A novel nonintrusive decision support approach for heart rate measurement

A framework to distinguish healthy/cancer renal CT images using the fused deep features

Introduction

Cancer happening rates in humankind are gradually rising due to a variety of reasons, and sensible detection and management are essential to decrease the disease rates. The kidney is one of the vital organs in human physiology, and cancer in the kidney is a medical emergency and needs accurate diagnosis and well-organized management.

Methods

The proposed work aims to develop a framework to classify renal computed tomography (CT) images into healthy/cancer classes using pre-trained deep-learning schemes. To improve the detection accuracy, this work suggests a threshold filter-based pre-processing scheme, which helps in removing the artefact in the CT slices to achieve better detection. The various stages of this scheme involve: (i) Image collection, resizing, and artefact removal, (ii) Deep features extraction, (iii) Feature reduction and fusion, and (iv) Binary classification using five-fold cross-validation.

Results and discussion

This experimental investigation is executed separately for: (i) CT slices with the artefact and (ii) CT slices without the artefact. As a result of the experimental outcome of this study, the K-Nearest Neighbor (KNN) classifier is able to achieve 100% detection accuracy by using the pre-processed CT slices. Therefore, this scheme can be considered for the purpose of examining clinical grade renal CT images, as it is clinically significant.

Robust Pulse Rate Measurements from Facial Videos in Diverse Environments

Pulse wave and pulse rate are important indicators of cardiovascular health. Technologies that can check the pulse by contacting the skin with optical sensors built into smart devices have been developed. However, this may cause inconvenience, such as foreign body sensation. Accordingly, studies have been conducted on non-contact pulse rate measurements using facial videos focused on the indoors. Moreover, since the majority of studies are conducted indoors, the error in the pulse rate measurement in outdoor environments, such as an outdoor bench, car and drone, is high. In this paper, to deal with this issue, we focus on developing a robust pulse measurement method based on facial videos taken in diverse environments. The proposed method stably detects faces by removing high-frequency components of face coordinate signals derived from fine body tremors and illumination conditions. It optimizes for extracting skin color changes by reducing illumination-caused noise using the Cg color difference component. The robust pulse wave is extracted from the Cg signal using FFT-iFFT with zero-padding. It can eliminate signal-filtering distortion effectively. We demonstrate that the proposed method relieves pulse rate measurement problems, producing 3.36, 5.81, and 6.09 bpm RMSE for an outdoor bench, driving car, and flying drone, respectively.

A Comprehensive Survey on Quantum Machine Learning and Possible Applications

Machine learning is a branch of artificial intelligence that is being used at a large scale to solve science, engineering, and medical tasks. Quantum computing is an emerging technology that has a very high computational ability to solve complex problems. Classical machine learning with traditional systems has some limitations for problem-solving due to a large amount of data availability. Quantum machine learning has high performance and computational ability that can effectively be used to solve computation tasks. This study reviews the latest articles in quantum computing and quantum machine learning. Building blocks of quantum computing and different flavors of quantum algorithms are also discussed. The latest work in quantum neural networks is also presented. In the end, different possible applications of quantum computing are also discussed.

An integrated framework for COVID-19 classification based on classical and quantum transfer learning from a chest radiograph

COVID-19 is a quickly spreading over 10 million persons globally. The overall number of infected patients worldwide is estimated to be around 133,381,413 people. Infection rate is being increased on daily basis. It has also caused a devastating effect on the world economy and public health. Early stage detection of this disease is mandatory to reduce the mortality rate. Artificial intelligence performs a vital role for COVID-19 detection at an initial stage using chest radiographs. The proposed methods comprise of the two phases. Deep features (DFs) are derived from its last fully connected layers of pre-trained models like AlexNet and MobileNet in phase-I. Later these feature vectors are fused serially. Best features are selected through feature selection method of PCA and passed to the SVM and KNN for classification. In phase-II, quantum transfer learning model is utilized, in which a pre-trained ResNet-18 model is applied for DF collection and then these features are supplied as an input to the 4-qubit quantum circuit for model training with the tuned hyperparameters. The proposed technique is evaluated on two publicly available x-ray imaging datasets. The proposed methodology achieved an accuracy index of 99.0% with three classes including corona virus-positive images, normal images, and pneumonia radiographs. In comparison to other recently published work, the experimental findings show that the proposed approach outperforms it.

A weighted least squares optimisation strategy for medical image super resolution via multiscale convolutional neural networks for healthcare applications

Medical imaging is an essential medical diagnosis system subsequently integrated with artificial intelligence for assistance in clinical diagnosis. The actual medical images acquired during the image capturing procedures generate poor quality images as a result of numerous physical restrictions of the imaging equipment and time constraints. Recently, medical image super-resolution (SR) has emerged as an indispensable research subject in the community of image processing to address such limitations. SR is a classical computer vision operation that attempts to restore a visually sharp high-resolution images from the degraded low-resolution images. In this study, an effective medical super-resolution approach based on weighted least squares optimisation via multiscale convolutional neural networks (CNNs) has been proposed for lesion localisation. The weighted least squares optimisation strategy that particularly is well-suited for progressively coarsening the original images and simultaneously extract multiscale information has been executed. Subsequently, a SR model by training CNNs based on wavelet analysis has been designed by carrying out wavelet decomposition of optimized images for multiscale representations. Then multiple CNNs have been trained separately to approximate the wavelet multiscale representations. The trained multiple convolutional neural networks characterize medical images in many directions and multiscale frequency bands, and thus facilitate image restoration subject to increased number of variations depicted in different dimensions and orientations. Finally, the trained CNNs regress wavelet multiscale representations from a LR medical images, followed by wavelet synthesis that forms a reconstructed HR medical image. The experimental performance indicates that the proposed model SR restoration approach achieve superior SR efficiency over existing comparative methods

A deep network designed for segmentation and classification of leukemia using fusion of the transfer learning models

White blood cells (WBCs) are a portion of the immune system which fights against germs. Leukemia is the most common blood cancer which may lead to death. It occurs due to the production of a large number of immature WBCs in the bone marrow that destroy healthy cells. To overcome the severity of this disease, it is necessary to diagnose the shapes of immature cells at an early stage that ultimately reduces the modality rate of the patients. Recently different types of segmentation and classification methods are presented based upon deep-learning (DL) models but still have some limitations. This research aims to propose a modified DL approach for the accurate segmentation of leukocytes and their classification. The proposed technique includes two core steps: preprocessing-based classification and segmentation. In preprocessing, synthetic images are generated using a generative adversarial network (GAN) and normalized by color transformation. The optimal deep features are extracted from each blood smear image using pretrained deep models i.e., DarkNet-53 and ShuffleNet. More informative features are selected by principal component analysis (PCA) and fused serially for classification. The morphological operations based on color thresholding with the deep semantic method are utilized for leukemia segmentation of classified cells. The classification accuracy achieved with ALL-IDB and LISC dataset is 100% and 99.70% for the classification of leukocytes i.e., blast, no blast, basophils, neutrophils, eosinophils, lymphocytes, and monocytes, respectively. Whereas semantic segmentation achieved 99.10% and 98.60% for average and global accuracy, respectively. The proposed method achieved outstanding outcomes as compared to the latest existing research works.

Cardiovascular assessment by imaging photoplethysmography - a review

Over the last few years, the contactless acquisition of cardiovascular parameters using cameras has gained immense attention. The technique provides an optical means to acquire cardiovascular information in a very convenient way. This review provides an overview on the technique's background and current realizations. Besides giving detailed information on the most widespread application of the technique, namely the contactless acquisition of heart rate, we outline further concepts and we critically discuss the current state.

Performance Evaluation of Time-Frequency Distributions for ECG Signal Analysis

The non-stationary and multi-frequency nature of biomedical signal activities makes the use of time-frequency distributions (TFDs) for analysis inevitable. Time-frequency analysis provides simultaneous interpretations in both time and frequency domain enabling comprehensive explanation, presentation and interpretation of electrocardiogram (ECG) signals. The diversity of TFDs and specific properties for each type show the need to determine the best TFD for ECG analysis. In this study, a performance evaluation of five TFDs in term of ECG abnormality detection is presented. The detection criteria based on extracted features from most important ECG signal components (QRS) to detect normal and abnormal cases. This is achieved by estimating its energy concentration magnitude using the TFDs. The TFDs analyse ECG signals in one-minute interval instead of conventional time domain approach that analyses based on beat or frame containing several beats. The MIT-BIH normal sinus rhythm ECG database total records of 18 long-term ECG sampled at 128 Hz have been analysed. The tested TFDs include Dual-Tree Wavelet Transform, Spectrogram, Pseudo Wigner-Ville, Choi-Williams, and Born-Jordan. Each record is divided into one-minute slots, which is not considered previously, and analysed. The sample periods (slots) are randomly selected ten minutes interval for each record. This result with 99.44% detection accuracy for 15,735 ECG beats shows that Choi-Williams distribution is most reliable to be used for heart problem detection especially in automated systems that provide continuous monitoring for long time duration.