Objective: This study aims to evaluate the diagnostic performance of radiomics features extracted from ADC maps for differentiating benign from malignant parotid tumors using machine learning models, demonstrating their potential as supplementary diagnostic tools. Materials and Methods: Forty-six patients who underwent...
E. Akay, Sercan Tosun, G. Demırpolat et al.· Balıkesır Health Sciences Jo...· 0 citations
optika is a Python library for simulating optical systems, similar to Zemax. It raytraces sequential systems of mirrors, refractive glasses, multilayer coatings, and diffraction gratings with a variety of ruling spacings and profiles, and computes the spectral response and resolution of the system. Surfaces are placed...
Roy Smart, J. D. Parker, C. C. Kankelborg· Zenodo (CERN European Organi...· 0 citations
Abstract Accurate patient-level risk stratification of clinically significant prostate cancer (csPCa) on biparametric MRI remains challenging, as most existing approaches require costly lesion-level annotations or have not been evaluated in large temporally separated cohorts. We developed and validated a multimodal dee...
Avtantil Dimitriadis, Grigorios Kalliatakis, Osuala Richard et al.· Scientific Reports· 0 citations
Concept erasure has emerged as a practical safeguard for suppressing unsafe or unwanted concepts in text-to-image diffusion models. However, existing methods are primarily designed for text-triggered generation and are usually evaluated under text-only prompting. In this paper, we identify a practical robustness gap by...
Abstract The present study investigates the modulation of the electroosmotic flow (EOF) and the transport and dispersion of uncharged solutes in a reservoir-connected soft nanochannel containing different electrolytes. The nanochannel walls are charged and coated with a fluid- and ion-permeable polyelectrolyte layer (P...
Abstract Dark matter sets the gravitational environment in which galaxies form and evolve, but cannot be observed directly. We present a conditional diffusion model that reconstructs the projected dark matter density field from the galaxy stellar-mass density field for direct application to galaxy surveys. The model is...
Kunyao Zhao, Yingjie Peng, Dingyi Zhao et al.· The Astrophysical Journal Le...· 0 citations
Predicting diffusion in chemically complex alloys remains challenging due to the strong dependence of migration barriers on local atomic environments. Migration barriers computed using density functional theory and nudged elastic band calculations are represented via a tensorial cluster expansion including transition s...
Abstract An automated algorithm to construct island divertors for stellarators is presented and is used to find divertors that meet heat load requirements determined by material limits. The algorithm uses just two initial conditions: two starting coordinates on the island separatrix chosen by the user. We leverage the...
Avigdor Veksler, Aaron Bader, H. Frerichs et al.· Plasma Physics and Controlle...· 0 citations
Perturbation screens hold the potential to systematically map regulatory processes at single-cell resolution, yet modeling and predicting transcriptome-wide responses to perturbations remains a major computational challenge. Existing methods often underperform simple baselines, fail to disentangle measurement noise fro...
Lars Lorch, Jia-Qi Zhang, Charlotte Bunne et al.· Proceedings of the National...· 7 citations· ⚡2
In this paper, we investigate a modified Trojan Y chromosome (TYC) strategy aimed at eradicating invasive species from natural habitats. The proposed mathematical model enhances the original TYC framework by ensuring the nonnegativity of population densities and preventing potential solution blow-up. The new model is f...
Abstract. Embedding high-dimensional data into a low-dimensional space is an indispensable component of data analysis. In numerous applications, it is necessary to align and jointly embed multiple datasets from different studies or experimental conditions. Such datasets may share underlying structures of interest but e...
Boris Landa, Yuval Kluger, Rong Ma· SIAM Journal on Mathematics...· 0 citations
ABSTRACT Background Although MR cytometry can probe microstructural features, the longitudinal trajectories of these changes during neoadjuvant chemotherapy (NAC) and their association with treatment response and prognosis remain poorly defined. Purpose To characterize longitudinal changes in NAC‐associated cellular mi...
Xiaoxia Wang, Yao Huang, Ruicheng Ba et al.· Journal of Magnetic Resonanc...· 1 citation
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
Microsoft Research Blog· microsoft.comOct 12, 2026
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.
