Jia Wang

Jia Wang


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 March 2019 in Frontiers in Genetics
Verified
Journal Article
Open access
PDF file
XXXiaolu Xu
Xiaolu Xu
HGHong Gu
Hong Gu
YWYang Wang
Yang Wang
JWJia Wang
Jia Wang
PQPan Qin
Pan Qin
Anticancer drug responses can be varied for individual patients. This difference is mainly caused by genetic reasons, like mutations and RNA expression. Thus, these genetic features are often used to construct classification models to predict the drug response. This research focuses on the feature selection issue for the classification models. Because of the vast dimensions of the feature space for predicting drug response, the autoencoder network was first built, and a subset of inputs with the important contribution was selected. Then by using the Boruta algorithm, a further small set of features was determined for the random forest, which was used to predict drug response. Two datasets, GDSC and CCLE, were used to illustrate the efficiency of the proposed method.

9 November 2020 in PLOS ONE
Verified
Journal Article
Open access
PDF file
HWHongyu Wang
Hongyu Wang
HGHong Gu
Hong Gu
PQPan Qin
Pan Qin
JWJia Wang
Jia Wang
Background: Pneumothorax can lead to a life-threatening emergency. The experienced radiologists can offer precise diagnosis according to the chest radiographs. The localization of the pneumothorax lesions will help to quickly diagnose, which will be benefit for the patients in the underdevelopment areas lack of the experienced radiologists. In recent years, with the development of large neural network architectures and medical imaging datasets, deep learning methods have become a methodology of choice for analyzing medical images. The objective of this study was to the construct convolutional neural networks to localize the pneumothorax lesions in chest radiographs. Methods and findings: We developed a convolutional neural network, called CheXLocNet, for the segmentation of pneumothorax lesions. The SIIM-ACR Pneumothorax Segmentation dataset was used to train and validate CheXLocNets. The training dataset contained 2079 radiographs with the annotated lesion areas. We trained six CheXLocNets with various hyperparameters. Another 300 annotated radiographs were used to select parameters of these CheXLocNets as the validation set. We determined the optimal parameters by the AP50 (average precision at the intersection over union (IoU) equal to 0.50), a segmentation evaluation metric used by several well-known competitions. Then CheXLocNets were evaluated by a test set (1082 normal radiographs and 290 disease radiographs), based on the classification metrics: area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and positive predictive value (PPV); segmentation metrics: IoU and Dice score. For the classification, CheXLocNet with best sensitivity produced an AUC of 0.87, sensitivity of 0.78 (95% CI 0.73-0.83), and specificity of 0.78 (95% CI 0.76-0.81). CheXLocNet with best specificity produced an AUC of 0.79, sensitivity of 0.46 (95% CI 0.40-0.52), and specificity of 0.92 (95% CI 0.90-0.94). For the segmentation, CheXLocNet with best sensitivity produced an IoU of 0.69 and Dice score of 0.72. CheXLocNet with best specificity produced an IoU of 0.77 and Dice score of 0.79. We combined them to form an ensemble CheXLocNet. The ensemble CheXLocNet produced an IoU of 0.81 and Dice score of 0.82. Our CheXLocNet succeeded in automatically detecting pneumothorax lesions, without any human guidance. Conclusions: In this study, we proposed a deep learning network, called, CheXLocNet, for the automatic segmentation of chest radiographs to detect pneumothorax. Our CheXLocNets generated accurate classification results and high-quality segmentation masks for the pneumothorax at the same time. This technology has the potential to improve healthcare delivery and increase access to chest radiograph expertise for the detection of diseases. Furthermore, the segmentation results can offer comprehensive geometric information of lesions, which can benefit monitoring the sequential development of lesions with high accuracy. Thus, CheXLocNets can be further extended to be a reliable clinical decision support tool. Although we used transfer learning in training CheXLocNet, the parameters of CheXLocNet was still large for the radiograph dataset. Further work is necessary to prune CheXLocNet suitable for the radiograph dataset.

25 March 2022 in Frontiers in Oncology
Verified
Journal Article
Open access
YLYujie Li
Yujie Li
HGHong Gu
Hong Gu
HWHongyu Wang
Hongyu Wang
PQPan Qin
Pan Qin
JWJia Wang
Jia Wang
Ultrasound (US) imaging is a main modality for breast disease screening. Automatically detecting the lesions in US images is essential for developing the artificial-intelligence-based diagnostic support technologies. However, the intrinsic characteristics of ultrasound imaging, like speckle noise and acoustic shadow, always degenerate the detection accuracy. In this study, we developed a deep learning model called BUSnet to detect the breast tumor lesions in US images with high accuracy. We first developed a two-stage method including the unsupervised region proposal and bounding-box regression algorithms. Then, we proposed a post-processing method to enhance the detecting accuracy further. The proposed method was used to a benchmark dataset, which includes 487 benign samples and 210 malignant samples. The results proved the effectiveness and accuracy of the proposed method.

1 June 2019 in Redox Biology
Verified
Journal Article
Open access
MWMin Wang
Min Wang
YXYijue Xue
Yijue Xue
LSLanlin Shen
Lanlin Shen
PQPan Qin
Pan Qin
XSXiaolin Sang
Xiaolin Sang
HCHailing Cheng
Hailing Cheng
Cervical cancer has poor prognosis and patients are often diagnosed at advanced stages of the disease with limited treatment options. There is thus an urgent need for the discovery of new therapeutic strategies in cervical cancer. The activation of SGK1 has been linked to the development of various cancer types but little is known about the role of SGK1 in cervical cancer and its potential as a therapeutic target. Here we report that SGK1 is an antioxidative factor that promotes survival of cervical cancer cells. Gene set enrichment analysis of RNA-Seq data reveals a strong inverse association between SGK1 and oxidative phosphorylation. Consistently, inhibition of SGK1 via siRNA or pharmacological inhibitor GSK650394 induces ROS and cytotoxicity upon H2O2 stress. Further analysis of clinical data associates SGK1 with gene expression signatures regulated by the antioxidant transcription factor NRF2 in cervical cancer. Mechanistically, SGK1 activation exerts antioxidant effect through induction of c-JUN-dependent NRF2 expression and activity. Importantly, we find that inhibition of SGK1 confers vulnerability to melatonin as a pro-oxidant, resulting in ROS over-accumulation and consequently enhanced cell cytotoxicity. We further demonstrate that combined use of GSK650394 and melatonin yields substantial regression of cervical tumors in vivo. This work opens new perspectives on the potential of SGK1 inhibitors as sensitizing agents to enable the design of therapeutically redox-modulating strategies against cervical cancer.

10 November 2020 in Frontiers in Genetics
Verified
Journal Article
Open access
PDF file
HGHong Gu
Hong Gu
XXXiaolu Xu
Xiaolu Xu
PQPan Qin
Pan Qin
JWJia Wang
Jia Wang
Identification of driver genes, whose mutations cause the development of tumors, is crucial for the improvement of cancer research and precision medicine. To overcome the problem that the traditional frequency-based methods cannot detect lowly recurrently mutated driver genes, researchers have focused on the functional impact of gene mutations and proposed the function-based methods. However, most of the function-based methods estimate the distribution of the null model through the non-parametric method, which is sensitive to sample size. Besides, such methods could probably lead to underselection or overselection results. In this study, we proposed a method to identify driver genes by using functional impact prediction neural network (FI-net). An artificial neural network as a parametric model was constructed to estimate the functional impact scores for genes, in which multi-omics features were used as the multivariate inputs. Then the estimation of the background distribution and the identification of driver genes were conducted in each cluster obtained by the hierarchical clustering algorithm. We applied FI-net and other 22 state-of-the-art methods to 31 datasets from The Cancer Genome Atlas project. According to the comprehensive evaluation criterion, FI-net was powerful among various datasets and outperformed the other methods in terms of the overlap fraction with Cancer Gene Census and Network of Cancer Genes database, and the consensus in predictions among methods. Furthermore, the results illustrated that FI-net can identify known and potential novel driver genes.

2 June 2022 in Frontiers in Medicine
Verified
Journal Article
Open access
HGHong Gu
Hong Gu
HWHongyu Wang
Hongyu Wang
PQPan Qin
Pan Qin
JWJia Wang
Jia Wang
We consider the problem of weakly supervised segmentation on chest radiographs. The chest radiograph is the most common means of screening and diagnosing thoracic diseases. Weakly supervised deep learning models have gained increasing popularity in medical image segmentation. However, these models are not suitable for the critical characteristics presented in chest radiographs: the global symmetry of chest radiographs and dependencies between lesions and their positions. These models extract global features from the whole image to make the image-level decision. The global symmetry can lead these models to misclassification of symmetrical positions of the lesions. Thoracic diseases often have special disease prone areas in chest radiographs. There is a relationship between the lesions and their positions. In this study, we propose a weakly supervised model, called Chest L-Transformer, to take these characteristics into account. Chest L-Transformer classifies an image based on local features to avoid the misclassification caused by the global symmetry. Moreover, associated with Transformer attention mechanism, Chest L-Transformer models the dependencies between the lesions and their positions and pays more attention to the disease prone areas. Chest L-Transformer is only trained with image-level annotations for lesion segmentation. Thus, Log-Sum-Exp voting and its variant are proposed to unify the pixel-level prediction with the image-level prediction. We demonstrate a significant segmentation performance improvement over the current state-of-the-art while achieving competitive classification performance.