Self-supervised contrastive learning using CT images for PD-1/PD-L1 expression prediction in hepatocellular carcinoma.

Background and purpose: Programmed cell death protein-1 (PD-1) and programmed cell death-ligand-1 (PD-L1) expression status, determined by immunohistochemistry (IHC) of specimens, can discriminate patients with hepatocellular carcinoma (HCC) who can derive the most benefits from immune checkpoint inhibitor (ICI) therapy. A non-invasive method of measuring PD-1/PD-L1 expression is urgently needed for clinical decision support. Materials and methods: We included a cohort of 87 patients with HCC from the West China Hospital and analyzed 3094 CT images to develop and validate our prediction model. We propose a novel deep learning-based predictor, Contrastive Learning Network (CLNet), which is trained with self-supervised contrastive learning to better extract deep representations of computed tomography (CT) images for the prediction of PD-1 and PD-L1 expression. Results: Our results show that CLNet exhibited an AUC of 86.56% for PD-1 expression and an AUC of 83.93% for PD-L1 expression, outperforming other deep learning and machine learning models. Conclusions: We demonstrated that a non-invasive deep learning-based model trained with self-supervised contrastive learning could accurately predict the PD-1 and PD-L1 expression status, and might assist the precision treatment of patients withHCC, in particular the use of immune checkpoint inhibitors.

Novel Computed-Tomography-Based Transformer Models for the Noninvasive Prediction of PD-1 in Pre-Operative Settings.

The expression status of programmed cell death protein 1 (PD-1) in patients with hepatocellular carcinoma (HCC) is associated with the checkpoint blockade treatment responses of PD-1/PD-L1. Thus, accurately and preoperatively identifying the status of PD-1 has great clinical implications for constructing personalized treatment strategies. To investigate the preoperative predictive value of the transformer-based model for identifying the status of PD-1 expression, 93 HCC patients with 75 training cohorts (2859 images) and 18 testing cohorts (670 images) were included. We propose a transformer-based network architecture, ResTransNet, that efficiently employs convolutional neural networks (CNNs) and self-attention mechanisms to automatically acquire a persuasive feature to obtain a prediction score using a nonlinear classifier. The area under the curve, receiver operating characteristic curve, and decision curves were applied to evaluate the prediction model's performance. Then, Kaplan-Meier survival analyses were applied to evaluate the overall survival (OS) and recurrence-free survival (RFS) in PD-1-positive and PD-1-negative patients. The proposed transformer-based model obtained an accuracy of 88.2% with a sensitivity of 88.5%, a specificity of 88.9%, and an area under the curve of 91.1% in the testing cohort.

Reinforcement Learning Based Diagnosis and Prediction for COVID-19 by Optimizing a Mixed Cost Function From CT Images.

A novel coronavirus disease (COVID-19) is a pandemic disease has caused 4 million deaths and more than 200 million infections worldwide (as of August 4, 2021). Rapid and accurate diagnosis of COVID-19 infection is critical to controlling the spread of the epidemic. In order to quickly and efficiently detect COVID-19 and reduce the threat of COVID-19 to human survival, we have firstly proposed a detection framework based on reinforcement learning for COVID-19 diagnosis, which constructs a mixed loss function that can integrate the advantages of multiple loss functions. This paper uses the accuracy of the validation set as the reward value, and obtains the initial model for the next epoch by searching the model corresponding to the maximum reward value in each epoch. We also have proposed a prediction framework that integrates multiple detection frameworks using parameter sharing to predict the progression of patients' disease without additional training. This paper also constructed a higher-quality version of the CT image dataset containing 247 cases screened by professional physicians, and obtained more excellent results on this dataset. Meanwhile, we used the other two COVID-19 datasets as external verifications, and still achieved a high accuracy rate without additional training. Finally, the experimental results show that our classification accuracy can reach 98.31%, and the precision, sensitivity, specificity, and AUC (Area Under Curve) are 98.82%, 97.99%, 98.67%, and 0.989, respectively. The accuracy of external verification can reach 93.34% and 91.05%. What's more, the accuracy of our prediction framework is 91.54%. A large number of experiments demonstrate that our proposed method is effective and robust for COVID-19 detection and prediction.

Asafoetida exerts neuroprotective effect on oxidative stress induced apoptosis through PI3K/Akt/GSK3ß/Nrf2/HO-1 pathway.

BACKGROUND: Alzheimer's Disease (AD) is a serious neurodegenerative disease and there is currently no effective treatment for AD progression. The use of TCM as a potential treatment strategy for AD is an evolving field of investigation. Asafoetida (ASF), an oleo-gum-resin isolated from Ferula assa-foetida root, has been proven to possess antioxidative potential and neuroprotective effects, which is closely associated with the neurological disorders. However, the efficacy and further mechanisms of ASF in AD experimental models are still unclear. METHODS: A cognitive impairment of mouse model induced by scopolamine was established to determine the neuroprotective effects of ASF in vivo, as shown by behavioral tests, biochemical assays, Nissl staining, TUNEL staining, Immunohistochemistry, western blot and qPCR. Furthermore, the PC12 cells stimulated by H2O2 were applied to explore the underlying mechanisms of ASF-mediated efficacy. Then, the UPLCM analysis and integrated network pharmacology approach was utilized to identified the main constitutes of ASF and the potential target of ASF against AD, respectively. And the main identified targets were validated in vitro by western blot, qPCR and immunofluorescence staining. RESULTS: In vivo, ASF treatment significantly ameliorated cognitive impairment induced by scopolamine, as evidenced by improving learning and memory abilities, and reducing neuronal injury, cholinergic system impairment, oxidative stress and apoptosis in the hippocampus of mice. In vitro, our results validated that ASF can dose-dependently attenuated H2O2-induced pathological oxidative stress in PC12 cells by inhibiting ROS and MDA production, as well as promoting the activities of SOD, CAT, GSH. We also found that ASF can significantly suppressed the apoptosis rate of PC12 cells increased by H2O2 exposure, which was confirmed by flow cytometry analysis. Moreover, treatment with ASF obviously attenuated H2O2-induced increase in caspase-3 and Bax expression levels, as well as decrease in Bcl-2 protein expression. KEGG enrichment analysis indicated that the PI3K/Akt/GSK3ß/Nrf2 /HO-1pathway may be involved in the regulation of cognitive impairment by ASF. The results of western blot, qPCR and immunofluorescence staining of vitro assay proved it. CONCLUSIONS: Collectively, our work first uncovered the significant neuroprotective effect of ASF in treating AD in vivo. Then, we processed a series of vitro experiments to clarify the biological mechanism action. These data demonstrate that ASF can inhibit oxidative stress induced neuronal apoptosis to foster the prevention of AD both in vivo and in vitro, and it may exert the function of inhibiting AD through PI3K/Akt/GSK3ß/Nrf2/HO-1pathway.

Deep Learning Using CT Images to Grade Clear Cell Renal Cell Carcinoma: Development and Validation of a Prediction Model.

This retrospective study aimed to develop and validate deep-learning-based models for grading clear cell renal cell carcinoma (ccRCC) patients. A cohort enrolling 706 patients (n = 706) with pathologically verified ccRCC was used in this study. A temporal split was applied to verify our models: the first 83.9% of the cases (years 2010-2017) for development and the last 16.1% (year 2018-2019) for validation (development cohort: n = 592; validation cohort: n = 114). Here, we demonstrated a deep learning(DL) framework initialized by a self-supervised pre-training method, developed with the addition of mixed loss strategy and sample reweighting to identify patients with high grade for ccRCC. Four types of DL networks were developed separately and further combined with different weights for better prediction. The single DL model achieved up to an area under curve (AUC) of 0.864 in the validation cohort, while the ensembled model yielded the best predictive performance with an AUC of 0.882. These findings confirms that our DL approach performs either favorably or comparably in terms of grade assessment of ccRCC with biopsies whilst enjoying the non-invasive and labor-saving property.

Functional dissection of neural circuitry using a genetic reporter for fMRI.

The complex connectivity of the mammalian brain underlies its function, but understanding how interconnected brain regions interact in neural processing remains a formidable challenge. Here we address this problem by introducing a genetic probe that permits selective functional imaging of distributed neural populations defined by viral labeling techniques. The probe is an engineered enzyme that transduces cytosolic calcium dynamics of probe-expressing cells into localized hemodynamic responses that can be specifically visualized by functional magnetic resonance imaging. Using a viral vector that undergoes retrograde transport, we apply the probe to characterize a brain-wide network of presynaptic inputs to the striatum activated in a deep brain stimulation paradigm in rats. The results reveal engagement of surprisingly diverse projection sources and inform an integrated model of striatal function relevant to reward behavior and therapeutic neurostimulation approaches. Our work thus establishes a strategy for mechanistic analysis of multiregional neural systems in the mammalian brain.