Chengjuan Ren's research while affiliated with Sichuan International Studies University and other places

Circular RNAs (circRNAs) play a significant role in cancer development and therapy resistance. There is substantial evidence indicating that the expression of circRNAs affects the sensitivity of cells to drugs. Identifying circRNAs-drug sensitivity association (CDA) is helpful for disease treatment and drug discovery. However, the identification of CDA through conventional biological experiments is both time-consuming and costly. Therefore, it is urgent to develop computational methods to predict CDA. In this study, we propose a new computational method, the subgraph-aware graph convolutional network (SAGCN), for predicting CDA. SAGCN first construct a heterogeneous network composed of circRNA similarity network, drug similarity network, and circRNA-drug bipartite network. Then, a subgraph extractor is proposed to learn the latent subgraph structure of the heterogeneous network using a graph convolutional network. The extractor can capture 1-hop and 2-hop information and then a fusing attention mechanism is designed to integrate them adaptively. Simultaneously, a novel subgraph-aware attention mechanism is proposed to detect intrinsic subgraph structure. The final node feature representation is obtained to make the CDA prediction. Experimental results demonstrate that SAGCN obtained an average AUC of 0.9120 and AUPR of 0.8693, exceeding the performance of the most advanced models under 10-fold cross-validation. Case studies have demonstrated the potential of SAGCN in identifying associations between circRNA and drug sensitivity.

Objective: To develop an accurate and automatic segmentation model based on convolution neural network to segment the prostate and its lesion regions. Methods: Of all 180 subjects, 122 healthy individuals and 58 patients with prostate cancer were included. For each subject, all slices of the prostate were comprised in the DWIs. A novel DCNN is proposed to automatically segment the prostate and its lesion regions. This model is inspired by the U-Net model with the encoding-decoding path as the backbone, importing dense block, attention mechanism techniques, and group norm-Atrous Spatial Pyramidal Pooling. Data augmentation was used to avoid overfitting in training. In the experimental phase, the data set was randomly divided into a training (70%), testing set (30%). four-fold cross-validation methods were used to obtain results for each metric. Results: The proposed model achieved in terms of Iou, Dice score, accuracy, sensitivity, 95% Hausdorff Distance, 86.82%,93.90%, 94.11%, 93.8%,7.84 for the prostate, 79.2%, 89.51%, 88.43%,89.31%,8.39 for lesion region in segmentation. Compared to the state-of-the-art models, FCN, U-Net, U-Net++, and ResU-Net, the segmentation model achieved more promising results. Conclusion: The proposed model yielded excellent performance in accurate and automatic segmentation of the prostate and lesion regions, revealing that the novel deep convolutional neural network could be used in clinical disease treatment and diagnosis.

To develop an accurate segmentation model for the prostate and lesion area to help clinicians diagnose diseases, we propose a multi-encoder and decoder segmentation network, denoted Muled-Net, which can concurrently segment the prostate and lesion regions in an image. The model performs parallel calculations for dual input. In two encoder branches of the model, a new transformer encoder is used to overcome the fact that only information from the neighborhood pixels can be captured, increasing the ability to capture global dependencies. Furthermore, given the usually small size of the lesion, ASPP and feature fusion are merged to expand the perceptual field and retain more contextual information of the shallow layer in decoder. To the best of our limited knowledge, there is no public dataset for the segmentation of the prostate and its lesion regions. So we made a publicly usable dataset. Muled-Net is compared with other deep learning methods, FCN, U-Net, U-Net++, and ResU-Net with four-fold cross-validation. Of all 218 subjects, 140 healthy individuals and 78 patients with prostate cancer were included in this work. Average Dice of 95%, Iou of 89%, sensitivity of 94%, 95HD of 9.56, and MSD of 0.66 are achieved for the prostate segmentation and average Dice of 89%, Iou of 82%, sensitivity of 92%, 95HD of 11.16, and MSD of 1.09 for the segmentation of the prostate lesion regions. The performance of the proposed model has made significant improvements to the segmentation of the lesion regions in particular, suggesting that the model could be considered as an auxiliary tool to ease the workload of physicians and help them in making treatment decisions.

Automatic and precise segmentation of the prostate is beneficial to various diagnostic and therapeutic procedures on magnetic resonance imaging. However, the work is very challenging because of the heterogeneity of prostate tissue, the lack of clearly defined boundaries, and the wide variation in prostate shape between individuals. Based on the segmentation scheme for the prostate and its lesion regions, a new deep convolutional neural network is proposed in this research. To acquire excellent segmentation performance with consistency in both appearance and space, CRF-RNN is added on top of the network. By introducing an attention mechanism, the network is made to focus more feature on the prostate zones in both channel and spatial dimensions. In addition, a new dense block is created to stabilize parameter updates and prevent gradients from disappearing as the network deepens. Finally, the model was trained and validated using the real prostate dataset of 180 patients with four cross-validations. The proposed model achieves 95% HD, 86.82%, 93.90%, 94.11%, 93.8%, 7.84% for prostate, 79.2%, 89.51%, 88.43%, 89.31%, 8.39% for lesion area in segmentation in terms of IOU, Dice score, accuracy, and sensitivity. Compared to the state-of-the-art models FCN, U-Net, U-Net++ and ResU-Net, the segmentation model shows more promising results. With an outstanding achievement in automated segmentation of prostate and lesion regions, the presented model highlights the ability of the novel deep convolutional neural network to facilitate clinical disease intervention and management.

In recent years, deep learning has been widely used in the field of coastal waste detection, with excellent results. However, there are difficulties in coastal waste detection such as, for example, detecting small objects and the low performance of the object detection model. To address these issues, we propose the Multi-Strategy Deconvolution Single Shot Multibox Detector (MS-DSSD) based on DSSD. The method combines feature fusion, dense blocks, and focal loss into a state-of-the-art feed-forward network with an end-to-end training style. In the network, we employ feature fusion to import contextual information to boost the accuracy of small object detection. The dense blocks are constructed by a complex function of three concurrent operations, which can yield better feature descriptions. Then, focal loss is applied to address the class imbalance. Due to the lack of coastal waste datasets, data augmentation is designed to increase the amount of data, prevent overfitting of the model, and speed up convergence. Experimental results show that MS-DSSD513 obtains a higher mAP, of 82.2% and 84.1%, compared to the state-of-the-art object detection algorithms on PASCAL VOC2007 and our coastal waste dataset. The proposed new model is shown to be effective for small object detection and can facilitate the automatic detection of coastal waste management.

The increase of motor vehicles year by year has led to a number of parking difficulties and traffic congestion problems. The intelligent parking system can effectively alleviate the parking difficulties and has received wide attention. Geomagnetic sensors are widely used due to their low cost and easy deployment. However, traditional geomagnetic parking detection algorithms cannot cope with complex parking behaviors and have low vehicle detection performance. Therefore, in this paper, a new parking guidance system is proposed by integrating related technologies such as ZigBee, geomagnetic sensor, and RNN. With our limited knowledge, in the research branch of the parking guidance system, RNN is applied to geomagnetic vehicle detection for the first time to detect the status of parking spaces and obtain more accurate identification results of geomagnetic signals. The training data is obtained from real scenarios. It is experimentally demonstrated that our method receives 96.6% accuracy in the detection of vehicle status, which is 9% higher than the state-of-the-art method. Finally, a robust parking guidance system gets 97% accuracy.

Predicting drug-target interactions (DTIs) is a convenient strategy for drug discovery. Although various computational methods have been put forward in recent years, DTIs prediction is still a challenging task. In this paper, based on indirect prior information (we term them as mediators), we proposed a new model, called Bridging-BPs (bridging paths), for DTIs prediction. Specifically, we regarded linkage process between mediators and DTs (drugs and proteins) as 'bridging' and source (drug)-mediators-destination (protein) as bridging paths. By integrating various bridging paths, we constructed a bridging heterogeneous graph for DTIs. After that, an improved graph-embedding algorithm-BPs2vec-was designed to capture deep topological features underlying the bridging graph, thereby obtaining the low-dimensional node vector representations. Then, the vector representations were fed into a Random Forest classifier to train and score the probability, outputting the final classification results for potential DTIs. Under 5-fold cross validation, our method obtained AUPR of 88.97% and AUC of 88.63%, suggesting that Bridging-BPs could effectively mine the link relationships hidden in indirect prior information and it significantly improved the accuracy and robustness of DTIs prediction without direct prior information. Finally, we confirmed the practical prediction ability of Bridging-BPs by case studies.

Coastal waste not only has a seriously destructive effect on human life and marine ecosystems, but it also poses a long-term economic and environmental threat. To solve the issues of a poor manual coastal waste sorting environment, such as low sorting efficiency and heavy tasks, we develop a novel deep convolutional neural network by combining several strategies to realize intelligent waste recognition and classification based on the state-of-the-art Faster R-CNN framework. Firstly, to effectively detect small objects, we consider multiple-scale fusion to get rich semantic information from the shallower feature map. Secondly, RoI Align is introduced to solve positioning deviation caused by the regions of interest pooling. Moreover, it is necessary to correct key parameters and take on data augmentation to improve model performance. Besides, we create a new waste object dataset, named IST-Waste, which is made publicly to facilitate future research in this field. As a consequence, the experiment shows that the algorithm’s mAP reaches 83%. Detection performance is significantly better than Faster R-CNN and SSD. Thus, the developed scheme achieves higher accuracy and better performance against the state-of-the-art alternative.