Teeth segmentation is crucial for the analysis of maxillofacial diseases, with Cone Beam Computed Tomography (CBCT) scans offering superior 3D imaging compared to conventional Computed Tomography (CT). We propose a semi-supervised framework based on a multi-iterative self-learning approach, introducing a novel ranking technique for pseudo-label selection and a post-processing algorithm to eliminate false positives and ensure mask consistency. Pseudo-label ranking is guided by average voxel-level entropy, which quantifies uncertainty between foreground and background classes. High-confidence labels are then selected to refine training in subsequent iterations. Our post-processing algorithm enhances segmentation fidelity by identifying connected components, retaining the largest within a defined radius, and filtering out extraneous voxels. Additionally, expert-refined pseudo-labels are incorporated to assess their impact on performance. To further validate our approach, we established a baseline model and conducted a comprehensive evaluation on both the private test set of the STS-3D Challenge and our self-collected out-of-set data. The framework employs nnUNetV2 with the ResEnc M preset, optimizing feature extraction and dataset adaptation. Our approach achieves a Dice score of 0.8244 and an IoU of 0.851 on the private test set of the STS-3D Challenge, outperforming previous published methods on the same benchmark and demonstrating the effectiveness of our semi-supervised teeth segmentation strategy.

Accurate segmentation of the pulp cavity, root canals, and inferior alveolar nerve (IAN) in dental imaging is essential for effective orthodontic interventions. Despite the availability of numerous Cone Beam Computed Tomography (CBCT) scans annotated for individual dental-anatomical structures, there is a lack of a comprehensive dataset covering all necessary parts. As a result, existing deep learning models have encountered challenges due to the scarcity of comprehensive datasets encompassing all relevant anatomical structures. We present our novel Pulpy3D dataset, specifically curated to address dental-anatomical structures’ segmentation and identification needs. Additionally, we noticed that many current deep learning methods in dental imaging prefer 2D segmentation, missing out on the benefits of 3D segmentation. Our study suggests a UNet-based approach capable of segmenting dental structures using 3D volume segmentation, providing a better understanding of spatial relationships and more precise dental anatomy representation. Pulpy3D contributed in creating the seeding model from 150 scans, which helped complete the remainder of the dataset. Other modifications in the architecture, such as using separate networks, one semantic network, and a multi-task network, were highlighted in the model description to show how versatile the Pulpy3D dataset is and how different models, architectures, and tasks can run on the dataset. Additionally, we stress the lack of attention to pulp segmentation tasks in existing studies, underlining the need for specialized methods in this area. The code and Pulpy3D links can be found at https://github.com/mahmoudgamal0/Pulpy3D .

Abstract Background qPCR is a widely used technique in scientific research as a basic tool in gene expression analysis. Classically, the quantitative endpoint of qPCR is the threshold cycle (CT) that ignores differences in amplification efficiency among many other drawbacks. While other methods have been developed to analyze qPCR results, none has statistically proven to perform better than the CT method. Therefore, we aimed to develop a new qPCR analysis method that overcomes the limitations of the CT method. Our f0% [eff naught percent] method depends on a modified flexible sigmoid function to fit the amplification curve with a linear part to subtract the background noise. Then, the initial fluorescence is estimated and reported as a percentage of the predicted maximum fluorescence (f0%). Results The performance of the new f0% method was compared against the CT method along with another two outstanding methods—LinRegPCR and Cy0. The comparison regarded absolute and relative quantifications and used 20 dilution curves obtained from 7 different datasets that utilize different DNA-binding dyes. In the case of absolute quantification, f0% reduced CV%, variance, and absolute relative error by 1.66, 2.78, and 1.8 folds relative to CT; and by 1.65, 2.61, and 1.71 folds relative to LinRegPCR, respectively. While, regarding relative quantification, f0% reduced CV% by 1.76, 1.55, and 1.25 folds and variance by 3.13, 2.31, and 1.57 folds regarding CT, LinRegPCR, and Cy0, respectively. Finally, f0% reduced the absolute relative error caused by LinRegPCR by 1.83 folds. Conclusions We recommend using the f0% method to analyze and report qPCR results based on its reported advantages. Finally, to simplify the usage of the f0% method, it was implemented in a macro-enabled Excel file with a user manual located on https://github.com/Mahmoud0Gamal/F0-perc/releases .

Video object segmentation is an essential task in robot manipulation to facilitate grasping and learning affordances. Incremental learning is important for robotics in unstructured environments. Inspired by the children learning process, human robot interaction (HRI) can be utilized to teach robots about the world guided by humans similar to how children learn from a parent or a teacher. A human teacher can show potential objects of interest to the robot, which is able to self adapt to the teaching signal without providing manual segmentation labels. We propose a novel teacher-student learning paradigm to teach robots about their surrounding environment. A two-stream motion and appearance “teacher” network provides pseudo-labels to adapt an appearance “student” network. The student network is able to segment the newly learned objects in other scenes, whether they are static or in motion. We also introduce a carefully designed dataset that serves the proposed HRI setup, denoted as (I)nteractive (V)ideo (O)bject (S)egmentation. Our IVOS dataset contains teaching videos of different objects, and manipulation tasks. Our proposed adaptation method outperforms the state-of-theart on DAVIS and FBMS with 6.8% and 1.2% in F-measure respectively. It improves over the baseline on IVOS dataset with 46.1% and 25.9% in mIoU.

As a new research concept for both academia and industry, there are several challenges faced by the Network Function Virtualization (NFV). One such challenge is to find the optimal mapping and scheduling for the incoming service requests which is the focus of this study. This optimization has been done by maximizing the number of accepted service requests, minimizing the number of bottleneck links and the overall processing time. The resultant problem is formulated as a multi- objective optimization problem, and two novel algorithms based on genetic algorithm have been developed. Through simulations, it has been shown that the developed algorithms can converge to the near to optimal solutions and they are scalable to large networks.