ABSTRACT
Lupus nephritis (LN) is one of the most common and serious clinical manifestations of systemic lupus erythe-matosus (SLE), which causes serious damage to the kidneys of patients. To effectively assist the pathological diagnosis of LN, many researchers utilize a scheme combining multi-threshold image segmentation (MIS) with metaheuristic algorithms (MAs) to classify LN. However, traditional MAs-based MIS methods tend to fall into local optima in the segmentation process and find it difficult to obtain the optimal threshold set. Aiming at this problem, this paper proposes an improved water cycle algorithm (SCWCA) and applies it to the MIS method to generate an SCWCA-based MIS method. Besides, this MIS method uses a non-local means 2D histogram to represent the image information and utilizes Renyi's entropy as the fitness function. First, SCWCA adds a sine initialization mechanism (SS) in the initial stage of the original WCA to generate the initial solution to improve the population quality. Second, the covariance matrix adaptation evolution strategy (CMA-ES) is applied in the population location update stage of WCA to mine high-quality population information. To validate the excellent performance of the SCWCA-based MIS method, the comparative experiment between some peers and SCWCA was carried out first. The experimental results show that the solution of SCWCA was closer to the global optimal solution and can effectively deal with the local optimal problems. In addition, the segmentation experiments of the SCWCA-based MIS method and other equivalent methods on LN images showed that the former can obtain higher-quality segmented LN images.
ABSTRACT
COVID-19 has spread rapidly across the world, leading to the insufficiency of medical resources in many regions. Early detection and identification of high-risk COVID-19 patients will contribute to early intervention and optimize medical resource allocation. Using the clinical data from the Affiliated Yueqing Hospital of Wenzhou Medical University (Yueqing, China), an evolutionary support vector machine model is designed to recognize and discriminate the severity of the COVID-19 by patients basic information and hematological indexes. The support vector machine is a frequently used pattern classification tool affected by both the kernel parameter setting and feature selection for its classification accuracy. This study recommends an enhanced Slime Mould Algorithm (ESMA), mixing a new movement strategy of white holes, black holes, and wormholes, to perform parameter optimization and feature selection simultaneously for SVM. Therefore, the proposed SVM framework (ESMA-SVM) can also obtain high-quality classification results, and it is less prone to stagnation in the classification process. To verify the capabilities of the proposed methodology, first, the performance of the ESMA is thoroughly verified by using IEEE CEC2017 benchmark functions and the diversity and compared with other similar methods experimentally using these standard benchmark functions. Moreover, the balance between diversification and intensification capability of the enhanced ESMA and the original SMA is also investigated statistically. Finally, the designed model ESMA-SVM and other competitive SVM models based on other optimization algorithms are applied to early recognition and discrimination of COVID-19 severity. Through the analysis of experimental results, the core compensations of ESMA are confirmed, and the ESMA-SVM can obtain strong performance in terms of several performance evaluation indexes on discrimination of COVID-19 severity. Author