Yongchao Xu

A global shortage of radiologists has increased the burden of chest X-ray interpretation, particularly in primary and resource-limited settings. Although artificial intelligence systems can assist with report generation, most lack rigorous prospective validation in real clinical environments. Here we show that Janus-Pro-CXR, a lightweight artificial intelligence system optimized for chest radiograph interpretation, improves report quality and workflow efficiency in a multicenter prospective study (NCT07117266). Developed through domain-specific fine-tuning of a multimodal foundation model, Janus-Pro-CXR achieved strong diagnostic performance for key thoracic findings and generated clinically structured reports aligned with expert standards. In real-world deployment involving 296 patients, AI assistance significantly improved report quality scores and reduced interpretation time by 18.3% compared with standard practice. The system operates efficiently on standard hardware, supporting practical implementation in resource-constrained settings. These findings demonstrate the clinical value of lightweight, human–AI collaborative systems in radiology practice.

Bamboo slips are a crucial medium for recording ancient civilizations in East Asia. However, many excavated bamboo slips have been fragmented into thousands of irregular pieces, making their rejoining a vital yet challenging step for understanding their content. Here we introduce WisePanda, a physics-driven deep learning framework designed to rejoin fragmented bamboo slips. Based on the physics of fracture and material deterioration, WisePanda automatically generates paired synthetic training data that captures the physical properties of bamboo fragmentations. This approach enables the training of a matching network without requiring manually paired samples, providing ranked suggestions to facilitate the rejoining process. Compared to the leading curve matching and modern generative methods, WisePanda yields a substantial and statistically significant increase in matching accuracy, accelerating archeologists’ efficiency in rejoining fragmented bamboo slips. WisePanda provides a new paradigm for addressing data scarcity in ancient artifact restoration through physics-driven machine learning.

Unsupervised anomaly detection methods primarily focus on modeling the distribution of normal samples at image/feature level. Significant deviation from the modeled distribution is then considered as anomaly. Yet, each normal sample may have its own unique characteristic drifting from the idea distribution, making it difficult to distinguish between anomaly and characteristic. In this paper, we propose a memory-based Coarse-to-Fine Feature Fusion (C3F) module to tackle this challenge. Specifically, we construct a group of memory banks that model the feature distribution of normal samples at various levels of granularity. The memory-based C3F is applied to each skip-connection between the encoder and the decoder, and progressively removes anomaly while maintaining characteristic. This helps to reconstruct defect-free image with characteristic preserved, encouraging large (resp small) deviation from the modeled distribution for anomaly (resp characteristic). Besides, we also introduce a novel rough anomaly score map Guided Segmentation (GS) module to achieve precise anomaly localization. Extensive experiments on widely used VisA and MVTec-AD benchmarks demonstrate the wide-ranging applicability of the proposed method termed C3FGS on industrial components of various forms. The implementation code is publicly available at https://github.com/LZL501/c3f_industrial_anomaly_detection.