Radiomic features based classifiers and neural networks have shown promising results in tumor classification. The classification performance can be further improved greatly by exploring and incorporating the discriminative features towards cancer into mathematical models. In this research work, we have developed two radiomics driven likelihood models in Computed Tomography(CT) images to classify lung, colon, head and neck cancer. Initially, two diagnostic radiomic signatures were derived by extracting 105 3-D features from 200 lung nodules and by selecting the features with higher average scores from several supervised as well as unsupervised feature ranking algorithms. The signatures obtained from both the ranking approaches were integrated into two mathematical likelihood functions for tumor classification. Validation of the likelihood functions was performed on 265 public data sets of lung, colon, head and neck cancer with high classification rate. The achieved results show robustness of the models and suggest that diagnostic mathematical functions using general tumor phenotype can be successfully developed for cancer diagnosis.
In this paper, a multi-objective optimization method is proposed which is a combination of Genetic algorithm, Differential Evolution and Adaptive Simulated Annealing algorithms. This technique is intended to generalize and improve the robustness of the three population based algorithms. In optimization problems, it is essential to keep the balance between local and global search abilities of algorithms. In the current method, DE, GA and ASA algorithms are linked in the variation stage to enrich the searching behavior and enhance the diversity of the population. The performance of the proposed DE-GA-ASA is tested against benchmark problems for multi-objectives and compared with two widely recognized vector optimizers. Next, the proposed technique is successfully implemented to optimize the design of plate-fin heat exchanger. The effectiveness of the present method is illustrated by comparing with various case studies. Some of the earlier case studies violated the constraints and/or only focused on single objective optimization. Results show that DE-GA-ASA method can be used effectively for the optimal design of plate-fin heat exchanger. Moreover, the effect of variation of fin and heat exchanger parameters on the optimal design is also investigated. Hot, cold and no-flow length of the heat exchanger, fin offset length, fin height and fin length are introduced as the optimization variables to obtain maximum heat transfer rate and minimum total annual cost. The investment cost and operating costs are independently optimized to provide a detailed investigation on the effect of fin and heat exchanger geometry parameters on their variation. Furthermore, a multi-criteria decision making method, TOPSIS is introduced for the selection of final optimal solution from the set of non-dominated solutions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.