A Convolutional Neural Network Based Deep Learning Algorithm for Identification of Oral Precancerous and Cancerous Lesion and Differentiation from Normal Mucosa: A Retrospective Study
“…After this screening process, 12 articles were selected, and the data retrieved, as shown in Table 1. [14][15][16][17][18][19][20][21][22][23][24][25] AI presents extensive opportunities in OC screening. Advances in the field of AI offer a powerful adjunctive method to perform an automated screening of the oral cavity.…”
Section: J O U R N a L P R E -P R O O F Resultsmentioning
confidence: 99%
“…After this screening process, 12 articles were selected, and the data were retrieved, as shown in Table 1 . 14 , 15 , 16 , 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 Fig. 1 PRISMA flowchart.…”
Section: Resultsmentioning
confidence: 99%
“… Study concluded that both morphological and textural features play a very important role in OSCC diagnosis. Sharma (2022) 18 To use pre-trained convolutional neural networks for identifying oral pre-cancerous (potentially malignant) and cancerous lesions and to differentiate them from normal mucosa using a dataset of clinically annotated photographic images. Clinical photographs of 329 oral squamous cell carcinoma and OPMDs patients.…”
“…After this screening process, 12 articles were selected, and the data retrieved, as shown in Table 1. [14][15][16][17][18][19][20][21][22][23][24][25] AI presents extensive opportunities in OC screening. Advances in the field of AI offer a powerful adjunctive method to perform an automated screening of the oral cavity.…”
Section: J O U R N a L P R E -P R O O F Resultsmentioning
confidence: 99%
“…After this screening process, 12 articles were selected, and the data were retrieved, as shown in Table 1 . 14 , 15 , 16 , 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 Fig. 1 PRISMA flowchart.…”
Section: Resultsmentioning
confidence: 99%
“… Study concluded that both morphological and textural features play a very important role in OSCC diagnosis. Sharma (2022) 18 To use pre-trained convolutional neural networks for identifying oral pre-cancerous (potentially malignant) and cancerous lesions and to differentiate them from normal mucosa using a dataset of clinically annotated photographic images. Clinical photographs of 329 oral squamous cell carcinoma and OPMDs patients.…”
“…An already-built pre-trained network was modified by expanding the tumor, ring-dividing it, and using T1-weighted contrast-enhanced MRI [ 34 ]. Hybridization of two methods entropy-based controlling and Multiclass Vector machine (M-SVM) is used for optimal feature extraction [ 35 , 36 , 37 ]. The differential deep-CNN model for detecting brain cancers in MRI images was put to the test by the authors in [ 38 ].…”
Section: Introductionmentioning
confidence: 99%
“…Here, CNN-multi-scale analysis was used to create 3D-CNN [ 39 ] utilizing MRI images of pituitary tumors. The classification procedure was made to perform better in [ 36 , 40 , 41 ] by using variational auto-encoders with generative adversarial networks and a hybrid model. These conventions still need to be refined because they do not produce adequate classification and segmentation results.…”
Background and Objectives: Brain Tumor Fusion-based Segments and Classification-Non-enhancing tumor (BTFSC-Net) is a hybrid system for classifying brain tumors that combine medical image fusion, segmentation, feature extraction, and classification procedures. Materials and Methods: to reduce noise from medical images, the hybrid probabilistic wiener filter (HPWF) is first applied as a preprocessing step. Then, to combine robust edge analysis (REA) properties in magnetic resonance imaging (MRI) and computed tomography (CT) medical images, a fusion network based on deep learning convolutional neural networks (DLCNN) is developed. Here, the brain images’ slopes and borders are detected using REA. To separate the sick region from the color image, adaptive fuzzy c-means integrated k-means (HFCMIK) clustering is then implemented. To extract hybrid features from the fused image, low-level features based on the redundant discrete wavelet transform (RDWT), empirical color features, and texture characteristics based on the gray-level cooccurrence matrix (GLCM) are also used. Finally, to distinguish between benign and malignant tumors, a deep learning probabilistic neural network (DLPNN) is deployed. Results: according to the findings, the suggested BTFSC-Net model performed better than more traditional preprocessing, fusion, segmentation, and classification techniques. Additionally, 99.21% segmentation accuracy and 99.46% classification accuracy were reached using the proposed BTFSC-Net model. Conclusions: earlier approaches have not performed as well as our presented method for image fusion, segmentation, feature extraction, classification operations, and brain tumor classification. These results illustrate that the designed approach performed more effectively in terms of enhanced quantitative evaluation with better accuracy as well as visual performance.
The moisture content of pharmaceutical powders can significantly impact the physical and chemical properties of drug formulations, solubility, flowability, and stability. However, current technologies for measuring moisture content in pharmaceutical materials require extensive calibration processes, leading to poor consistency and a lack of speed. To address this challenge, this study explores the feasibility of using impedance spectroscopy to enable accurate, rapid testing of moisture content of pharmaceutical materials with minimal to zero calibration. By utilizing electrochemical impedance spectroscopy (EIS) signals, we identify a strong correlation between the electrical properties of the materials and varying moisture contents in pharmaceutical samples. Equivalent circuit modeling is employed to unravel the underlying mechanism, providing valuable insights into the sensitivity of impedance spectroscopy to moisture content variations. Furthermore, the study incorporates deep learning techniques utilizing a 1D convolutional neural network (1DCNN) model to effectively process the complex spectroscopy data. The proposed model achieved a notable predictive accuracy with an average error of just 0.69% in moisture content estimation. This method serves as a pioneering study in using deep learning to provide a reliable solution for realtime moisture content monitoring, with potential applications extending from pharmaceuticals to the food, energy, environmental, and healthcare sectors.
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.
