Hand-crafted Machine Learning Research Articles

Automated asthma detection in a 1326-subject cohort using a one-dimensional attractive-and-repulsive center-symmetric local binary pattern technique with cough sounds

Asthma is a common disease. The clinical diagnosis is usually confirmed on a pulmonary function test, which is not always readily accessible. We aimed to develop a computationally lightweight handcrafted machine learning model for asthma detection based on cough sounds recorded using mobile phones. Toward this aim, we proposed a novel feature extractor based on a one-dimensional version of the published attractive-and-repulsive center-symmetric local binary pattern (1D-ARCSLBP), which we tested on a new cough sound dataset. We prospectively recorded cough sounds from 511 asthmatics and 815 non-asthmatic subjects (comprising mostly healthy volunteers), which yielded 1875 one-second cough sound segments for analysis. Our model comprised four steps: (i) preprocessing, in which speech signals and stop times (silent zones between coughs) were removed, leaving behind analyzable cough sound segments; (ii) feature extraction, in which tunable q-factor wavelet transformation was used to perform multilevel signal decomposition into wavelet subbands, allowing 1D-ARCSLBP to extract local low- and high-level features; (iii) feature selection, in which neighborhood component analysis was used to select the most discriminative features; and (iv) classification, in which a standard shallow cubic support vector machine was deployed to calculate binary classification results (asthma versus non-asthma) using tenfold and leave-one-subject-out cross-validations. Our model attained 98.24% and 96.91% accuracy rates with tenfold and leave-one-subject-out cross-validation strategies, respectively, and obtained a low-time complexity. The excellent results confirmed the feature extraction capability of 1D-ARCSLBP and the feasibility of the model being developed into a real-world application for asthma screening.

Automated Adrenal Gland Disease Classes Using Patch-Based Center Symmetric Local Binary Pattern Technique with CT Images.

Incidental adrenal masses are seen in 5% of abdominal computed tomography (CT) examinations. Accurate discrimination of the possible differential diagnoses has important therapeutic and prognostic significance. A new handcrafted machine learning method has been developed for the automated and accurate classification of adrenal gland CT images. A new dataset comprising 759 adrenal gland CT image slices from 96 subjects were analyzed. Experts had labeled the collected images into four classes: normal, pheochromocytoma, lipid-poor adenoma, and metastasis. The images were preprocessed, resized, and the image features were extracted using the center symmetric local binary pattern (CS-LBP) method. CT images were next divided into 16 × 16 fixed-size patches, and further feature extraction using CS-LBP was performed on these patches. Next, extracted features were selected using neighborhood component analysis (NCA) to obtain the most meaningful ones for downstream classification. Finally, the selected features were classified using k-nearest neighbor (kNN), support vector machine (SVM), and neural network (NN) classifiers to obtain the optimum performing model. Our proposed method obtained an accuracy of 99.87%, 99.21%, and 98.81% with kNN, SVM, and NN classifiers, respectively. Hence, the kNN classifier yielded the highest classification results with no pathological image misclassified as normal. Our developed fixed patch CS-LBP-based automatic classification of adrenal gland pathologies on CT images is highly accurate and has low time complexity [Formula: see text]. It has the potential to be used for screening of adrenal gland disease classes with CT images.

Novel favipiravir pattern-based learning model for automated detection of specific language impairment disorder using vowels.

Specific language impairment (SLI) is one of the most common diseases in children, and early diagnosis can help to obtain better timely therapy economically. It is difficult and time-consuming for clinicians to accurately detect SLI through standard clinical assessments. Hence, machine learning algorithms have been developed to assist in the accurate diagnosis of SLI. This work aims to investigate the graph of the favipiravir molecule-based feature extraction function and propose an accurate SLI detection model using vowels. We proposed a novel handcrafted machine learning framework. This architecture comprises the favipiravir molecular structure pattern, statistical feature extractor, wavelet packet decomposition (WPD), iterative neighborhood component analysis (INCA), and support vector machine (SVM) classifier. Two feature extraction models, statistical and textural, are employed in the handcrafted feature generation methodology. A new nature-inspired graph-based feature extractor that uses the chemical depiction of the favipiravir (favipiravir became popular with the COVID-19 pandemic) is employed for feature extraction. Finally, the proposed favipiravir pattern, statistical feature extractor, and wavelet packet decomposition are used to create a feature vector. Moreover, a statistical feature extractor is used in this work. The WPD generates multilevel features, and the most meaningful features are selected using the NCA feature selector. Finally, these chosen features are fed to SVM classifier for automated classification. Two validation methods, (i) leave one subject out (LOSO) and (ii) tenfold cross-validations (CV), are used to obtain robust classification results. Our proposed favipiravir pattern-based model developed using a vowel dataset can detect SLI children with an accuracy of 99.87% and 98.86% using tenfold and LOSO CV strategies, respectively. These results demonstrated the high vowel classification ability of the proposed favipiravir pattern-based model.

Deep Neural Network Models for Colon Cancer Screening.

Simple SummaryDeep learning models have been shown to achieve high performance in diagnosing colon cancer compared to conventional image processing and hand-crafted machine learning methods. Hence, several studies have focused on developing hybrid learning, end-to-end, and transfer learning techniques to reduce manual interaction and for labelling the regions of interest. However, these weak learning techniques do not always provide a clear diagnosis. Therefore, it is necessary to develop a clear explainable learning method that can highlight factors and form the basis of clinical decisions. However, there has been little research carried out employing such transparent approaches. This study discussed the aforementioned models for colon cancer diagnosis.Early detection of colorectal cancer can significantly facilitate clinicians’ decision-making and reduce their workload. This can be achieved using automatic systems with endoscopic and histological images. Recently, the success of deep learning has motivated the development of image- and video-based polyp identification and segmentation. Currently, most diagnostic colonoscopy rooms utilize artificial intelligence methods that are considered to perform well in predicting invasive cancer. Convolutional neural network-based architectures, together with image patches and preprocesses are often widely used. Furthermore, learning transfer and end-to-end learning techniques have been adopted for detection and localization tasks, which improve accuracy and reduce user dependence with limited datasets. However, explainable deep networks that provide transparency, interpretability, reliability, and fairness in clinical diagnostics are preferred. In this review, we summarize the latest advances in such models, with or without transparency, for the prediction of colorectal cancer and also address the knowledge gap in the upcoming technology.

Novel multiple pooling and local phase quantization stable feature extraction techniques for automated classification of brain infarcts

This study aims to introduce a hand-crafted machine learning method to classify ischemic and hemorrhagic strokes with satisfactory performance. In the first step of this work, a new CT brain for images dataset was collected for stroke patients. A highly accurate hand-crafted machine learning method is developed and tested for these cases. This model uses preprocessing, feature creation using a novel pooling method (it is named P9), a local phase quantization (LPQ) operator, and a Chi2-based selector responsible for selecting the most significant features. After that, classification is done using the k-nearest neighbor (kNN) classifier with ten-fold cross-validation (CV). The novel aspect of this model is the P9 pooling method. The inspiration for this pooling method was drawn from the deep learning models, where features are extracted with multiple layers using a convolution operator applied to the pooling method. However, pooling decompositions have a routing problem. The P9 pooling function creates nine decomposed models, hence the name. The LPQ feature extractor is applied to images to generate sub-bands for feature generation. The Chi2 selector is then employed to select the most significant features from the created feature vector, and these features are utilized for the classification using the k-nearest neighbor algorithm (kNN). The introduced P9-LPQ feature extraction-based learning model attained over 98% classification accuracy in all cases. The results obtained in this paper show that the proposed method can successfully classify stroke types. For this reason, the developed model can pre-diagnose stroke types in the future.

Hyp-Net: Automated detection of hypertension using deep convolutional neural network and Gabor transform techniques with ballistocardiogram signals

Hypertension (HPT) is a physiological abnormality characterized by high blood pressure, headache, wooziness, and fainting that may lead to various heart, kidney, or brain diseases. Detection and continuous monitoring of HPT by sphygmometer is arduous and hectic. Nowadays, ballistocardiogram (BCG) signals are used to determine HPT as it indicates the vibration of the heart. Usual linear and nonlinear hand-crafted machine learning methods are subjective, involve decomposition of signal, features elicitation, selection, and classification steps. In this work, a completely automated HPT detection system is proposed using time–frequency (T-F) spectral images and a convolutional neural network (CNN) for the accurate detection of HPT using BCG signals. The BCG signals are subjected to Gabor transform (GT), smoothed pseudo-Wigner Ville distribution (SPWVD), and short-time Fourier transform (STFT) techniques to obtain T-F spectral images. These T-F spectral images are fed to benchmarked Alex-Net, Res-Net50, and proposed CNN (Hyp-Net) to develop the automated HPT detection model with a 10-fold cross-validation scheme. The proposed Hyp-Net obtained the highest detection accuracy of 97.65% with GT-based spectral images. In comparison to Alex-Net and Res-Net50 pre-trained models, our developed Hyp-Net needs minimal learnable parameters, makes it computationally fast and more efficient. This shows that our proposed model has outperformed other two transfer learning methods. The experimental results with collected BCG signals from a public dataset are provided to show the effectiveness of the presented technique for automated detection of HPT.

Artificial Intelligence in Colorectal Polyp Detection and Characterization.

Background:Over the past 20 years, the advancement of artificial intelligence (AI) and deep learning (DL) has allowed for fast sorting and analysis of large sets of data. In the field of gastroenterology, colorectal screening procedures produces an abundance of data through video and imaging. With AI and DL, this information can be used to create systems where automatic polyp detection and characterization is possible. Convoluted Neural Networks (CNNs) have proven to be an effective way to increase polyp detection and ultimately adenoma detection rates. Different methods of polyp characterization of being hyperplastic vs. adenomatous or non-neoplastic vs. neoplastic has also been investigated showing promising results.Findings:The rate of missed polyps on colonoscopy can be as high as 25%. At the beginning of the 2000s, hand-crafted machine learning (ML) algorithms were created and trained retrospectively on colonoscopy images and videos, achieving high sensitivity, specificity, and accuracy of over 90% in many of the studies. Over time, the advancement of DL and CNNs has allowed algorithms to be trained on non-medical images and applied retrospectively to colonoscopy videos and images with similar results. Within the past few years, these algorithms have been applied in real-time colonoscopies and has shown mixed results, one showing no difference while others showing increased polyp detection.Various methods of polyp characterization have also been investigated. Through AI, DL, and CNNs polyps can be identified has hyperplastic/adenomatous or non-neoplastic/neoplastic with high sensitivity, specificity, and accuracy. One of the research areas in polyp characterization is how to capture the polyp image. This paper looks at different modalities of characterizing polyps such as magnifying narrow band imaging (NBI), endocytoscopy, laser-induced florescent spectroscopy, auto-florescent endoscopy, and white-light endoscopy.Conclusions:Overall, much progress has been made in automatic detection and characterization of polyps in real time. Barring ethical or mass adoption setbacks, it is inevitable that AI will be involved in the field of GI, especially in colorectal polyp detection and identification.

Machine learning and deep learning for clinical data and PET/SPECT imaging in Parkinson's disease: a review

Machine Learning (ML) is a subfield of Artificial Intelligence (AI) that is increasingly applied to several medical diagnosis tasks, including a wide range of diseases. Importantly, various ML models were developed to address the complexity of Parkinson's Disease (PD) diagnosis. PD is a neurodegenerative disease characterized by motor and non-motor disorders where its syndromes affect the daily lives of patients. Several Computer Aided Diagnosis and Detection (CADD) systems based on hand-crafted ML algorithms achieved promising results in distinguishing PD patients from Healthy Control (HC) subjects and other Parkinsonian syndrome categories using clinical data (e.g., speech and gait impairments) and medical imaging [e.g., Position Emission Tomography (PET) and Single Photon Emission Computed Tomography (SPECT)]. Despite the good performance of hand-crafted ML algorithms, there is still a problem linked to the features' extraction and selection. In fact, Deep Learning DL has provided an ultimate solution for the features' extraction and selection related issue. An important number of studies on the diagnosis of PD using DL algorithms were developed recently. This study provides an overview of the application of hand-crafted ML algorithms and DL techniques for PD diagnosis. It also introduces key concepts for understanding the application of ML methods to diagnose PD.

Precision transplant pathology.

Transplant pathology contributes substantially to personalized treatment of organ allograft recipients. Rapidly advancing next-generation human leukocyte antigen (HLA) sequencing and pathology are enhancing the abilities to improve donor/recipient matching and allograft monitoring. The present review summarizes the workflow of a prototypical patient through a pathology practice, highlighting histocompatibility assessment and pathologic review of tissues as areas that are evolving to incorporate next-generation technologies while emphasizing critical needs of the field. Successful organ transplantation starts with the most precise pratical donor-recipient histocompatibility matching. Next-generation sequencing provides the highest resolution donor-recipient matching and enables eplet mismatch scores and more precise monitoring of donor-specific antibodies (DSAs) that may arise after transplant. Multiplex labeling combined with hand-crafted machine learning is transforming traditional histopathology. The combination of traditional blood/body fluid laboratory tests, eplet and DSA analysis, traditional and next-generation histopathology, and -omics-based platforms enables risk stratification and identification of early subclinical molecular-based changes that precede a decline in allograft function. Needs include software integration of data derived from diverse platforms that can render the most accurate assessment of allograft health and needs for immunosuppression adjustments.

A review of deep learning with special emphasis on architectures, applications and recent trends

Deep learning (DL) has solved a problem that a few years ago was thought to be intractable — the automatic recognition of patterns in spatial and temporal data with an accuracy superior to that of humans. It has solved problems beyond the realm of traditional, hand-crafted machine learning algorithms and captured the imagination of practitioners who are inundated with all types of data. As public awareness of the efficacy of DL increases so does the desire to make use of it. But even for highly trained professionals it can be daunting to approach the rapidly increasing body of knowledge in the field. Where does one start? How does one determine if a particular DL model is applicable to their problem? How does one train and deploy them? With these questions in mind, we present an overview of some of the key DL architectures. We also discuss some new automatic architecture optimization protocols that use multi-agent approaches. Further, since guaranteeing system uptime is critical to many applications, a section dwells on using DL for fault detection and mitigation. This is followed by an exploratory survey of several areas where DL emerged as a game-changer: fraud detection in financial applications, financial time-series forecasting, predictive and prescriptive analytics, medical image processing, power systems research and recommender systems. The thrust of this review is to outline emerging applications of DL and provide a reference to researchers seeking to use DL in their work for pattern recognition with unparalleled learning capacity and the ability to scale with data.

Recognition of ischaemia and infection in diabetic foot ulcers: Dataset and techniques

Recognition and analysis of Diabetic Foot Ulcers (DFU) using computerized methods is an emerging research area with the evolution of image-based machine learning algorithms. Existing research using visual computerized methods mainly focuses on recognition, detection, and segmentation of the visual appearance of the DFU as well as tissue classification. According to DFU medical classification systems, the presence of infection (bacteria in the wound) and ischaemia (inadequate blood supply) has important clinical implications for DFU assessment, which are used to predict the risk of amputation. In this work, we propose a new dataset and computer vision techniques to identify the presence of infection and ischaemia in DFU. This is the first time a DFU dataset with ground truth labels of ischaemia and infection cases is introduced for research purposes. For the handcrafted machine learning approach, we propose a new feature descriptor, namely the Superpixel Colour Descriptor. Then we use the Ensemble Convolutional Neural Network (CNN) model for more effective recognition of ischaemia and infection. We propose to use a natural data-augmentation method, which identifies the region of interest on foot images and focuses on finding the salient features existing in this area. Finally, we evaluate the performance of our proposed techniques on binary classification, i.e. ischaemia versus non-ischaemia and infection versus non-infection. Overall, our method performed better in the classification of ischaemia than infection. We found that our proposed Ensemble CNN deep learning algorithms performed better for both classification tasks as compared to handcrafted machine learning algorithms, with 90% accuracy in ischaemia classification and 73% in infection classification.

Deep Learning Approaches to Detect Atrial Fibrillation Using Photoplethysmographic Signals: Algorithms Development Study.

BackgroundWearable devices have evolved as screening tools for atrial fibrillation (AF). A photoplethysmographic (PPG) AF detection algorithm was developed and applied to a convenient smartphone-based device with good accuracy. However, patients with paroxysmal AF frequently exhibit premature atrial complexes (PACs), which result in poor unmanned AF detection, mainly because of rule-based or handcrafted machine learning techniques that are limited in terms of diagnostic accuracy and reliability.ObjectiveThis study aimed to develop deep learning (DL) classifiers using PPG data to detect AF from the sinus rhythm (SR) in the presence of PACs after successful cardioversion.MethodsWe examined 75 patients with AF who underwent successful elective direct-current cardioversion (DCC). Electrocardiogram and pulse oximetry data over a 15-min period were obtained before and after DCC and labeled as AF or SR. A 1-dimensional convolutional neural network (1D-CNN) and recurrent neural network (RNN) were chosen as the 2 DL architectures. The PAC indicator estimated the burden of PACs on the PPG dataset. We defined a metric called the confidence level (CL) of AF or SR diagnosis and compared the CLs of true and false diagnoses. We also compared the diagnostic performance of 1D-CNN and RNN with previously developed AF detectors (support vector machine with root-mean-square of successive difference of RR intervals and Shannon entropy, autocorrelation, and ensemble by combining 2 previous methods) using 10 5-fold cross-validation processes.ResultsAmong the 14,298 training samples containing PPG data, 7157 samples were obtained during the post-DCC period. The PAC indicator estimated 29.79% (2132/7157) of post-DCC samples had PACs. The diagnostic accuracy of AF versus SR was 99.32% (70,925/71,410) versus 95.85% (68,602/71,570) in 1D-CNN and 98.27% (70,176/71,410) versus 96.04% (68,736/71,570) in RNN methods. The area under receiver operating characteristic curves of the 2 DL classifiers was 0.998 (95% CI 0.995-1.000) for 1D-CNN and 0.996 (95% CI 0.993-0.998) for RNN, which were significantly higher than other AF detectors (P<.001). If we assumed that the dataset could emulate a sufficient number of patients in training, both DL classifiers improved their diagnostic performances even further especially for the samples with a high burden of PACs. The average CLs for true versus false classification were 98.56% versus 78.75% for 1D-CNN and 98.37% versus 82.57% for RNN (P<.001 for all cases).ConclusionsNew DL classifiers could detect AF using PPG monitoring signals with high diagnostic accuracy even with frequent PACs and could outperform previously developed AF detectors. Although diagnostic performance decreased as the burden of PACs increased, performance improved when samples from more patients were trained. Moreover, the reliability of the diagnosis could be indicated by the CL. Wearable devices sensing PPG signals with DL classifiers should be validated as tools to screen for AF.

Beyond Manual Tuning of Hyperparameters

The success of hand-crafted machine learning systems in many applications raises the question of making machine learning algorithms more autonomous, i.e., to reduce the requirement of expert input to a minimum. We discuss two strategies towards this goal: (1) automated optimization of hyperparameters (including mechanisms for feature selection, preprocessing, model selection, etc) and (2) the development of algorithms with reduced sets of hyperparameters. Since many research directions (e.g., deep learning), show a tendency towards increasingly complex algorithms with more and more hyperparamters, the demand for both of these strategies continuously increases. We review recent hyperparameter optimization methods and discuss data-driven approaches to avoid the introduction of hyperparameters using unsupervised learning. We end in discussing how these complementary strategies can work hand-in-hand, representing a very promising approach towards autonomous machine learning.