Search

Lymph node metastasis examined by the resected lymph nodes is considered one of the most important prognostic factors for colorectal cancer (CRC). However, it requires careful and comprehensive inspection by expert pathologists. To relieve the pathologists' burden and speed up the diagnostic process, in this paper, we develop a deep learning system with the binary positive/negative labels of the lymph nodes to solve the CRC lymph node classification task. The multi-instance learning (MIL) framework is adopted in our method to handle the whole slide images (WSIs) of gigapixels in size at once and get rid of the labor-intensive and time-consuming detailed annotations. First, a transformer-based MIL model, DT-DSMIL, is proposed in this paper based on the deformable transformer backbone and the dual-stream MIL (DSMIL) framework. The local-level image features are extracted and aggregated with the deformable transformer, and the global-level image features are obtained with the DSMIL aggregator. The final classification decision is made based on both the local and the global-level features. After the effectiveness of our proposed DT-DSMIL model is demonstrated by comparing its performance with its predecessors, a diagnostic system is developed to detect, crop, and finally identify the single lymph nodes within the slides based on the DT-DSMIL and the Faster R-CNN model. The developed diagnostic model is trained and tested on a clinically collected CRC lymph node metastasis dataset composed of 843 slides (864 metastasis lymph nodes and 1415 non-metastatic lymph nodes), achieving the accuracy of 95.3% and the area under the receiver operating characteristic curve (AUC) of 0.9762 (95% confidence interval [CI]: 0.9607–0.9891) for the single lymph node classification. As for the lymph nodes with micro-metastasis and macro-metastasis, our diagnostic system achieves the AUC of 0.9816 (95% CI: 0.9659–0.9935) and 0.9902 (95% CI: 0.9787–0.9983), respectively. Moreover, the system shows reliable diagnostic region localizing performance: the model can always identify the most likely metastases, no matter the model's predictions or manual labels, showing great potential in avoiding false negatives and discovering incorrectly labeled slides in actual clinical use. [ABSTRACT FROM AUTHOR]

Electricity demand forecasting plays a crucial role in the operation of electrical power systems because it can provide management decisions related to load switching and power grid. Thus, there have been models developed to estimate the electricity demand. However, inaccurate demand forecasting may raise the operating cost of electric power sector, which means that it would waste considerable money. In this paper, a novel modeling framework was proposed for forecasting electricity demand. Sample entropy was developed to identify the nonlinearity and uncertainty in the original time series, after that redundant noise was removed through a decomposition technique. Besides, the most optimal modes of original series and the optimal input form of the model were determined by the feature selection method. Finally, electricity demand series can be conducted forecasting through least squares support vector machine tuned by multi-objective sine cosine optimization algorithm. The case studies of Australia demonstrated that the proposed framework can ensure high accuracy and strong stability. Thus, it can be considered as a useful tool for electricity demand forecasting. [ABSTRACT FROM AUTHOR]

Nowadays, a great deal of petroleum geology and engineering projects associated with underground fluid injection and production (FIP) are widely conducted around the world. The FIP engineering may cause complex stress perturbation and trigger seismicity, which have been extensively reported and studied. In this paper, we investigated the fault slippage characteristics influenced by FIP. It reveals that for a fault (normal or reverse) that penetrating through the reservoir into the caprock and underburden, the footwall reservoir is the relatively stable one for fluid injection in a fluid FIP engineering. No matter it is a normal or a reverse fault, injecting fluid into footwall reservoir and producing fluid from the hanging wall reservoir can induce smaller fault slippage. After having determined the better fluid injection-production pattern, we studied the influence of three key factors of fault, i.e., dip, offset and depth, on fault stability. We found that, in our range of study, the influence of single action of fault dip, offset or depth on fault slippage in a FIP engineering was small. However, the influence of the combined effects of the factors may be large. Finally, we studied the effect of different pressure management scenarios on fault responses based on the specific fluid injection-production pattern. The results revealed that appropriate pressure management could effectively reduce fault slippage in a FIP engineering. However, inappropriate pressure management may cause much larger fault slippage. Given these concerns, it is therefore vital that the effect of pressure management scenario to be modeled prior to FIP. [ABSTRACT FROM AUTHOR]

Injection or withdrawal of fluid at depth may trigger felt seismicity. At a site with natural faults or artificial fracturing cracks, understanding how to avoid triggering felt earthquakes plays a crucial role in the success of underground anthropogenic activities, such as subsurface energy storage and CO geological sequestration. With the application of a hydromechanical coupling finite element model, we examine the potential of injection-induced pore pressure change and the responding fault slippage along the fault surface in two injection scenarios: multi-layer injection (MLI) and single-layer injection (SLI). The results indicate that fault slippage buildup is mainly located along the portion of the fault intersecting the reservoir. MLI leads to a relatively lower level of induced seismicity compared with SLI. In the fault zone, the external zone and core of the fault exert a connection effect and barrier effect on the hydraulic connectivity, respectively. After 20 years of injection, the pore pressure in the core presents a smaller change than that in the internal and external zones. Furthermore, an uncertainty analysis was performed to evaluate the statistical significance of permeability in the caprock, reservoir, and fault (core, internal zone, and external zone), and only the permeability in the reservoir significantly affects the level of fault slippage based on the fault zone hydromechanics associated with subsurface energy storage and CO geological sequestration. [ABSTRACT FROM AUTHOR]

In view of the probability dilution problem of the existing quantitative indexes of rendezvous trajectory safety performance using collision probability, this paper proposes a new quantitative index of rendezvous trajectory safety performance by well combining collision probability with warning threshold. The proposed new index increases monotonously as the position errors of the chaser spacecraft increase, therefore it can effectively overcome the problems of the reduction in the largest performance value and the advancement in the most dangerous time induced by the probability dilution. The proposed new index is applied to the safety design of close range rendezvous missions. The mission's safety requirements for initial navigation precision and the safe region of initial and final keeping points' positions with a certain navigation precision are analyzed, and several valuable conclusions about the relation between position navigation precision and velocity navigation precision as well as the relation between keeping points' positions and navigation precision are obtained. [ABSTRACT FROM AUTHOR]