Abstract:Cardiovascular diseases (CVD) are the leading cause of death and morbidity in the world and are a major contributor to healthcare costs. Although enormous progress has been made in diagnosing CVD, there is an urgent need for more efficient early detection and the development of novel diagnostic tools. Currently, CVD diagnosis relies primarily on clinical symptoms based on molecular imaging (MOI) or biomarkers associated with CVDs. However, sensitivity, specificity, and accuracy of the assay are still challengi… Show more
“…Moreover, the majority of the population often has difficulty getting access to pathology and laboratory medicine services. Regarding cancer, cardiovascular disease, and bone generation as examples, few communities can get the pathology and laboratory medicine treatment [16][17][18][19][20][21].…”
Section: Introductionmentioning
confidence: 99%
“…Moreover, the majority of the population can barely get access to pathology and laboratory medicine services. Take cancer and cardiovascular disease as examples, only a few and unbalanced communities can get the PLAM treatment [14][15][16] .…”
(1) Purpose: To improve the capability of EfficientNet, including developing a cropping method called Random Center Cropping (RCC) to retain the original image resolution and significant features on the images’ center area, reducing the downsampling scale of EfficientNet to facilitate the small resolution images of RPCam datasets, and integrating attention and Feature Fusion (FF) mechanisms with EfficientNet to obtain features containing rich semantic information. (2) Methods: We adopt the Convolutional Neural Network (CNN) to detect and classify lymph node metastasis in breast cancer. (3) Results: Experiments illustrate that our methods significantly boost performance of basic CNN architectures, where the best-performed method achieves an accuracy of 97.96% ± 0.03% and an Area Under the Curve (AUC) of 99.68% ± 0.01% on RPCam datasets, respectively. (4) Conclusions: (1) To our limited knowledge, we are the only study to explore the power of EfficientNet on Metastatic Breast Cancer (MBC) classification, and elaborate experiments are conducted to compare the performance of EfficientNet with other state-of-the-art CNN models. It might provide inspiration for researchers who are interested in image-based diagnosis using Deep Learning (DL). (2) We design a novel data augmentation method named RCC to promote the data enrichment of small resolution datasets. (3) All of our four technological improvements boost the performance of the original EfficientNet.
“…Moreover, the majority of the population often has difficulty getting access to pathology and laboratory medicine services. Regarding cancer, cardiovascular disease, and bone generation as examples, few communities can get the pathology and laboratory medicine treatment [16][17][18][19][20][21].…”
Section: Introductionmentioning
confidence: 99%
“…Moreover, the majority of the population can barely get access to pathology and laboratory medicine services. Take cancer and cardiovascular disease as examples, only a few and unbalanced communities can get the PLAM treatment [14][15][16] .…”
(1) Purpose: To improve the capability of EfficientNet, including developing a cropping method called Random Center Cropping (RCC) to retain the original image resolution and significant features on the images’ center area, reducing the downsampling scale of EfficientNet to facilitate the small resolution images of RPCam datasets, and integrating attention and Feature Fusion (FF) mechanisms with EfficientNet to obtain features containing rich semantic information. (2) Methods: We adopt the Convolutional Neural Network (CNN) to detect and classify lymph node metastasis in breast cancer. (3) Results: Experiments illustrate that our methods significantly boost performance of basic CNN architectures, where the best-performed method achieves an accuracy of 97.96% ± 0.03% and an Area Under the Curve (AUC) of 99.68% ± 0.01% on RPCam datasets, respectively. (4) Conclusions: (1) To our limited knowledge, we are the only study to explore the power of EfficientNet on Metastatic Breast Cancer (MBC) classification, and elaborate experiments are conducted to compare the performance of EfficientNet with other state-of-the-art CNN models. It might provide inspiration for researchers who are interested in image-based diagnosis using Deep Learning (DL). (2) We design a novel data augmentation method named RCC to promote the data enrichment of small resolution datasets. (3) All of our four technological improvements boost the performance of the original EfficientNet.
“…Protein targets are first sensed by recognition molecules such as antibodies, aptamers, or molecularly imprinted polymers, and the sensing is then quantitatively detected by various methods, including electrochemistry (EC), electrochemiluminescence (ECL), fluorescent methods (FL), colorimetry, surface-enhanced Raman scattering (SERS), and surface plasmon resonance technology (SPR). 33 Nanomaterials with excellent optoelectronic properties greatly improve the detection sensitivity by orders of magnitude. 21 , 34 , 35 , 36 , 37 , 38 With ZnSnO 3 perovskite nanomaterial-decorated glassy carbon electrodes, Singh et al.…”
Section: Nanotechnology Approaches To Detect Cadsmentioning
“…Moreover, EVs‐based therapeutics against cancer is being challenged due to inadequate secretion and low potency of drug payload for desirable anti‐tumor efficacy. [ 78,79 ] Due to the aforementioned limitation, multiple strategies have been developed for EVs mass production and to involve a substantial amount of therapeutic agents into EVs. For instance, Ryosuke et al.…”
Section: Current Progress Of Immunotherapymentioning
Glioblastoma multiforme (GBM) is the most aggressive primary central nervous system (CNS) tumor, and treatment for GBM is regarded as the most challenging task in clinical oncology. Although multiple treatments are available, including surgery, chemotherapy, and radiotherapy, these conventional therapies barely improve the functional prognosis and life quality of patients with glioblastoma. Immunotherapy, has become a promising approach for treating GBM because of the ability to overcome the blood-brain barrier (BBB) and complicated unique tumor immune microenvironment. Developing an efficient immunotherapy for GBM requires understanding the glioblastoma immune microenvironment; accordingly, this study begins by summarizing this and what it indicates for the development of immunological effects. Then current immunotherapy management for GBM and advanced studies including checkpoint inhibitors, cell vaccines, and extracellular vesicle-based immunotherapy is reviewed. Because monotherapies are inadequate for treating GBM, combinational GBM immunotherapy with other classical cancer therapies, especially chemo-immunotherapy, radiotherapy-immunotherapy, and the combination of gene therapy and immunotherapy, is introduced and discussed. The recent progress introduced in this review suggests that cancer immunotherapy and its combinatory therapies are highly promising treatment modalities for glioblastoma patients. However, systematical and in-depth investigations are required to improve the efficacy of GBM immunotherapy for future clinical translation.
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.