Magnetic Resonance Imaging (MRI) and its automatic segmentation are pivotal in assisting physicians with clinical diagnosis. In recent years, with the scarcity of labeled data, significant advancements have been made in semi-supervised segmentation. However, the prediction of many current methods is affected by the presence of false positive regions, which limits their reliability in clinical applications. To tackle this issue, we propose a pseudo-label optimization method based on polar coordinate modeling and prior constraints (PMPC), which refines false positive regions in pseudo-labels by leveraging prior knowledge within the polar coordinate system. Firstly, to improve the efficiency and rationality during polar coordinate modeling, the Adaptive Pole Selection (APS) algorithm is presented to ensure that the pole is located within the foreground region. Secondly, to mitigate false positive regions in pseudo-labels that violate medical anatomical priors, we propose the Prior Knowledge Constraint in Polar Coordinate System (KCP) module to reassign pixel categories in these regions. Finally, the Shape-aware Weighting (SaW) strategy is presented to evaluate the quality of the optimized pseudo-labels based on their shape and then determine their weight in guiding network parameter updates. Experiments on three MRI datasets demonstrate that the proposed method can be effectively integrated with existing pelvic MRI segmentation approaches, significantly reducing false positive rates and further improving segmentation quality.

Semi-Supervised medical image segmentation is crucial for clinical applications. Recent methods tend to adopt the weak-to-strong consistency strategy to boost model performance. However, these approaches predominantly emphasize spatial domain perturbations, restricting the expansion of the perturbation space. Additionally, reliance on the confidence threshold for pseudo-label selection frequently neglects noisy pixels with high confidence, leading to their accumulation and degradation of model performance. To address these challenges, we propose the Adaptive Wavelet and Uncertainty Refinement (AWUR) framework, incorporating two modules: (1) Adaptive Wavelet Perturbation (AWP), which employs wavelet transform and adaptive noise to introduce gentle frequency perturbations, effectively broadening the original perturbation space and enhancing model performance; (2) Uncertainty Weight Refinement (UWR), which refines high-uncertainty pixels and adjusts pseudo-label weights based on confidence and uncertainty, effectively improving pseudo-label reliability and guiding model training. Extensive experiments show that AWUR surpasses state-of-the-art methods across various medical image segmentation tasks.

The article studies an adaptive practical fixed-time tracking control problem of nonlinear system using the funnel control method and the dynamic event-triggered control mechanism. First, an adaptive practical fixed-time controller is built using radial basis function neural networks and an improved funnel function. On the one hand, it eliminates the impact of unknown nonlinear functions on system performance and forces the tracking error to evolve within the funnel boundary. On the other hand, the transient performance of the system is enhanced by the preassigned funnel boundary. Second, a nonlinear command filter with high-order nonlinear term is constructed to solve the problem of “explosion of complexity” in the backstepping approach. Further, the filter error compensating input is designed to counteract the detrimental impacts of the filter error on the tracking performance. In addition, to achieve the dynamic modification of threshold parameters and minimize communication resources, a dynamic event-triggered mechanism is devised based on auxiliary dynamic variables and dynamic threshold parameters. It is rigorously proved theoretically that the closed-loop system is practical fixed-time stable and Zeno behavior is ruled out. Ultimately, the single-link robotic arm system validates the efficiency of the acquired control approach. Note to Practitioners—The application of traditional control algorithms is severely limited in real industrial systems due to typical constraints on input, output, and communication resources, particularly in autonomous surface vehicles and robot fields. Nevertheless, the existing methods only take into account asymptotic tracking control problems based on the time-triggered mechanism, which is impracticable for a large number of systems in reality. Therefore, the paper studies the problem of funnel control and communication resource of the nonlinear system, and an adaptive practical tracking control scheme is proposed through the dynamic event-triggered mechanism and funnel function, which not only ensures that the nonlinear system is practical fixed-time stable but also improves the transient and steady-state performances of the nonlinear system.

This article investigates the adaptive neural network (NN) tracking control problem for nonlinear networked control systems (NCSs) with finite-time prescribed performance (FTPP) subject to intermittent denial-of-service (DoS) attacks. It is noticeable that when the DoS attacker is active, the controller does not receive any information, which makes the controller fail to work. To tackle the challenge, an adaptive NN switching state observer is first built to estimate the unmeasurable states. Second, an FTPP function is constructed to boost the transient and steady-state performances of NCSs. Third, under the framework of the backstepping technique, an adaptive command filter is established by combining the dynamic adaptive technique with the switching state observer, which handles the “complexity explosion” problem and improves the robustness of NCSs. Besides, it is rigorously proved mathematically that the boundedness of all signals in the closed-loop system and the designed controller compels the tracking error to fall into the predefined boundary within a finite time. Finally, an application-oriented example of the single-link robotic arm system is utilized to demonstrate the viability of the proposed control method.

This article addresses the fixed-time control problem for high-order nonlinear systems with unknown nonlinear functions and asymmetric output constraint. First, a continuous state-feedback controller is constructed by revamping the adding a power integrator technique (API), which guarantees that the system output does not exceed the pregiven asymmetric output constraint boundary. Second, with the barrier Lyapunov function (BLF) method and the backstepping technique, a fixed-time stability criterion is constructed. It is rigorously proven that the closed-loop systems are fixed-time stable by the Lyapunov theory. The proposed BLF can not only deal with the symmetric output constraint but also cover the traditional logarithm-type BLF as a special case. Finally, a practical application example of the boiler–turbine unit system is offered to certify the availability of the proposed control algorithm.