As the most frequent wound complication, infection has become a major clinical challenge in wound management. To overcome the “Black Box” status of the wound‐healing process, next‐generation wound dressings with the abilities of real‐time monitoring, diagnosis during early stages, and on‐demand therapy has attracted considerable attention. Here, by combining the emerging development of bioelectronics, a smart flexible electronics‐integrated wound dressing with a double‐layer structure, the upper layer of which is polydimethylsiloxane‐encapsulated flexible electronics integrated with a temperature sensor and ultraviolet (UV) light‐emitting diodes, and the lower layer of which is a UV‐responsive antibacterial hydrogel, is designed. This dressing is expected to provide early infection diagnosis via real‐time wound‐temperature monitoring by the integrated sensor and on‐demand infection treatment by the release of antibiotics from the hydrogel by in situ UV irradiation. The integrated system possesses good flexibility, excellent compatibility, and high monitoring sensitivity and durability. Animal experiment results demonstrate that the integrated system is capable of monitoring wound status in real time, detecting bacterial infection and providing effective treatment on the basis of need. This proof‐of‐concept research holds great promise in developing new strategies to significantly improve wound management and other pathological diagnoses and treatments.

We report on a multi-petawatt 3-cascaded all-optical parametric chirped-pulse amplification laser facility. The experimental results demonstrate that the maximum energy after the final amplifier and after the compressor is 168.7 J and 91.1 J, respectively. The pulse width (FWHM) is 18.6 fs in full width at half maximum after optimization of pulse compression. Therefore, 4.9 PW peak power has been achieved for the laser facility. To the best of our knowledge, this is the highest peak power reported so far for an all-optical parametric chirped-pulse amplification facility, and a compressed pulse shorter than 20 fs is achieved in a PW-class laser facility for the first time.

Background: Early-stage diagnosis and treatment can improve survival rates of liver cancer patients. Dynamic contrast-enhanced MRI provides the most comprehensive information for differential diagnosis of liver tumors. However, MRI diagnosis is affected by subjective experience, so deep learning may supply a new diagnostic strategy. We used convolutional neural networks (CNNs) to develop a deep learning system (DLS) to classify liver tumors based on enhanced MR images, unenhanced MR images, and clinical data including text and laboratory test results. Methods: Using data from 1,210 patients with liver tumors (N = 31,608 images), we trained CNNs to get seven-way classifiers, binary classifiers, and three-way malignancyclassifiers (Model A-Model G). Models were validated in an external independent extended cohort of 201 patients (N = 6,816 images). The area under receiver operating characteristic (ROC) curve (AUC) were compared across different models. We also compared the sensitivity and specificity of models with the performance of three experienced radiologists. Results: Deep learning achieves a performance on par with three experienced radiologists on classifying liver tumors in seven categories. Using only unenhanced images, CNN performs well in distinguishing malignant from benign liver tumors (AUC, 0.946; 95% CI 0.914-0.979 vs. 0.951; 0.919-0.982, P = 0.664). New CNN combining unenhanced images with clinical data greatly improved the performance of classifying malignancies as hepatocellular carcinoma (AUC, 0.985; 95% CI 0.960-1.000), metastatic tumors (0.998; 0.989-1.000), and other primary malignancies (0.963; 0.896-1.000), and the agreement with pathology was 91.9%.These models mined diagnostic information in unenhanced images and clinical data by deepneural-network, which were different to previous methods that utilized enhanced images. The sensitivity and specificity of almost every category in these models reached the same high level compared to three experienced radiologists. Zhen et al. Deep Learning for Liver Tumor Diagnosis Conclusion: Trained with data in various acquisition conditions, DLS that integrated these models could be used as an accurate and time-saving assisted-diagnostic strategy for liver tumors in clinical settings, even in the absence of contrast agents. DLS therefore has the potential to avoid contrast-related side effects and reduce economic costs associated with current standard MRI inspection practices for liver tumor patients.

The current global production of plastics is over 300 million tons, 20% of which is produced in China. It has been estimated that about 90% of the discarded plastics are not recycled. China was the world's leading importer of waste plastics, while since January 1, 2018, China's import ban on waste plastics has been put into force, which has had a far-reaching effect on global plastic production and solid waste management. Southeast Asian countries like Malaysia have replaced China as the leading importer of plastic wastes. As the main exporter of waste plastics, EU has released strategy and initiative about plastics to restrict the use of micro plastics and single-use plastics. Meanwhile main European counties like UK, German and France have also taken own active measures to realize the control of packaging waste and non-recycled plastic and the recycling of plastic wastes in several years. As For the US, some areas such as Seattle and San Francisco have positively responded to the global trend of plastic ban. However, the controversy over "plastic restriction" in the whole state obstructed the promulgation and implementation of the national plastic ban. On the whole, major companies and more than 60 countries all over the world have introduced levies or bans to combat single-use plastic wastes. The Chinese government began to rectify the domestic waste plastics market and the Ministry of Industry and Information Technology of China has clarified the threshold of waste plastic treatment capacity for key enterprises. In addition to landfill, direct recovery and waste to energy processes are the main disposal methods of waste plastics. Thermoplastics like PE, PP and PET that are sorted out from the waste stream by citizens can be directly recycled to the primary material. The mixed waste plastics can be used as fuel in waste to energy plants, or as feedstock to pyrolysis plants that transform them to high value-added oil or chemical materials, which are more promising disposal methods of waste plastics.