Guangxi Wang | Searcharxiv

arXiv2025

Now and Future of Artificial Intelligence-based Signet Ring Cell Diagnosis: A Survey

Signet ring cells (SRCs), associated with a high propensity for peripheral metastasis and poor prognosis, critically influence surgical decision-making and outcome prediction. However, their detection remains challenging even for experienced pathologists. While artificial intelligence (AI)-based automated SRC diagnosis has gained increasing attention for its potential to enhance diagnostic efficiency and accuracy, existing methodologies lack systematic review. This gap impedes the assessment of disparities between algorithmic capabilities and clinical applicability. This paper presents a comprehensive survey of AI-driven SRC analysis from 2008 through June 2025. We systematically summarize the biological characteristics of SRCs and challenges in their automated identification. Representative algorithms are analyzed and categorized as unimodal or multi-modal approaches. Unimodal algorithms, encompassing image, omics, and text data, are reviewed; image-based ones are further subdivided into classification, detection, segmentation, and foundation model tasks. Multi-modal algorithms integrate two or more data modalities (images, omics, and text). Finally, by evaluating current methodological performance against clinical assistance requirements, we discuss unresolved challenges and future research directions in SRC analysis. This survey aims to assist researchers, particularly those without medical backgrounds, in understanding the landscape of SRC analysis and the prospects for intelligent diagnosis, thereby accelerating the translation of computational algorithms into clinical practice.

eess.IV↗

arXiv2006

Terahertz All-Optical Modulation in a Silicon-Polymer Hybrid System

Although Gigahertz-scale free-carrier modulators have been previously demonstrated in silicon, intensity modulators operating at Terahertz speeds have not been reported because of silicon's weak ultrafast optical nonlinearity. We have demonstrated intensity modulation of light with light in a silicon-polymer integrated waveguide device, based on the all-optical Kerr effect - the same ultrafast effect used in four-wave mixing. Direct measurements of time-domain intensity modulation are made at speeds of 10 GHz. We showed experimentally that the ultrafast mechanism of this modulation functions at the optical frequency through spectral measurements, and that intensity modulation at frequencies in excess of 1 THz can be obtained in this device. By integrating optical polymers through evanescent coupling to high-mode-confinement silicon waveguides, we greatly increase the effective nonlinearity of the waveguide for cross-phase modulation. The combination of high mode confinement, multiple integrated optical components, and high nonlinearities produces all-optical ultrafast devices operating at continuous-wave power levels compatible with telecommunication systems. Although far from commercial radio frequency optical modulator standards in terms of extinction, these devices are a first step in development of large-scale integrated ultrafast optical logic in silicon, and are two orders of magnitude faster than previously reported silicon devices.

physics.optics↗