Corrigendum: PI-YOLO: dynamic sparse attention and lightweight convolutional based YOLO for vessel detection in pathological images.

[This corrects the article DOI: 10.3389/fonc.2024.1347123.].

Corrigendum: PI-YOLO: dynamic sparse attention and lightweight convolutional based YOLO for vessel detection in pathological images.

[This corrects the article DOI: 10.3389/fonc.2024.1347123.].

PI-YOLO: dynamic sparse attention and lightweight convolutional based YOLO for vessel detection in pathological images.

Vessel density within tumor tissues strongly correlates with tumor proliferation and serves as a critical marker for tumor grading. Recognition of vessel density by pathologists is subject to a strong inter-rater bias, thus limiting its prognostic value. There are many challenges in the task of object detection in pathological images, including complex image backgrounds, dense distribution of small targets, and insignificant differences between the features of the target to be detected and the image background. To address these problems and thus help physicians quantify blood vessels in pathology images, we propose Pathological Images-YOLO (PI-YOLO), an enhanced detection network based on YOLOv7. PI-YOLO incorporates the BiFormer attention mechanism, enhancing global feature extraction and accelerating processing for regions with subtle differences. Additionally, it introduces the CARAFE upsampling module, which optimizes feature utilization and information retention for small targets. Furthermore, the GSConv module improves the ELAN module, reducing model parameters and enhancing inference speed while preserving detection accuracy. Experimental results show that our proposed PI-YOLO network has higher detection accuracy compared to Faster-RCNN, SSD, RetinaNet, YOLOv5 network, and the latest YOLOv7 network, with a mAP value of 87.48%, which is 2.83% higher than the original model. We also validated the performance of this network on the ICPR 2012 mitotic dataset with an F1 value of 0.8678, outperforming other methods, demonstrating the advantages of our network in the task of target detection in complex pathology images.

Personalising Management of Behavioural and Psychological Symptoms of Dementia in Nursing Homes: Exploring the Synergy of Quantitative and Qualitative Data.

Researchers have been exploring how to manage Behavioural and Psychological Symptoms of Dementia (BPSD) in a personalised way, meanwhile, assistive technologies have been developed to collect a variety of personal data. This urges more research in investigating the combination of: data collected by the care team, which are mainly qualitative; and data collected by assistive technologies, the majority of which are quantitative. Previous studies, however, have yet to explore if and how a combination of quantitative and qualitative data could facilitate the care team to better understand each resident with dementia in the nursing home context for personalised BPSD management. Guided by a Research through Design approach, a prototype for collecting and visualising the quantitative and qualitative data towards personalised BPSD management was developed together with the care team. Via developing this prototype, knowledge was gained in what types of data could be combined for personalised BPSD management in nursing homes, what are their values, how to collect and present them, and how to introduce them in the working routine of the care team for analysis. The main findings suggest that the types of data to be collected could be unique for each resident with dementia; the quantitative and qualitative data are of value to each other during data collection and analysis; data collection should be quick and standardised yet flexible for the care team; the overview page is vital for data presentation; and user scenarios could be created to nudge the care team to analyse the data at certain points of their working routine. In general, a combination of qualitative data and quantitative data could help the care team to discover more insights about each resident with dementia and thus improve the current practice of personalised BPSD management.

Accuracy and Precision Evaluation of International Standard Spherical Model by Digital Dental Scanners.

With the popularization of digital technology and the exposure of traditional technology's defects, computer-aided design and computer-aided manufacturing (CAD/CAM) has been widely used in the field of dentistry. And the accuracy of the scanning system determines the ultimate accuracy of the prosthesis, which is a very important part of CAD/CAM, so we decided to evaluate the accuracy of the intraoral and extraoral scanners. In this study, we selected the sphere model as the scanning object and obtained the final result through data analysis and 3D fitting. In terms of trueness and precision, the scanner of SHINING was significantly different from that of others; however, there was no significant difference between TRIOS and CEREC. SHINING showed the lowest level of accuracy, with CEREC slightly lower than TRIOS. The sphere model has also been proven to be scanned successfully.

Light-driven micro/nanomotors: from fundamentals to applications.

Light, as an external stimulus, is capable of driving the motion of micro/nanomotors (MNMs) with the advantages of reversible, wireless and remote manoeuvre on demand with excellent spatial and temporal resolution. This review focuses on the state-of-the-art light-driven MNMs, which are able to move in liquids or on a substrate surface by converting light energy into mechanical work. The general design strategies for constructing asymmetric fields around light-driven MNMs to propel themselves are introduced as well as the photoactive materials for light-driven MNMs, including photocatalytic materials, photothermal materials and photochromic materials. Then, the propulsion mechanisms and motion behaviors of the so far developed light-driven MNMs are illustrated in detail involving light-induced phoretic propulsion, bubble recoil and interfacial tension gradient, followed by recent progress in the light-driven movement of liquid crystalline elastomers based on light-induced deformation. An outlook is further presented on the future development of light-driven MNMs towards overcoming key challenges after summarizing the potential applications in biomedical, environmental and micro/nanoengineering fields.

Complex-Mediated Synthesis of Tantalum Oxyfluoride Hierarchical Nanostructures for Highly Efficient Photocatalytic Hydrogen Evolution.

In this work, we have, for the first time, developed a facile wet-chemical route to obtain a novel photocatalytic material of tantalum oxyfluoride hierarchical nanostructures composed of amorphous cores and single crystalline TaO2F nanorod shells (ACHNs) by regulating the one-step hydrothermal process of TaF5 in a mixed solution of isopropanol (i-PrOH) and H2O. In this approach, elaborately controlling the reaction temperature and volume ratio of i-PrOH and H2O enabled TaF5 to transform into intermediate coordination complex ions of [TaOF3·2F](2-) and [TaF7](2-), which subsequently produced tantalum oxyfluoride ACHNs via a secondary nucleation and growth due to a stepwise change in hydrolysis rates of the two complex ions. Because of the unique chemical composition, crystal structure and micromorphology, the as-prepared tantalum oxyfluoride ACHNs show a more negative flat band potential, an accelerated charge transfer, and a remarkable surface area of 152.4 m(2) g(-1) contributing to increased surface reaction sites. As a result, they exhibit a photocatalytic activity for hydrogen production up to 1.95 mmol h(-1) g(-1) under the illumination of a simulated solar light without any assistance of co-catalysts, indicating that the as-prepared tantalum oxyfluoride ACHNs are a novel promising photocatalytic material for hydrogen production.