Abstract:Objective: COVID-19 is a sort of infectious disease caused by a new strain of coronavirus. This study aims to develop a more accurate COVID-19 diagnosis system.Methods: First, the n-conv module (nCM) is introduced. Then we built a 12-layer convolutional neural network (12l-CNN) as the backbone network. Afterwards, PatchShuffle was introduced to integrate with 12l-CNN as a regularization term of the loss function. Our model was named PSCNN. Moreover, multiple-way data augmentation and Grad-CAM are employed to a… Show more
“…In future we may include feature selection methods to train the model only with the most informative features. We may use hybrid models (combination of two or more pre-trained models) from pre-trained models and test their performance on the dataset without augmentation and multiple way data augmentation [23] also.…”
Section: Resultsmentioning
confidence: 99%
“…We have used gamma values from 0.8 to 1.1 to generate new samples. [23] used patchshuffle, a multiple way data augmentation technique. Since chest radiography images contain various kind of lung opacity information and we have four different classes where COVID-19, pneumonia and non COVID lung opacity show very close symptoms, we have implemented only two types of augmentation techniques.…”
“…In future we may include feature selection methods to train the model only with the most informative features. We may use hybrid models (combination of two or more pre-trained models) from pre-trained models and test their performance on the dataset without augmentation and multiple way data augmentation [23] also.…”
Section: Resultsmentioning
confidence: 99%
“…We have used gamma values from 0.8 to 1.1 to generate new samples. [23] used patchshuffle, a multiple way data augmentation technique. Since chest radiography images contain various kind of lung opacity information and we have four different classes where COVID-19, pneumonia and non COVID lung opacity show very close symptoms, we have implemented only two types of augmentation techniques.…”
“…However, since the image will be similar to the original image, the risk of overfitting, i.e., a decrease in the performance on the test dataset due to the prediction model fitting to match into the training dataset, cannot be ruled [57][58][59][60][61][62][63][64][65][66][67][68]. Thus, data augmentation effectively enables learning with a small number of data.…”
Section: Angles and Data Split In Deepsnap-dl With Digits And Python ...mentioning
Molecular design and evaluation for drug development and chemical safety assessment have been advanced by quantitative structure–activity relationship (QSAR) using artificial intelligence techniques, such as deep learning (DL). Previously, we have reported the high performance of prediction models molecular initiation events (MIEs) on the adverse toxicological outcome using a DL-based QSAR method, called DeepSnap-DL. This method can extract feature values from images generated on a three-dimensional (3D)-chemical structure as a novel QSAR analytical system. However, there is room for improvement of this system’s time-consumption. Therefore, in this study, we constructed an improved DeepSnap-DL system by combining the processes of generating an image from a 3D-chemical structure, DL using the image as input data, and statistical calculation of prediction-performance. Consequently, we obtained that the three prediction models of agonists or antagonists of MIEs achieved high prediction-performance by optimizing the parameters of DeepSnap, such as the angle used in the depiction of the image of a 3D-chemical structure, data-split, and hyperparameters in DL. The improved DeepSnap-DL system will be a powerful tool for computer-aided molecular design as a novel QSAR system.
“…The experiment is done as 10 runs of 10-fold crossvalidation and it achieves an accuracy of approximately 94.03%. Wang et al 19 introduced a 12 level CNN for the diagnosis of COVID-19. They have integrated Pat-chShuffle along with the 12 levels to regularize the loss function.…”
Pulmonic nodules are unusual growing of tissues; originate on one lung or both lungs. They are the round, trifling mass of soft tissues in the lung area. Habitually, pulmonic nodules are indications of lung tumors, but they may be nonthreatening. When identified earlier and treated in time, the patient's life expectancy increases. The anatomy of the lung is highly interconnected in nature, which makes it difficult to diagnose pulmonic nodules by diverse clinical imaging practices. A network model is presented in this paper for accurate classification of pulmonic nodules from computed tomography scans images. The lung images are subjected to semantic segmentation using Attention U‐Net to isolate the pulmonary nodules. The proposed Directional Hexagonal Mixed Pattern is applied to generate a new texture pattern. Then, the nodules are classified by combining the proposed multilevel network model with the self‐attention network. This paper also demonstrates an experimental arrangement called tenfold cross‐validation without a segmentation mask, in which the nodules that had been marked as less than 3 mm by radiologists are discarded. This has obtained an improved result. The experimental results show that with and without segmentation masks the proposed classifier scores an accuracy of 90.48% and 91.83%. In addition, it has efficiently produced the measure of area under curve as 98.08%.
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.