Deep Evolutionary Networks with Expedited Genetic Algorithms for Medical Image Denoising

A review of AutoML optimization techniques for medical image applications

Automatic analysis of medical images using machine learning techniques has gained significant importance over the years. A large number of approaches have been proposed for solving different medical image analysis tasks using machine learning and deep learning approaches. These approaches are quite effective thanks to their ability to analyze large volume of medical imaging data. Moreover, they can also identify patterns that may be difficult for human experts to detect. Manually designing and tuning the parameters of these algorithms is a challenging and time-consuming task. Furthermore, designing a generalized model that can handle different imaging modalities is difficult, as each modality has specific characteristics. To solve these problems and automate the whole pipeline of different medical image analysis tasks, numerous Automatic Machine Learning (AutoML) techniques have been proposed. These techniques include Hyper-parameter Optimization (HPO), Neural Architecture Search (NAS), and Automatic Data Augmentation (ADA). This study provides an overview of several AutoML-based approaches for different medical imaging tasks in terms of optimization search strategies. The usage of optimization techniques (evolutionary, gradient-based, Bayesian optimization, etc.) is of significant importance for these AutoML approaches. We comprehensively reviewed existing AutoML approaches, categorized them, and performed a detailed analysis of different proposed approaches. Furthermore, current challenges and possible future research directions are also discussed.

Multi-degradation-adaptation network for fundus image enhancement with degradation representation learning

Fundus image quality serves a crucial asset for medical diagnosis and applications. However, such images often suffer degradation during image acquisition where multiple types of degradation can occur in each image. Although recent deep learning based methods have shown promising results in image enhancement, they tend to focus on restoring one aspect of degradation and lack generalisability to multiple modes of degradation. We propose an adaptive image enhancement network that can simultaneously handle a mixture of different degradations. The main contribution of this work is to introduce our Multi-Degradation-Adaptive module which dynamically generates filters for different types of degradation. Moreover, we explore degradation representation learning and propose the degradation representation network and Multi-Degradation-Adaptive discriminator for our accompanying image enhancement network. Experimental results demonstrate that our method outperforms several existing state-of-the-art methods in fundus image enhancement. Code will be available at https://github.com/RuoyuGuo/MDA-Net.

Medical Image Segmentation Using Automatic Optimized U-Net Architecture Based on Genetic Algorithm

Image segmentation is a crucial aspect of clinical decision making in medicine, and as such, it has greatly enhanced the sustainability of medical care. Consequently, biomedical image segmentation has become a prominent research area in the field of computer vision. With the advent of deep learning, many manual design-based methods have been proposed and have shown promising results in achieving state-of-the-art performance in biomedical image segmentation. However, these methods often require significant expert knowledge and have an enormous number of parameters, necessitating substantial computational resources. Thus, this paper proposes a new approach called GA-UNet, which employs genetic algorithms to automatically design a U-shape convolution neural network with good performance while minimizing the complexity of its architecture-based parameters, thereby addressing the above challenges. The proposed GA-UNet is evaluated on three datasets: lung image segmentation, cell nuclei segmentation in microscope images (DSB 2018), and liver image segmentation. Interestingly, our experimental results demonstrate that the proposed method achieves competitive performance with a smaller architecture and fewer parameters than the original U-Net model. It achieves an accuracy of 98.78% for lung image segmentation, 95.96% for cell nuclei segmentation in microscope images (DSB 2018), and 98.58% for liver image segmentation by using merely 0.24%, 0.48%, and 0.67% of the number of parameters in the original U-Net architecture for the lung image segmentation dataset, the DSB 2018 dataset, and the liver image segmentation dataset, respectively. This reduction in complexity makes our proposed approach, GA-UNet, a more viable option for deployment in resource-limited environments or real-world implementations that demand more efficient and faster inference times.

A Survey on Evolutionary Neural Architecture Search

Deep neural networks (DNNs) have achieved great success in many applications. The architectures of DNNs play a crucial role in their performance, which is usually manually designed with rich expertise. However, such a design process is labor-intensive because of the trial-and-error process and also not easy to realize due to the rare expertise in practice. Neural architecture search (NAS) is a type of technology that can design the architectures automatically. Among different methods to realize NAS, the evolutionary computation (EC) methods have recently gained much attention and success. Unfortunately, there has not yet been a comprehensive summary of the EC-based NAS algorithms. This article reviews over 200 articles of most recent EC-based NAS methods in light of the core components, to systematically discuss their design principles and justifications on the design. Furthermore, current challenges and issues are also discussed to identify future research in this emerging field.

A novel dictionary learning-based approach for Ultrasound Elastography denoising

Ultrasound Elastography is a late-model Ultrasound imaging technique mainly used to diagnose tumors and diffusion diseases that can't be detected by traditional Ultrasound imaging. However, artifact noise, speckle noise, low contrast and low signal-to-noise ratio in images make disease diagnosing a challenging task. Medical images denoising, as the first step in the follow-up processing of medical images, has been concerned by many people. With the widespread use of deep learning technique in the research field, dictionary learning method are once again receiving attention. Dictionary learning, as a traditional machine learning method, requires less sample size, has high training efficiency, and can describe images well. In this work, we present a novel strategy based on K-clustering with singular value decomposition (K-SVD) and principal component analysis (PCA) to reduce noise in Ultrasound Elastography images. At this stage of dictionary training, we implement a PCA method to transform the way dictionary atoms are updated in K-SVD. Finally, we reconstructed the image based on the dictionary atoms and sparse coefficients to obtain the denoised image. We applied the presented method on datasets of clinical Ultrasound Elastography images of lung cancer from Nanjing First Hospital, and compared the results of the presented method and the original method. The experimental results of subjective and objective evaluation demonstrated that presented approach reached a satisfactory denoising effect and this research provides a new technical reference for computer aided diagnosis.

Genetic U-Net: Automatically Designed Deep Networks for Retinal Vessel Segmentation Using a Genetic Algorithm

Recently, many methods based on hand-designed convolutional neural networks (CNNs) have achieved promising results in automatic retinal vessel segmentation. However, these CNNs remain constrained in capturing retinal vessels in complex fundus images. To improve their segmentation performance, these CNNs tend to have many parameters, which may lead to overfitting and high computational complexity. Moreover, the manual design of competitive CNNs is time-consuming and requires extensive empirical knowledge. Herein, a novel automated design method, called Genetic U-Net, is proposed to generate a U-shaped CNN that can achieve better retinal vessel segmentation but with fewer architecture-based parameters, thereby addressing the above issues. First, we devised a condensed but flexible search space based on a U-shaped encoder-decoder. Then, we used an improved genetic algorithm to identify better-performing architectures in the search space and investigated the possibility of finding a superior network architecture with fewer parameters. The experimental results show that the architecture obtained using the proposed method offered a superior performance with less than 1% of the number of the original U-Net parameters in particular and with significantly fewer parameters than other state-of-the-art models. Furthermore, through in-depth investigation of the experimental results, several effective operations and patterns of networks to generate superior retinal vessel segmentations were identified. The codes of this work are available at https://github.com/96jhwei/Genetic-U-Net.

QSAR and deep learning model for virtual screening of potential inhibitors against Inosine 5' Monophosphate dehydrogenase (IMPDH) of Cryptosporidium parvum

Cryptosporidium parvum (Cp) causes a gastro-intestinal disease called Cryptosporidiosis. C. parvum Inosine 5' monophosphate dehydrogenase (CpIMPDH) is responsible for the production of guanine nucleotides. In the present study, 37 known urea-based congeneric compounds were used to build a 2D and 3D QSAR model against CpIMPDH. The built models were validated based on OECD principles. A deep learning model was adopted from a framework called Deep Purpose. The model was trained with 288 known active compounds and validated using a test set. From the training set of the 3D QSAR, a pharmacophore model was built and the best pharmacophore hypotheses were scored and sorted using a phase-hypo score. A phytochemical database was screened using both the pharmacophore model and a deep learning model. The screened compounds were considered for glide XP docking, followed by quantum polarized ligand docking. Finally, the best compound among them was considered for molecular dynamics simulation study.

A bioinspired neural architecture search based convolutional neural network for breast cancer detection using histopathology images

The design of neural architecture to address the challenge of detecting abnormalities in histopathology images can leverage the gains made in the field of neural architecture search (NAS). The NAS model consists of a search space, search strategy and evaluation strategy. The approach supports the automation of deep learning (DL) based networks such as convolutional neural networks (CNN). Automating the process of CNN architecture engineering using this approach allows for finding the best performing network for learning classification problems in specific domains and datasets. However, the engineering process of NAS is often limited by the potential solutions in search space and the search strategy. This problem often narrows the possibility of obtaining best performing networks for challenging tasks such as the classification of breast cancer in digital histopathological samples. This study proposes a NAS model with a novel search space initialization algorithm and a new search strategy. We designed a block-based stochastic categorical-to-binary (BSCB) algorithm for generating potential CNN solutions into the search space. Also, we applied and investigated the performance of a new bioinspired optimization algorithm, namely the Ebola optimization search algorithm (EOSA), for the search strategy. The evaluation strategy was achieved through computation of loss function, architectural latency and accuracy. The results obtained using images from the BACH and BreakHis databases showed that our approach obtained best performing architectures with the top-5 of the architectures yielding a significant detection rate. The top-1 CNN architecture demonstrated a state-of-the-art performance of base on classification accuracy. The NAS strategy applied in this study and the resulting candidate architecture provides researchers with the most appropriate or suitable network configuration for using digital histopathology.

Assessing the Impact of Deep Neural Network-Based Image Denoising on Binary Signal Detection Tasks

A variety of deep neural network (DNN)-based image denoising methods have been proposed for use with medical images. Traditional measures of image quality (IQ) have been employed to optimize and evaluate these methods. However, the objective evaluation of IQ for the DNN-based denoising methods remains largely lacking. In this work, we evaluate the performance of DNN-based denoising methods by use of task-based IQ measures. Specifically, binary signal detection tasks under signal-known-exactly (SKE) with background-known-statistically (BKS) conditions are considered. The performance of the ideal observer (IO) and common linear numerical observers are quantified and detection efficiencies are computed to assess the impact of the denoising operation on task performance. The numerical results indicate that, in the cases considered, the application of a denoising network can result in a loss of task-relevant information in the image. The impact of the depth of the denoising networks on task performance is also assessed. The presented results highlight the need for the objective evaluation of IQ for DNN-based denoising technologies and may suggest future avenues for improving their effectiveness in medical imaging applications.

GA-based multi-objective optimization technique for medical image denoising in wavelet domain

Medical images that are acquired with reduced radiation exposure or following the administration of imaging agents with a low dose, are often known to experience problems by the noise stemming from acquisition hardware as well as psychological sources. This noise can adversely affect the quality of diagnosis, but also prevent practitioners from computing quantitative functional information. With a view to overcoming these challenges, the current paper puts forward optimization of multi-objective for denoising medical images within the wavelet domain. This proposed technique entails the use of genetic algorithm (GA) to get the threshold optimized within the denoising framework of wavelets. Two purposes are associated with this technique: First, its ability to adapt with different noise types of noise in the image without requiring prior information about the imaging process per se. In addition, it balances relevant diagnostic details’ preservation against the reduction of noise by considering the optimization of the error factor of Liu and SNR as the foundation of objective function. According to the implementation of this method on magnetic resonance (MR) and ultrasound (US) images of the brain, a better performance has been observed as compared to the existing wavelet-based denoising methods with regard to quantitative and qualitative metrics.

Convolutional neural network with group theory and random selection particle swarm optimizer for enhancing cancer image classification

As an epitome of deep learning, convolutional neural network (CNN) has shown its advantages in solving many real-world problems. Successful CNN applications on medical prognosis and diagnosis have been achieved in recent years. Their common goal is to recognize the insights from the subtle details from medical images by building a suitable CNN model with maximum accuracy and minimum error. The CNN performance is extremely sensitive to the parameter tuning for any given network structure. To approach this concern, a novel self-tuning CNN model is proposed with a significant characteristic of having a metaheuristic-based optimizer. The most optimal set of parameters is often found via our proposed method, namely group theory and random selection-based particle swarm optimization (GTRS-PSO). The insights of symmetric essentials of model structure and parameter correlation are extracted, followed by the hierarchical partitioning of parameter space, and four operators on those partitions are designed for moving neighborhoods and formulating the swarm topology accordingly. The parameters are updated by a random selection strategy at each interval of partitions during the search process. Preliminary experiments over two radiology image datasets: breast cancer and lung cancer, are conducted for a comprehensive comparison of GTRS-PSO versus other optimization algorithms. The results show that CNN with GTRS-PSO optimizer can achieve the best performance for cancer image classifications, especially when there are symmetric components inside the data properties and model structures.

Learning non-local perfusion textures for high-quality computed tomography perfusion imaging

Background. Computed tomography perfusion (CTP) imaging plays a critical role in the acute stroke syndrome assessment due to its widespread availability, speed of image acquisition, and relatively low cost. However, due to its repeated scanning protocol, CTP imaging involves a substantial radiation dose, which might increase potential cancer risks.Methods. In this work, we present a novel deep learning model called non-local perfusion texture learning network (NPTN) for high-quality CTP imaging at low-dose cases. Specifically, considering abundant similarities in the CTP images, i.e. latent self-similarities within the non-local region in the CTP images, we firstly search the most similar pixels from the adjacent frames within a fixed search window to obtain the non-local similarities and to construct non-local textures vector. Then, both the low-dose frame and these non-local textures from adjacent frames are fed into a convolution neural network to predict high-quality CTP images, which can help better characterize the structure details and contrast variants in the targeted CTP image rather than simply utilizing the targeted frame itself. The residual learning strategy and batch normalization are utilized to boost the performance of the convolution neural network. In the experiment, the CTP images of 31 patients with suspected stroke disease are collected to demonstrate the performance of the presented NPTN method.Results. The results show the presented NPTN method obtains superior performance compared with the competing methods. From numerical value, at all dose levels, the presented NPTN method has achieved around 3.0 dB improvement of average PSNR, an increase of around 1.4% of average SSIM, and a decrease of around 4.8% of average RMSE in the low-dose CTP reconstruction task, and also has achieved an increase of around 3.4% of average SSIM and a decrease of around 61.1% of average RMSE in the cerebral blood flow (CBF) estimation task.Conclusions. The presented NPTN method can obtain high-quality CTP images and estimate high-accuracy CBF map by characterizing more structure details and contrast variants in the CTP image and outperform the competing methods at low-dose cases.

Multi-Modal Evolutionary Deep Learning Model for Ovarian Cancer Diagnosis

Ovarian cancer (OC) is a common reason for mortality among women. Deep learning has recently proven better performance in predicting OC stages and subtypes. However, most of the state-of-the-art deep learning models employ single modality data, which may afford low-level performance due to insufficient representation of important OC characteristics. Furthermore, these deep learning models still lack to the optimization of the model construction, which requires high computational cost to train and deploy them. In this work, a hybrid evolutionary deep learning model, using multi-modal data, is proposed. The established multi-modal fusion framework amalgamates gene modality alongside with histopathological image modality. Based on the different states and forms of each modality, we set up deep feature extraction network, respectively. This includes a predictive antlion-optimized long-short-term-memory model to process gene longitudinal data. Another predictive antlion-optimized convolutional neural network model is included to process histopathology images. The topology of each customized feature network is automatically set by the antlion optimization algorithm to make it realize better performance. After that the output from the two improved networks is fused based upon weighted linear aggregation. The deep fused features are finally used to predict OC stage. A number of assessment indicators was used to compare the proposed model to other nine multi-modal fusion models constructed using distinct evolutionary algorithms. This was conducted using a benchmark for OC and two benchmarks for breast and lung cancers. The results reveal that the proposed model is more precise and accurate in diagnosing OC and the other cancers.

Learning Medical Image Denoising with Deep Dynamic Residual Attention Network

Image denoising performs a prominent role in medical image analysis. In many cases, it can drastically accelerate the diagnostic process by enhancing the perceptual quality of noisy image samples. However, despite the extensive practicability of medical image denoising, the existing denoising methods illustrate deficiencies in addressing the diverse range of noise appears in the multidisciplinary medical images. This study alleviates such challenging denoising task by learning residual noise from a substantial extent of data samples. Additionally, the proposed method accelerates the learning process by introducing a novel deep network, where the network architecture exploits the feature correlation known as the attention mechanism and combines it with spatially refine residual features. The experimental results illustrate that the proposed method can outperform the existing works by a substantial margin in both quantitative and qualitative comparisons. Also, the proposed method can handle real-world image noise and can improve the performance of different medical image analysis tasks without producing any visually disturbing artefacts.

Femoral neck fracture detection in X-ray images using deep learning and genetic algorithm approaches

Objectives

This study aims to detect frontal pelvic radiograph femoral neck fracture using deep learning techniques.

Patients and methods

This retrospective study was conducted between January 2013 and January 2018. A total of 234 frontal pelvic X-ray images collected from 65 patients (32 males, 33 females; mean age 74.9 years; range, 33 to 89 years) were augmented to 2106 images to achieve a satisfactory dataset. A total of 1,341 images were fractured femoral necks while 765 were non-fractured ones. The proposed convolutional neural network (CNN) architecture contained five blocks, each containing a convolutional layer, batch normalization layer, rectified linear unit, and maximum pooling layer. After the last block, a dropout layer existed with a probability of 0.5. The last three layers of the architecture were a fully connected layer of two classes, a softmax layer and a classification layer that computes cross entropy loss. The training process was terminated after 50 epochs and an Adam Optimizer was used. Learning rate was dropped by a factor of 0.5 on every five epochs. To reduce overfitting, regularization term was added to the weights of the loss function. The training process was repeated for pixel sizes 50x50, 100x100, 200x200, and 400x400. The genetic algorithm (GA) approach was employed to optimize the hyperparameters of the CNN architecture and to minimize the error after testing the model created by the CNN architecture in the training phase.

Results

Performance in terms of sensitivity, specificity, accuracy, F1 score, and Cohen’s kappa coefficient were evaluated using five- fold cross validation tests. Best performance was obtained when cropped images were rescaled to 50x50 pixels. The kappa metric showed more reliable classifier performance when 50x50 pixels image size was used to feed the CNN. The classifier performance was more reliable according to other image sizes. Sensitivity and specificity rates were computed to be 83% and 73%, respectively. With the inclusion of the GA, this rate increased by 1.6%. The detection rate of fractured bones was found to be 83%. A kappa coefficient of 55% was obtained, indicating an acceptable agreement.

Conclusion

This experimental study utilized deep learning techniques in the detection of bone fractures in radiography. Although the dataset was unbalanced, the results can be considered promising. It was observed that use of smaller image size decreases computational cost and provides better results according to evaluation metrics.

A Novel Hybrid Genetic-Whale Optimization Model for Ontology Learning from Arabic Text

Ontologies are used to model knowledge in several domains of interest, such as the biomedical domain. Conceptualization is the basic task for ontology building. Concepts are identified, and then they are linked through their semantic relationships. Recently, ontologies have constituted a crucial part of modern semantic webs because they can convert a web of documents into a web of things. Although ontology learning generally occupies a large space in computer science, Arabic ontology learning, in particular, is underdeveloped due to the Arabic language’s nature as well as the profundity required in this domain. The previously published research on Arabic ontology learning from text falls into three categories: developing manually hand-crafted rules, using ordinary supervised/unsupervised machine learning algorithms, or a hybrid of these two approaches. The model proposed in this work contributes to Arabic ontology learning in two ways. First, a text mining algorithm is proposed for extracting concepts and their semantic relations from text documents. The algorithm calculates the concept frequency weights using the term frequency weights. Then, it calculates the weights of concept similarity using the information of the ontology structure, involving (1) the concept’s path distance, (2) the concept’s distribution layer, and (3) the mutual parent concept’s distribution layer. Then, feature mapping is performed by assigning the concepts’ similarities to the concept features. Second, a hybrid genetic-whale optimization algorithm was proposed to optimize ontology learning from Arabic text. The operator of the G-WOA is a hybrid operator integrating GA’s mutation, crossover, and selection processes with the WOA’s processes (encircling prey, attacking of bubble-net, and searching for prey) to fulfill the balance between both exploitation and exploration, and to find the solutions that exhibit the highest fitness. For evaluating the performance of the ontology learning approach, extensive comparisons are conducted using different Arabic corpora and bio-inspired optimization algorithms. Furthermore, two publicly available non-Arabic corpora are used to compare the efficiency of the proposed approach with those of other languages. The results reveal that the proposed genetic-whale optimization algorithm outperforms the other compared algorithms across all the Arabic corpora in terms of precision, recall, and F-score measures. Moreover, the proposed approach outperforms the state-of-the-art methods of ontology learning from Arabic and non-Arabic texts in terms of these three measures.