通用电气

The application of 21-gene assays in clinical practice is jeopardized by their cost and availability. This study aimed to predict the recurrence score (RS) of a 21-gene assay using MRI peritumoral radiomics in ER+/HER2- breast cancers. 154 and 39 patients with ER+/HER2- breast cancer from two centers were enrolled, who underwent 21-gene test and preoperative MRI. Patients from Center 1 were divided into training (n = 108) and internal validation (n = 46) cohorts, and patients from Center 2 were enrolled in the external validation cohort. Radiomics features were extracted from the tumoral, peritumoral and dilation volumes of interest with peritumoral ranges of 1 mm, 3 mm, 5 mm, 7 mm, and 9 mm. After feature selection, RS-prediction models were constructed using support vector machine method to distinguish high (RS ≥ 26) from low RS (RS < 26). As the thickness of the peritumor tissue increased, the AUC of models increased and then decreased, with the 3-mm model performing the best. Among all RS-prediction models, the 3 mm peritumoral model based on T2WI (T2-p3) achieved larger AUCs (0.70 and 0.69 in the internal and external validation cohorts, separately). The peritumoral-fusion model integrating intratumoral radiomic and imaging-clinicopathological features with the T2-p3 model, obtained greater AUCs (0.82 and 0.75 in the internal and external validation cohorts, separately). MRI peritumoral radiomic data exhibits the potential to serve as a biomarker of recurrence risk in patients with ER+/HER2- breast cancer.

The stochastic linear bandit, where actions are represented as vectors and rewards are linear, is a central paradigm for sequential decision making. We study a partially observed variant of this problem in which the learning agent only sees a random subset of coordinates for each action. Such partial observability arises naturally in settings like recommendation and healthcare, where full action descriptions can be expensive or even impossible to obtain. In general, this makes sublinear regret information-theoretically impossible. However, we show that this barrier can be overcome when the action vectors have low intrinsic dimension. We propose an algorithm, TOFU-POV, that estimates the latent action subspace using the masked actions, imputes current actions using an epoch-wise frozen representation, and runs OFUL in the resulting low-dimensional coordinates. Our theory shows that TOFU-POV enjoys a √(T) regret that scales with the intrinsic action subspace dimension as opposed to the ambient dimension and quantifies the interaction between these quantities and the missingness, decision set size, and subspace conditioning. We also devise a rank-adaptive algorithm that does not require the knowledge of the intrinsic dimension. We complement these guarantees with a lower bound based on a novel product construction that separates usual reward-learning uncertainty from a missingness-dependent cost intrinsic to partial observation. Synthetic and real data experiments support our theory and show that TOFU-POV can substantially improve upon natural baselines in this challenging problem.

Abstract The micropitting behavior of eight greases has been investigated for wind turbine main shaft bearings. Results reveal that micropitting resistance is not solely governed by base oil viscosity, as low- and medium-viscosity greases outperform higher-viscosity ones. Special tests have been carried out to investigate the effectiveness of rescue grease in mitigating surface damage progression. Controlled predamage phases have been introduced using a low reference grease to simulate varying severity levels, followed by the application of rescue grease. Both laboratory and field evaluations demonstrate that rescue grease effectively suppresses the progression of surface damage, evidenced by reductions in bearing temperature and vibration levels. Surface analyses revealed that rescue grease promotes polishing of existing cracks and prevents further propagation. Comparisons across different scenarios confirm its ability to stabilize tribological performance and preserve surface integrity over extended cycles. Together with field case studies showing that the early introduction of rescue grease delays damage escalation and maintains stable bearing temperatures, these findings highlight the potential of rescue grease as a proactive and practical solution for extending component life in demanding wind turbine applications.

Purpose:The aim of the study was to investigate the feasibility of developing a standardized brim set with a scalable design to streamline transfemoral prosthetic socket production.Design:A two-phase mixed-methods study comprising: (1) a design based on quantitative analysis and (2) an observational, cross-sectional approach.Methods:In phase 1, existing brims were analyzed to develop a standardized brim set. Participants using hybrid transfemoral prosthetic sockets were selected, and the dimensions of the 3D-scanned brims were measured, including circumference, ischial-trochanteric distance, ischial support area, and trimline heights. Statistical analyses were performed to explore potential correlations to inform the scalable brim design. In phase 2, appropriate brims were fitted to participants with transfemoral residual limbs, and each brim section was evaluated using a custom-designed questionnaire.Results:Phase 1 resulted in a standardized brim set based on 13 brims, revealing a statistically significant exploratory correlation between brim circumference and ischial-trochanteric distance. In phase 2, involving eight participants, most brim sections achieved satisfactory fitting scores. However, some participants reported discomfort in the groin area and issues with ischial support placement.Conclusions:While limited by a small sample size, this study demonstrates the feasibility of developing a scalable brim design for transfemoral sockets. The exploratory findings suggest potential for broader applicability, but further validation with a larger dataset and additional fittings is needed. This approach may improve the consistency, efficiency, and quality of transfemoral prosthetic socket fittings.Clinical Relevance:This study contributes to more consistent and anatomically accurate transfemoral prosthetic socket design by introducing a standardized, data-driven hybrid brim set, with the potential to improve clinical efficiency and user outcomes.