Arithmetic Optimization Algorithm with Deep Learning-Based Medical X-Ray Image Classification Model

The current global enhancement algorithm for medical X-ray image has problems of poor de-noising and enhancement effect and low reduction of the enhanced medical X-ray image. To address the problems, a global enhancement algorithm for X-ray image in medical image classification is proposed in this paper. The medical X-ray image is gray scaled, which provides the basis for the further processing of the image. The noise in medical X-ray image is removed by using multi-wavelet transform to improve the enhancement effect of the method. With the curve-let domain the medical X-ray image is enhanced, the reduction degree of medical X-ray image is improved and the global enhancement of the medical X-ray image is completed. Experimental results show that the de-noising effect of the proposed method is effective, the enhanced medical X ray image is better, and the reduction degree of medical X-ray image is high.

The classification of medical images is an important step for image-based clinical decision support systems. With the number of images taken per patient scan rapidly increasing, there is a need for automatic medical image classification systems that are accurate because manual classification and annotation is time-consuming and prone to errors. This paper focuses on automatic classification of X-ray image from the ImageCLEF 2009 dataset based on anatomical and biological information using the InceptionV3 model. The X-ray images are prepared and preprocessed with two different padding techniques, two image enhancement techniques and layering to convert the grey-scale images to 3-channel images to prepare them for InceptionV3. In terms of classification loss, constant padding with no enhancements had the best performance with an accuracy of 68.67% and a loss of 1.442. In terms of classification accuracy, constant padding with enhancement had the best performance with an accuracy of 71.34% and a loss of 1.608.

The study aim at classifying medical X-ray images into their respective categories with the employment of deep learning which is a machine learning technique. The motivation behind this study is to improve the classification accuracy of medical X-ray images in large databases at various hospitals and research centers. Previously the usage of various handcrafted techniques have been employed to classify the images. The handcrafted techniques have not been very effective because of their limitations in image feature extraction process. This study explored the employment of deep learning technique to alleviate the problem associated with handcrafted techniques in medical X -ray image automatic classification task. The end result of this study is to propose a more efficient and effective technique for medical X-ray image retrieval which will be of tremendous benefit in medical diagnosis, education and for research purposes.

Medical image classification is an important step in the effective and accurate retrieval of medical images from large digital database where they are stored. This paper examines the effectiveness of using domain transferred neural networks (DCNNs) for classification of medical X-ray images. We employed two different convolutional neural network (CNN) architectures. VGGNet-16 and AlexNet pre-trained on ImageNet, a non- medical image database consisting of over 1.2 million scenery images were used for the classification task. The pre-trained networks served both as feature extractors and as fine-tuned networks. The extracted feature vector was used to train a linear support vector machine (SVM) to generate a model for the classification task. The fine-tuning process was done by replacing and retraining the last fully connected layers through backward propagation. Our method was evaluated on ImageCLEF2007 medical database. The database consist of 11,000 medical X-ray images (training dataset) and 1,000 images (testing dataset) classified into 116 categories. We compared the performance of the two networks both as feature generators and as fine-tuned networks on our dataset. The overall classification accuracy across all the 116 image classes shows that VGGNet-16 + SVM produced 79.6% and 85.77% as fine-tuned network. AlexNet + SVM produced a total classification accuracy of 84.27% and as a fine-tuned network produced a total of 86.47% which is the highest among the four techniques across all the 116 image classes. This study shows that the employment of a shallower pre-trained neural network such as AlexNet learn features that are more generalizable compared to deeper networkers such as VGGNet-16 and has a greater capability of increasing classification accuracy of medical image database. Though the pre-trained AlexNet outperformed VGGNet-16 in both ways, it can be noted that some image classes from the same sub-body region are difficult to classify accurately. This is as a result of inter-class similarity that exists among the images.

The rapid growth and spread of radiographic equipment in medical centres have resulted in a corresponding increase in the number of medical X-ray images produced. Therefore, more efficient and effective image classification techniques are required. Three different techniques for automatic classification of medical X-ray images were compared. A bag-of-visual-words model and a Convolutional Neural Network (CNN) were used to extract features from the images. The two groups of extracted feature vectors were each used to train a linear support vector machine classifier. Third, a fine-tuned CNN was used for end-to-end classification. A pre-trained CNN was used to overcome dataset limitations. The three techniques were evaluated on the ImageCLEF 2007 medical database. The database provides medical X-ray images in 116 categories. The experimental results showed that fine-tuned CNN outperforms the other two techniques by achieving per class classification accuracy above 80% in 60 classes compared to 24 and 26 classes for bag-of-visual-words and CNN extracted features respectively. However, certain classes remain difficult to classify accurately such as classes in the same sub-body region due to inter-class similarity.

The classification of medical images enables physicians to perform expeditious and accurate data analysis, increasing the chances of timely disease diagnosis and early intervention to the patient. However, classification is a time‐consuming and labour intensive process when done manually. The Capsule Network (CapsNet) architecture has advantages in accurately and quickly classifying medical images due to its ability to evaluate images within part‐whole relationships, robustness to data rotations and affine transformations, and good performance on small datasets. However, CapsNet may demonstrate low performance on complex datasets. In this study, a new CapsNet model named MResCaps is proposed to overcome this disadvantage and enhance its performance on complex images. MResCaps utilizes an increasing number of residual blocks in each layer in parallel lane to obtain rich feature maps at different levels, aiming to achieve high success in the classification of various medical images. To evaluate the model's performance, the CIFAR10 dataset and the DermaMNIST, PneumoniaMNIST, and OrganMNIST‐S datasets from the MedMNIST dataset collection are used. MResCaps outperformed CapsNet by 20% in terms of accuracy on the CIFAR10 dataset. In addition, AUC values of 96.25%, 96.30%, and 97.12% were achieved in DermaMNIST, PneumoniaMNIST, and OrganMNIST‐S datasets, respectively. The results show that the proposed new model MResCaps improves the performance of CapsNet in the classification of complex and medical images. Furthermore, the model has demonstrated a better performance in comparison with extant studies in the literature. This study aims to contribute significantly to the literature by introducing a novel perspective on CapsNet‐based architectures for the classification of medical images through a parallel‐laned architecture and a rich feature capsule‐focused approach.

Classification of medical X-Ray image (XRI) is a task where machine learning (ML) approaches are utilized to categorize XRIs into various categories on the basis of some criteria.The core objective is to automate the task of evaluating XRIs and enhance the efficiency and accuracy of diagnosis.Current advancements in deep learning (DL) have given rise to better performance in various medical image analysis processes.Chest radiographs, the frequently performed radiological exam, are specifically significant modalities for which various applications were studied.The issue of publicly available, multiple, large chest X-Ray datasets in recent times has increased investigation.Therefore, this article presents a new barnacles mating optimizer with DL based medical image classification model (BMODL-MICM) for XRIs.The BMODL-MICM technique uses wiener filtering (WF) as a preprocessing step to eradicate the noise.Besides, the ShuffleNetv2 feature extractor is involved to create a collection of feature vectors.Moreover, the BMODL-MICM technique uses the BMO algorithm for the hyperparameter tuning procedure.At last, elman neural network (ENN) technique is applied for XRIs classification.The investigational assessment of the BMODL-MICM approach on the benchmark XRI dataset reported its effectual outcome of 99.67% over the other methods.

Pneumonia is a significant public health concern worldwide, causing substantial morbidity and mortality. Early, accurate diagnosis is vital in ensuring timely treatment and improving patient outcomes. Chest X-ray analysis is the standard procedure used most frequently to diagnose pneumonia, but the accurate and timely interpretation of these images can be complex and time consuming. This research aimed to develop a capsule network (CapsNet) model for image classification, based on the Capsule network model introduced by Sabour and his colleagues in 2017 enabling automated chest X-ray analysis for early detection of pneumonia. Pneumonia impacts diverse populations, with vulnerable groups such as the elderly, young children and immunocompromised individuals at heightened risk. Delayed or missed diagnoses can lead to severe complications and increased healthcare costs. The reliance on human expertise for chest X-ray interpretation introduces the potential or errors, therefore there is a dire need to develop automated and precise diagnostic models and tools which are crucial for facilitating timely interventions. In this study secondary data obtained from Mendeley data was comprehensively pre-processed thoroughly by applying image resizing, standardization and normalization for consistent image quality, followed by a gaussian blur for noise reduction, and histogram equalization for contrast enhancement. The enhanced dataset enabled the main features of the pneumonia-infected images to be captured effectively during model training. The dataset was split into sets for training, testing and validation in an 80%, 10% and 10% ratio. The training set was used to train the CapsNet model which demonstrated a commendable performance with a 96% accuracy, a precision of 96.97% and a recall of 97.42%. The Capsule Network model shows a significant promise as a tool for improving the efficiency and accuracy of pneumonia diagnosis, thus befitting patients and healthcare providers.

In this paper, we propose a symbolic approach for classification of medical X-ray images. Graph cut segmentation is applied to segment the body part of medical X-ray images. A complete directed graph is constructed using the centroid points in the boundary image of the segmented body part image. The complete directed graph is in turn used to extract features of distance and orientation. Further, the boundaries of segmented images are represented by its skeleton end points. Shape features are then extracted from the represented skeleton end points. To assimilate feature variations, we propose to symbolically represent the extracted features of each class in the form of interval valued features. Based on the proposed symbolic representation, symbolic classifier is then used for classification of medical X-ray images. Experimental results reveal the efficiency of our proposed symbolic classification model.

Image representation is one of the major aspects of automatic classification algorithms. In this paper, different feature extraction techniques have been utilized to represent medical X-ray images. They are categorized into two groups; (i) low-level image representation such as Gray Level Co-occurrence Matrix(GLCM), Canny Edge Operator, Local Binary Pattern(LBP) , pixel value, and (ii) local patch-based image representation such as Bag of Words (BoW). These features have been exploited in different algorithms for automatic classification of medical Xray images. We then analyzed the classification performance obtained with regard to the image representation techniques used. These experiments were evaluated on ImageCLEF 2007 database consists of 11000 medical X-ray images with 116 classes. Experimental results showed the classification performance obtained by exploiting LBP and BoW outperformed the other algorithms with respect to the image representation techniques used.

In recent years, generative adversarial networks (GANs) have gained tremendous popularity for various imaging related tasks such as artificial image generation to support AI training. GANs are especially useful for medical imaging-related tasks where training datasets are usually limited in size and heavily imbalanced against the diseased class. We present a systematic review, following the PRISMA guidelines, of recent GAN architectures used for medical image analysis to help the readers in making an informed decision before employing GANs in developing medical image classification and segmentation models. We have extracted 54 papers that highlight the capabilities and application of GANs in medical imaging from January 2015 to August 2020 and inclusion criteria for meta-analysis. Our results show four main architectures of GAN that are used for segmentation or classification in medical imaging. We provide a comprehensive overview of recent trends in the application of GANs in clinical diagnosis through medical image segmentation and classification and ultimately share experiences for task-based GAN implementations.

Medical Image databases are a key component in future diagnosis and preventive medicine. Automatic categorization of medical images plays an important role for structuring of given medical databases as well as for searching and retrieval of medical images. This paper focuses on a general framework for efficient representation and classification of X-ray images, appropriate for medical image archives. The proposed methodology is comprised of a graph theoretic image representation scheme and image matching measures. In this work, x-ray images are represented by undirected graphs and categorization is done based on an inexact graph matching scheme, graph edit distance. Initially, an unsupervised clustering algorithm is applied on input x-ray images in order to extract coherent regions in feature space, and corresponding coherent segments in the image content. The segmented images are then represented as graphs, which are used in the image matching process. Finally, the experimental results have also been presented at the end of the paper.

With advanced digital manipulation techniques making it more challenging to distinguish between genuine and fake information, deepfakes pose a threat to the integrity of digital evidence within the health sector. This study reviews the performance of three deep learning architectures: Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Convolutional Neural Network (CNN), in the classification of medical chest x-ray images as real or fake. A balanced dataset of real and synthetic digital images is used to train the models. To support the generalisation ability of the models, operations such as image normalisation and augmentation are carried out on the images. Performance evaluation metrics such as accuracy, precision, recall, and F1-score are used to quantify and compare the performance of the models. The study found that CNN performs better than RNN and LSTM in detecting deepfake images. Spatial feature extraction is among the attributes that explain CNN's improved performance. RNN and LSTM models can handle sequential or temporal data, but they are challenged regarding the detection of spatial patterns in images. CNNs are also parameter efficient due to their high learning efficiency. CNNs prevent overfitting and improve generalisation by learning using fewer parameters, feasible through weight sharing and local receptive fields. The study outcome indicates that the CNN model was 97% accurate, outperforming the RNN model at 52% and the LSTM model at 54%. This demonstrates that CNNs are a reliable approach for deepfake image detection and recommends their adoption as the primary architecture for deepfake classification systems to preserve medical diagnostic integrity.

Due to rapid growth of computerized medical imagery, the research area of medical image classification has been very active for the past decade. This paper presents an approach to achieve high recognition rate from classification of medical x-ray images. The methodology is based on local binary pattern as a feature extraction technique and support vector machine (SVM) as a classifier. This classification model was built based on merging scheme where overlapped classes were combined with each other and SVM classifier was re-trained to construct the model. The overlapped classes used in merging scheme are detected based on their accuracy, miss-classification ratio and similarity in their body anatomy. The proposed algorithm was evaluated on a database consisting of 36 classes of medical X-ray images which are suffering from high inter-class similarity and intra-class variability. The accuracy rate obtained for this model is 91%.

In Health Care, the medical image processing becomes a necessary marathon for the Computer Aided Diagnostic (CAD) systems. Blobs are the heterogeneous small parts of an image, which helps in finding and locating the abnormalities and damages of the body organs from the digital medical images. For the disease early diagnosis and staging purpose, the blobs’ location, size, shape, center and radius like properties should be calculated from the medical images. As on, many former researchers were proposed several blob detections models and algorithms to accurately find the blobs from the medical images. Although many researchers proposed various blob detection models, they are still facing several limitations in detection, due to the indistinct boundaries and the diversity in shape and distribution of the blobs. As part of the research on blob detection, in this survey paper we are presenting the essential information regarding the medical image blob detection and classification models.