Yang Zhang

Background: Predicting the postoperative visual outcome of pituitary adenoma patients is important but remains challenging. This study aimed to identify a novel prognostic predictor which can be automatically obtained from routine MRI using a deep learning approach. Materials and methods: A total of 220 pituitary adenoma patients were prospectively enrolled and stratified into the recovery and nonrecovery groups according to the visual outcome at 6 months after endoscopic endonasal transsphenoidal surgery. The optic chiasm was manually segmented on preoperative coronal T2WI, and its morphometric parameters were measured, including suprasellar extension distance, chiasmal thickness, and chiasmal volume. Univariate and multivariate analyses were conducted on clinical and morphometric parameters to identify predictors for visual recovery. Additionally, a deep learning model for automated segmentation and volumetric measurement of optic chiasm was developed with nnU-Net architecture and evaluated in a multicenter data set covering 1026 pituitary adenoma patients from four institutions. Results: Larger preoperative chiasmal volume was significantly associated with better visual outcomes (P=0.001). Multivariate logistic regression suggested it could be taken as the independent predictor for visual recovery (odds ratio=2.838, P<0.001). The auto-segmentation model represented good performances and generalizability in internal (Dice=0.813) and three independent external test sets (Dice=0.786, 0.818, and 0.808, respectively). Moreover, the model achieved accurate volumetric evaluation of the optic chiasm with an intraclass correlation coefficient of more than 0.83 in both internal and external test sets. Conclusion: The preoperative volume of the optic chiasm could be utilized as the prognostic predictor for visual recovery of pituitary adenoma patients after surgery. Moreover, the proposed deep learning-based model allowed for automated segmentation and volumetric measurement of the optic chiasm on routine MRI.

Carbon Capture, Utilization, and Storage (CCUS) technology has emerged as the bottom-line technology for achieving carbon neutrality goals in China. The development of Carbon Dioxide Enhanced Oil Recovery (CO₂-EOR) not only increases revenue for high-investment CCUS projects but also enables permanent CO₂storage in the oil reservoir. However, the basin is used as the research object to evaluate the CO₂storage potential of the oil reservoir. The evaluation results are inaccurate and unable to support the implementation of later CCUS projects. Here, more accurate oil reservoir data is employed as the evaluation object. It is the first time at the national level to screen oil reservoirs to distinguish between CO₂miscible and immiscible, and evaluate the potential of CO₂-EOR and CO₂storage in the reservoir. The research results show a total of 2570 suitable oil reservoirs in 4386 candidate oil reservoirs nationwide. About 1.26 billion tons of additional crude oil can be produced by CO₂-EOR technology. This includes approximately 580 million tons of additional oil from CO₂miscible flooding and 680 million tons from CO₂immiscible flooding. The study further refines the CO₂geological utilization data and provides a theoretical basis for CCUS project site selection in China.

For the tumors located in the anterior skull base, germinoma and craniopharyngioma (CP) are unusual types with similar clinical manifestations and imaging features. The difference in treatment strategies and outcomes of patients highlights the importance of making an accurate preoperative diagnosis. This retrospective study enrolled 107 patients diagnosed with germinoma (n = 44) and CP (n = 63). The region of interest (ROI) was drawn independently by two researchers. Radiomic features were extracted from contrast-enhanced T1WI and T2WI sequences. Here, we established the diagnosis models with a combination of three selection methods, as well as three classifiers. After training the models, their performances were evaluated on the independent validation cohort and compared based on the index of the area under the receiver operating characteristic curve (AUC) in the validation cohort. Nine models were established and compared to find the optimal one defined with the highest AUC in the validation cohort. For the models applied in the contrast-enhanced T1WI images, RF_S + RF_C and LASSO + LDA were observed to be the optimal models with AUCs of 0.91. For the models applied in the T2WI images, DC + LDA and LASSO + LDA were observed to be the optimal models with AUCs of 0.88. The evidence of this study indicated that radiomics-based machine learning could be potentially considered as the radiological method in the presurgical differential diagnosis of germinoma and CP with a reliable diagnostic performance.

Preoperative prediction of visual recovery after pituitary adenoma surgery remains a challenge. We aimed to investigate the value of MRI-based radiomics of the optic chiasm in predicting postoperative visual field outcome using machine learning technology. A total of 131 pituitary adenoma patients were retrospectively enrolled and divided into the recovery group (N = 79) and the non-recovery group (N = 52) according to visual field outcome following surgical chiasmal decompression. Radiomic features were extracted from the optic chiasm on preoperative coronal T2-weighted imaging. Least absolute shrinkage and selection operator regression were first used to select optimal features. Then, three machine learning algorithms were employed to develop radiomic models to predict visual recovery, including support vector machine (SVM), random forest and linear discriminant analysis. The prognostic performances of models were evaluated via five-fold cross-validation. The results showed that radiomic models using different machine learning algorithms all achieved area under the curve (AUC) over 0.750. The SVM-based model represented the best predictive performance for visual field recovery, with the highest AUC of 0.824. In conclusion, machine learning-based radiomics of the optic chiasm on routine MR imaging could potentially serve as a novel approach to preoperatively predict visual recovery and allow personalized counseling for individual pituitary adenoma patients.

The purpose of this study was to determine whether a deep-learning-based assessment system could facilitate preoperative grading of meningioma. This was a retrospective study conducted at two institutions covering 643 patients. The system, designed with a cascade network structure, was developed using deep-learning technology for automatic tumor detection, visual assessment, and grading prediction. Specifically, a modified U-Net convolutional neural network was first established to segment tumor images. Subsequently, the segmentations were introduced into rendering algorithms for spatial reconstruction and another DenseNet convolutional neural network for grading prediction. The trained models were integrated as a system, and the robustness was tested based on its performance on an external dataset from the second institution involving different magnetic resonance imaging platforms. The results showed that the segment model represented a noteworthy performance with dice coefficients of 0.920 ± 0.009 in the validation group. With accurate segmented tumor images, the rendering model delicately reconstructed the tumor body and clearly displayed the important intracranial vessels. The DenseNet model also achieved high accuracy with an area under the curve of 0.918 ± 0.006 and accuracy of 0.901 ± 0.039 when classifying tumors into low-grade and high-grade meningiomas. Moreover, the system exhibited good performance on the external validation dataset.

By analyzing the algorithm of Scale Invariant Feature Transition (SIFT), in the process of the experiments, we found, the original image will become serious fuzzy after Gaussian smoothing. At this time, if we do matching directly using the algorithm of SIFT, the matching results will produce many wrong matching points, the number of the feature points successfully matched will be reduced. We found the main reason is that the image is serious blurred by the Gaussian smoothing. In the process of smoothing, the edge points and the pixels whose gray value changed largely are also smoothed, then leading to the number of feature points reduced. Through the analysis of the experiment, we found, if we use the Laplace operator to process the blurred image before matching. This can enhance the characteristics of edge. Then, using SIFT to match image. This method is better than using SIFT directly. The number of feature points is increased significantly. So, this method can improve the probability of a success matching.