Abstract Occlusion due to hair in dermoscopic images affects the diagnostic operation and the acc... more Abstract Occlusion due to hair in dermoscopic images affects the diagnostic operation and the accuracy of its analysis of a skin lesion. Also, dermis hair has the following different characteristics: thin; overlapping; faded; of similar contrast or colour to the underlying skin; and obscuring/covering textured lesions. These make digital hair removal (DHR), which involves hair segmentation and hair gap inpainting, a challenging task. Thus, traditional hard-coded threshold-based hair removal methods are not effective, resulting in over-removal which loses important information of the skin lesion, or under-removal which cannot remove the hair effectively. In this paper, we propose a deep learning approach to DHR based on U-Net and a free-form image inpainting architecture. In hair segmentation, a well-labelled dataset is created and used to train U-Net in order to obtain accurate hair masks. In inpainting, a free-form image inpainting architecture (i.e., Gated convolution and SN-PatchGAN) which has been trained on millions of images is used to inpaint any hair gaps. We also propose an evaluation method to analyze the effect of hair removal based on a single dermoscopic image, named intra structural similarity (Intra-SSIM). The process of DHR is repeated until there is no change in the average value of Intra-SSIM. Using the ISIC 2018 dataset, the performance of the proposed method is shown to be better than other state-of-the-art methods.
Sudden Cardiac Arrest (SCA) is a sudden loss of heart function often resulting from an electrical... more Sudden Cardiac Arrest (SCA) is a sudden loss of heart function often resulting from an electrical disturbance of the heart that disrupts the blood pumping function. This is mainly due to Ventricular Fibrillation (VF) or due to Ventricular Tachycardia (VT). Electrocardiogram (ECG) and Heart Rate Variability (HRV) signals are most commonly used to detect SCA before the VF onset. In the literature, researchers have proposed different markers to predict the SCA before the VF onset using ECG morphological features such as QRS complex, T Wave Alternas (TWA), and ST segment. This present work analyzed the new morphological feature called R–Tend wave (ECG wave from R peak to T wave end) for predicting SCA which is 5–9 min before VF onset. International standard MIT-BIH database (Sudden Cardiac Death (SCD) and Normal Sinus Rhythm (NSR)) is used to extract the three simple statistical features (mean, variance and median) from 1 min ECG sample which is 5–9 min before VF onset. The extracted features are statistically validated using one-way ANOVA and classified into SCA or non-SCA using two nonlinear classifiers [K Nearest Neighbor (KNN) and Support Vector Machine (SVM)]. Finally, the experimental results of R–Tend wave are compared with QRS complex features for benchmarking. The proposed R–Tend wave features predicted the SCA which is 5–9 min before the VF onset with a mean accuracy higher than 75%, However, QRS complex features gives higher classification rate than R–Tend wave features and achieved a maximum mean classification rate in predicting the SCA of 88.9, 88.9, 94.4, 86.1, 88.9% for 5, 6, 7, 8, and 9 min before the VF onset.
In this paper, we present a simple yet efficient method for determination of the relative permitt... more In this paper, we present a simple yet efficient method for determination of the relative permittivity of thin dielectric materials. An analysis that led to definition of the proper size and placement of a sample under test (SUT) on the surface of a microstrip ring resonator (MRR) was presented based on the full-wave simulations and measurements on benchmark materials. For completeness, the paper includes short descriptions of the design of an MRR and the variational method-based algorithm that processes the measured values. The efficiency of the proposed method is demonstrated on 12 SUT materials of different thicknesses and permittivity values, and the accuracy between 0% and 10% of the relative error was achieved for all SUTs thinner than 2 mm.
Infrared (IR) face recognition is getting wide attention with its increased number of application... more Infrared (IR) face recognition is getting wide attention with its increased number of applications as it provides numerous advantages over visual face recognition. As IR images are invariant to different illumination conditions they can provide robust thermal characteristics. The paper proposes a thermal IR based face recognition system using Zernike moments ZM and Multi Layer Perceptron Neural Network. The recognition experiment was performed using the images obtained from Terravic Facial IR Database with variations in poses (front, left and right) and environments (indoor/outdoor). The proposed method shows that the combination of magnitudes of ZM obtained from orders zero to two as feature vector provides the best average recognition accuracy of 89.5% and false acceptance rate of 0.356%.
Many methods have been developed to derive respiration signals from electrocardiograms (ECGs). Ho... more Many methods have been developed to derive respiration signals from electrocardiograms (ECGs). However, traditional methods have two main issues: (1) focusing on certain specific morphological characteristics and (2) not considering the nonlinear relationship between ECGs and respiration. In this paper, an improved ECG-derived respiration (EDR) based on empirical wavelet transform (EWT) and kernel principal component analysis (KPCA) is proposed. To tackle the first problem, EWT is introduced to decompose the ECG signal to extract the low-frequency part. To tackle the second issue, KPCA and preimaging are introduced to capture the nonlinear relationship between ECGs and respiration. The parameter selection of the radial basis function kernel in KPCA is also improved, ensuring accuracy and a reduction in computational cost. The correlation coefficient and amplitude square coherence coefficient are used as metrics to carry out quantitative and qualitative comparisons with three traditi...
One of the major health problems of global concern is Tuberculosis (TB). According to global repo... more One of the major health problems of global concern is Tuberculosis (TB). According to global report of the WHO, approximately 1.3 million people, out of the 8.6 million reported, died of TB in 2012. Most of the TB deaths can be prevented if it is detected at an early stage. Hindrance to this is improper diagnosis at initial stages. Chest X ray (CXR) image is the primary medical diagnosis used for identifying the lung diseases at the first stage. Interpreting the information from CXR depends upon the experience of the physician and the possibility of over and under diagnosis is very high. To identify the disease accurately a proper classification tool along with computer aided diagnosis should be used. Neural network can be used as a classifier tool for the same. Advancement in VLSI technology reduces the computational complexity of Artificial Neural Networks (ANN). Applications of neural networks to medical images (X-ray images of TB and lung cancer) during adolescent stages have re...
2017 IEEE International Conference on Real-time Computing and Robotics (RCAR), 2017
In this paper, we study various video stabilization techniques and develop an algorithm which can... more In this paper, we study various video stabilization techniques and develop an algorithm which can perform video stabilization under strict time constraints. To do this, an optimized version of block matching in a restricted search space is utilized to minimize the use of computational resources. We also develop an experimental setup to do real-time video stabilization under various vibrating conditions. In this study, we have also compared our algorithm with an existing stabilization algorithm and looked at how the two techniques perform under different circumstances.
Nipple is a vital landmark in the breast lesion diagnosis. Although there are advanced computer-a... more Nipple is a vital landmark in the breast lesion diagnosis. Although there are advanced computer-aided detection (CADe) systems for nipple detection in breast mediolateral oblique (MLO) views of mammogram images, few academic works address the coronal views of breast ultrasound (BUS) images. This paper addresses a novel CADe system to locate the Nipple Shadow Area (NSA) in ultrasound images. Here the Hu Moments and Gray-level Co-occurrence Matrix (GLCM) were calculated through an iterative sliding window for the extraction of shape and texture features. These features are then concatenated and fed into an Artificial Neural Network (ANN) to obtain probable NSA’s. Later, contour features, such as shape complexity through fractal dimension, edge distance from the periphery and contour area, were computed and passed into a Support Vector Machine (SVM) to identify the accurate NSA in each case. The coronal plane BUS dataset is built upon our own, which consists of 64 images from 13 patien...
Pneumonia is one of the foremost lung diseases and untreated pneumonia will lead to serious threa... more Pneumonia is one of the foremost lung diseases and untreated pneumonia will lead to serious threats for all age groups. The proposed work aims to extract and evaluate the Coronavirus disease (COVID-19) caused pneumonia infection in lung using CT scans. We propose an image-assisted system to extract COVID-19 infected sections from lung CT scans (coronal view). It includes following steps: (i) Threshold filter to extract the lung region by eliminating possible artifacts; (ii) Image enhancement using Harmony-Search-Optimization and Otsu thresholding; (iii) Image segmentation to extract infected region(s); and (iv) Region-of-interest (ROI) extraction (features) from binary image to compute level of severity. The features that are extracted from ROI are then employed to identify the pixel ratio between the lung and infection sections to identify infection level of severity. The primary objective of the tool is to assist the pulmonologist not only to detect but also to help plan treatment...
Computational and Mathematical Methods in Medicine, 2021
Cardiovascular disease (CVD) is the most common type of disease and has a high fatality rate in h... more Cardiovascular disease (CVD) is the most common type of disease and has a high fatality rate in humans. Early diagnosis is critical for the prognosis of CVD. Before using myocardial tissue strain, strain rate, and other indicators to evaluate and analyze cardiac function, accurate segmentation of the left ventricle (LV) endocardium is vital for ensuring the accuracy of subsequent diagnosis. For accurate segmentation of the LV endocardium, this paper proposes the extraction of the LV region features based on the YOLOv3 model to locate the positions of the apex and bottom of the LV, as well as that of the LV region; thereafter, the subimages of the LV can be obtained, and based on the Markov random field (MRF) model, preliminary identification and binarization of the myocardium of the LV subimages can be realized. Finally, under the constraints of the three aforementioned positions of the LV, precise segmentation and extraction of the LV endocardium can be achieved using nonlinear lea...
Localization techniques involve estimating the robot’s pose and uncertainty with respect to a wor... more Localization techniques involve estimating the robot’s pose and uncertainty with respect to a world map by making use of sensors available on the robotic platform being used. Using the camera as a sensor involves preprocessing images to get range and bearing measurements of landmarks visible in the image with respect to the local frame of the camera. In this paper we explore template matching, phase correlation and contour based marker detection methods as preprocessors for landmark extraction for the localization problem. We compare performance of the three methods by embedding them in a Kalman filter framework running on a simulated quadrotor in V-REP.
Breast ultrasound examination is a routine, fast, and safe method for clinical diagnosis of breas... more Breast ultrasound examination is a routine, fast, and safe method for clinical diagnosis of breast tumors. In this paper, a classification method based on multi-features and support vector machines was proposed for breast tumor diagnosis. Multi-features are composed of characteristic features and deep learning features of breast tumor images. Initially, an improved level set algorithm was used to segment the lesion in breast ultrasound images, which provided an accurate calculation of characteristic features, such as orientation, edge indistinctness, characteristics of posterior shadowing region, and shape complexity. Simultaneously, we used transfer learning to construct a pretrained model as a feature extractor to extract the deep learning features of breast ultrasound images. Finally, the multi-features were fused and fed to support vector machine for the further classification of breast ultrasound images. The proposed model, when tested on unknown samples, provided a classificat...
The pandemic of Coronavirus Disease-19 (COVID-19) has spread around the world, causing an existen... more The pandemic of Coronavirus Disease-19 (COVID-19) has spread around the world, causing an existential health crisis. Automated detection of COVID-19 infections in the lungs from Computed Tomography (CT) images offers huge potential in tackling the problem of slow detection and augments the conventional diagnostic procedures. However, segmenting COVID-19 from CT Scans is problematic, due to high variations in the types of infections and low contrast between healthy and infected tissues. While segmenting Lung CT Scans for COVID-19, fast and accurate results are required and furthermore, due to the pandemic, most of the research community has opted for various cloud based servers such as Google Colab, etc. to develop their algorithms. High accuracy can be achieved using Deep Networks but the prediction time would vary as the resources are shared amongst many thus requiring the need to compare different lightweight segmentation model. To address this issue, we aim to analyze the segment...
People can get consistent Automated Breast Ultrasound (ABUS) images due to the imaging mechanism ... more People can get consistent Automated Breast Ultrasound (ABUS) images due to the imaging mechanism of scanning. Therefore, it has unique advantages in breast tumor classification using artificial intelligence technology. This paper proposes a method for classifying benign and malignant breast tumors using ABUS sequence based on deep learning. First, Images of Interest (IOI) will be extracted and Region of Interest (ROI) will be cropped in ABUS sequence by two preprocessing deep learning models, Extracting-IOI model and Cropping-ROI model. Then, we propose a Shallowly Dilated Convolutional Branch Network (SDCB-Net). We combine this network with the VGG16 transfer learning network to construct a brand-new Shared Extracting Feature Network (SEF-Net) to extract ROI sequence features. Finally, the correlation features of ABUS images are extracted and integrated by using GRU Classified Network (GRUC-Net) to achieve the accurate breast tumors classification. The final results show that the accuracy of the test set for classifying benign and malignant ABUS sequence is 92.86 %. This method not only has high accuracy but also greatly improves the speed and efficiency of breast tumor classification. It has high clinical application significance that more women can discover breast tumors timely.
International Journal of Imaging Systems and Technology
The novel coronavirus disease (SARS‐CoV‐2 or COVID‐19) is spreading across the world and is affec... more The novel coronavirus disease (SARS‐CoV‐2 or COVID‐19) is spreading across the world and is affecting public health and the world economy. Artificial Intelligence (AI) can play a key role in enhancing COVID‐19 detection. However, lung infection by COVID‐19 is not quantifiable due to a lack of studies and the difficulty involved in the collection of large datasets. Segmentation is a preferred technique to quantify and contour the COVID‐19 region on the lungs using computed tomography (CT) scan images. To address the dataset problem, we propose a deep neural network (DNN) model trained on a limited dataset where features are selected using a region‐specific approach. Specifically, we apply the Zernike moment (ZM) and gray level co‐occurrence matrix (GLCM) to extract the unique shape and texture features. The feature vectors computed from these techniques enable segmentation that illustrates the severity of the COVID‐19 infection. The proposed algorithm was compared with other existing state‐of‐the‐art deep neural networks using the Radiopedia and COVID‐19 CT Segmentation datasets presented specificity, sensitivity, sensitivity, mean absolute error (MAE), enhance‐alignment measure (EMφ), and structure measure (Sm) of 0.942, 0.701, 0.082, 0.867, and 0.783, respectively. The metrics demonstrate the performance of the model in quantifying the COVID‐19 infection with limited datasets.
Handbook of Research on Deep Learning-Based Image Analysis Under Constrained and Unconstrained Environments
Early prediction of cancer type has become very crucial. Breast cancer is common to women and it ... more Early prediction of cancer type has become very crucial. Breast cancer is common to women and it leads to life threatening. Several imaging techniques have been suggested for timely detection and treatment of breast cancer. More research findings have been done to accurately detect the breast cancer. Automated whole breast ultrasound (AWBUS) is a new breast imaging technology that can render the entire breast anatomy in 3-D volume. The tissue layers in the breast are segmented and the type of lesion in the breast tissue can be identified which is essential for cancer detection. In this chapter, a u-net convolutional neural network architecture is used to implement the segmentation of breast tissues from AWBUS images into the different layers, that is, epidermis, subcutaneous, and muscular layer. The architecture was trained and tested with the AWBUS dataset images. The performance of the proposed scheme was based on accuracy, loss and the F1 score of the neural network that was calc...
Handbook of Research on Deep Learning-Based Image Analysis Under Constrained and Unconstrained Environments
Color fundus image is the most basic way to diagnose diabetic retinopathy, papillary edema, and g... more Color fundus image is the most basic way to diagnose diabetic retinopathy, papillary edema, and glaucoma. In particular, since observing the morphological changes of the optic disc is conducive to the diagnosis of related diseases, accurate and effective positioning and segmentation of the optic disc is an important process. Optic disc segmentation algorithms are mainly based on template matching, deformable model and learning. According to the character that the shape of the optic disc is approximately circular, this proposed research work uses Kirsch operator to get the edge of the green channel fundus image through morphological operation, and then detects the optic disc by HOUGH circle transformation. In addition, supervised learning in machine learning is also applied in this chapter. First, the vascular mask is obtained by morphological operation for vascular erasure, and then the SVM classifier is segmented by HU moment invariant feature and gray level feature. The test resul...
Handbook of Research on Deep Learning-Based Image Analysis Under Constrained and Unconstrained Environments
Finding faces in the clutter scenes is a challenging task in automatic face recognition systems a... more Finding faces in the clutter scenes is a challenging task in automatic face recognition systems as facial images are subjected to changes in the illumination, facial expression, orientation, and occlusions. Also, in the cluttered scenes, faces are not completely visible and detecting them is essential as it is significant in surveillance applications to study the mood of the crowd. This chapter utilizes the deep learning methods to understand the cluttered scenes to find the faces and discriminate them into partial and full faces. The work proves that MTCNN used for detecting the faces and Zernike moments-based kernels employed in CNN for classifying the faces into partial and full takes advantage in delivering a notable performance as compared to the other techniques. Considering the limitation of recognition on partial face emotions, only the full faces are preserved, and further, the KDEF dataset is modified by MTCNN to detect only faces and classify them into four emotions. Patt...
Abstract Occlusion due to hair in dermoscopic images affects the diagnostic operation and the acc... more Abstract Occlusion due to hair in dermoscopic images affects the diagnostic operation and the accuracy of its analysis of a skin lesion. Also, dermis hair has the following different characteristics: thin; overlapping; faded; of similar contrast or colour to the underlying skin; and obscuring/covering textured lesions. These make digital hair removal (DHR), which involves hair segmentation and hair gap inpainting, a challenging task. Thus, traditional hard-coded threshold-based hair removal methods are not effective, resulting in over-removal which loses important information of the skin lesion, or under-removal which cannot remove the hair effectively. In this paper, we propose a deep learning approach to DHR based on U-Net and a free-form image inpainting architecture. In hair segmentation, a well-labelled dataset is created and used to train U-Net in order to obtain accurate hair masks. In inpainting, a free-form image inpainting architecture (i.e., Gated convolution and SN-PatchGAN) which has been trained on millions of images is used to inpaint any hair gaps. We also propose an evaluation method to analyze the effect of hair removal based on a single dermoscopic image, named intra structural similarity (Intra-SSIM). The process of DHR is repeated until there is no change in the average value of Intra-SSIM. Using the ISIC 2018 dataset, the performance of the proposed method is shown to be better than other state-of-the-art methods.
Sudden Cardiac Arrest (SCA) is a sudden loss of heart function often resulting from an electrical... more Sudden Cardiac Arrest (SCA) is a sudden loss of heart function often resulting from an electrical disturbance of the heart that disrupts the blood pumping function. This is mainly due to Ventricular Fibrillation (VF) or due to Ventricular Tachycardia (VT). Electrocardiogram (ECG) and Heart Rate Variability (HRV) signals are most commonly used to detect SCA before the VF onset. In the literature, researchers have proposed different markers to predict the SCA before the VF onset using ECG morphological features such as QRS complex, T Wave Alternas (TWA), and ST segment. This present work analyzed the new morphological feature called R–Tend wave (ECG wave from R peak to T wave end) for predicting SCA which is 5–9 min before VF onset. International standard MIT-BIH database (Sudden Cardiac Death (SCD) and Normal Sinus Rhythm (NSR)) is used to extract the three simple statistical features (mean, variance and median) from 1 min ECG sample which is 5–9 min before VF onset. The extracted features are statistically validated using one-way ANOVA and classified into SCA or non-SCA using two nonlinear classifiers [K Nearest Neighbor (KNN) and Support Vector Machine (SVM)]. Finally, the experimental results of R–Tend wave are compared with QRS complex features for benchmarking. The proposed R–Tend wave features predicted the SCA which is 5–9 min before the VF onset with a mean accuracy higher than 75%, However, QRS complex features gives higher classification rate than R–Tend wave features and achieved a maximum mean classification rate in predicting the SCA of 88.9, 88.9, 94.4, 86.1, 88.9% for 5, 6, 7, 8, and 9 min before the VF onset.
In this paper, we present a simple yet efficient method for determination of the relative permitt... more In this paper, we present a simple yet efficient method for determination of the relative permittivity of thin dielectric materials. An analysis that led to definition of the proper size and placement of a sample under test (SUT) on the surface of a microstrip ring resonator (MRR) was presented based on the full-wave simulations and measurements on benchmark materials. For completeness, the paper includes short descriptions of the design of an MRR and the variational method-based algorithm that processes the measured values. The efficiency of the proposed method is demonstrated on 12 SUT materials of different thicknesses and permittivity values, and the accuracy between 0% and 10% of the relative error was achieved for all SUTs thinner than 2 mm.
Infrared (IR) face recognition is getting wide attention with its increased number of application... more Infrared (IR) face recognition is getting wide attention with its increased number of applications as it provides numerous advantages over visual face recognition. As IR images are invariant to different illumination conditions they can provide robust thermal characteristics. The paper proposes a thermal IR based face recognition system using Zernike moments ZM and Multi Layer Perceptron Neural Network. The recognition experiment was performed using the images obtained from Terravic Facial IR Database with variations in poses (front, left and right) and environments (indoor/outdoor). The proposed method shows that the combination of magnitudes of ZM obtained from orders zero to two as feature vector provides the best average recognition accuracy of 89.5% and false acceptance rate of 0.356%.
Many methods have been developed to derive respiration signals from electrocardiograms (ECGs). Ho... more Many methods have been developed to derive respiration signals from electrocardiograms (ECGs). However, traditional methods have two main issues: (1) focusing on certain specific morphological characteristics and (2) not considering the nonlinear relationship between ECGs and respiration. In this paper, an improved ECG-derived respiration (EDR) based on empirical wavelet transform (EWT) and kernel principal component analysis (KPCA) is proposed. To tackle the first problem, EWT is introduced to decompose the ECG signal to extract the low-frequency part. To tackle the second issue, KPCA and preimaging are introduced to capture the nonlinear relationship between ECGs and respiration. The parameter selection of the radial basis function kernel in KPCA is also improved, ensuring accuracy and a reduction in computational cost. The correlation coefficient and amplitude square coherence coefficient are used as metrics to carry out quantitative and qualitative comparisons with three traditi...
One of the major health problems of global concern is Tuberculosis (TB). According to global repo... more One of the major health problems of global concern is Tuberculosis (TB). According to global report of the WHO, approximately 1.3 million people, out of the 8.6 million reported, died of TB in 2012. Most of the TB deaths can be prevented if it is detected at an early stage. Hindrance to this is improper diagnosis at initial stages. Chest X ray (CXR) image is the primary medical diagnosis used for identifying the lung diseases at the first stage. Interpreting the information from CXR depends upon the experience of the physician and the possibility of over and under diagnosis is very high. To identify the disease accurately a proper classification tool along with computer aided diagnosis should be used. Neural network can be used as a classifier tool for the same. Advancement in VLSI technology reduces the computational complexity of Artificial Neural Networks (ANN). Applications of neural networks to medical images (X-ray images of TB and lung cancer) during adolescent stages have re...
2017 IEEE International Conference on Real-time Computing and Robotics (RCAR), 2017
In this paper, we study various video stabilization techniques and develop an algorithm which can... more In this paper, we study various video stabilization techniques and develop an algorithm which can perform video stabilization under strict time constraints. To do this, an optimized version of block matching in a restricted search space is utilized to minimize the use of computational resources. We also develop an experimental setup to do real-time video stabilization under various vibrating conditions. In this study, we have also compared our algorithm with an existing stabilization algorithm and looked at how the two techniques perform under different circumstances.
Nipple is a vital landmark in the breast lesion diagnosis. Although there are advanced computer-a... more Nipple is a vital landmark in the breast lesion diagnosis. Although there are advanced computer-aided detection (CADe) systems for nipple detection in breast mediolateral oblique (MLO) views of mammogram images, few academic works address the coronal views of breast ultrasound (BUS) images. This paper addresses a novel CADe system to locate the Nipple Shadow Area (NSA) in ultrasound images. Here the Hu Moments and Gray-level Co-occurrence Matrix (GLCM) were calculated through an iterative sliding window for the extraction of shape and texture features. These features are then concatenated and fed into an Artificial Neural Network (ANN) to obtain probable NSA’s. Later, contour features, such as shape complexity through fractal dimension, edge distance from the periphery and contour area, were computed and passed into a Support Vector Machine (SVM) to identify the accurate NSA in each case. The coronal plane BUS dataset is built upon our own, which consists of 64 images from 13 patien...
Pneumonia is one of the foremost lung diseases and untreated pneumonia will lead to serious threa... more Pneumonia is one of the foremost lung diseases and untreated pneumonia will lead to serious threats for all age groups. The proposed work aims to extract and evaluate the Coronavirus disease (COVID-19) caused pneumonia infection in lung using CT scans. We propose an image-assisted system to extract COVID-19 infected sections from lung CT scans (coronal view). It includes following steps: (i) Threshold filter to extract the lung region by eliminating possible artifacts; (ii) Image enhancement using Harmony-Search-Optimization and Otsu thresholding; (iii) Image segmentation to extract infected region(s); and (iv) Region-of-interest (ROI) extraction (features) from binary image to compute level of severity. The features that are extracted from ROI are then employed to identify the pixel ratio between the lung and infection sections to identify infection level of severity. The primary objective of the tool is to assist the pulmonologist not only to detect but also to help plan treatment...
Computational and Mathematical Methods in Medicine, 2021
Cardiovascular disease (CVD) is the most common type of disease and has a high fatality rate in h... more Cardiovascular disease (CVD) is the most common type of disease and has a high fatality rate in humans. Early diagnosis is critical for the prognosis of CVD. Before using myocardial tissue strain, strain rate, and other indicators to evaluate and analyze cardiac function, accurate segmentation of the left ventricle (LV) endocardium is vital for ensuring the accuracy of subsequent diagnosis. For accurate segmentation of the LV endocardium, this paper proposes the extraction of the LV region features based on the YOLOv3 model to locate the positions of the apex and bottom of the LV, as well as that of the LV region; thereafter, the subimages of the LV can be obtained, and based on the Markov random field (MRF) model, preliminary identification and binarization of the myocardium of the LV subimages can be realized. Finally, under the constraints of the three aforementioned positions of the LV, precise segmentation and extraction of the LV endocardium can be achieved using nonlinear lea...
Localization techniques involve estimating the robot’s pose and uncertainty with respect to a wor... more Localization techniques involve estimating the robot’s pose and uncertainty with respect to a world map by making use of sensors available on the robotic platform being used. Using the camera as a sensor involves preprocessing images to get range and bearing measurements of landmarks visible in the image with respect to the local frame of the camera. In this paper we explore template matching, phase correlation and contour based marker detection methods as preprocessors for landmark extraction for the localization problem. We compare performance of the three methods by embedding them in a Kalman filter framework running on a simulated quadrotor in V-REP.
Breast ultrasound examination is a routine, fast, and safe method for clinical diagnosis of breas... more Breast ultrasound examination is a routine, fast, and safe method for clinical diagnosis of breast tumors. In this paper, a classification method based on multi-features and support vector machines was proposed for breast tumor diagnosis. Multi-features are composed of characteristic features and deep learning features of breast tumor images. Initially, an improved level set algorithm was used to segment the lesion in breast ultrasound images, which provided an accurate calculation of characteristic features, such as orientation, edge indistinctness, characteristics of posterior shadowing region, and shape complexity. Simultaneously, we used transfer learning to construct a pretrained model as a feature extractor to extract the deep learning features of breast ultrasound images. Finally, the multi-features were fused and fed to support vector machine for the further classification of breast ultrasound images. The proposed model, when tested on unknown samples, provided a classificat...
The pandemic of Coronavirus Disease-19 (COVID-19) has spread around the world, causing an existen... more The pandemic of Coronavirus Disease-19 (COVID-19) has spread around the world, causing an existential health crisis. Automated detection of COVID-19 infections in the lungs from Computed Tomography (CT) images offers huge potential in tackling the problem of slow detection and augments the conventional diagnostic procedures. However, segmenting COVID-19 from CT Scans is problematic, due to high variations in the types of infections and low contrast between healthy and infected tissues. While segmenting Lung CT Scans for COVID-19, fast and accurate results are required and furthermore, due to the pandemic, most of the research community has opted for various cloud based servers such as Google Colab, etc. to develop their algorithms. High accuracy can be achieved using Deep Networks but the prediction time would vary as the resources are shared amongst many thus requiring the need to compare different lightweight segmentation model. To address this issue, we aim to analyze the segment...
People can get consistent Automated Breast Ultrasound (ABUS) images due to the imaging mechanism ... more People can get consistent Automated Breast Ultrasound (ABUS) images due to the imaging mechanism of scanning. Therefore, it has unique advantages in breast tumor classification using artificial intelligence technology. This paper proposes a method for classifying benign and malignant breast tumors using ABUS sequence based on deep learning. First, Images of Interest (IOI) will be extracted and Region of Interest (ROI) will be cropped in ABUS sequence by two preprocessing deep learning models, Extracting-IOI model and Cropping-ROI model. Then, we propose a Shallowly Dilated Convolutional Branch Network (SDCB-Net). We combine this network with the VGG16 transfer learning network to construct a brand-new Shared Extracting Feature Network (SEF-Net) to extract ROI sequence features. Finally, the correlation features of ABUS images are extracted and integrated by using GRU Classified Network (GRUC-Net) to achieve the accurate breast tumors classification. The final results show that the accuracy of the test set for classifying benign and malignant ABUS sequence is 92.86 %. This method not only has high accuracy but also greatly improves the speed and efficiency of breast tumor classification. It has high clinical application significance that more women can discover breast tumors timely.
International Journal of Imaging Systems and Technology
The novel coronavirus disease (SARS‐CoV‐2 or COVID‐19) is spreading across the world and is affec... more The novel coronavirus disease (SARS‐CoV‐2 or COVID‐19) is spreading across the world and is affecting public health and the world economy. Artificial Intelligence (AI) can play a key role in enhancing COVID‐19 detection. However, lung infection by COVID‐19 is not quantifiable due to a lack of studies and the difficulty involved in the collection of large datasets. Segmentation is a preferred technique to quantify and contour the COVID‐19 region on the lungs using computed tomography (CT) scan images. To address the dataset problem, we propose a deep neural network (DNN) model trained on a limited dataset where features are selected using a region‐specific approach. Specifically, we apply the Zernike moment (ZM) and gray level co‐occurrence matrix (GLCM) to extract the unique shape and texture features. The feature vectors computed from these techniques enable segmentation that illustrates the severity of the COVID‐19 infection. The proposed algorithm was compared with other existing state‐of‐the‐art deep neural networks using the Radiopedia and COVID‐19 CT Segmentation datasets presented specificity, sensitivity, sensitivity, mean absolute error (MAE), enhance‐alignment measure (EMφ), and structure measure (Sm) of 0.942, 0.701, 0.082, 0.867, and 0.783, respectively. The metrics demonstrate the performance of the model in quantifying the COVID‐19 infection with limited datasets.
Handbook of Research on Deep Learning-Based Image Analysis Under Constrained and Unconstrained Environments
Early prediction of cancer type has become very crucial. Breast cancer is common to women and it ... more Early prediction of cancer type has become very crucial. Breast cancer is common to women and it leads to life threatening. Several imaging techniques have been suggested for timely detection and treatment of breast cancer. More research findings have been done to accurately detect the breast cancer. Automated whole breast ultrasound (AWBUS) is a new breast imaging technology that can render the entire breast anatomy in 3-D volume. The tissue layers in the breast are segmented and the type of lesion in the breast tissue can be identified which is essential for cancer detection. In this chapter, a u-net convolutional neural network architecture is used to implement the segmentation of breast tissues from AWBUS images into the different layers, that is, epidermis, subcutaneous, and muscular layer. The architecture was trained and tested with the AWBUS dataset images. The performance of the proposed scheme was based on accuracy, loss and the F1 score of the neural network that was calc...
Handbook of Research on Deep Learning-Based Image Analysis Under Constrained and Unconstrained Environments
Color fundus image is the most basic way to diagnose diabetic retinopathy, papillary edema, and g... more Color fundus image is the most basic way to diagnose diabetic retinopathy, papillary edema, and glaucoma. In particular, since observing the morphological changes of the optic disc is conducive to the diagnosis of related diseases, accurate and effective positioning and segmentation of the optic disc is an important process. Optic disc segmentation algorithms are mainly based on template matching, deformable model and learning. According to the character that the shape of the optic disc is approximately circular, this proposed research work uses Kirsch operator to get the edge of the green channel fundus image through morphological operation, and then detects the optic disc by HOUGH circle transformation. In addition, supervised learning in machine learning is also applied in this chapter. First, the vascular mask is obtained by morphological operation for vascular erasure, and then the SVM classifier is segmented by HU moment invariant feature and gray level feature. The test resul...
Handbook of Research on Deep Learning-Based Image Analysis Under Constrained and Unconstrained Environments
Finding faces in the clutter scenes is a challenging task in automatic face recognition systems a... more Finding faces in the clutter scenes is a challenging task in automatic face recognition systems as facial images are subjected to changes in the illumination, facial expression, orientation, and occlusions. Also, in the cluttered scenes, faces are not completely visible and detecting them is essential as it is significant in surveillance applications to study the mood of the crowd. This chapter utilizes the deep learning methods to understand the cluttered scenes to find the faces and discriminate them into partial and full faces. The work proves that MTCNN used for detecting the faces and Zernike moments-based kernels employed in CNN for classifying the faces into partial and full takes advantage in delivering a notable performance as compared to the other techniques. Considering the limitation of recognition on partial face emotions, only the full faces are preserved, and further, the KDEF dataset is modified by MTCNN to detect only faces and classify them into four emotions. Patt...
Uploads