Application of Multiobjective Optimization Techniques in Biomedical Image Segmentation—A Study

Image segmentation is the first step in image analysis and pattern recognition, and it is one of the most difficult tasks in image processing, and determines the quality of the final result of analysis. Image segmentation requires the improvement because most image segmentation solution is problem based. Biomedical image segmentation is different than normal image segmentation. Because normal image is taken from camera which is free of noise. While biomedical image is taken from MRI, CT, Microscopic Instrument or X-ray which is it noisy and fuzzy. Medical image segmentation methods generally have restrictions because medical images have very similar gray level and texture among the interested. While extracting region of interest in biomedical image, region of interest can avoid the processing of irrelevant image point. Biomedical Image segmentation is necessary when we want the computer to make decision, surgical planning and robotically assisted surgical invention. Biomedical image segmentation is nothing but the classification of similar pixel and their following extraction into separate segment. There are different methods to do the Biomedical image segmentation but they are slow. he method which is described in this paper is fast and efficient. This paper gives comparative research of different method of each of category. The method described in the paper is for fast biomedical image segmentation

Biomedical images have complex tissue structures, and there are great differences between images of the same part of different individuals. Although deep learning methods have made some progress in automatic segmentation of biomedical images, the segmentation accuracy is relatively low for biomedical images with significant changes in segmentation targets, and there are also problems of missegmentation and missed segmentation. To address these challenges, we proposed a biomedical image segmentation method based on dense atrous convolution. First, we added a dense atrous convolution module (DAC) between the encoding and decoding paths of the U-Net network. This module was based on the inception structure and atrous convolution design, which can effectively capture multi-scale features of images. Second, we introduced a dense residual pooling module to detect multi-scale features in images by connecting residual pooling blocks of different sizes. Finally, in the decoding part of the network, we adopted an attention mechanism to suppress background interference by enhancing the weight of the target area. These modules work together to improve the accuracy and robustness of biomedical image segmentation. The experimental results showed that compared to mainstream segmentation networks, our segmentation model exhibited stronger segmentation ability when processing biomedical images with multiple-shaped targets. At the same time, this model can significantly reduce the phenomenon of missed segmentation and missegmentation, improve segmentation accuracy, and make the segmentation results closer to the real situation.

<div class="section abstract"><div class="htmlview paragraph">This paper presents a novel approach to augment existing engine calibrations to deliver improved engine performance during a transient, through the application of multi-objective optimization techniques to the calibration of the Variable Valve Timing (VVT) system of a 1.0 litre gasoline engine. Current mature calibration approaches for the VVT system are predominantly based on steady state techniques which fail to consider the engine dynamic behaviour in real world driving, which is heavily transient.</div><div class="htmlview paragraph">In this study the total integrated fuel consumption and engine-out NO<sub>x</sub> emissions over a 2-minute segment of the transient Worldwide Light-duty Test Cycle are minimised in a constrained multi-objective optimisation framework to achieve an updated calibration for the VVT control. The cycle segment was identified as an area with high NOx emissions. The optimisation framework was developed around a Mean Value Engine Model (MVEM) with representative engine controls which was validated against an engine tested on a dynamometer. The aim of this study was to demonstrate a practical benefit without having to significantly change the existing engine control strategy. Offline optimization with the MVEM model allows exploitation of workstation computational performance to effectively explore the calibration space, reducing both time and investment in engine testing.</div><div class="htmlview paragraph">The initial simulation optimization results show a strong dominance of both fuel and NOx objectives with a potential reduction in fuel consumption and engine out NO<sub>X</sub> emissions of up to 5% and 18% respectively compared to the original steady-state based VVT calibration. Engine experimental results have confirmed that NO<sub>X</sub> emissions can be significantly reduced without any significant detriment to fuel economy over this 2min transient.</div></div>

As the world is progressing towards faster and more efficient computing techniques, cloud computing has emerged as an efficient and cheaper solution to such increasing and demanding requirements. Cloud computing is a computing model which facilitates not only the end-users but also organizational and other enterprise users with high availability of resources on demand basis. This involves the use of scientific workflows that require large amount of data processing, which can be costly and time-consuming if not properly scheduled in cloud environment. Various scheduling strategies have been developed, which include swarm-based optimization approaches as well. Due to the presence of multiple and conflicting requirements of users, multi-objective optimization techniques have become popular for workflow scheduling. This paper deals with cat swarm-based multi-objective optimization approach to schedule workflows in a cloud computing environment. The objectives considered are minimization of cost, makespan and CPU idle time. Proposed technique gives improved performance, compared with multi-objective particle swarm optimization (MOPSO) technique.

A Stacked Generalization U-shape network based on zoom strategy and its application in biomedical image segmentation

With the wide applications of biomedical images in the medical field, the segmentation of biomedical images plays an important role in clinical diagnosis, pathological analysis, and medical intervention. Full convolutional neural networks, especially U‐net, have improved the performance of segmentation greatly in recent years. However, due to their regular geometric structure, the standard convolutions that they use are inherently limited in dealing with geometric transformations while biomedical objects have huge variations in shape and size. In this study, the authors propose the DRU‐net, which is a novel U‐net with deformable encoder and reshaping upsampling convolution decoder, for biomedical image segmentation. First, deformable convolutional networks are applied and improved to enhance the learning ability of the encoder for geometric transformations. Second, a novel upsampling method named reshape upsampling convolution is proposed for better‐restoring resolution and fusion features. Furthermore, focal loss is used to address class imbalance and model overwhelmed problems in biomedical image segmentation tasks. Theoretic analysis and experimental results have shown that the proposed algorithm not only reduces the number of parameters of U‐Net, but also achieves produces competitive results compared with the state‐of‐the‐art algorithms in terms of various quantitative measures on Drosophila electron microscopy dataset and Warwick‐QU dataset.

A lecturer assistant is expected to be professional when dealing with the score or decision. Being professional, the lecturer assistant will be constantly respected by the students. The lecturer assistant should be able to make use of the time to keep the disciplinary. Selecting and determining the lecturer assistant at Computer Science of Unika St. Thomas Medan are conducted by the phases of selecting and taking value of the test score, the semester of lecturer assistant candidate, the number of classes to be assisted, cumulative grade point achievement, and the score of the assisted course. The Method of Multi-Objective Optimization on the Basis of Ratio Analysis (MOORA) is in the part of Decision Support System introduced by Brauers dan Zavadkas. This method is the multi-objective optimization technique which is successfully applied to solve the various complicated decision-making and well-used in terms of lecturer assistant selection due to its simple calculation and easiness to understand.

With the rapid growth of medical and biomedical image data, energy-efficient solutions for analyzing such image data that can be processed fast and accurately on platforms with low power budget are highly desirable. This paper uses segmenting glial cells in brain microscopy images as a case study to demonstrate how to achieve biomedical image segmentation with significant energy saving and minimal comprise in accuracy. Specifically, we design, train, implement, and evaluate Fully Convolutional Networks (FCNs) for biomedical image segmentation on IBM's neurosynaptic DNN processor - TrueNorth (TN). Comparisons in terms of accuracy and energy dissipation of TN with that of a low power NVIDIA TX2 mobile GPU platform have been conducted. Experimental results show that TN can offer at least two orders of magnitude improvement in energy efficiency when compared to TX2 GPU for the same workload.

In the last years, it has become very popular as well as significant to diagnose patients as less invasively as only it is possible. This becomes extremely important mainly when diagnosing adolescent patients or even babies. This paper describes the possibilities of medical diagnostics from a different point of view which is the evaluation of microscopic biomedical images of patient's body instead of examining him directly, i.e., invasively. The subject of research is human respiratory system and its diseases which are often caused or closely connected with proper function of small microscopic structures which should serve to clean one's airways. Such structures are called cilia of respiratory epithelium and can be found within nose, trachea or bronchi. The old way of diagnostic of a patient who is suspected to suffer from a disease called Primary ciliary dyskinesia (PCD), as he often undergoes serious inflammations and other breathing complications, comprises several repeated bronchoscopies which cut a small pieces of epithelium from selected parts of respiratory apparatus that are consequently observed using microscope. This is very uncomfortable and many times very hard to perform as the most affected group of patients are children under the age of three. Moreover, evaluation of microscopic samples is often imprecise because doctors assess it subjectively and the proper frequency of ciliary movement is only estimated and classified “slow” or “quick enough”, without accurate value. This paper proposes automated, much faster and much more exact ways of frequency measurements of ciliary movement based on processing and segmentation of biomedical microscopic images, which means more precise evaluation of patient's ciliary health status without such invasiveness as it is used during older methods of examination.

Recently, the introduction of Convolutional Neural Network (CNNs) has advanced the way of solving image segmentation tasks. Semantic image segmentation has considerably benefited from employing various CNN models. The most widely used network in this field is U-Net and its different variations. However, these models require significant number of trainable parameters, floating-point operations per second, and great computational power to be trained. These factors make real-time semantic segmentation in low powered devices very hard. Therefore, in the present paper, we aim to modify particular aspects of the U-Net model to improve its performance through developing a fast U-Net (FU-Net) relying on bottleneck convolution layers in the contraction and expansion paths of the model. The proposed model can be utilized in semantic segmentation applications even on the devices with limited computational power and memory by ensuring the state-of-the-art performance. The amount of memory required by the proposed model is reduced by 23 times when compared with the original U-Net. Moreover, the modifications allowed achieving better performance. In conducted experiments, we assessed the performance of the proposed model on two biomedical image segmentation datasets, namely 2018 Data Science Bowl and ICIS 2018: Skin Lesion Analysis Towards Melanoma Detection. FU-Net demonstrated the state-of-the-art results in biomedical image segmentation, requiring the number of trainable parameters reduced by eight times compared with the original U-Net model. In addition, using bottleneck layers decreased the number of computations, resulting in nearly 30% speed-up at the training, validation and test stages. Furthermore, despite relying on fewer parameters FU-Net achieved a slight improvement of the performance in terms of pixel accuracy, Jaccard index, and dice coefficient evaluation metrics.

In practical engineering optimization problems (such as risk assessments), the parameters of the objective functions can be intervals because of noise and uncertainty; however, such problems cannot be solved by traditional multiobjective optimization methods. Yet, very little study has addressed interval multiobjective optimization methods compared to traditional multiobjective optimization methods. Therefore, a novel interval multiobjective optimization method called the Interval Cooperative Multiobjective Artificial Bee Colony Algorithm (ICMOABC) based on multiple populations for multiple objectives and interval credibility is proposed. Interval credibility is selected as the interval dominant method. Interval credibility is easy to combine with multiobjective optimization methods because it can describe the mean and width of intervals without increasing the dimension of the objective functions. The proposed algorithm has M single-objective optimization subpopulations updated by artificial bee colony algorithm, meaning it uses evolutionary resources more efficiently. In order to bring in diversity, the elitist learning strategy is used in the archive. The results of ICMOABC on various benchmark problems sets with different characteristics demonstrate its superior performance compared to some state-of-the-art algorithms.

Methodology for the design of industrial hydrogen networks and the optimal placement of purification units using multi-objective optimisation techniques

Many biomedical image analysis applications require segmentation. Convolutional neural networks (CNN) have become a promising approach to segment biomedical images; however, the accuracy of these methods is highly dependent on the training data. We focus on biomedical image segmentation in the context where there is variation between source and target datasets and ground truth for the target dataset is very limited or non-existent. We use an adversarial based training approach to train CNNs to achieve good accuracy on the target domain. We use the DRIVE and STARE eye vasculture segmentation datasets and show that our approach can significantly improve results where we only use labels of one domain in training and test on the other domain. We also show improvements on membrane detection between MIC-CAI 2016 CREMI challenge and ISBI2013 EM segmentation challenge datasets.

Segmentation of patchy areas in biomedical images based on local edge density estimation

Multi-objective optimization for GPU3 Stirling engine by combining multi-objective algorithms