Background Accurate segmentation and recognition algorithm of lung nodules has great important value of reference for early diagnosis of lung cancer. An algorithm is proposed for 3D CT sequence images in this paper based on 3D Res U-Net segmentation network and 3D ResNet50 classification network. The common convolutional layers in encoding and decoding paths of U-Net are replaced by residual units while the loss function is changed to Dice loss after using cross entropy loss to accelerate network convergence. Since the lung nodules are small and rich in 3D information, the ResNet50 is improved by replacing the 2D convolutional layers with 3D convolutional layers and reducing the sizes of some convolution kernels, 3D ResNet50 network is obtained for the diagnosis of benign and malignant lung nodules. Results 3D Res U-Net was trained and tested on 1044 CT subcases in the LIDC-IDRI database. The segmentation result shows that the Dice coefficient of 3D Res U-Net is above 0.8 for the segmentation of lung nodules larger than 10 mm in diameter. 3D ResNet50 was trained and tested on 2960 lung nodules in the LIDC-IDRI database. The classification result shows that the diagnostic accuracy of 3D ResNet50 is 87.3% and AUC is 0.907. Conclusion The 3D Res U-Net module improves segmentation performance significantly with the comparison of 3D U-Net model based on residual learning mechanism. 3D Res U-Net can identify small nodules more effectively and improve its segmentation accuracy for large nodules. Compared with the original network, the classification performance of 3D ResNet50 is significantly improved, especially for small benign nodules.
Berberine (BBR) has a neuroprotective effect against ischemic stroke, but its specific protective mechanism has not been clearly elaborated. This study explored the effect of BBR on the canopy FGF signaling regulator 2 (CNPY2) signaling pathway in the ischemic penumbra of rats. The model of cerebral ischemia-reperfusion injury (CIRI) was established by the thread embolization method, and BBR was gastrically perfused for 48 h or 24 h before operation and 6 h after operation. The rats were randomly divided into four groups: the Sham group, BBR group, CIRI group, and CIRI + BBR group. After 2 h of ischemia, followed by 24 h of reperfusion, we confirmed the neurologic dysfunction and apoptosis induced by CIRI in rats (p < 0.05). In the ischemic penumbra, the expression levels of CNPY2-regulated endoplasmic reticulum stress-induced apoptosis proteins (CNPY2, glucose-regulated protein 78 (GRP78), double-stranded RNA-activated protein kinase-like ER kinase (PERK), C/EBP homologous protein (CHOP), and Caspase-3) were significantly increased, but these levels were decreased after BBR treatment (p < 0.05). To further verify the inhibitory effect of BBR on CIRI-induced neuronal apoptosis, we added an endoplasmic reticulum-specific agonist and a PERK inhibitor to the treatment. BBR was shown to significantly inhibit the expression of apoptotic proteins induced by endoplasmic reticulum stress agonist, while the PERK inhibitor partially reversed the ability of BBR to inhibit apoptotic protein (p < 0.05). These results confirm that berberine may inhibit CIRI-induced neuronal apoptosis by downregulating the CNPY2 signaling pathway, thereby exerting a neuroprotective effect.
BackgroundColposcopy is an important method in the diagnosis of cervical lesions. However, experienced colposcopists are lacking at present, and the training cycle is long. Therefore, the artificial intelligence-based colposcopy-assisted examination has great prospects. In this paper, a cervical lesion segmentation model (CLS-Model) was proposed for cervical lesion region segmentation from colposcopic post-acetic-acid images and accurate segmentation results could provide a good foundation for further research on the classification of the lesion and the selection of biopsy site.MethodsFirst, the improved Faster Region-convolutional neural network (R-CNN) was used to obtain the cervical region without interference from other tissues or instruments. Afterward, a deep convolutional neural network (CLS-Net) was proposed, which used EfficientNet-B3 to extract the features of the cervical region and used the redesigned atrous spatial pyramid pooling (ASPP) module according to the size of the lesion region and the feature map after subsampling to capture multiscale features. We also used cross-layer feature fusion to achieve fine segmentation of the lesion region. Finally, the segmentation result was mapped to the original image.ResultsExperiments showed that on 5455 LSIL+ (including cervical intraepithelial neoplasia and cervical cancer) colposcopic post-acetic-acid images, the accuracy, specificity, sensitivity, and dice coefficient of the proposed model were 93.04%, 96.00%, 74.78%, and 73.71%, respectively, which were all higher than those of the mainstream segmentation model.ConclusionThe CLS-Model proposed in this paper has good performance in the segmentation of cervical lesions in colposcopic post-acetic-acid images and can better assist colposcopists in improving the diagnostic level.
Hyperspectral imaging (HSI) is a popular method of substance identification and mapping in many fields. Light-emitting diodes (LEDs) can be introduced as an active light source, which have been widely used with the distinct advantages of small size, low energy consumption, long lifetime, and fast switching. In this paper, we propose an active HSI system that is based on a multi-wavelength LED-array light source. This LED-based HSI system has a simple and stable configuration, without the complex dispersive spectrometer and mechanical scanning device. The proposed HSI system has been validated using the standard color checker, showing a reliable spectral performance. Moreover, the spatial-spectral information of Chinese paper-cuttings has been successfully extracted, which indicates the great potential in practical applications.
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.