Oct 2026· Japanese Journal of Radiology· 75 references
Abstract
Abstract Robotic systems for computed tomography (CT)-guided needle insertion have been developed to address the limitations of conventional manual needle insertion. Thus far, various robotic systems have been clinically implemented, and accumulating evidence has suggested their clinical utility. The evidence has evolved beyond initial feasibility and early clinical experience to include larger observational and comparative studies. These studies have demonstrated high success rates of robot-assisted needle insertion in various CT-guided interventions, including thermal ablation, biopsy, and preoperative localization. Furthermore, an increasing number of comparative studies have demonstrated the advantages of robot-assisted procedures over conventional manual procedures. These advantages include improved needle insertion accuracy and reduced radiation doses to patients and/or physicians. Although most currently available robotic systems are needle-guiding robots designed to align a needle guide with a predetermined insertion trajectory, we have developed a CT-guided needle insertion robot capable of robotic needle advancement via remote control. Clinical studies have demonstrated the feasibility of robotic needle insertion using this system, as well as needle placement accuracy comparable to that of manual procedures, while eliminating radiation exposure to physicians. The integration of artificial intelligence and the implementation of telerobotic interventions are expected to contribute significantly to the further advancement of robotic systems for CT-guided needle insertion. This narrative review summarizes the current clinical implementations and available evidence for robotic systems for CT-guided needle insertion, including our system, and discusses future perspectives in this field.
This paper investigates developing real-world perception for active agents, proposes Gibson Environment for this purpose, and showcases a set of perceptual tasks learned therein.
F. Xia, Amir Zamir, Zhi-Yang He et al.· 2018 IEEE/CVF Conference on...· 1,069 citations· ⚡112
GAOKAO-Bench is introduced, an intuitive benchmark that employs questions from the Chinese GAOKAO examination as test samples, including both subjective and objective questions that contribute a robust evaluation benchmark for future large language models and offers valuable insights into the advantages and limitations...
Xiaotian Zhang, Chun-yan Li, Yi Zong et al.· arXiv.org· 216 citations· ⚡17
An algorithm is proposed which leverages disentangled semantic factors to generate adversarial perturbation by altering controlled semantic attributes to fool the learner towards various "adversarial" targets.
Haonan Qiu, Chaowei Xiao, Lei Yang et al.· arXiv.org· 208 citations· ⚡17
This work proposes a HALO that directly maximizes the utility of generations instead of maximizing the log-likelihood of preferences, and suggests that the best loss depends on the inductive biases most appropriate for a given setting, an oft-overlooked consideration.
This work investigates the possibilities of using LLMs in a resume screening setting via a document retrieval framework that simulates job candidate selection and finds that the MTEs are biased, significantly favoring White-associated names in 85% of cases and female-associated names in only 11.1% of cases.
This work shows that orders of magnitude enhancement in performance could be obtained by a combination of hardware improvements and tight quantum-HPC integration and introduces high-performance architectures for quantum-probabilistic computing with custom-designed accelerators to tackle today's industry-scale classical...
Masoud Mohseni, Artur Scherer, K. Johnson et al.· arXiv.org· 121 citations· ⚡9