Search

Background Ovarian injury is one of the side effects of chemotherapy in female patients, which seriously endangers female reproductive health. Indole-3-carbinol (I3C), a natural substance abundant in cruciferous vegetables, has been reported to attenuate tissue damage. This study aimed to investigate whether I3C could prevent from ovarian damage induced by chemotherapy. Methods A mouse model of ovarian damage was established by intraperitoneal injection of cisplatin or co-treatment with I3C. Then the ovarian index and estrous cycle was assessed. Meanwhile, follicles counting was conducted to evaluate the effect of I3C in follicular development. Also, we performed the TUNEL and IHC staining to analyze the level of apoptosis and fibrosis, respectively. Western blot and qRT-PCR was used as quantitative methods to evaluate the expression of relative markers and TGF-β1/Smad pathway. Hela cells and Caski cells was used to investigate the anti-tumor activity of I3C by cell counting kit-8, the wound healing assay and colony formation assay in vitro. Results Our results showed that administration of I3C restored the ovary index and improved estrous cycle disorders. Follicle counting results showed that I3C is able to inhibit primordial follicles over-activation caused by cisplatin treatment, and maintained primordial follicle pool. We also found that I3C can down-regulate the levels of Bax and γH2ax, and inhibit the apoptosis of ovarian granulosa cells. In addition, I3C also reduced ovarian fibrosis and inhibited α-SMA and Collagen I expression levels. Further research revealed that I3C treatment significantly down-regulated the activity of the TGF-β1/smad signaling pathway. Finally, we demonstrated that I3C could inhibit the proliferation, migration and colony formation of cervical cancer cells in vitro. Conclusions In summary, I3C alleviates primordial follicular over-activation, granulosa cell apoptosis and ovarian fibrosis induced by cisplatin, and exhibits antitumor activity. Our study provides an innovative therapeutic strategy for preventing ovarian function from chemotherapy in female cancer patients.

The aim of this study was to compare the components of waxy and non-waxy corn kernels from a metabolomic perspective. All samples were analysed by liquid chromatography-mass spectrometry (LC-MS) with mode+ and mode− to obtain spectral data. Unsupervised principal component analysis (PCA), Partial least squares discrimination analysis (PLS-DA) and orthogonal partial least squares discriminant analysis (OPLS-DA) were used to identify significant components of waxy and non-waxy corn kernels. A total of 1589 features in (ESI+) ion mode and 2310 features in (ESI-) ion mode were obtained in this project. OPLS-DA identified 117 differential metabolites, including citric acid, alpha-linolenic metabolites, distinguished non-waxy corn from waxy corn. Compared with waxy corn, non-waxy corn expressed the enhanced metabolites such as guanine, guanosine and the reduced ones represented by citric acid, and oleic acid. This study offer new clues for the study of the taste and nutritional value of waxy and non-waxy corn.

Purpose To automate the detection and identification of visible components in feces for early diagnosis of gastrointestinal diseases, we propose FecalNet, a method using multiple deep neural networks. Methods FecalNet uses the ResNet152 residual network to extract and learn the characteristics of visible components in fecal microscopic images, acquire feature maps in combination with the feature pyramid network, apply the full convolutional network to classify and locate the fecal components, and implement the improved focal loss function to reoptimize the classification results. This allowed the complete automation of the detection and identification of the visible components in feces. Results We validated this method using a fecal database of 1,122 patients. The results indicated a mean average precision (mAP) of 92.16% and an average recall (AR) of 93.56%. The average precision (AP) and AR of erythrocyte, leukocyte, intestinal mucosal epithelial cells, hookworm eggs, ascarid eggs, and whipworm eggs were 92.82% and 93.38%, 93.99% and 96.11%, 90.71% and 92.41%, 89.95% and 93.88%, 96.90% and 91.21%, and 88.61% and 94.37%, respectively. The average times required by the GPU and the CPU to analyze a fecal microscopic image are approximately 0.14 and 1.02 s, respectively. Conclusion FecalNet can automate the detection and identification of visible components in feces. It also provides a detection and identification framework for detecting several other types of cells in clinical practice.

Purpose Urinary particles are particularly important parameters in clinical urinalysis, especially for the diagnosis of nephropathy. Therefore, it is highly important to precisely detect urinary particles in the clinical setting. However, artificial microscopy is subjective and time consuming, and various previous detection algorithms lack the adequate accuracy. In this study, a method is proposed for the analysis of urinary particles based on deep learning. Methods We used seven cellular components (i.e., erythrocytes, leukocytes, epithelial, low-transitional epithelium, casts, crystal, and squamous epithelial cells) in the microscopic imaging of urine as the detection targets. After the extraction of features using Resnet50, feature maps of different sizes are obtained in the last few layers of the feature pyramid net (FPN). The feature maps are then input into the classification subnetwork and regression subnetwork for classification and localization respectively, and detection results are obtained. First, we introduce the basic model (RetinaNet) to detect the cellular components in urinary particles, and the features of the objects can then be extracted more effectively by replacing different basic networks. Lastly, the effects of different weight initialization methods and different anchor scales on the performance of the model are investigated. Results We obtained the optimal network structure based on the adjustment of the loss functional parameters, thereby achieving the best results in the test set of urinary particles. The experimental data yielded an accuracy of 88.65% with a processing time of only 0.2 s for each image on a GeForce GTX 1080 graphics processing unit (GPU). Our results demonstrate that this method cannot only achieve the speed of the first-stage target detector, but also the accuracy of the two-stage target algorithm in the analysis of urinary particles. Conclusion This study developed new automated analysis urinary particles based on deep learning, and this method is expected to be used for the automated analysis and detection of urinary particles. Moreover, our approach will be useful for the detection of other cells in the clinical setting.

Urine casts is a particularly important examination item in clinical urinalysis, especially for the diagnosis of nephritis. Therefore, it is of great significance to identify the cast precisely in clinical urinalysis. However, due to subjectivity, time-consuming artificial microscopy, and the accuracy of various recognition algorithms, previous research is not considered to be sufficient. In this paper, an efficient approach to cast detection and recognition in urine sediment images is proposed. We used urine casts in urine microscopy as the detection target and then passed it to the ResNet50 network; in the last few layers of networks (FPN), we can obtain feature maps of different sizes. Finally, we input target area feature maps into the classification sub-network and the regression sub-network separately for classification and localization, and obtain detection results. The data shows that the mean average precision of the recognition result is 89.4%, while taking only 0.2s per image on the NVIDA Titan X GPU.

Computer-aided sperm analysis (CASA) can detect male infertility by classifying and counting sperm motility. However, a commonly used threshold segmentation method is prone to loss of sperm target when sperm and impurities collide, resulting in detection errors. In this regard, we propose a method based on the Gaussian mixture model for sperm cell tracking recognition and classification. Through background modeling, the motile sperm can be sensitively tracked, which can effectively avoid the loss of sperm target caused by a collision of sperm and impurities. Experimental results show that the accuracy of the algorithm for forward progressive motility sperm identification, sensitivity and specificity is 96%, 98%, and 95%, respectively. The accuracy of non-progressive motility sperm recognition, sensitivity, and specificity is 90%, 98%, and 92%, respectively. The accuracy of immotility sperm recognition, sensitivity, and specificity is 90%, 80%, and 87%, respectively.

Purpose To automate the segmentation of retinal layers, we propose DeepRetina, a method based on deep neural networks. Methods DeepRetina uses the improved Xception65 to extract and learn the characteristics of retinal layers. The Xception65-extracted feature maps are inputted to an atrous spatial pyramid pooling module to obtain multiscale feature information. This information is then recovered to capture clearer retinal layer boundaries in the encoder-decoder module, thus completing retinal layer auto-segmentation of the retinal optical coherence tomography (OCT) images. Results We validated this method using a retinal OCT image database containing 280 volumes (40 B-scans per volume) to demonstrate its effectiveness. The results showed that the method exhibits excellent performance in terms of the mean intersection over union and sensitivity (Se), which are as high as 90.41 and 92.15%, respectively. The intersection over union and Se values of the nerve fiber layer, ganglion cell layer, inner plexiform layer, inner nuclear layer, outer plexiform layer, outer nuclear layer, outer limiting membrane, photoreceptor inner segment, photoreceptor outer segment, and pigment epithelium layer were found to be above 88%. Conclusions DeepRetina can automate the segmentation of retinal layers and has great potential for the early diagnosis of fundus retinal diseases. In addition, our approach will provide a segmentation model framework for other types of tissues and cells in clinical practice. Translational relevance Automating the segmentation of retinal layers can help effectively diagnose and monitor clinical retinal diseases. In addition, it requires only a small amount of manual segmentation, significantly improving work efficiency.