Hamed Hamid Muhammed | KTH Royal Institute of Technology (original) (raw)
Papers by Hamed Hamid Muhammed
Segmenting hyperspectral images is an important task for simplifying the analysis of the data by ... more Segmenting hyperspectral images is an important task for simplifying the analysis of the data by focusing on a certain part of the data set or on data samples of the same or at least "nearby" spectral properties. A new class of neuro-fuzzy systems, based on so-called weighted incremental neural networks (WINN), is briefly introduced, exemplified and finally used for unsupervised
WSEAS Transactions on Signal Processing archive, 2014
One of the challenging and important problems that still needs solution within the field of denta... more One of the challenging and important problems that still needs solution within the field of dental implant surgery is to monitor the osseointegration process. Therefore, this work aims to achieve a reliable noninvasive automatic method to evaluate dental implant stability which is directly related to the grade of osseointegration. For this purpose, an experimental phantom study was performed to simulate this process and evaluate it. Ultrasonic spectrometry was proposed and used to take measurements that were processed and analyzed to estimate the stability of the simulated dental implant. The phantom that was designed and used in the experiments simulated a jawbone with a dental implant and was made of a little pool filled with soft-tissueequivalent material (with respect to ultrasound waves) and a solid cylinder of fresh oak-wood immersed into it to simulate the jawbone. A metal screw was used to simulate the dental implant. By screwing this screw into or out of the wooden cylinder, varying grades of stiffness and contact between the screw and the wooden tissues were obtained. And by this way, varying screw stability grades which simulate varying osseointegration grades were achieved. Pulse-echo ultrasound was used to measure the power spectra of the received ultrasonic echosignals. These power spectra were, at first, processed and normalized then analyzed by using the partial least squares method to estimate the corresponding implant stability or stiffness grades. The number of screwing turns (for the screw into or out of the wooden cylinder) was used as a measure of stiffness grade.The feasibility of this approach was investigated through experimental tasks and promising results were achieved. A coefficient of determination R 2 of 96.4% and a mean absolute error of ±0.23 screwing turns were achieved when comparing real and estimated stiffness-grade values, indicating the high efficiency and good accuracy of this approach.
Gait analysis is the methodic measurement, description and evaluation of factors that affect huma... more Gait analysis is the methodic measurement, description and evaluation of factors that affect human locomotion. It can be used for rehabilitation purposes, for optimizing sport results and lower risks of injury and as a diagnostic tool for neurological diseases, example given Parkinson. Hitherto, there are many precise methods of doing gait analysis. However, expensive equipment is often required, otherwise the only option is visual analysis, which is less reliable. This study will construct an inexpensive method to analyze gait, that is both reliable and portable. One laser was attached to each shoulder and two on a helmet put on the subjects’ heads. The lasers formed a formation of laser dots on the ceiling. The test subjects walked on a treadmill, which caused the laser dots to move. These were recorded with a camera. The video sequences were then analyzed with a program written in Matlab. The results showed the laser movement, as intended. By analysing the laser movement in different walking conditions, for example with different shoes, it was shown in this study that they differed and the method could be useful to compare gait. However, further research needs to be undertaken in order to confirm these findings. Introduction Biomechanics is an increasingly well-known field of research, which takes a mechanical approach to the human body. As a combination between mechanics and biology, it can help increase our knowledge in orthopaedics and ergonomics, but also in other areas such as rehabilitation and sports [4, 5, 7]. An important sub-field of biomechanics is gait analysis which is the methodical measurement, description and evaluation of factors that affect human locomotion [1, 6]. The invention of the camera made it possible to investigate human bipedal locomotion more accurately. However, this early technique required the pictures to be analyzed frame by frame, which was ineffecient and time-consuming. As technology developed and computers enabled faster analysis, gait analysis became more efficient [2, 6]. Using clinical gait analysis, joint disabilities and some neurological diseases like Parkinson can be discovered and evaluated in an early stage [2, 4, 6]. Gait analysis can also be used to identify individuals, for example, in recorded security footage after a crime scene. This identifying type of gait analysis is called biometric gait analysis [4, 9]. A common method in motion analysis is tracking. There are many forms of tracking, where the common denominator is video analysis. Tracking is often divided into three steps when analysing videos. First, the moving objects of interest are detected, then these are tracked one frame at a time, and at last these tracks get analyzed to identify their behaviour or inconsistent movements [8]. Tracking is a useful tool when analysing gait, since gait is a complex motion needed to be investigated, divided into as small parts as possible. Hitherto, there are many precise methods of gait analysis. The problem with these are that they are either too expensive and need special laboratories for analysis, which results in both economical and practical disadvantages, or inexpensive, but based on only visual analysis and therefore are more unreliable [3, 5, 6]. In this study, a new, less expensive and
Attribution License, which permits unrestricted use, distribution, and reproduction in any medium... more Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. A novel method for characterizing and visualizing the progression of waves along the walls of the carotid artery is presented. The new approach is noninvasive and able to simultaneously capture the spatial and the temporal propagation of wavy patterns along the walls of the carotid artery in a completely automatedmanner. Spatiotemporal and spatiospectral 2Dmaps describing these patterns (in both the spatial and the frequency domains, resp.) were generated and analyzed by visual inspection as well as automatic feature extraction and classification. Three categories of cases were considered: pathological elderly, healthy elderly, and healthy young cases. Automatic differentiation, between cases of these three categories, was achieved with a sensitivity of 97.1 % and a specificity of 74.5%. Two features were proposed and computed to measure th...
The most serious limitation of conventional multi- and hyperspectral imagery systems is the need ... more The most serious limitation of conventional multi- and hyperspectral imagery systems is the need for scanning time to be able to acquire the whole image cube, which contains huge amount of data needing large memory-capacity and giving rise to another serious limitation of these systems. In this work, a novel cost-effective technique, that solves the problems mentioned above, is presented. The system has no moving parts and the whole multi- or hyperspectral image cube is acquired instantaneously, making it ready to record multi- and hyperspectral digital video.
Jiliang Xuebao/Acta Metrologica Sinica, 2017
Several techniques have been introduced for detecting, measuring, processing and analyzing the si... more Several techniques have been introduced for detecting, measuring, processing and analyzing the signals generated during muscular activities. With the development of more advanced technical solutions, the measurement and analysis of these signals help not only to understand the medical abnormalities and characterization of muscle activities but also to develop human machine interfaces of higher efficiency. In this work, a novel technique to detect and measure the displacement caused on the surface of the skin due to muscle activities was introduced and developed using near-infrared photoelectric sensors. The new technique was coined as OptoMyoGraphy (OMG). In order to evaluate the new technique, real-time pairs of signals were registered using two photoelectric sensors measuring near-infrared rays reflected on the forearm while moving the hand to make a number of different gestures. Different pairs of signals, changing over time and showing repeated patterns while repeating the same ...
2016 1st International Conference on Biomedical Engineering (IBIOMED), 2016
In Positron Emission Tomography (PET), image quality is highly degraded by noise. Therefore, two ... more In Positron Emission Tomography (PET), image quality is highly degraded by noise. Therefore, two main PETimage denoising approaches can be used: pre- and postreconstruction denoising. In the pre-reconstruction approach the PET sinogram is denoised before forwarding it to the image reconstruction algorithm. On the other hand, the reconstructed PET-image is denoised in the post-reconstruction approach. In this study, comparison of image quality of the resulting images of the pre- and post-reconstruction approaches is performed. In both types of approaches, the Gaussian filter, the Non-Local Means filter (NLM), the Block-Matching and 3D filter (BM3D), the K-Nearest Neighbors Filter (KNN) and the Patch Confidence K-Nearest Neighbors Filter (PCkNN) are utilized. These approaches are evaluated on a simulated PET-phantom dataset, a real-life physical thorax-phantom PET dataset as well as a reallife MicroPET-scan dataset of a mouse. The performance is measured using the Signal-to-Noise Ratio (SNR) in addition to the Contrast-to-Noise Ratio (CNR) in the resulting images.
Den har studien visar att det ar mojligt att detektera tydliga temperaturskillnader mellan cancer... more Den har studien visar att det ar mojligt att detektera tydliga temperaturskillnader mellan cancervavnad och frisk vavnad. Detta kan vara ett resultat av bade angiogenes (processen som leder till ny ...
Jiliang Xuebao/Acta Metrologica Sinica, 2017
Several techniques have been introduced for detecting, measuring, processing and analyzing the si... more Several techniques have been introduced for detecting, measuring, processing and analyzing the signals generated during muscular activities. With the development of more advanced technical solutions, the measurement and analysis of these signals help not only to understand the medical abnormalities and characterization of muscle activities but also to develop human machine interfaces of higher efficiency. In this work, a novel technique to detect and measure the displacement caused on the surface of the skin due to muscle activities was introduced and developed using near-infrared photoelectric sensors. The new technique was coined as OptoMyoGraphy (OMG). In order to evaluate the new technique, real-time pairs of signals were registered using two photoelectric sensors measuring near-infrared rays reflected on the forearm while moving the hand to make a number of different gestures. Different pairs of signals, changing over time and showing repeated patterns while repeating the same ...
2016 1st International Conference on Biomedical Engineering (IBIOMED), 2016
In Positron Emission Tomography (PET), image quality is highly degraded by noise. Therefore, two ... more In Positron Emission Tomography (PET), image quality is highly degraded by noise. Therefore, two main PETimage denoising approaches can be used: pre- and postreconstruction denoising. In the pre-reconstruction approach the PET sinogram is denoised before forwarding it to the image reconstruction algorithm. On the other hand, the reconstructed PET-image is denoised in the post-reconstruction approach. In this study, comparison of image quality of the resulting images of the pre- and post-reconstruction approaches is performed. In both types of approaches, the Gaussian filter, the Non-Local Means filter (NLM), the Block-Matching and 3D filter (BM3D), the K-Nearest Neighbors Filter (KNN) and the Patch Confidence K-Nearest Neighbors Filter (PCkNN) are utilized. These approaches are evaluated on a simulated PET-phantom dataset, a real-life physical thorax-phantom PET dataset as well as a reallife MicroPET-scan dataset of a mouse. The performance is measured using the Signal-to-Noise Ratio (SNR) in addition to the Contrast-to-Noise Ratio (CNR) in the resulting images.
Den har studien visar att det ar mojligt att detektera tydliga temperaturskillnader mellan cancer... more Den har studien visar att det ar mojligt att detektera tydliga temperaturskillnader mellan cancervavnad och frisk vavnad. Detta kan vara ett resultat av bade angiogenes (processen som leder till ny ...
Wseas Transactions on Biology and Biomedicine, 2014
A novel automated method for the classification of the physiological condition of the carotid art... more A novel automated method for the classification of the physiological condition of the carotid artery in 2D ultrasound image sequences is introduced. Unsupervised clustering was applied for the segmentation process in which both spatial and temporal information was utilized. Radial distension is then measured in the inner surface of the vessel wall, and this characteristic signal is extracted to reveal the detailed radial motion of the variable inner part of the vessel wall that is in contact with flowing blood. Characteristic differences in this time signal were noticed among healthy young, healthy elderly and pathological elderly cases. The discrete Fourier transform of the radial distension signal is then computed, and the area subtended by the transform is calculated and utilized as a diagnostic feature. The method was tested successfully and could differentiate among the categories of patients mentioned above. Therefore, this computer-aided method would significantly simplify the task of medical specialists in detecting any defects in the carotid artery and thereby in detecting early cardiovascular symptoms. The significance of the proposed method is that it is intuitive, semi-automatic, reproducible, and significantly reduces the reliance upon subjective measures.
Segmenting hyperspectral images is an important task for simplifying the analysis of the data by ... more Segmenting hyperspectral images is an important task for simplifying the analysis of the data by focusing on a certain part of the data set or on data samples of the same or at least "nearby" spectral properties. A new class of neuro-fuzzy systems, based on so-called weighted incremental neural networks (WINN), is briefly introduced, exemplified and finally used for unsupervised
WSEAS Transactions on Signal Processing archive, 2014
One of the challenging and important problems that still needs solution within the field of denta... more One of the challenging and important problems that still needs solution within the field of dental implant surgery is to monitor the osseointegration process. Therefore, this work aims to achieve a reliable noninvasive automatic method to evaluate dental implant stability which is directly related to the grade of osseointegration. For this purpose, an experimental phantom study was performed to simulate this process and evaluate it. Ultrasonic spectrometry was proposed and used to take measurements that were processed and analyzed to estimate the stability of the simulated dental implant. The phantom that was designed and used in the experiments simulated a jawbone with a dental implant and was made of a little pool filled with soft-tissueequivalent material (with respect to ultrasound waves) and a solid cylinder of fresh oak-wood immersed into it to simulate the jawbone. A metal screw was used to simulate the dental implant. By screwing this screw into or out of the wooden cylinder, varying grades of stiffness and contact between the screw and the wooden tissues were obtained. And by this way, varying screw stability grades which simulate varying osseointegration grades were achieved. Pulse-echo ultrasound was used to measure the power spectra of the received ultrasonic echosignals. These power spectra were, at first, processed and normalized then analyzed by using the partial least squares method to estimate the corresponding implant stability or stiffness grades. The number of screwing turns (for the screw into or out of the wooden cylinder) was used as a measure of stiffness grade.The feasibility of this approach was investigated through experimental tasks and promising results were achieved. A coefficient of determination R 2 of 96.4% and a mean absolute error of ±0.23 screwing turns were achieved when comparing real and estimated stiffness-grade values, indicating the high efficiency and good accuracy of this approach.
Gait analysis is the methodic measurement, description and evaluation of factors that affect huma... more Gait analysis is the methodic measurement, description and evaluation of factors that affect human locomotion. It can be used for rehabilitation purposes, for optimizing sport results and lower risks of injury and as a diagnostic tool for neurological diseases, example given Parkinson. Hitherto, there are many precise methods of doing gait analysis. However, expensive equipment is often required, otherwise the only option is visual analysis, which is less reliable. This study will construct an inexpensive method to analyze gait, that is both reliable and portable. One laser was attached to each shoulder and two on a helmet put on the subjects’ heads. The lasers formed a formation of laser dots on the ceiling. The test subjects walked on a treadmill, which caused the laser dots to move. These were recorded with a camera. The video sequences were then analyzed with a program written in Matlab. The results showed the laser movement, as intended. By analysing the laser movement in different walking conditions, for example with different shoes, it was shown in this study that they differed and the method could be useful to compare gait. However, further research needs to be undertaken in order to confirm these findings. Introduction Biomechanics is an increasingly well-known field of research, which takes a mechanical approach to the human body. As a combination between mechanics and biology, it can help increase our knowledge in orthopaedics and ergonomics, but also in other areas such as rehabilitation and sports [4, 5, 7]. An important sub-field of biomechanics is gait analysis which is the methodical measurement, description and evaluation of factors that affect human locomotion [1, 6]. The invention of the camera made it possible to investigate human bipedal locomotion more accurately. However, this early technique required the pictures to be analyzed frame by frame, which was ineffecient and time-consuming. As technology developed and computers enabled faster analysis, gait analysis became more efficient [2, 6]. Using clinical gait analysis, joint disabilities and some neurological diseases like Parkinson can be discovered and evaluated in an early stage [2, 4, 6]. Gait analysis can also be used to identify individuals, for example, in recorded security footage after a crime scene. This identifying type of gait analysis is called biometric gait analysis [4, 9]. A common method in motion analysis is tracking. There are many forms of tracking, where the common denominator is video analysis. Tracking is often divided into three steps when analysing videos. First, the moving objects of interest are detected, then these are tracked one frame at a time, and at last these tracks get analyzed to identify their behaviour or inconsistent movements [8]. Tracking is a useful tool when analysing gait, since gait is a complex motion needed to be investigated, divided into as small parts as possible. Hitherto, there are many precise methods of gait analysis. The problem with these are that they are either too expensive and need special laboratories for analysis, which results in both economical and practical disadvantages, or inexpensive, but based on only visual analysis and therefore are more unreliable [3, 5, 6]. In this study, a new, less expensive and
Attribution License, which permits unrestricted use, distribution, and reproduction in any medium... more Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. A novel method for characterizing and visualizing the progression of waves along the walls of the carotid artery is presented. The new approach is noninvasive and able to simultaneously capture the spatial and the temporal propagation of wavy patterns along the walls of the carotid artery in a completely automatedmanner. Spatiotemporal and spatiospectral 2Dmaps describing these patterns (in both the spatial and the frequency domains, resp.) were generated and analyzed by visual inspection as well as automatic feature extraction and classification. Three categories of cases were considered: pathological elderly, healthy elderly, and healthy young cases. Automatic differentiation, between cases of these three categories, was achieved with a sensitivity of 97.1 % and a specificity of 74.5%. Two features were proposed and computed to measure th...
The most serious limitation of conventional multi- and hyperspectral imagery systems is the need ... more The most serious limitation of conventional multi- and hyperspectral imagery systems is the need for scanning time to be able to acquire the whole image cube, which contains huge amount of data needing large memory-capacity and giving rise to another serious limitation of these systems. In this work, a novel cost-effective technique, that solves the problems mentioned above, is presented. The system has no moving parts and the whole multi- or hyperspectral image cube is acquired instantaneously, making it ready to record multi- and hyperspectral digital video.
Jiliang Xuebao/Acta Metrologica Sinica, 2017
Several techniques have been introduced for detecting, measuring, processing and analyzing the si... more Several techniques have been introduced for detecting, measuring, processing and analyzing the signals generated during muscular activities. With the development of more advanced technical solutions, the measurement and analysis of these signals help not only to understand the medical abnormalities and characterization of muscle activities but also to develop human machine interfaces of higher efficiency. In this work, a novel technique to detect and measure the displacement caused on the surface of the skin due to muscle activities was introduced and developed using near-infrared photoelectric sensors. The new technique was coined as OptoMyoGraphy (OMG). In order to evaluate the new technique, real-time pairs of signals were registered using two photoelectric sensors measuring near-infrared rays reflected on the forearm while moving the hand to make a number of different gestures. Different pairs of signals, changing over time and showing repeated patterns while repeating the same ...
2016 1st International Conference on Biomedical Engineering (IBIOMED), 2016
In Positron Emission Tomography (PET), image quality is highly degraded by noise. Therefore, two ... more In Positron Emission Tomography (PET), image quality is highly degraded by noise. Therefore, two main PETimage denoising approaches can be used: pre- and postreconstruction denoising. In the pre-reconstruction approach the PET sinogram is denoised before forwarding it to the image reconstruction algorithm. On the other hand, the reconstructed PET-image is denoised in the post-reconstruction approach. In this study, comparison of image quality of the resulting images of the pre- and post-reconstruction approaches is performed. In both types of approaches, the Gaussian filter, the Non-Local Means filter (NLM), the Block-Matching and 3D filter (BM3D), the K-Nearest Neighbors Filter (KNN) and the Patch Confidence K-Nearest Neighbors Filter (PCkNN) are utilized. These approaches are evaluated on a simulated PET-phantom dataset, a real-life physical thorax-phantom PET dataset as well as a reallife MicroPET-scan dataset of a mouse. The performance is measured using the Signal-to-Noise Ratio (SNR) in addition to the Contrast-to-Noise Ratio (CNR) in the resulting images.
Den har studien visar att det ar mojligt att detektera tydliga temperaturskillnader mellan cancer... more Den har studien visar att det ar mojligt att detektera tydliga temperaturskillnader mellan cancervavnad och frisk vavnad. Detta kan vara ett resultat av bade angiogenes (processen som leder till ny ...
Jiliang Xuebao/Acta Metrologica Sinica, 2017
Several techniques have been introduced for detecting, measuring, processing and analyzing the si... more Several techniques have been introduced for detecting, measuring, processing and analyzing the signals generated during muscular activities. With the development of more advanced technical solutions, the measurement and analysis of these signals help not only to understand the medical abnormalities and characterization of muscle activities but also to develop human machine interfaces of higher efficiency. In this work, a novel technique to detect and measure the displacement caused on the surface of the skin due to muscle activities was introduced and developed using near-infrared photoelectric sensors. The new technique was coined as OptoMyoGraphy (OMG). In order to evaluate the new technique, real-time pairs of signals were registered using two photoelectric sensors measuring near-infrared rays reflected on the forearm while moving the hand to make a number of different gestures. Different pairs of signals, changing over time and showing repeated patterns while repeating the same ...
2016 1st International Conference on Biomedical Engineering (IBIOMED), 2016
In Positron Emission Tomography (PET), image quality is highly degraded by noise. Therefore, two ... more In Positron Emission Tomography (PET), image quality is highly degraded by noise. Therefore, two main PETimage denoising approaches can be used: pre- and postreconstruction denoising. In the pre-reconstruction approach the PET sinogram is denoised before forwarding it to the image reconstruction algorithm. On the other hand, the reconstructed PET-image is denoised in the post-reconstruction approach. In this study, comparison of image quality of the resulting images of the pre- and post-reconstruction approaches is performed. In both types of approaches, the Gaussian filter, the Non-Local Means filter (NLM), the Block-Matching and 3D filter (BM3D), the K-Nearest Neighbors Filter (KNN) and the Patch Confidence K-Nearest Neighbors Filter (PCkNN) are utilized. These approaches are evaluated on a simulated PET-phantom dataset, a real-life physical thorax-phantom PET dataset as well as a reallife MicroPET-scan dataset of a mouse. The performance is measured using the Signal-to-Noise Ratio (SNR) in addition to the Contrast-to-Noise Ratio (CNR) in the resulting images.
Den har studien visar att det ar mojligt att detektera tydliga temperaturskillnader mellan cancer... more Den har studien visar att det ar mojligt att detektera tydliga temperaturskillnader mellan cancervavnad och frisk vavnad. Detta kan vara ett resultat av bade angiogenes (processen som leder till ny ...
Wseas Transactions on Biology and Biomedicine, 2014
A novel automated method for the classification of the physiological condition of the carotid art... more A novel automated method for the classification of the physiological condition of the carotid artery in 2D ultrasound image sequences is introduced. Unsupervised clustering was applied for the segmentation process in which both spatial and temporal information was utilized. Radial distension is then measured in the inner surface of the vessel wall, and this characteristic signal is extracted to reveal the detailed radial motion of the variable inner part of the vessel wall that is in contact with flowing blood. Characteristic differences in this time signal were noticed among healthy young, healthy elderly and pathological elderly cases. The discrete Fourier transform of the radial distension signal is then computed, and the area subtended by the transform is calculated and utilized as a diagnostic feature. The method was tested successfully and could differentiate among the categories of patients mentioned above. Therefore, this computer-aided method would significantly simplify the task of medical specialists in detecting any defects in the carotid artery and thereby in detecting early cardiovascular symptoms. The significance of the proposed method is that it is intuitive, semi-automatic, reproducible, and significantly reduces the reliance upon subjective measures.