Pub Date : 2022-12-25DOI: 10.3329/bjmp.v15i1.63560
Avijit Dey Joy, S. Sarkar, Abul Kalam Azad
Epileptic seizure is a chronic neurological disorder which affects millions of people all over the globe. It can be treated in a better way if the symptoms are detected at an early stage. In this study, we have demonstrated and evaluated the classification performances of different machine learning classifiers for the detection of epileptic seizures from electroencephalography (EEG) signals. For this, we have first applied principal component analysis (PCA) on EEG signals to obtain much reduced-length PCA vectors. These vectors are then applied to decision tree (DT), k-nearest neighbor (KNN), Naïve Bayes (NB), support vector machine (SVM) and artificial neural network (ANN) classifiers for the detection of epileptic seizures. The effects of length of PCA vectors on the performances of these classifiers have also been analyzed rigorously for 2-class, 3-class and 5-class classification of EEG signals. Besides such PCA-based classifiers, we have also proposed and evaluated the performances of a customized convolutional neural network (CNN) to directly extract features from the EEG signals as well as to perform classification tasks. The results showed that CNN outperforms PCA-based machine learning classifiers. For 2-class classification cases, CNN attains classification accuracies in the range from 99.50% to 100%, whereas 98.48% and 96.32% accuracies are obtained with CNN for 3-class and 5-class classification cases. The results signify that the proposed CNN classifier can be considered as a highly-efficient scheme for the reliable detection of epileptic seizures from EEG signals. Bangladesh Journal of Medical Physics Vol.15 No.1 2022 P 28-42
癫痫发作是一种慢性神经系统疾病，影响着全球数百万人。如果在早期发现症状，可以更好地治疗。在这项研究中，我们展示并评估了不同机器学习分类器从脑电图(EEG)信号中检测癫痫发作的分类性能。为此，我们首先将主成分分析(PCA)应用于脑电图信号，得到长度大大缩短的PCA向量。然后将这些向量应用于决策树(DT)、k近邻(KNN)、Naïve贝叶斯(NB)、支持向量机(SVM)和人工神经网络(ANN)分类器中，用于癫痫发作的检测。针对脑电信号的2类、3类和5类分类，严格分析了主成分向量长度对分类器性能的影响。除了这些基于pca的分类器，我们还提出并评估了自定义卷积神经网络(CNN)的性能，以直接从EEG信号中提取特征并执行分类任务。结果表明，CNN优于基于pca的机器学习分类器。对于2类分类案例，CNN的分类准确率在99.50% ~ 100%之间，而对于3类和5类分类案例，CNN的分类准确率分别为98.48%和96.32%。结果表明，本文提出的CNN分类器可以被认为是一种从脑电图信号中可靠检测癫痫发作的高效方案。孟加拉国医学物理杂志Vol.15 no . 2022 P . 28-42
{"title":"Detection of Epileptic Seizures from EEG Signals Using Machine Learning Classifiers","authors":"Avijit Dey Joy, S. Sarkar, Abul Kalam Azad","doi":"10.3329/bjmp.v15i1.63560","DOIUrl":"https://doi.org/10.3329/bjmp.v15i1.63560","url":null,"abstract":"Epileptic seizure is a chronic neurological disorder which affects millions of people all over the globe. It can be treated in a better way if the symptoms are detected at an early stage. In this study, we have demonstrated and evaluated the classification performances of different machine learning classifiers for the detection of epileptic seizures from electroencephalography (EEG) signals. For this, we have first applied principal component analysis (PCA) on EEG signals to obtain much reduced-length PCA vectors. These vectors are then applied to decision tree (DT), k-nearest neighbor (KNN), Naïve Bayes (NB), support vector machine (SVM) and artificial neural network (ANN) classifiers for the detection of epileptic seizures. The effects of length of PCA vectors on the performances of these classifiers have also been analyzed rigorously for 2-class, 3-class and 5-class classification of EEG signals. Besides such PCA-based classifiers, we have also proposed and evaluated the performances of a customized convolutional neural network (CNN) to directly extract features from the EEG signals as well as to perform classification tasks. The results showed that CNN outperforms PCA-based machine learning classifiers. For 2-class classification cases, CNN attains classification accuracies in the range from 99.50% to 100%, whereas 98.48% and 96.32% accuracies are obtained with CNN for 3-class and 5-class classification cases. The results signify that the proposed CNN classifier can be considered as a highly-efficient scheme for the reliable detection of epileptic seizures from EEG signals. \u0000Bangladesh Journal of Medical Physics Vol.15 No.1 2022 P 28-42","PeriodicalId":134261,"journal":{"name":"Bangladesh Journal of Medical Physics","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126702520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-25DOI: 10.3329/bjmp.v15i1.63561
M. Mobarak, K. S. Rabbani
Bio-Electrical impedance is of special interest in the detection and diagnosis of lung problems, particularly in the low and medium income countries. An age old simple technique employing four electrodes is known as ‘Tetra Polar Impedance Measurement (TPIM)’ but it cannot localize a particular zone of interest region. A new technique named as ‘Focused Impedance Method (FIM)’ was innovated by a Dhaka University group which gives high sensitivity in a localized zone of interest. Previously FIM was used from one side of the thorax which gave a rather limited information from the lungs, from shallow depths only. In order to get information from deeper regions of the lungs a new configuration of electrodes for FIM was proposed by the same group at Dhaka University which placed two electrodes at the front and two electrodes at the back of the thorax in a horizontal plane. It is expected that the degree of depth sensitivity would depend on electrode separation on both the sides. The electrode width may also have an effect. In order to study these quantitatively, COMSOL Multiphysics software was used to simulate the measurements in a rounded rectangular volume to represent a typical thorax, which was filled with isotonic saline. Electrode separations of 5cm, 10cm, 15cm and 20cm were studied while electrode widths studied were 0.15cm, 1cm and 3cm. The work supported the proposed new configuration of electrodes for FIM in that this method gives enhanced sensitivity throughout the depths of a lung and that for a thorax with a cross section of 33cm26cm, an electrode separation between 10cm and 15cm would give optimum results. For electrode width, the ones studied did not give any significant difference, however, the smallest (0.15cm) one appeared to give slightly better results. Bangladesh Journal of Medical Physics Vol.15 No.1 2022 P 43-54
生物电阻抗在肺部疾病的检测和诊断方面具有特别重要的意义，特别是在低收入和中等收入国家。一种使用四个电极的古老的简单技术被称为“四极阻抗测量(TPIM)”，但它不能定位特定的感兴趣区域。达卡大学的一个研究小组发明了一种名为“聚焦阻抗法(FIM)”的新技术，可以在局部感兴趣的区域内提供高灵敏度。以前的FIM是从胸腔的一侧使用的，这只能从浅的深度获得相当有限的肺信息。为了从肺部的深层区域获得信息，达卡大学的同一个小组提出了一种新的FIM电极配置，将两个电极放在胸腔的前部和后部，在一个水平面上。预计深度敏感性的程度将取决于电极两侧的分离程度。电极宽度也可能有影响。为了定量研究这些，使用COMSOL Multiphysics软件在一个圆形矩形体中模拟测量结果，以代表一个典型的胸腔，该胸腔充满等渗盐水。电极间距分别为5cm、10cm、15cm和20cm，电极宽度分别为0.15cm、1cm和3cm。这项工作支持了FIM电极的新配置，因为这种方法在肺的整个深度都提高了灵敏度，对于横截面为33cm26cm的胸腔，电极间距在10cm和15cm之间将获得最佳结果。就电极宽度而言，所研究的电极并没有产生任何显著差异，然而，最小的(0.15厘米)电极的效果似乎略好一些。孟加拉国医学物理杂志Vol.15 no . 2022 P . 43-54
{"title":"Improving Deep Sensitivity of Four-Electrode Focused Impedance Method In Lungs by Varying Electrode Geometries","authors":"M. Mobarak, K. S. Rabbani","doi":"10.3329/bjmp.v15i1.63561","DOIUrl":"https://doi.org/10.3329/bjmp.v15i1.63561","url":null,"abstract":"Bio-Electrical impedance is of special interest in the detection and diagnosis of lung problems, particularly in the low and medium income countries. An age old simple technique employing four electrodes is known as ‘Tetra Polar Impedance Measurement (TPIM)’ but it cannot localize a particular zone of interest region. A new technique named as ‘Focused Impedance Method (FIM)’ was innovated by a Dhaka University group which gives high sensitivity in a localized zone of interest. Previously FIM was used from one side of the thorax which gave a rather limited information from the lungs, from shallow depths only. In order to get information from deeper regions of the lungs a new configuration of electrodes for FIM was proposed by the same group at Dhaka University which placed two electrodes at the front and two electrodes at the back of the thorax in a horizontal plane. It is expected that the degree of depth sensitivity would depend on electrode separation on both the sides. The electrode width may also have an effect. In order to study these quantitatively, COMSOL Multiphysics software was used to simulate the measurements in a rounded rectangular volume to represent a typical thorax, which was filled with isotonic saline. Electrode separations of 5cm, 10cm, 15cm and 20cm were studied while electrode widths studied were 0.15cm, 1cm and 3cm. The work supported the proposed new configuration of electrodes for FIM in that this method gives enhanced sensitivity throughout the depths of a lung and that for a thorax with a cross section of 33cm26cm, an electrode separation between 10cm and 15cm would give optimum results. For electrode width, the ones studied did not give any significant difference, however, the smallest (0.15cm) one appeared to give slightly better results. \u0000Bangladesh Journal of Medical Physics Vol.15 No.1 2022 P 43-54","PeriodicalId":134261,"journal":{"name":"Bangladesh Journal of Medical Physics","volume":"383 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124767585","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-25DOI: 10.3329/bjmp.v15i1.63559
Fahmida Ahmed Antara, A. Arefin, Md Tamjid Rayhan, Sabbir Ahmed Chowdhury
This research was conducted with the aim to detect schizophrenia automatically from EEG signals using machine learning algorithms. The 16 electrode EEG data were collected from the online repository where 43 schizophrenic and 39 healthy persons’ dataset is available. By applying Low Pass Filter and Total Variation Denoising method, raw EEG signals were denoised and were decomposed into beta, alpha, theta and delta waves by using Dual Tree Complex Wavelet Transform. To apply machine learning algorithms, five features: mean, median, standard deviation, energy and kurtosis were considered for all the four wave bands. With Linear Support Vector Machine and Random Forest classifier machine learning algorithms, 12 out of 16 channels were classified with test accuracy above 95% and F1 score above 90%. Among them, 7 channels were predicted with 100% test accuracy. This research thus has the potential to detect schizophrenia unsupervised and within a noticeably short period of time giving the opportunity to real time monitoring of patients. Hence, people living in remote areas or deprived of adequate healthcare professionals can be benefitted through the outcome of this research. Bangladesh Journal of Medical Physics Vol.15 No.1 2022 P 8-27
本研究的目的是利用机器学习算法从脑电图信号中自动检测精神分裂症。16个电极脑电图数据来自在线存储库，其中有43个精神分裂症患者和39个健康人的数据集。采用低通滤波和全变差去噪方法，对原始脑电信号进行去噪，并利用对偶树复小波变换将其分解为β、α、θ和δ波。为了应用机器学习算法，对所有四个波段考虑了五个特征:平均值、中位数、标准差、能量和峰度。使用线性支持向量机和随机森林分类器机器学习算法，16个通道中有12个通道的分类测试准确率在95%以上，F1得分在90%以上。其中7个通道的预测准确率达到100%。因此，这项研究有可能在无人监督的情况下，在非常短的时间内发现精神分裂症，从而有机会对患者进行实时监测。因此，生活在偏远地区或缺乏适当保健专业人员的人们可以通过这项研究的结果受益。孟加拉国医学物理杂志Vol.15 no . 2022 P . 8-27
{"title":"Detection of Schizophrenia from EEG Signals using Dual Tree Complex Wavelet Transform and Machine Learning Algorithms","authors":"Fahmida Ahmed Antara, A. Arefin, Md Tamjid Rayhan, Sabbir Ahmed Chowdhury","doi":"10.3329/bjmp.v15i1.63559","DOIUrl":"https://doi.org/10.3329/bjmp.v15i1.63559","url":null,"abstract":"This research was conducted with the aim to detect schizophrenia automatically from EEG signals using machine learning algorithms. The 16 electrode EEG data were collected from the online repository where 43 schizophrenic and 39 healthy persons’ dataset is available. By applying Low Pass Filter and Total Variation Denoising method, raw EEG signals were denoised and were decomposed into beta, alpha, theta and delta waves by using Dual Tree Complex Wavelet Transform. To apply machine learning algorithms, five features: mean, median, standard deviation, energy and kurtosis were considered for all the four wave bands. With Linear Support Vector Machine and Random Forest classifier machine learning algorithms, 12 out of 16 channels were classified with test accuracy above 95% and F1 score above 90%. Among them, 7 channels were predicted with 100% test accuracy. This research thus has the potential to detect schizophrenia unsupervised and within a noticeably short period of time giving the opportunity to real time monitoring of patients. Hence, people living in remote areas or deprived of adequate healthcare professionals can be benefitted through the outcome of this research. \u0000Bangladesh Journal of Medical Physics Vol.15 No.1 2022 P 8-27","PeriodicalId":134261,"journal":{"name":"Bangladesh Journal of Medical Physics","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125650426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-25DOI: 10.3329/bjmp.v15i1.63558
S. Ahmed, Mjh Khan, A. Nahar, M.F. Mortuza, M. Hosan
The aim of this work is to investigate the existing shield design aspects of a semi-industrial Cobalt- 60 Gamma Irradiation Facility for 100 kCi, designed for irradiation of pharmaceutical products and daily foodstuffs as well as for research and development purposes at the Institute of Food and Radiation Biology (IFRB) of the Bangladesh Atomic Energy Commission. Earlier, the initial activity of this facility was 65 kCi and stone based reinforced concrete (SBRC) of density 2.60 g/cc and specific thicknesses were used to shield the facility for safety to operational personnel and outside public. Due to a large demand for irradiation of pharmaceutical products as well as of daily foodstuffs, IFRB has decided to increase the initial activity up to 100 kCi for this facility. For this reason, the shielding design aspects of this facility were needed to be recalculated and checked for safety. This analysis was done using the Point-kernel Shielding Code Micro-Shield 5.05 and public domain Point-kernel Shielding code QAD-CGGP2 respectively considering the radiation worker dose limit of 10 μSv/hr of the International Commission on Radiological Protection, ICRP-60, 1990. The corresponding dose limit for public at large is 0.5 μSv/hr. The calculated dose rates at different locations around the facility are far below 10 μSv/hr except in one area. This location is inside the source room. No one is allowed to enter the room when the facility is in the ON mode. However, except one location, positions outside the facility have dose rates about 3 time higher than 0.5 μSv/hr, the dose limit for public at large. Therefore, this analysis shows that the existing shield design aspects of IFRB’s Co-60 gamma source room is safe for a 100 kCi source from the viewpoint of radiation safety to operating personnel but not for public at large within proximity of the facility. Bangladesh Journal of Medical Physics Vol.15 No.1 2022 P 1-7
{"title":"A Study on Shield Design Aspects of a Semi-Industrial Co-60 Gamma Irradiation Facility at Gamma Source Division of Institute of Food and Radiation Biology of the Bangladesh Atomic Energy Commission","authors":"S. Ahmed, Mjh Khan, A. Nahar, M.F. Mortuza, M. Hosan","doi":"10.3329/bjmp.v15i1.63558","DOIUrl":"https://doi.org/10.3329/bjmp.v15i1.63558","url":null,"abstract":"The aim of this work is to investigate the existing shield design aspects of a semi-industrial Cobalt- 60 Gamma Irradiation Facility for 100 kCi, designed for irradiation of pharmaceutical products and daily foodstuffs as well as for research and development purposes at the Institute of Food and Radiation Biology (IFRB) of the Bangladesh Atomic Energy Commission. Earlier, the initial activity of this facility was 65 kCi and stone based reinforced concrete (SBRC) of density 2.60 g/cc and specific thicknesses were used to shield the facility for safety to operational personnel and outside public. Due to a large demand for irradiation of pharmaceutical products as well as of daily foodstuffs, IFRB has decided to increase the initial activity up to 100 kCi for this facility. For this reason, the shielding design aspects of this facility were needed to be recalculated and checked for safety. This analysis was done using the Point-kernel Shielding Code Micro-Shield 5.05 and public domain Point-kernel Shielding code QAD-CGGP2 respectively considering the radiation worker dose limit of 10 μSv/hr of the International Commission on Radiological Protection, ICRP-60, 1990. The corresponding dose limit for public at large is 0.5 μSv/hr. The calculated dose rates at different locations around the facility are far below 10 μSv/hr except in one area. This location is inside the source room. No one is allowed to enter the room when the facility is in the ON mode. However, except one location, positions outside the facility have dose rates about 3 time higher than 0.5 μSv/hr, the dose limit for public at large. Therefore, this analysis shows that the existing shield design aspects of IFRB’s Co-60 gamma source room is safe for a 100 kCi source from the viewpoint of radiation safety to operating personnel but not for public at large within proximity of the facility. \u0000Bangladesh Journal of Medical Physics Vol.15 No.1 2022 P 1-7","PeriodicalId":134261,"journal":{"name":"Bangladesh Journal of Medical Physics","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132187385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-31DOI: 10.3329/bjmp.v14i1.57314
Trilochan Khanal, K. S. Rabbani
Focused Impedance Method (FIM) is a new and simple technique of electrical bio-impedance that provides an opportunity for localized measurement down to reasonable depths of the body surface using skin surface electrodes. Conceived by one of the authors (KSR) and developed in Bangladesh by a group led by him, FIM has potential applications in physiological study and in the detection or diagnosis of diseases and disorders. Being a simple technique, it is particularly suitable for low and medium income countries (LMIC). To obtain long term benefit from any technology it is necessary that the technology is understood and developed indigenously, particularly under the limitation of a resource limited country. Indigenous development also allows for further improvisation, innovation, and application in future. This paper presents the indigenous design and development of the electronic instrumentation necessary for the implementation of six electrode version of Focused Impedance Method (FIM-6) in Nepal. The work involved basic characterization of the necessary circuit blocks developed through experimental validation. In particular, the design of isolating ferrite transformers required for the instrumentation posed a challenge which was solved limiting the range of the instrumentation to range variations encountered in practice on the human body, for which initial experiments were carried out on a live human subject. This led to a simplified design. The values obtained using the developed circuitry appears to give reasonable accuracy and would be useful for further implementation of the instrumentation using PCBs. However, further work can also be taken to improve the design of the current source used and of the transformers. Thus this work satisfies the initial requirement of attempting indigenous development of the FIM technique in an LMIC like Nepal. Bangladesh Journal of Medical Physics Vol.14 No.1 2021 P 1-15
聚焦阻抗法(FIM)是一种新的、简单的电生物阻抗技术，它提供了利用皮肤表面电极在体表的合理深度下进行局部测量的机会。FIM由其中一位作者(KSR)构思，并由他领导的一个小组在孟加拉国开发，在生理研究以及疾病和失调的检测或诊断方面具有潜在的应用。作为一种简单的技术，它特别适用于低收入和中等收入国家。为了从任何技术中获得长期利益，必须在当地了解和开发该技术，特别是在资源有限的国家的限制下。本土发展也允许进一步的即兴创作、创新和应用。本文介绍了在尼泊尔实施六电极聚焦阻抗法(FIM-6)所需的电子仪器的自主设计和开发。这项工作涉及通过实验验证开发的必要电路块的基本特征。特别是，该仪器所需的隔离铁氧体变压器的设计提出了一个挑战，该挑战的解决办法是将仪器的范围限制在人体实践中遇到的范围变化，为此，最初的实验是在活人身上进行的。这导致了简化的设计。使用开发的电路获得的值似乎给出了合理的精度，并且对于使用pcb的仪器的进一步实现是有用的。然而，还可以采取进一步的工作来改进所使用的电流源和变压器的设计。因此，这项工作满足了在尼泊尔这样的中低收入国家尝试本土发展FIM技术的初步要求。孟加拉国医学物理杂志Vol.14 no . 2021 P . 1-15
{"title":"Instrumentation for Six Electrode Focused Impedance Method (FIM-6) for the study of localized regions in a volume conductor","authors":"Trilochan Khanal, K. S. Rabbani","doi":"10.3329/bjmp.v14i1.57314","DOIUrl":"https://doi.org/10.3329/bjmp.v14i1.57314","url":null,"abstract":"Focused Impedance Method (FIM) is a new and simple technique of electrical bio-impedance that provides an opportunity for localized measurement down to reasonable depths of the body surface using skin surface electrodes. Conceived by one of the authors (KSR) and developed in Bangladesh by a group led by him, FIM has potential applications in physiological study and in the detection or diagnosis of diseases and disorders. Being a simple technique, it is particularly suitable for low and medium income countries (LMIC). To obtain long term benefit from any technology it is necessary that the technology is understood and developed indigenously, particularly under the limitation of a resource limited country. Indigenous development also allows for further improvisation, innovation, and application in future. This paper presents the indigenous design and development of the electronic instrumentation necessary for the implementation of six electrode version of Focused Impedance Method (FIM-6) in Nepal. The work involved basic characterization of the necessary circuit blocks developed through experimental validation. In particular, the design of isolating ferrite transformers required for the instrumentation posed a challenge which was solved limiting the range of the instrumentation to range variations encountered in practice on the human body, for which initial experiments were carried out on a live human subject. This led to a simplified design. The values obtained using the developed circuitry appears to give reasonable accuracy and would be useful for further implementation of the instrumentation using PCBs. However, further work can also be taken to improve the design of the current source used and of the transformers. Thus this work satisfies the initial requirement of attempting indigenous development of the FIM technique in an LMIC like Nepal. \u0000Bangladesh Journal of Medical Physics Vol.14 No.1 2021 P 1-15","PeriodicalId":134261,"journal":{"name":"Bangladesh Journal of Medical Physics","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127335083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-31DOI: 10.3329/bjmp.v14i1.57315
K. S. Rabbani
The astounding developments in healthcare technology is not available to about 84% of the global population in the low-medium income countries (LMIC). Good meaning medical equipment donation programmes from the high income countries (HIC) have made very little impact, most devices failing to give the desired service and increasing e-waste. The author, with his four decade-long experience feels that people in the LMICs with higher education in science and technology should be motivated and trained in the design and manufacture of medical devices, and they should also take the responsibility for commercial manufacture and distribution of the developed products. With this realisation early in life, he initiated similar efforts in his home country Bangladesh about four decades back against many challenges and obstacles. This produced some success stories and this paper lists some of the devices developed and distributed by groups under his leadership. The author argues that the existing industries in the LMICs are based on fully foreign technology, and do not have the capability or preparedness to take up commercial manufacture of indigenously developed technology based products. He has come up with the design of a ‘Micro-eco-system’ for the LMICs which involve the leadership of a single technology innovator or a single group of innovators to organise R&D and commercial manufacture, both. An LMIC may have hundreds or thousands of the above ‘Micro-eco-system’ to create an overall eco-system, which may be the solution eventually leading to a more equitable world, with each and every person of the globe having access to developments in science and technology in healthcare. Bangladesh Journal of Medical Physics Vol.14 No.1 2021 P 1-15
全球约84%的中低收入国家(LMIC)人口无法享受到医疗保健技术的惊人发展。来自高收入国家(HIC)的善意医疗设备捐赠方案几乎没有产生影响，大多数设备无法提供所需的服务，并增加了电子废物。作者以其40年的工作经验认为，中低收入国家中受过高等科技教育的人应该在医疗器械的设计和制造方面受到激励和培训，他们还应该负责开发产品的商业生产和分销。四十年前，由于早年就意识到这一点，他在自己的祖国孟加拉国发起了类似的努力，克服了许多挑战和障碍。这产生了一些成功的故事，本文列出了在他领导下的小组开发和分发的一些设备。作者认为，中低收入国家现有的工业完全以外国技术为基础，没有能力或准备将自主开发的技术产品投入商业生产。他提出了一个针对低收入和中等收入国家的“微生态系统”的设计，其中包括由一个技术创新者或一个创新者群体领导组织研发和商业生产。一个低收入和中等收入国家可能有数百或数千个上述“微生态系统”来创建一个整体生态系统，这可能是最终导致一个更公平的世界的解决方案，全球每个人都有机会获得卫生保健方面的科学和技术发展。孟加拉国医学物理杂志Vol.14 no . 2021 P . 1-15
{"title":"Efforts to establish indigenous technology for healthcare in a low resource country – Bangladesh experience","authors":"K. S. Rabbani","doi":"10.3329/bjmp.v14i1.57315","DOIUrl":"https://doi.org/10.3329/bjmp.v14i1.57315","url":null,"abstract":"The astounding developments in healthcare technology is not available to about 84% of the global population in the low-medium income countries (LMIC). Good meaning medical equipment donation programmes from the high income countries (HIC) have made very little impact, most devices failing to give the desired service and increasing e-waste. The author, with his four decade-long experience feels that people in the LMICs with higher education in science and technology should be motivated and trained in the design and manufacture of medical devices, and they should also take the responsibility for commercial manufacture and distribution of the developed products. With this realisation early in life, he initiated similar efforts in his home country Bangladesh about four decades back against many challenges and obstacles. This produced some success stories and this paper lists some of the devices developed and distributed by groups under his leadership. The author argues that the existing industries in the LMICs are based on fully foreign technology, and do not have the capability or preparedness to take up commercial manufacture of indigenously developed technology based products. He has come up with the design of a ‘Micro-eco-system’ for the LMICs which involve the leadership of a single technology innovator or a single group of innovators to organise R&D and commercial manufacture, both. An LMIC may have hundreds or thousands of the above ‘Micro-eco-system’ to create an overall eco-system, which may be the solution eventually leading to a more equitable world, with each and every person of the globe having access to developments in science and technology in healthcare. \u0000Bangladesh Journal of Medical Physics Vol.14 No.1 2021 P 1-15 ","PeriodicalId":134261,"journal":{"name":"Bangladesh Journal of Medical Physics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132708065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-31DOI: 10.3329/bjmp.v14i1.57313
Parama Sridevi, A. Arefin, Abu Shahadat Md. Ibrahim
Diabetes mellitus, a common disease of the modern era, is a glucose level disorder in the human body that affects the vital organs of the body and damages them gradually if left untreated. Regular blood glucose monitoring is one of the prescribed routines to control the complications of diabetes. Unfortunately, most available methods of blood glucose level measurement involve invasive ways. Invasive techniques are painful, make the finger skin calloused and the patients suffer from the risk of infectious diseases. Hence, there lies a need to develop an effective non-invasive blood sugar measurement technique to relieve the patients from the nuisance. In order to address the issue, a non-invasive technique has been designed and implemented using 940 nm near-infrared (NIR) LED and a corresponding photodiode. Initially, the in-vitro test was performed over the glucose solution of various concentrations to check the sensitivity of the device. After that pilot experiments were carried out on diabetic patients. The obtained results conformed the theory of near infra-red spectroscopic optical theory. The results also showed that the developed technique can be comparable with the conventional invasive glucometer based method. Furthermore, the implemented prototype is economically viable, especially for the low-income population. This promising results thus pledge the potentials, feasibility, and reliability of the NIR based non-invasive blood glucose detection devices. Bangladesh Journal of Medical Physics Vol.14 No.1 2021 P 1-13
糖尿病是一种现代常见病，是一种影响人体重要器官的血糖水平紊乱，如果不及时治疗，会逐渐损害这些器官。定期血糖监测是控制糖尿病并发症的规定程序之一。不幸的是，大多数可用的血糖测量方法都涉及侵入性方法。侵入性技术是痛苦的，使手指皮肤起茧子，患者有感染传染病的危险。因此，有必要开发一种有效的非侵入性血糖测量技术，以减轻患者的麻烦。为了解决这个问题，我们设计并实现了一种使用940 nm近红外(NIR) LED和相应的光电二极管的非侵入性技术。最初，在不同浓度的葡萄糖溶液中进行体外测试，以检查该装置的灵敏度。之后，对糖尿病患者进行了试点实验。所得结果符合近红外光谱光学理论。结果还表明，所开发的技术可以与传统的侵入性血糖仪方法相媲美。此外，实施的原型在经济上是可行的，特别是对低收入人群。因此，这一有希望的结果保证了基于近红外的无创血糖检测设备的潜力、可行性和可靠性。孟加拉国医学物理杂志Vol.14 no . 2021 P . 1-13
{"title":"A Feasibility Study of Non-invasive Blood Glucose Level Detection Using Near-Infrared Optical Spectroscopy","authors":"Parama Sridevi, A. Arefin, Abu Shahadat Md. Ibrahim","doi":"10.3329/bjmp.v14i1.57313","DOIUrl":"https://doi.org/10.3329/bjmp.v14i1.57313","url":null,"abstract":"Diabetes mellitus, a common disease of the modern era, is a glucose level disorder in the human body that affects the vital organs of the body and damages them gradually if left untreated. Regular blood glucose monitoring is one of the prescribed routines to control the complications of diabetes. Unfortunately, most available methods of blood glucose level measurement involve invasive ways. Invasive techniques are painful, make the finger skin calloused and the patients suffer from the risk of infectious diseases. Hence, there lies a need to develop an effective non-invasive blood sugar measurement technique to relieve the patients from the nuisance. In order to address the issue, a non-invasive technique has been designed and implemented using 940 nm near-infrared (NIR) LED and a corresponding photodiode. Initially, the in-vitro test was performed over the glucose solution of various concentrations to check the sensitivity of the device. After that pilot experiments were carried out on diabetic patients. The obtained results conformed the theory of near infra-red spectroscopic optical theory. The results also showed that the developed technique can be comparable with the conventional invasive glucometer based method. Furthermore, the implemented prototype is economically viable, especially for the low-income population. This promising results thus pledge the potentials, feasibility, and reliability of the NIR based non-invasive blood glucose detection devices. \u0000Bangladesh Journal of Medical Physics Vol.14 No.1 2021 P 1-13","PeriodicalId":134261,"journal":{"name":"Bangladesh Journal of Medical Physics","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125049700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-12-03DOI: 10.3329/bjmp.v10i1.39147
S. Farhan, K. T. Nahiyan
Myocardial ischemia occurs when blood flow to heart is reduced preventing it from receiving enough oxygen. It is a possible indication of partial or complete blockage of coronary arteries. Though ischemia is accompanied by symptoms (fatigue, chest pain, shortness of breath etc.) sometimes it can be silent. If not treated, it can lead to various heart diseases. Most importantly it can progress to myocardial infarction (heart attack), which can be fatal. Thus detecting ischemia at an early stage is important to prevent serious implications. Nowadays personal healthcare monitoring systems are used which provide vital physiological information. In future ECG measurement devices would also be common in homes. So, the proposed work intends to develop an algorithm in detecting myocardial ischemia from ECG, which would be computationally less complex and easy to implement in homecare ECG devices. One way to do it is through continuous or long term monitoring of ECG. The ST segment elevation (or depression) indicates presence of ischemia. The proposed method measures slope of ST segment which must vary in case of ST changes. The algorithm is tested on selected records of the European ST-T database and returns an accuracy of 83.33%.Bangladesh Journal of Medical Physics Vol.10 No.1 2017 12-24
{"title":"Myocardial Ischemia Detection from Slope of ECG ST Segment","authors":"S. Farhan, K. T. Nahiyan","doi":"10.3329/bjmp.v10i1.39147","DOIUrl":"https://doi.org/10.3329/bjmp.v10i1.39147","url":null,"abstract":"Myocardial ischemia occurs when blood flow to heart is reduced preventing it from receiving enough oxygen. It is a possible indication of partial or complete blockage of coronary arteries. Though ischemia is accompanied by symptoms (fatigue, chest pain, shortness of breath etc.) sometimes it can be silent. If not treated, it can lead to various heart diseases. Most importantly it can progress to myocardial infarction (heart attack), which can be fatal. Thus detecting ischemia at an early stage is important to prevent serious implications. Nowadays personal healthcare monitoring systems are used which provide vital physiological information. In future ECG measurement devices would also be common in homes. So, the proposed work intends to develop an algorithm in detecting myocardial ischemia from ECG, which would be computationally less complex and easy to implement in homecare ECG devices. One way to do it is through continuous or long term monitoring of ECG. The ST segment elevation (or depression) indicates presence of ischemia. The proposed method measures slope of ST segment which must vary in case of ST changes. The algorithm is tested on selected records of the European ST-T database and returns an accuracy of 83.33%.Bangladesh Journal of Medical Physics Vol.10 No.1 2017 12-24","PeriodicalId":134261,"journal":{"name":"Bangladesh Journal of Medical Physics","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128292737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-12-03DOI: 10.3329/BJMP.V10I1.39150
A. Amin
For a fully paralysed person, EEG (Electroencephalogram) based Brain Computer Interface (BCI) has a great promise for controlling electromechanical equipment such as a wheelchair. Again EOG (Electrooculography) based Human Machine Interface system also provides a possibility. Individually, none of these methods is capable of giving a fully error free reliable and safe control, but an appropriate combination may provide a better reliability, which is the aim of the present work. Here we intend to use EEG data to classify two classes, corresponding to left and right hand movement, and EOG data to classify two classes corresponding to left and right sided eyeball movement. We will use these classifications independently first and then combine these with different weightage to find if a better and reliable control is possible. For this purpose offline classification of motor imaginary EEG data of a subject was carried out extracting features using Common Spatial Pattern (CSP) and classifying using Linear Discriminative Analysis. The independent EEG motor imaginary data classification resulted in 89.8% of accuracy in 10 fold one leave out cross validation. The EOG eyeball movement produces distinctive signals of opposite polarities and is classified using a simple discriminant type classification resulting in 100% accuracy. However, using EOG solely is not acceptable as there always will be unintentional eye movement giving false commands. Combining both EEG and EOG with different weightage to the two classifications produced varied degrees of improvement. For 50% weightage to both resulted in 100% accuracy, without any error, and this may be accepted as a practical solution because the chances of unintentional false commands will be very rare. Therefore, a combination of EOG and BCI may lead to a greater reliability in terms of avoidance of undesired control signals.Bangladesh Journal of Medical Physics Vol.10 No.1 2017 47-58
{"title":"A Feasibility Study of Employing EOG Signal in Combination with EEG Based BCI System for Improved Control of a Wheelchair","authors":"A. Amin","doi":"10.3329/BJMP.V10I1.39150","DOIUrl":"https://doi.org/10.3329/BJMP.V10I1.39150","url":null,"abstract":"For a fully paralysed person, EEG (Electroencephalogram) based Brain Computer Interface (BCI) has a great promise for controlling electromechanical equipment such as a wheelchair. Again EOG (Electrooculography) based Human Machine Interface system also provides a possibility. Individually, none of these methods is capable of giving a fully error free reliable and safe control, but an appropriate combination may provide a better reliability, which is the aim of the present work. Here we intend to use EEG data to classify two classes, corresponding to left and right hand movement, and EOG data to classify two classes corresponding to left and right sided eyeball movement. We will use these classifications independently first and then combine these with different weightage to find if a better and reliable control is possible. For this purpose offline classification of motor imaginary EEG data of a subject was carried out extracting features using Common Spatial Pattern (CSP) and classifying using Linear Discriminative Analysis. The independent EEG motor imaginary data classification resulted in 89.8% of accuracy in 10 fold one leave out cross validation. The EOG eyeball movement produces distinctive signals of opposite polarities and is classified using a simple discriminant type classification resulting in 100% accuracy. However, using EOG solely is not acceptable as there always will be unintentional eye movement giving false commands. Combining both EEG and EOG with different weightage to the two classifications produced varied degrees of improvement. For 50% weightage to both resulted in 100% accuracy, without any error, and this may be accepted as a practical solution because the chances of unintentional false commands will be very rare. Therefore, a combination of EOG and BCI may lead to a greater reliability in terms of avoidance of undesired control signals.Bangladesh Journal of Medical Physics Vol.10 No.1 2017 47-58","PeriodicalId":134261,"journal":{"name":"Bangladesh Journal of Medical Physics","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132894153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-12-03DOI: 10.3329/BJMP.V10I1.39148
Muhammad S. Alam, A. Arefin
Electromyography (EMG) signals acquired from surface of arms can be crucial in recognizing nature of hand gestures. The concept is used in current highly demanding fields such as controlling prosthetic limbs, diagnosing neuromuscular disorders, manipulation of robotic arm etc. The purpose of the work was to classify a set of hand motions from corresponding multi-channel surface EMG signals by developing MATLAB tools. The research focused on extracting multiple signal features and finding the appropriate combination of extracted intelligible features to get the best classification accuracy for the specific set of hand gestures. For dynamic and fast classification purpose, linear discriminant analysis (LDA) classifier was employed. Effect of feature dimensionality reduction on classification accuracy was also investigated via Principal Component Analysis (PCA) in this research. Finally, the research analyzed different electrode placements by comparing classification accuracy for each of the set of motions and proposed a simple and compact data acquisition instrumentation having less number of electrodes while maintaining high classification accuracy.Bangladesh Journal of Medical Physics Vol.10 No.1 2017 25-39
{"title":"Real-Time Classification of Multi-Channel Forearm EMG to Recognize Hand Movements using Effective Feature Combination and LDA Classifier","authors":"Muhammad S. Alam, A. Arefin","doi":"10.3329/BJMP.V10I1.39148","DOIUrl":"https://doi.org/10.3329/BJMP.V10I1.39148","url":null,"abstract":"Electromyography (EMG) signals acquired from surface of arms can be crucial in recognizing nature of hand gestures. The concept is used in current highly demanding fields such as controlling prosthetic limbs, diagnosing neuromuscular disorders, manipulation of robotic arm etc. The purpose of the work was to classify a set of hand motions from corresponding multi-channel surface EMG signals by developing MATLAB tools. The research focused on extracting multiple signal features and finding the appropriate combination of extracted intelligible features to get the best classification accuracy for the specific set of hand gestures. For dynamic and fast classification purpose, linear discriminant analysis (LDA) classifier was employed. Effect of feature dimensionality reduction on classification accuracy was also investigated via Principal Component Analysis (PCA) in this research. Finally, the research analyzed different electrode placements by comparing classification accuracy for each of the set of motions and proposed a simple and compact data acquisition instrumentation having less number of electrodes while maintaining high classification accuracy.Bangladesh Journal of Medical Physics Vol.10 No.1 2017 25-39","PeriodicalId":134261,"journal":{"name":"Bangladesh Journal of Medical Physics","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123305093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：