing inter-expert variability, particularly in uncertainty-class segmentation. The numerical findings are supported by the provided analytical arguments. These findings indicate that multiple annotations per case may not be strictly necessary for training effective uncertainty-aware segmentation models, offering practical implications for reducing annotation costs and enabling scalable development of reliable uncertainty-aware systems.