Hybrid deep learning and handcrafted feature fusion for pneumonia detection in chest X-rays

Pneumonia is one infectious disease caused by viruses/bacteria, and early screening is necessary for the detection and treatment. Furthermore, pneumonia causes severe problems in children and elderly. The proposed work aims to develop a disease screening scheme for efficiently classifying the chest radiograph (X-ray) pictures into the Normal/Pneumonia group. The proposed process has the below phases; (i) Image collecting and resizing, (ii) Deep-feature extraction, (iii) Handcrafted feature extraction, (iv) Bat-Algorithm based feature selection and (v) Classification. In this work, the VGG16 scheme is considered to extract the deep-features and the necessary handcrafted features are mined using the Weighted Local Binary Pattern (WLBP). The necessary feature is then selected using the bat-algorithm supported feature selection. The experimental result of this study proves the accuracy of KNN is healthier (>98%) than other methods.

An empirical study of handcrafted and dense feature extraction techniques for lung and colon cancer classification from histopathological images

Automatic early diagnosis of COVID‐19 with computer‐aided tools is crucial for disease treatment and control. Radiology images of COVID‐19 and other lung diseases like bacterial pneumonia, viral pneumonia have common features. Thus, this similarity makes it difficult for radiologists to detect COVID‐19 cases. A reliable method for classifying non‐COVID‐19 and COVID‐19 chest x‐ray images could be useful to reduce triage process and diagnose. In this study, we develop an original framework (HANDEFU) that supports handcrafted, deep, and fusion‐based feature extraction techniques for feature engineering. The user interactively builds any model by selecting feature extraction technique and classification method through the framework. Any feature extraction technique and model could then be added dynamically to the library of software at a later time upon request. The novelty of this study is that image preprocessing and diverse feature extraction and classification techniques are assembled under an original framework. In this study, this framework is utilized for diagnosing COVID‐19 from chest x‐ray images on an open‐access dataset. All of the experimental results and performance evaluations on this dataset are performed with this software. In experimental studies, COVID‐19 prediction is performed by 27 different models through software. The superior performance with accuracy of 99.36% is obtained by LBP+SVM model.

The upsurge in advancements of digital imaging technology has led to archival of high-quality images embedded with rich content. This has facilitated content-based image classification (CBIC) as one of the most popular techniques to accurately classify these images by extracting robust low-level features like color, shape, texture, and so on. However, designing a robust feature descriptor to cater diversified set of images is a challenging task. Traditional handcrafted feature extraction techniques have taken a back sit after the advent of deep neural network-based image feature extraction. However, generalization of neural network-based feature vectors for smaller datasets has posed significant challenges due to overfitting caused by high variance of pre-trained networks. Hence, this research has primarily investigated the possibilities of designing generalized features using final layer of different pre-trained neural networks individually vis-a-vis handcrafted feature extraction. The process is followed by concatenation of final layers from diversified pre-trained networks along with handcrafted feature. In the process of experimentation, the paper aims at using representation learning using VGG19 and ResNet50. It has also considered handcrafted technique of feature extraction named color histogram (CH). Each of the techniques are separately tested for feature generalization efficiency using assorted classifiers. Further, the research has proposed fusion of features in several combinations using each of these descriptors to observe any improvement caused in feature generalization while tested for classification results. The outcomes using the proposed fusion approach have resulted in improved generalization by outshining classification accuracy of individual methods.

Modality corresponding to medical images is a vital filter in medical image retrieval systems, as radiologists or physicians are interested in only one of radiology images e.g CT scan, MRI, X-ray. Various handcrafted feature schemes have been proposed for medical image modality classification. On the other hand not enough attempts have been made for deep learned feature extraction. A comparative evaluation of both handcrafted and deep learned features for medical image modality classification is presented in this paper. The experiments are performed on IMAGECLEF 2012 data. After carrying out the experiments it is shown that the handcrafted features outperforms the deep learned features and shows the potential of handcrafted feature extraction models in the medical image field.

Pneumonia is a dangerous disease that kills millions of children and elderly patients worldwide every year. The detection of pneumonia from a chest x-ray is perpetrated by expert radiologists. The chest x-ray is cheaper and is most often used to diagnose pneumonia. However, chest x-ray-based diagnosis requires expert radiologists which is time-consuming and laborious. Moreover, COVID-19 and pneumonia have similar symptoms which leads to false positives. Machine learning-based solutions have been proposed for the automatic prediction of pneumonia from chest X-rays, however, such approaches lack robustness and high accuracy due to data imbalance and generalization errors. This study focuses on elevating the performance of machine learning models by dealing with data imbalanced problems using data augmentation. Contrary to traditional machine learning models that required hand-crafted features, this study uses transfer learning for automatic feature extraction using Xception and VGG-16 to train classifiers like support vector machine, logistic regression, K nearest neighbor, stochastic gradient descent, extra tree classifier, and gradient boosting machine. Experiments involve the use of hand-crafted features, as well as, transfer learning-based feature extraction for pneumonia detection. Performance comparison using Xception and VGG-16 features suggest that transfer learning-based features tend to show better performance than hand-crafted features and an accuracy of 99.23% can be obtained for pneumonia using chest X-rays.

Sign Language is the main communication medium for people who have a difficulty with speaking or hearing. To communicate with other deaf or healthy people, they use sign language. Deaf and mute people of Bangladesh and India use Bangla sign language to fulfill their communication needs. But, the learning process of sign language is time consuming and arduous. Therefore, as the artificial intelligence technology advances, automatic recognition of Bangla sign language is gaining more attention from researchers. In this paper, the proposed research aims to develop an approach to automate the identification of Bangla Sign Digits comparing the efficacy of handcrafted and deep neural network features. The handcrafted feature extractors like Histogram of Oriented Gradient (HOG), Scale invariant feature transform (SIFT), and pre-trained deep neural network feature extractors such as InceptionV3, Xception, and DenseNet-121 was used on publicly available Ishara-Lipi dataset to extract features. Moreover, to recognize sign digits, we used three fine-tuned classification algorithms namely K-Nearest Neighbor (KNN), Random Forest (RF), Support Vector Machine (SVM) that were fed by extracted features. Experimental result shows that the deep neural network features outperformed the handcrafted features based approach. DenseNet-121 combined with SVM based approach achieved highest test accuracy of 99.53% on Ishara-Lipi dataset.

The improvements in computation facility and technology support the development and implementation of automatic methods for medical data assessment. This study tries to extend a framework for efficiently classifying chest radiographs (X-rays) into normal/COVID-19 class. The proposed framework consists subsequent phases: (i) image resizing, (ii) deep features extraction using a pretrained deep learning method (PDLM), (iii) handcrafted feature extraction, (iv) feature optimization with Brownian Mayfly-Algorithm (BMA), (v) serial integration of optimized features, and (vi) binary classification with 10-fold cross validation. In addition, this work implements two methodologies: (i) performance evaluation of the existing PDLM in the literature and (ii) improving the COVID-19 detection performance of chosen PDLM with this proposal. The experimental investigation of this study authenticates that the effort performed using pretrained VGG16 with SoftMax helped get a classification accuracy of >94%. Further, the research performed using the proposed framework with BMA selected features (VGG16 + handcrafted features) helps achieve a classification accuracy of 99.17% on the chosen X-ray image database. This outcome proves the scientific importance of the implemented framework, and in the future, this proposal can be adopted to inspect the clinically collected X-rays.

Multi-class tissue classification from histological images is a complex challenge. The gold standard still relies on manual assessment by a trained pathologist, but it is a time-expensive task with issues about intra- and inter-operator variability. The rise of computational models in Digital Pathology has the potential to revolutionize the field. Historically, image classifiers relied on handcrafted feature extraction, combined with statistical classifiers, as Support Vector Machines (SVMs) or Artificial Neural Networks (ANNs). In recent years, there has been a tremendous growth in Deep Learning (DL), for all the image recognition tasks, including, of course, those concerning medical images. Thanks to DL, it is now possible to also learn the process of capturing the most relevant features from the image, easing the design of specialized classification algorithms and improving the performance. An important problem of DL is that it requires tons of training data, which is not easy to obtain in medical domain, since images have to be annotated by expert physicians. In this work, we extensively compared three classes of approaches for the multi-class tissue classification task: (1) extraction of handcrafted features with the adoption of a statistical classifier; (2) extraction of deep features using the transfer learning paradigm, then exploiting SVM or ANN classifiers; (3) fine-tuning of deep classifiers. After a cross-validation on a publicly available dataset, we validated our results on two independent test sets, obtaining an accuracy of 97% and of 77%, respectively. The second test set has been provided by the Pathology Department of IRCCS Istituto Tumori Giovanni Paolo II and has been made publicly available (http://doi.org/10.5281/zenodo.4785131).

In this paper, we will review face representation techniques that are used in face recognition process. There are two types of feature extraction: handcraft and learned features. PCA and LBP are handcraft feature extraction while the DeepFace, generating from convolutional neural network, is learned feature. PCA is an orthogonal transformation where a set of observations is converted to the principal components. The first few principal components have the largest variance hence represented images with small number of features. LBP is a local binary pattern which encodes local image into a binary pattern. LBP tolerates against changes in gray scale variations. By allowing the deep learning to automatically discover the image representations from raw data therefore DeepFace is a learned feature. In some cases, data may be unable to define specific feature especially for face representation. DeepFace is an alternative technique where features are generated through training/learning process without relying on specific algorithms. Learned features significantly outperform the handcraft one where the test set is unseen. PCA, LBP and DeepFace will be compared in terms of accuracy and computational time.

The Covid-19 pandemic is our era’s most significant public health emergency. To aid in the Covid-19 affected ones detection of at the hospital, Rib Cage X-Rays have been a vital imaging technique to use. However, radiologists have to spend a lot of time interpreting them. Covid-19 can be diagnosed early and effectively triaged with the assistance of accurate machine learning-based computer systems. Deep feature Extraction which is tactic of Machine learning can be used in amalgamation with Rib Cage X-ray images to help detect the disease with greater accuracy and speed, which can aid assuage the problem of a dearth of detection kits during Covid wave. Persons sick with Covid-19 can be differentiated from hale and hearty ones using a Deep Feature Extraction-based approach proposed in this paper. 94.49% classification accuracy is achieved during experimentation, confirming the proposed mechanism’s effectiveness.

An effective COVID-19 classification in X-ray images using a new deep learning framework.

Pattern classification for breast lesion on FFDM by integration of radiomics and deep features.

Optical coherence tomography (OCT) is a leading imaging technique for diagnosing retinal disorders such as age-related macular degeneration and diabetic retinopathy. Its ability to detect structural changes, especially in the optic nerve head, has made it vital for early diagnosis and monitoring. This paper surveys techniques for ocular disease prediction using OCT, focusing on both hand-crafted and deep learning-based feature extractors. While the field has seen rapid growth, a detailed comparative analysis of these methods has been lacking. We address this by reviewing research from the past 20 years, evaluating methods based on accuracy, sensitivity, specificity, and computational cost. Key diseases examined include glaucoma, diabetic retinopathy, cataracts, amblyopia, and macular degeneration. We also assess public OCT datasets widely used in model development. A unique contribution of this paper is the exploration of adversarial attacks targeting OCT-based diagnostic systems and the vulnerabilities of different feature extraction techniques. We propose a practical, robust defense strategy that integrates with existing models and outperforms current solutions. Our findings emphasize the value of combining classical and deep learning methods with strong defenses to enhance the security and reliability of OCT-based diagnostics, and we offer guidance for future research and clinical integration.

Pneumonia is a major cause of hospitalisation in children. Chest x-ray represents the gold-standard method for the detection of pneumonia for more than a century. However, some recent studies showed good sensitivity of the chest ultrasound for the detection of pneumonia. The aim of our study was to compare the sensitivity of ultrasound and chest x-ray for the detection of community-acquired pneumonia in children. We included 54 otherwise healthy children with signs or symptoms of pneumonia who had pulmonary infiltrates detected with chest x-ray and/or ultrasound, both performed in all patients. Number and type of infiltrates and the presence of pleural effusion was recorded. Sensitivity of ultrasound and chest x-ray was compared with McNemar chi-square test. Pneumonia was caused by bacteria, viruses and Mycoplasma pneumoniae in 17, 15 and 22 of patients, respectively. Infiltrates were seen on chest X-ray in 45 out of 54 cases. With the chest ultrasound infiltrates were seen in 53 out of 54 cases. Sensitivity of the chest ultrasound for the detection of pneumonia was 98.1%, which is significantly higher than 83.3% sensitivity of the chest x-ray (p=0.03). Bilateral infiltrates were detected with chest x-ray in 4 cases and with ultrasound in 14 cases (p=0.01). Pleural effusion was detected with chest x-ray in 3 cases and with ultrasound in 7 cases (p=0.04). Chest ultrasound is sensitive, safe, and widely available method for the detection of community-acquired pneumonia in children. However, a prospective study on larger sample and standardisation of the investigation and terminology is needed before the implementation of chest ultrasound in everyday clinical practice.