To solve the problem that the method based on tumor morphology or overall average parameters of tumor cannot conduct the early evaluation of tumor treatment response, we proposed a voxel-wise method. The voxel-wise method uses the method combining rigid and elastic registration algorithm to align the tumor area before and after treatment on the images which are acquired by the dynamic contrast enhanced magnetic resonance imaging (DCE-MRI). We calculated voxel-wise volume transport constant (Ktrans) using pharmacokinetic model, and designed a threshold d to get the volume fraction of voxels which Ktrans increased significantly (F+), Ktrans decreased significantly (F-) or had no significant change (F0). Linear regression analysis was performed to get the correlation between volume fractions and pathological tumor cell necrosis rate (TCNR). We then determined the ability of volume fractions to evaluate treatment response at early stage by receiver operating characteristic (ROC) curve analysis. We performed experiments on 10 patients with soft tissue sarcomas. The results indicated that F- had significant negative correlation with TCNR (R2=0.832 8, P=0.0002), F0 has significant positively correlation with TCNR (R2=0.788 4, P=0.0006). In addition, F-(AUC=0.905,P=0.053), F0 (AUC=0.857,P=0.087) had a good ability in early tumor treatment response evaluation. Therefore, F- and F0 can be used as effective imaging biomarkers for early evaluation of tumor treatment.
Objective To investigate the effect of microRNA-27a (miR-27a) on the apoptosis of human lung adenocarcinoma cells A549 induced by lipopolysaccharide (LPS) by regulating the phosphatidylinositol-3-kinase (PI3K)/protein kinase B (AKT) pathway, and its mechanism is discussed preliminarily. Methods The complementary binding sites of miR-27a and phosphatidylinositol-3 kinase catalytic subunit delta (PIK3CD) were analyzed by Starbase and verified by double luciferase. The A549 cells were divided into normal group, LPS group, LPS+miR-27a mimic negative control group, LPS+miR-27a mimic group, LPS+miR-27a mimic+PI3K activator group. In the LPS+miR-27a mimic negative control group, LPS+miR-27a mimic group and LPS+miR-27a mimic+PI3K activator group, the cells were transfected with miR-27a mimic negative control, miR-27a mimic and miR-27a mimic, respectively, and were cultured for 6 h. After that, the cells were cultured in complete medium for 24 h, and then, except for the normal group, the cells in the other groups were stimulated with 10 mg/L LPS for 24 h, and the PI3K activator 740 Y-P was added to the LPS+miR-27a mimic+PI3K activator group, and cells in normal group were cultured in complete medium for the same time. Real-time quantitative polymerase chain reaction was used to detect the expression level of miR-27a in cells; cell counting kit 8 was used to detect cell proliferation; Hoechst33342 staining and flow cytometry was used to detect apoptosis; autophagy of A549 cells was observed by transmission electron microscope; Western blot was used to detect the expression of PIK3CD, phosphorylated-AKT (p-AKT), B-cell lymphoma-2 (Bcl-2), Bcl-2-associated X protein (Bax), cleaved caspase-3 and microtubule-associated protein 1 light chain 3 II (LC3II) protein. Results There was a binding site between miR-27a and PIK3CD, which was verified by double luciferase. Compared with those in normal group, the expression level of miR-27a, proliferation rate and protein expression level of Bcl-2 in LPS group and LPS+miR-27a mimic negative control group were lower (P<0.05), the apoptosis rate, protein expression levels of PIK3CD, p-AKT, Bax, cleaved caspase-3, LC3Ⅱ were higher (P<0.05); compared with those in LPS group and LPS+miR-27a mimic negative control group, the expression level of miR-27a, proliferation rate and protein expression level of Bcl-2 in LPS+miR-27a mimic group were higher (P<0.05), the apoptosis rate, protein expression levels of PIK3CD, p-AKT, Bax, cleaved caspase-3, LC3Ⅱ were lower (P<0.05); compared with those in LPS+miR-27a mimic group, the expression level of miR-27a and proliferation rate in LPS+miR-27a mimic+PI3K activator group were lower (P<0.05), the apoptosis rate, protein expression levels of PIK3CD, p-AKT, cleaved caspase-3, LC3Ⅱ were higher (P<0.05). The number of cells in the normal group was more, the cells were closely arranged, the nucleus size was uniform, and the organelle structure was normal; in LPS group and LPS+miR-27a mimic negative control group, cells became round, nuclei pyknosis, formed clumps, and showed multiple round autophagic vesicles of different sizes; the number of nuclear pyknotic cells in LPS+miR-27a mimic group decreased, and the number of nuclear pyknotic cells in LPS+miR-27a mimic+PI3K activator group increased compared with LPS+miR-27a mimic group, a small number of circular autophagic vesicles were observed, but the number was different. Conclusion Overexpression of miR-27a can inhibit PI3K/Akt pathway and reduce LPS induced apoptosis of human lung adenocarcinoma cells A549, which may be related to the reduction of autophagy.
Melanocytic lesions occur on the surface of the skin, in which the malignant type is melanoma with a high fatality rate, seriously endangering human health. The histopathological analysis is the gold standard for diagnosis of melanocytic lesions. In this study, a fully automated intelligent diagnosis method based on deep learning was proposed to classify the pathological whole slide images (WSI) of melanocytic lesions. Firstly, the color normalization based on CycleGAN neural network was performed on multi-center pathological WSI; Secondly, ResNet-152 neural network-based deep convolutional network prediction model was built using 745 WSI; Then, a decision fusion model was cascaded, which calculates the average prediction probability of each WSI; Finally, the diagnostic performance of the proposed method was verified by internal and external test sets containing 182 and 54 WSI, respectively. Experimental results showed that the overall diagnostic accuracy of the proposed method reached 94.12% in the internal test set and exceeded 90% in the external test set. Furthermore, the color normalization method adopted was superior to the traditional color statistics-based and staining separation-based methods in terms of structure preservation and artifact suppression. The results demonstrate that the proposed method can achieve high precision and strong robustness in pathological WSI classification of melanocytic lesions, which has the potential in promoting the clinical application of computer-aided pathological diagnosis.
Computed tomography (CT) imaging is a vital tool for the diagnosis and assessment of lung adenocarcinoma, and using CT images to predict the recurrence-free survival (RFS) of lung adenocarcinoma patients post-surgery is of paramount importance in tailoring postoperative treatment plans. Addressing the challenging task of accurate RFS prediction using CT images, this paper introduces an innovative approach based on self-supervised pre-training and multi-task learning. We employed a self-supervised learning strategy known as “image transformation to image restoration” to pretrain a 3D-UNet network on publicly available lung CT datasets to extract generic visual features from lung images. Subsequently, we enhanced the network’s feature extraction capability through multi-task learning involving segmentation and classification tasks, guiding the network to extract image features relevant to RFS. Additionally, we designed a multi-scale feature aggregation module to comprehensively amalgamate multi-scale image features, and ultimately predicted the RFS risk score for lung adenocarcinoma with the aid of a feed-forward neural network. The predictive performance of the proposed method was assessed by ten-fold cross-validation. The results showed that the consistency index (C-index) of the proposed method for predicting RFS and the area under curve (AUC) for predicting whether recurrence occurs within three years reached 0.691 ± 0.076 and 0.707 ± 0.082, respectively, and the predictive performance was superior to that of existing methods. This study confirms that the proposed method has the potential of RFS prediction in lung adenocarcinoma patients, which is expected to provide a reliable basis for the development of individualized treatment plans.