Weighted Ensemble of Deep Learning Models based on Comprehensive Learning Particle Swarm Optimization for Medical Image Segmentation

Dang, Truong; Nguyen, Tien Thanh; Moreno‐García, Carlos Francisco; Elyan, Eyad; McCall, John

doi:10.1109/cec45853.2021.9504929

Cited by 16 publications

(11 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A DL-based framework was proposed by Luo et al [99] to segment the chambers of the heart from magnetic resonance images. More specifically for pulmonary hypertension detection, in a recent study by Dang et al [100] authors implemented a weighted ensemble of DL methods based on comprehensive learning particle swarm optimisation (CLPSO). To this end, they trained a total of six transfer learning models for segmentation, and these were then assembled to get the best possible output.…”

Section: Segmentationmentioning

confidence: 99%

Computer vision and machine learning for medical image analysis: recent advances, challenges, and way forward

Elyan¹,

Vuttipittayamongkol²,

Johnston³

et al. 2022

Art Int Surg

Self Cite

View full text Add to dashboard Cite

The recent development in the areas of deep learning and deep convolutional neural networks has significantly progressed and advanced the field of computer vision (CV) and image analysis and understanding. Complex tasks such as classifying and segmenting medical images and localising and recognising objects of interest have become much less challenging. This progress has the potential of accelerating research and deployment of multitudes of medical applications that utilise CV. However, in reality, there are limited practical examples being physically deployed into front-line health facilities. In this paper, we examine the current state of the art in CV as applied to the medical domain. We discuss the main challenges in CV and intelligent data-driven medical applications and suggest future directions to accelerate research, development, and deployment of CV applications in health practices. First, we critically review existing literature in the CV domain that addresses complex vision tasks, including: medical image classification; shape and object recognition from images; and medical segmentation. Second, we present an in-depth discussion of the various challenges that are considered barriers to accelerating research, development, and deployment of intelligent CV methods in real-life medical applications and hospitals. Finally, we conclude by discussing future directions.

show abstract

Section: Segmentationmentioning

confidence: 99%

Computer vision and machine learning for medical image analysis: recent advances, challenges, and way forward

Elyan¹,

Vuttipittayamongkol²,

Johnston³

et al. 2022

Art Int Surg

Self Cite

View full text Add to dashboard Cite

show abstract

“…In [32], the authors used a number of CNN models to extract the histology image features at different scales, then the optimal subset of CNN models was selected to create the ensemble. Anonymous et al proposed a weighted ensemble of deep learning-based segmentation algorithms for cardiographic segmentation and achieved good results on the CAMUS competition [3]. Besides, there are some novel ensemble generation approaches inspired by the success of deep neural networks.…”

Section: B Ensemble Learningmentioning

confidence: 99%

“…The parameters n 1 and n 2 were set to 100 and 3 respectively. The proposed method were compared with the 9 base segmentation models and three additional benchmarks, weighted ensemble [3], Decision Template [18] (denoted by DT) and the optimal Decision Template found via PSO method without using surrogate model (denoted by ODTwS).…”

Section: A Experimental Settingsmentioning

confidence: 99%

Ensemble of deep learning models with surrogate-based optimization for medical image segmentation

Dang

Luong

Liew

et al. 2022

2022 IEEE Congress on Evolutionary Computation (CEC)

Self Cite

View full text Add to dashboard Cite

Deep Neural Networks (DNNs) have created a breakthrough in medical image analysis in recent years. Because clinical applications of automated medical analysis are required to be reliable, robust and accurate, it is necessary to devise effective DNNs based models for medical applications. In this paper, we propose an ensemble framework of DNNs for the problem of medical image segmentation with a note that combining multiple models can obtain better results compared to each constituent one. We introduce an effective combining strategy for individual segmentation models based on swarm intelligence, which is a family of optimization algorithms inspired by biological processes. The problem of expensive computational time of the optimizer during the objective function evaluation is relieved by using a surrogate-based method. We train a surrogate on the objective function information of some populations and then use it to predict the objective values of each candidate in the subsequent populations. Experiments run on a number of public datasets indicate that our framework achieves competitive results within reasonable computation time.

show abstract

“…Another notable work is [26] in which the authors proposed attention UNet for pancreas segmentation, achieving 2-3% higher Dice scores compared to other benchmarks. [9] proposed a weighted ensemble of deep learning-based segmentation models in which weighted summation is used to combine the predictions of each segmentation model. The authors used the weights found by solving an optimisation problem using CLPSO for the summation.…”

Section: Background and Related Work A Medical Image Segmentationmentioning

confidence: 99%

“…The 5-fold cross-validation was used in the experiments and was run using GPU. For the CLPSO algorithm, the iteration was set to 500 and the number of candidates nP op was set to 10 based on [9]. Two performance metrics were used for the evaluation of the segmentation models and the proposed ensemble: Dice coefficient and Hausdorff distance.…”

Section: Experimental Studies a Datasets And Performance Metricsmentioning

confidence: 99%

Ensemble Learning based on Classifier Prediction Confidence and Comprehensive Learning Particle Swarm Optimisation for Medical Image Segmentation

Dang

Nguyen

McCall

et al. 2022

2022 IEEE Symposium Series on Computational Intelligence (SSCI)

Self Cite

View full text Add to dashboard Cite

LVSegmentation, a process of partitioning an image into multiple segments to locate objects and boundaries, is considered one of the most essential medical imaging process. In recent years, Deep Neural Networks (DNN) have achieved many notable successes in medical image analysis, including image segmentation. Due to the fact that medical imaging applications require robust, reliable results, it is necessary to devise effective DNN models for medical applications. One solution is to combine multiple DNN models in an ensemble system to obtain better results than using each single DNN model. Ensemble learning is a popular machine learning technique in which multiple models are combined to improve the final results and has been widely used in medical image analysis. In this paper, we propose to measure the confidence in the prediction of each model in the ensemble system and then use an associate threshold to determine whether the confidence is acceptable or not. A segmentation model is selected based on the comparison between the confidence and its associated threshold. The optimal threshold for each segmentation model is found by using Comprehensive Learning Particle Swarm Optimisation (CLPSO), a swarm intelligence algorithm. The Dice coefficient, a popular performance metric for image segmentation, is used as the fitness criteria. The experimental results on three medical image segmentation datasets confirm that our ensemble achieves better results compared to some wellknown segmentation models.

show abstract

Weighted Ensemble of Deep Learning Models based on Comprehensive Learning Particle Swarm Optimization for Medical Image Segmentation

Cited by 16 publications

References 43 publications

Computer vision and machine learning for medical image analysis: recent advances, challenges, and way forward

Computer vision and machine learning for medical image analysis: recent advances, challenges, and way forward

Ensemble of deep learning models with surrogate-based optimization for medical image segmentation

Ensemble Learning based on Classifier Prediction Confidence and Comprehensive Learning Particle Swarm Optimisation for Medical Image Segmentation

Contact Info

Product

Resources

About