Crack is an important indicator for evaluating the damage level of concrete structures. However, traditional crack detection algorithms have complex implementation and weak generalization. The existing crack detection algorithms based on deep learning are mostly window-level algorithms with low pixel precision. In this article, the CrackUnet model based on deep learning is proposed to solve the above problems. First, crack images collected from the lab, earthquake sites, and the Internet are resized, labeled manually, and augmented to make a dataset (1200 subimages with 256 × 256 × 3 resolutions in total). Then, an improved Unet-based method called CrackUnet is proposed for automated pixel-level crack detection. A new loss function named generalized dice loss is adopted to detect cracks more accurately. How the size of the dataset and the depth of the model affect the training time, detecting accuracy, and speed is researched. The proposed methods are evaluated on the test dataset and a previously published dataset. The highest results can reach 91.45%, 88.67%, and 90.04% on test dataset and 98.72%, 92.84%, and 95.44% on CrackForest Dataset for precision, recall, and F1 score, respectively. By comparing the detecting accuracy, the training time, and the information of datasets, CrackUnet model outperform than other methods. Furthermore, six images with complicated noise are used to investigate the robustness and generalization of CrackUnet models.
Background: The patent literature contains a large amount of information on the internal state of current industrial technologies that are not available in other literature studies. Scientific articles are the direct achievements of theoretical research in this field and can reveal how current theories in basic research have developed. In this study, the progress and status of natural anticancer products in this field were summarized, and the research hotspots were explored through the analysis of the relevant patent literature and scientific articles.Methods: Patent data were retrieved from the incoPat patent retrieval database, and paper data were retrieved from the Web of Science core set and PubMed. GraphPad Prism 8, Microsoft Excel 2010, and CiteSpace 5.8.R3 were used to perform visual processing. The analyzed patent literature includes the patent applicant type, country (or region), and technical subject. The analyzed scientific article includes academic groups, subject areas, keyword clustering, and burst detection.Results: A total of 20,435 patent families and 38,746 articles were collected by 4 January 2022. At present, antitumor drugs derived from natural products mainly include 1) apoptosis inducers such as curcumin, gallic acid, resveratrol, Theranekron D6, and gaillardin; 2) topoisomerase inhibitors such as camptothecins, scaffold-hopped flavones, podophyllotoxin, oxocrebanine, and evodiamine derivatives; 3) telomerase inhibitors such as camptothecin and isoquinoline alkaloids of Chelidonium majus, amentoflavone, and emodin; 4) microtubule inhibitors such as kolaflavanone, tanshinone IIA analog, eugenol, and millepachine; 5) immunomodulators such as fucoidan, myricetin, bergapten, and atractylenolide I; 6) tumor microenvironment regulators such as beta-escin and icaritin; 7) multidrug resistance reversal agents such as berberine, quercetin, and dihydromyricetin; and 8) antiangiogenic and antimetastatic agents such as epigallocatechin-3-gallate, lupeol, ononin, and saikosaponin A.Conclusion: Anticancer natural product technology was introduced earlier, but the later development momentum was insufficient. In addition, scientific research activities are relatively closed, and technical exchanges need to be strengthened. Currently, the development of medicinal plants and the research on the anticancer mechanism of natural active products are still research hotspots, especially those related to immune checkpoints, essential oils, and metastatic cancer. Theories of traditional Chinese medicine (TCM), such as “restraining excessiveness to acquire harmony,” “same treatment for different diseases,” “Meridian induction theory,” and “Fuzheng Quxie,” have important guiding significance to the research of anticancer mechanisms and the development of new drugs and can provide new ideas for this process.Systematic Review Registration: [https://sourceforge.net/projects/citespace/], identifier [000755430500001].
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.