Biomedical Engineering

Permanent URI for this collection

http://etd.aau.edu.et/handle/123456789/50

Browse

Recent Submissions

Now showing 1 - 20 of 49
  • No Thumbnail Available
    Item
    Classification of Fatty Liver Disease Using Deep Learning Technique
    (Addis Ababa University, 2023-08) Hume Degebassa; Dawit Assefa (PhD); Million Molla (Mr.) Co-Advisor
    Fatty liver disease (FLD) also termed steatosis liver disease can be classified into two broad spectrums: Alcoholic fatty liver disease (AFLD) and Non-alcoholic liver disease (NAFLD). AFLD is a type of liver disease associated with alcohol intake of 40 to 80 grams of ethanol/day for males and of 20 to 40 grams/day for females. NAFLD is a disorder characterized by excess accumulation of fat (in the form of triglycerides) with an amount >5% in the hepatocytes. The progression of the disease is manifested by ongoing inflammation and consequent steatosis grade: G1 (mild steatosis), G2 (moderate steatosis), and G3 (severe steatosis). If no early strategies are adopted, FLD can progress to steatohepatitis (SH) which is a risk factor for liver fibrosis, cirrhosis, and hepatocellular carcinoma (liver cancer). Cirrhosis is currently the 11th most common cause of death globally and liver cancer is the 16th leading cause of death. In Ethiopia, cirrhosis was the 7th leading cause of mortality accounting for 24 deaths per 100,000 populations in 2019. Hence, early diagnosis is important to avoid advanced stages of FLD. In order to diagnose and grade FLDs, Ultrasound imaging is the most well-known technique. The visual assessment of these Ultrasound images is not only time taking and labor-intensive task but it is also prone to inter-observer variability. That calls for the development of an automated system that overcomes subjectivity and inconsistency in the screening process. Different studies in the literature have proposed the classification of FLDs using deep learning and machine learning techniques. However, most of these techniques are limited to binary classification and don’t consider the severity level. The current study aims to develop an automatic fatty liver classification and grading scheme using deep learning techniques. A total of 550 liver ultrasound images were collected from Zenode repository and image pre-processing was employed on the acquired images before the images were used to train the deep learning model. The effect of important deep network hyper parameters including batch size, learning rate, regularizer and epoch was investigated. Different pre-trained deep learning networks were tested for their classification efficacy including VGGNet, MobileNetV2, ResNet and Xception based on useful performance matrices. Accordingly, the Xception model was found to outperform the rest for multiclass (normal, mild, moderate, and severe) fatty liver classification. It offered a precision of 96.25%, recall of 97.75%, F1 score of 96.75%, and overall accuracy of 96.36% showing the great promises of the model.
  • No Thumbnail Available
    Item
    Improving Ultrasound Kidney Stone Detection Using Deep Learning
    (Addis Ababa University, 2023-04) Bekalu Gedifew; Dawit Assefa (PhD)
    Background: Currently a CT scan is preferred over Ultrasound images for Kidney stone diagnosis. The major problem regarding diagnosis of these stones under CT imaging mo-dality is that once these patients are diagnosed as positive; there is a high chance for the stone to be formed again in the patient’s lifetime after removal. As a result, use of the CT modality repeatedly exposes the patient for unwanted radiation exposure. Purpose of the Research: In ultrasound imaging, additive and multiplicative noises are taken as disadvantage for its imaging output. However, its ability to form real time imaging makes it preferable in many diagnosis procedures. The current study is aimed at developing an effective kidney stone detection scheme using a Convolutional Neural Network (CNN) by incorporating useful image pre-processing tools applied on Ultrasound images. Methods: The approach implemented in the proposed kidney stone detection scheme mainly involves two stages. The first stage employed using useful pre-processing steps applied on the Ultrasound images, which include image filtering, contrast enhancement and 2-D Directional Wavelet Transforms. The second stage is employed using multiclass se-mantic segmentation CNN models, which include Deep Lab V3 , U-net and Seg-net mod-els. In order to detect multiclass regions of ultrasound kidney stone image.The performance of the models was evaluated using useful quantitative matrices. Results and Conclusion: Results have shown that the Deep Lab V3 CNN model had greater performance than U-net and Seg-net CNN models tested in this study. The model was able to maintain a global accuracy and mean accuracy of 95.1% and 80.9% respec-tively showing its great promises in improving the detection of kidney stones based on Ultrasound images. Compared to performances reported in the literature by previous schol-ars who have developed different method of kidney stone detection algorithms, the pro-posed method has offered commendable results in terms of global accuracy and mean ac-curacy.
  • No Thumbnail Available
    Item
    Design and Development of Steam Sterilizer
    (Addis Ababa University, 2023-06) Yemane Tesfay; Dawit Assefa (PhD)
    According to the 2010 WHO infectious disease report, hundreds of millions of patients around the world are affected by healthcare-associated infections which cause extended clinic stays, long-term disability, massive additional costs, and unnecessary deaths. This folds higher in low-income countries but it is a global burden. To minimize the burden of these infections, cleaning, disinfection, and sterilization techniques have been applied. For a sterilization technique, different steam sterilizers are available in the market ranging from the simplest electro-mechanical portable systems to the complex microcontroller-based double-door floor fixed types. However, those steam sterilizers can’t adjust environmental pressure for altitudinal changes that often fail to function properly under significant pressure variation. Countries like Ethiopia have great geographical diversity, known altitude ranges from the highest peak at Ras Dashen (4,620m) down to the Dallol Depression (-148m), which highly affect the performance of steam sterilizers. The main intent of this thesis study is to design a microcontroller-based smart steam sterilizer that adjusts itself to variable altitudes since steam sterilizers that work in all altitudes are vital for the healthcare system. The sterilizer also comes with a water electrical conductivity sensor to completely avoid the use of hard water integrated with a water level regulator to protect the heater when water runs out inside the chamber. Interfacing between the proposed smart pressure compensator, conductivity sensor with water level regulator of steam sterilizers is worked out in this study. The developed control system senses the environmental condition using BMP280 sensor to adjust itself based on the altitudinal changes as well as water electrical conductivity, water level, pressure, and temperature sensors. A formula is developed based on the altitude pressure compensation to solve the problem of altitudinal effect and for water quality and quantity measurement guided by a programmable microcontroller. The control system can adjust the pressure based on the altitudinal variations. The system offers better efficiency, precision and comes with great ease of use. The designed smart steam sterilizer is as effective as existing modern sterilizers with an added feature of blocking use of hard water. Meanwhile, further research might be needed to make the device more efficient, lower cost, durable, and safer.
  • No Thumbnail Available
    Item
    A Trilingual Android Application with Automatic Malaria Detection from Microscopic Images of Red Blood Cells
    (Addis Ababa University, 2023-12) Berihun Nigussa; Dawit Assefa (PhD)
    Malaria, which is a mosquito-borne blood disease caused by Plasmodium parasites, is one of the virulent infectious diseases affecting human beings and other animals since antiquity. Even though there were promising progresses in the reduction of malaria morbidity and mortality in the past two decades before the outbreak of COVID-19, the latest two reports of theWorld Health Organization (WHO) statistics indicate that malaria has been overlooked due to the COVID pandemics. Malaria is still prevalent specifically in low resource setting areas such as the sub-Saharan African countries, including Ethiopia. WHO reported that there were 229 million new cases of malaria and 409,000 deaths globally in 2019, alone. Whereas in the year 2021, the morbidity and mortality was reported to rise up to 247 million and 619,000, respectively. Timely diagnosis and treatment as well as good awareness about the disease play a major role to combat malaria. In the current project work, it was intended to design and develop a multi-lingual Android App that offers useful information about the malaria disease and is capable of automatically detecting malaria infected red blood cells (RBCs) from color microscopic images based on a deep learning approach. The Convolutional Neural Network (CNN) based deep learning model was trained, validated and tested on a publicly available dataset composed of microscopic images of RBCs taken from individuals with confirmed malaria infection as well as normal control groups. Experimental results generated from the deep learning model showed that the detection capability of the model achieved 100% training accuracy, 96% validation accuracy and 96% testing accuracy. The developed App avails useful information about malaria disease in general and tips users with fundamental information regarding its prevention and transmission mechanisms acting as an m-health system.
  • No Thumbnail Available
    Item
    Design and Evaluation of Simulated PEM Scanner for EarlyStage Breast Lesion Detection
    (Addis Ababa University, 2022-06) Bethel, Haile; Dawit, Assefa; Samuel, Taddesse (Mr.) Co-Advisor
    Breast cancer is the most commonly diagnosed cancer in females worldwide, contributing around 11.7 % (~2.3 million people) of new cancer cases in 2020 only, with a death rate of 6.9%. Early diagnosis and check-up are essential for effective treatment and reduction of incidences and mortality rates. Different modalities exist to diagnose breast cancers. Positron emission tomography (PET) is the one imaging tool in nuclear medicine providing physiological information about the breast by quantifying the metabolic activities of the cells in the breast tissues. Both whole-body (WB) PET scanners and organ-specific PET scanners are available in the market. But current trends show that there is a complete shift towards dedicated, organ specific PETs. One of those is Positron Emission Mammography (PEM), believed to be better than mammography and other imaging modalities to detect small breast lesions. Semiconductor-based PEM detectors are simulated with good spatial resolution but are expensive. Scintillator-based PET and PEM detectors can provide quit good sensitivity and are cost effective. On the contrary, these detectors cannot detect small breast lesions due to their poor spatial resolution. This requires development of detectors that give rise to better spatial resolution. In the current thesis work, a high-performance PEM scanner is simulated using TOC (Transparent Optical Ceramic) scintillators of 1 x 1 x 10mm 3 crystals with the aim to improve the spatial resolution, sensitivity as well as scattering fraction. Those TOC scintillators are LHO: cerium doped lutetium hafnate (Lu 2 Hf 2 O 7 : Ce), BHO: cerium doped barium hafnate (BaHfO 3 : Ce) and SHO: cerium doped strontium hafnate (SrHfo 3 : Ce). The design was based on the GATE (Geant4 Application for Emission Tomography) simulation software. Its performance was tested and evaluated by following the NEMA (National Electrical Manufacturers Association) NU 4-2008 standards. The complete scanner has 39 heads and 10 x 30 x 59 modules in the detector. Based on the type of scintillator used, the designed scanner provided a spatial resolution between 1.0 and 1.1 mm FWHM (Full Width at Half Maximum) in the axial direction, 7.24% to 9.11% system sensitivity and 11.01% to 11.19% scatter fraction. The design offered good uniformity as well as image quality. The computed spatial resolution, sensitivity and scatter fraction values are superior to those already reported in the literature.
  • No Thumbnail Available
    Item
    Trinion Based WBC Segmentation Using Texture to Detect Acute Lymphoblastic Leukemia
    (Addis Ababa University, 2021-10) Amin, Hussien; Dawit, Assefa (PhD)
    Many diseases are detected based on examination of microscopic images of blood samples. Changes in the blood condition show the development of diseases in an individual. One type of disease caused by change of blood condition is Leukemia. Leukemia can cause early death when it is not treated on time. In Ethiopia, Leukemia accounts to about 35.5% of hematological admissions. The death rate in Ethiopia due to Leukemia is different with time and region. The average death rate is increasing from time to time and shows variation between country side and urban population. Reports from the World Health Organization (WHO) show that death rate due to Leukemia in Ethiopia has reached 5.56% and ranked 18 th highest in the world. Leukemia originates in the bone marrow, a thin material inside the bone. Leukemia is detected by analyzing white blood cells (WBCs also called Leucocytes), one of the constituents of blood along with red blood cells (RBC or Erythrocytes), platelets and blood plasma. WBCs have five different types (Lymphocytes, Myelocytes, Neutrophils, Basophils and Eosinophils) and among these Lymphocytes and Myelocytes are the ones that could start to change in the bone marrow and get infected and become Leukemic or infected cells. These Leukemia cells have strange properties compared to the normal cells in that their growth is abnormal and they survive much longer than the normal cells. They also interrupt functions of the normal cells. Through time, the normal cells perish while leukemia cells still survive. Old leukemia cells last for a longer time and production of new leukemia continue in an abnormal way. Traditionally, Leukemia detection is carried out manually based on visual examination of microscopic images of blood samples. This is lengthy and time taking process which depends on the skills and experiences of the observer which makes the process subjective. In this regard, computer based automated schemes play their great role and several efforts have been made in the literature to develop such schemes. In the current study, a novel mathematical technique for Leukemia detection based on holistic analysis of color microscopic images of blood samples is proposed. The approach utilizes a holistic representation of microscopic blood images in the three (Trinion) space and applies trinion based Fourier transform implemented in the L*a*b color space to extract useful higher order features to segment normal and infected WBCs and classify them. The technique has been applied in analyzing microscopic images acquired from standard ALL-IDB database. Classification of normal and Leukemic WBCs was performed based of Artificial Neural Network (ANN) which resulted in 95.7% sensitivity, 100% specificity and 97.6% accuracy.
  • No Thumbnail Available
    Item
    Application of Virtual Reality for Teaching in the Dissection Room
    (Addis Ababa University, 2021-09) Alemseged, Getachew; Dawit, Assefa (PhD)
    Virtual reality (VR) is a computer graphics technology which can be used to develop applications to support teaching human anatomy. Using VR, virtual 3D models of various parts of the human body can be developed and interacted with. The present thesis work addresses the problem that medical students often encounter in their practice in wet specimens with the absence of cadavers, using kidney as an example. The main objective of the thesis is to reconstruct highly detailed 3D virtual model of the kidney based on small interval cross- sectional images (CT-DICOM dataset), suitable for undergraduate students teaching virtual dissection through animation using kidney as an example, to supplement the wet specimen dissection procedure.. A 3D slicer software is used to develop 3D model of the kidney from the imported CT-DICOM data. Output of the 3D slicer is high poly object which is exported in an STL file format to the Transmutr software for simplifying the number of faces of the model by preserving the overall shapes of the original object which is used by Google sketch up & SimLab Composer software. Google Sketch Up is used for dissecting the kidney while SimLab Composer is used for rendering the 3D image and finally used for interactive VR viewing purpose. The final results of the developed 3D model of the kidney are used for interactive virtual reality viewing using desktop computer and virtually dissecting the kidney using Google sketch Up for visualization of the internal structure of the developed model. The developed 3D model allows students to perform detaching and interactively viewing a dissected kidney sequentially without the need of a supervisor. It can be also used inside the dissecting room to practice virtual kidney dissection by other medical practitioners.
  • No Thumbnail Available
    Item
    Genetic Algorithm based Optimized Radiotherapy Patient Scheduling
    (Addis Ababa University, 2022-02) Metadel, Hailu; Dawit, Assefa
    Radiotherapy is the major means to treat cancer patients. Radiotherapy comprises two phases: pretreatment and treatment on radiation machines. This thesis work focuses on the treatment phase. Treatment consists of multiple, almost daily irradiation appointments, followed by optional imaging and control assignments. The scheduling of radiotherapy appointments is a complex problem due to various medical and scheduling constraints, such as patient category, machine availability, waiting time targets and also due to the size of the problem (i.e., number of machines, facilities and patients). The objective of this thesis is to minimize waiting time and maximize device utilization in) patient’s appointment scheduling. Thus, this thesis presents an optimization algorithm for scheduling of radiotherapy treatments for categorized cancer patients. In order to manage patient information effectively in digital data format a web application is built. This web application registers users (professionals) that are responsible to register patients and includes a database to store patient’s information. Following this, custom genetic algorithm (GA) is developed considering constraints primarily patient category and the rest constraints such as patient in date and time, number of fractions, number of machine and also working days and working hour. Moreover, for the GA to be user friendly a desktop application with graphical user interface (GUI) is developed. The GUI supports the medical professionals to easily manipulate the GA parameters such as number of populations, crossover probability, and mutation probability and also change the dynamic resources or attributes like number of machines, number of patients treated per single machine and number of working days. As a result, the medical professional can schedule patients dynamically. In this thesis best GA performances (i.e., fitness value of 88% - 96.67% accuracy) are obtained for probability crossover (Pc) values between 60% - 80% and probability of mutation (Pm) between 20% - 40%. This means if the health professional sets the cross-over and mutation probability in these ranges, the scheduling will have better optimization, i.e. prioritize high-risk patients, minimize high risk patient waiting time, thus better care for patients. From the resuls, emergency patients are able to get early treatment than radical patients. Compared to traditional manual scheduling, where scheduling is done based on patients arrival date, GA based scheduling enables to prioritize higher risk patients.
  • No Thumbnail Available
    Item
    Toward A Simulation Framework For Magnetic Resonance Fingerprinting Using Spiral Underdamping
    (Addis Ababa University, 2020-12) Muhammed, Ezriku; Dawit, Assefa (PhD)
    Magnetic Resonance (MR) is a powerful and multipurpose measurement technique to look inside the human body using magnetic properties of the body non-invasively. Quantification of tissue properties including the relaxation parameters has long been a goal of magnetic resonance imaging (MRI), to provide a basis for diagnosis, longitudinal study and, inter-patient comparability. However, prolonged acquisition times have hindered the usage of quantification for clinical applications. Magnetic Resonance Fingerprinting (MRF) was introduced as a promising technique for simultaneous and fast quantification of multiple tissue parameters through a new approach to data acquisition and postprocessing. However, the development and optimization of MRF process is time-consuming, expensive which requisite repetitive experiment and often needs a synthetic phantom or human subject to test it on the real scanner and detect the results. This work aimed to develop an implementation of a Simulation Framework for MRF based on spiral under-sampling. Simulation framework for magnetic resonance fingerprinting (MRF) along with evaluating the effect of noise on the parameter map is significantly studied by using custom generated phantom and phantom generated from the brain web of a simulated database. The undersampling capability of MRF is significantly studied and evaluated by comparing the parameter map that is generated at each undersampling level. Significant undersampling is used to make the MRF time-efficient with several undersampling folds and undersampling with the factor of 24-fold is substantially evaluated and results in acceptable tissue quantification result irrespective of the undersampling artifacts. A comparison between the proposed MRF simulation and the existing simulation used for MRF was done and the proposed methods showed superior results to simulate the effect of gradient on the reconstructed image and at the quantified parameter map. The effect of noise on the parameter map is evaluated by adding different levels of noise on the simulated kspace signal. At a given undersampling level, as the level of noise increases, its effect on the parameter maps gets more and more pronounced specifically in the off-resonance map.
  • No Thumbnail Available
    Item
    Customizing the Pressure-based Spirometer for Improving its Accuracy for Chronic Obstructive Pulmonary Disease Tests
    (Addis Ababa University, 2021-11) Ashebir, Worku; Masreshaw, Demelash
    Breathing is a fundamental and essential process for the proper functioning of human being. It is a process of supplying oxygen to the body and removing of waste carbon dioxide from the body. This process takes place through the respiratory system and organs involving the nose, pharynx, trachea, bronchi, and lungs. There are several diseases and conditions that can affect the respiratory system. Chronic obstructive pulmonary disease (COPD) is the most common one that arises from airway obstructions. A differential pressure-based spirometer is the most dominant device used to perform pulmonary function test in order to diagnose and monitor COPD. This pressure-based spirometer acquires a signal through a pressure difference between two points of the patient breathing tube (PBT) created by the patient against the atmospheric pressure. This means as the COPD patient finds it hard to breath, the differential pressure created by the patient across PBT reduces. The detection sensitivity of the PBT and altitude correction are the main important parameters which need to be considered while designing a differential pressure-based spirometry. So the aim of this thesis is to customize a differential pressure-based spirometer device with respect to altitude in order to improve accuracy of COPD tests. In this thesis, LabVIEW software has been used to generate and analyze the measured signal, and customize the spirometer with respect to altitude. Moreover, Bernoulli’s equation has been used to calculate air flowrate and forced vital capacity of the lung which are used to grade COPD test result. Finally, the designed PBT is simulated using Ansys 19.2 software and a prototype is created using 3D printer. The flowrate vs time, and volume vs time graphs were obtained and displayed using LabVIEW. The result shows that the accuracy of COPD test can be improved by increasing the sensitivity of PBT and customizing a pressure-based spirometer using the altitude correction factor during designing and operating the pressure-based spirometer.
  • No Thumbnail Available
    Item
    Heart Arrhythmias Detection and Classification using ECG Signals and Deep Convolutional Neural Networks
    (Addis Ababa University, 2021-12) Wafa, Mohammed; Dawit, Assefa (PhD)
    According to the World Health Organization, almost 17 million people die each year as a result of cardiovascular illness. The irregularity and abnormalities of heartbeat rhythm which is known as arrhythmia is one of the conditions that can affect the cardiovascular system. Electrocardiogram (ECG) is a reliable tool that can be used for monitoring the cardiovascular health. Recently, classifying the ECG signals based on Artificial Intelligence (AI) is increasingly being studied. Convolutional Neural Networks (CNN) in particular have been effectively applied for the classification of ECG signals. Although high prediction accuracies have been reported, majority of previous studies have only been developed to classify limited number of arrhythmias. The methods were developed to evaluate all major types of arrhythmias using 1-D CNN to classify time domain representation of ECG waveforms. However, using 1-D CNNs has limited flexibility due to the use of 1-D kernels. There are methods reported to transform the time series signals into 2-D images using STFT and use 2- D CNN. However, STFT is difficult to apply to non stationary signals; there is no way to resolve the complete frequency content of such signals with a single localizing window size. To overcome this obstacle of Fourier decomposition, the Continuous Wavelet Transform (CWT) could be used to breakdown a signal into wavelets with a high degree of temporal localization. The S-transform could be another option since it takes the advantage of STFT and wavelet. This thesis study uses CNN classifiers for detecting and classifying heart arrhythmias based on analysis of ECG signals in time-frequency domain. The used data were extracted from a subset of MIT-BIH arrhythmia data set, that contain 1000 ECG signals of 17 classes in total, collected from 45 patients. 12 classes were chosen from the subset which include Normal Sinus Rhythm (NSR), Atrial Premature Beat (APB), Atrial Flutter (AFL), Atrial Fibrillation (AFIB), Supraventricular Tachyarrhythmia (SVTA), Premature Ventricular Contraction (PVC), Ventricular Tachycardia (VT), Idioventricular Rhythm (IVR), Ventricular Flutter (VFL), Left Bundle Branch Block Beat (LBBB), Right Bundle Branch Block Beat (RBBB), and Pacemaker Rhythm (PR). The one dimensional ECG signals were transformed into joint time frequency spectrograms using Stockwell transform and into scalograms using Continuous Wavelet Transform (CWT). By using different pretrained networks for classifying spectrograms and scalograms namely GoogleNet, SqueezeNet, and ResNet-50, different results were achieved. GoogleNet pretrained network showed the best v performance when using CWT generated scalograms with 93.85% accuracy, 96.42% precision, 84.14% sensitivity, 99.36% average specificity and 89.86 F1-score. Based on the results, transfer learning especially GoogleNet proved to be efficient in classifying the twodimensional scalograms of cardiac arrhythmias, while reducing the burden of training network from scratch makes it easily applicable. Compared with recent techniques, results obtained using the proposed technique show the great promises of the 2-D CNN model in accurate classification of arrhythmias using CWT and S-transform and the proposed method resulted in higher accuracy and F1-score.
  • No Thumbnail Available
    Item
    Application of CNN in Hypertensive Retinopathy Classification
    (Addis Ababa University, 2022-01) Degel, Sharon; Dawit, Assefa (PhD)
    Hypertension (HTN) as defined by the world health organization (WHO) is when the blood pressure is elevated with a systolic blood pressure equal to or greater than 140mmHg and a diastolic blood pressure equal to or greater than 90mmHg when measured on 2 separate days. HTN, according to Center for Disease Control and Prevention (CDC), raises the risk for stroke and other heart diseases. In a previous study, it was estimated that there were 972 million adults with HTN in 2000; 333 million in developed countries and 639 million people in developing countries. In a review of current trends by WHO, there has been an increase in adults with HTN from 594 million in 1975 to 1.13 billion in year 2015 with a prevalence of 27% in Africa and 18% in the America. Hypertensive Retinopathy (HPR) is damage to the retinal blood vessels caused by HTN. The use of artificial intelligence has recently been applied in Medical Imaging. One of such areas is in classification of eye diseases. In HPR, previous studies only focused on classification according to two classes; normal or HPR. In the current study, a classification method based on four classes according to the Wong and Mitchell classification which gives a classification based on the severity of HTN severity is presented; Normal, Mild, Moderate, and Severe or Malignant HPR. The study explored the idea of applying Convolutional Neural Network (CNN) in classifying HPR. The work focused on images collected solely from patients with HTN and will play an important role in assisting physicians to speed up the process of diagnosis. The study used the HPR features of the retina for classification. Transfer learning using existing pretrained models was employed in classifying the dataset. Five state-of-the-art pretrained models were employed for classification into two classes; normal and abnormal and into four classes: normal and three stages of HTR. The five different neural architectures namely: ResNet-101, GoogleNet, AlexNet, VGG-19 and Xception achieved an accuracy of 91.61%, 93.01%, 87.41%, 90.21% & 85.31% for the 4 Classification task and 100%, 100%,100%, 99.30% & 97.89% for the 2 Classification task respectively. The best accuracy was obtained using GoogleNet. The pretrained models show that with proper tuning of training parameters like the learning rate, number of epochs, batch size, type of
  • No Thumbnail Available
    Item
    Mobile Phone Microscope Imaging for e-health Applications at Low Resource Setting; Image Processing for Automatic Counting of Blood Cells
    (Addis Ababa University, 2021) Mulugeta, Mideksa; Aster, Tsegaye (PhD); Frehiwot, Woldehanna (PhD); Dawit, Assefa (PhD)
    BACKGROUND: currently, there is limited information on study to design web page that incorporates a clinical laboratory atlas and to couple, portable mobile phone- microscope imaging (PMPMI) device for e-health application in low resource settings (specially in Ethiopia) to enable the health extension workers (HEW)/community health workers (CHWs) promote early detection and protection of diseases by means of automatic complete blood cell (CBC) count. MATERIAL and METHODS: collect HP-model mobile phone, Microscope Eye piece, objective lens, 300 clinical laboratory slides; develop a comprehensive technique that includes designing and assembling a mobile attached microscope, a web page that incorporates a clinical laboratory atlas, image sharing apps and rigorous mathematical algorithm for automatic CBC count to test the quality and functionality of the new device. RESULTS: the proposed coupled mobile phone-microscope imaging device is able to share sample images with next level lab technologists/pathologists via image sharing open applications and the developed image processing scheme allows automated CBC count on images acquired through the new coupled system. The counting algorithm offered an overall accuracy of 90% in RBC count and 99.9% in WBC count. Additionally, JossyBME.com web site is developed to upload lab-atlas images for further reference. CONCLUSIONS: The new coupled mobile phone-microscope device functions in white light settings. The work promotes early detection and protection of diseases and presented here as a cost-effective option. The device has been designed in such a way that it could be used not only by HEWs but also by the higher-level hospital laboratory personals. The effectiveness of the developed cell counting algorithm could show the great promises of the proposed imaging system and the new device.
  • No Thumbnail Available
    Item
    Optimizing Operating Rooms’ Facility Layout Design
    (Addis Ababa University, 2021-08) Meba, Hailu; Dawit, Assefa (PhD)
    In Low and Middle-Income Countries such as Ethiopia, most operating rooms (ORs) are built without the proper consideration given to the layout design of the room. This is one of the major causes for the spread of infection. According to WHO, this affects one third of surgical patients in these countries [1]. Research relates the highest bio-burden in an OR to the professionals working in it. This research thesis aims to develop an improved and optimized OR layout [2]. The objective is to maximize infection control by considering the flow patients and of the professionals. Eight hospitals in Addis Ababa were selected for case study via a questionnaire. Literature review was done to study standards and guidelines requirement and recommendation on OR facility layout design and to investigate facility layout problems and modeling techniques. Based on the data collected from case studies and literature reviews on national and international standards, the flow of the professionals inside the OR was studied. It was then developed to an interaction adjacency matrix of the rooms inside the department. Then the OR layout model was created using graph theory technique which has shown to be the most successful modeling technique and the model was implemented on a MATLAB platform. The output was used to create alternative detailed OR designs for surgical center premise set up with minimum requirement and in a general and specialized hospital setups. Additionally, through the questionnaire, application of technologies in the OR facility and knowhow of the OR staff regarding facility layout design were studied. A block layout with 85.6% optimization was acquired. The alternative detailed/architectural designs were made using this block layout. These met national and international standards. The study clearly revealed the possibility of infection control through optimized OR layout design. The research also indicated that there is lack in the application of technologies and in professionals training (regarding their OR facility layout design) within the selected hospital ORs. This indicates that further in-depth research is necessary to collect input data that specifies a more detailed and accurate interaction between rooms in the OR department. In this case, using the developed MATLAB code, up to 96% optimization can be reached. As the staff and the technologies used have direct effect on infection control; on job training for the staff (to give awareness about the environment they work in) and implementation of technological advancements is essential.
  • No Thumbnail Available
    Item
    Simulation of the Effect of Atrioventricular Block on Left Ventricular Performance
    (Addis Ababa University, 2021-10) Ojaj, Stephen Jakuma; Dawit, Assefa (PhD)
    With the growing interests in multiscale computation studies in different fields in recent decades, its application in the biomedical field has been of great importance specially to analyse, process, design and diagnose different biological activities at both microscopic and macroscopic levels. This has resulted into improvement in medical technologies and disease management. Despite the continued efforts to improve computational interventions in biomedical studies, little has been done to understand the cardiovascular system (heart) in terms of its electrical behaviour in relation to its mechanical responses. This gap in computational knowledge especially in normal cardiac physiology and pathological conditions presents a problem to be tackled in order to improve diagnosis, and treatment of different cardio pathological conditions. This thesis investigates the effects of AVN block on left ventricular performance via an electromechanical coupled setup. The cardiac electromechanical properties work on the principles that the electrical impulses from Sinoatrial node (SAN) in the atria via the AVN convey to the ventricles causing mechanical contraction and hence pumping of the blood. A 3D left ventricular model was developed on SOLIDWORKS and imported into COMSOL Multiphysics. Furthermore, through simulation using finite element (FE) analysis software COMSOL Multiphysics, a parametric study was performed on the effect of atrioventricular block on left ventricular function. Based on the data adopted, the effects of varying the current stimulus as parameter were noted and discussed. From our model, observable and quantitative results were derived. The results obtained in this thesis allow the drawing of essential conclusions with regards to the left ventricular mechanical response to degrees of atrioventricular blockage which are essential to further computational studies. Also, in the simplified ventricular model the orthotropic nature of the myocardium, fiber orientations, and fluid mechanics were considered. The transmembrane chemical effects such as calcium handling, potassium, sodium concentration in the cytoplasm and mechano-electrical feed-back were neglected. The perturbations of the electrical impulses for the three AVN block cases resulted into variations in action potential durations (APDs). The variations were also noted on the myocardial voltage dependent stress during the simulations. Conclusively, the LV mechanical function was greatly affected by the variations of impulse stimulus due to AVN blockage.
  • No Thumbnail Available
    Item
    Epileptic Seizure Detection and Source Localization Based on Stockwell Transform
    (Addis Ababa University, 2020-02) Tewodros, Sewnet; Dawit, Assefa (PhD)
    Neurologists often have to scan long term electroencephalogram (EEG) recordings in order to diagnose epilepsy. Detection of seizures from recorded EEG signal is crucial for diagnosis of epilepsy. Localization of the seizure origin is also important for treatment and surgery of focal epilepsy cases. Visual scanning of EEG is time consuming and suffers from issues of subjectivity due to imprecise definition of abnormal seizure EEG patterns. EEG recordings between seizures or inter-ictal EEG findings also offer evidence of epilepsy though not decisive as observed epileptic seizures. Although the main task is detecting seizures, the accuracy of a seizure detection scheme is based on clear characterization of inter-ictal, seizure and normal EEG’s. The challenge here is that abnormal patterns of EEG signals from epilepsy patients are case specific, especially for inter-ictal EEG. Additionally, EEG signals are composed of multiple frequencies and hence non-stationary. This thesis majorly considers temporal lobe epilepsy. An automated EEG signal classification scheme has been proposed for use in efficient detection and source localization of epileptic seizures based on the Stockwell (S) transform. Important features were extracted from the S-transform plane of EEG segments to categorize them into seizure, inter-ictal and normal signals. Classification of the features was done using support vector machine. For classification problem between seizure and normal EEG (recorded with closed eyes and/or open eyes), 100% sensitivity, 100% specificity and 100% accuracy were obtained. For classification between seizure and inter-ictal EEGs recorded from the epileptogenic zone, the proposed scheme achieved 99 % sensitivity, 99% specificity and 99 % accuracy. For seizure and inter-ictal signals recorded from non-epileptogenic zone, the classification scheme resulted in 99% sensitivity, 98% specificity and 98.5% accuracy. Empirical mode decomposition was also employed to improve the performance of the classification between seizure and non-seizure dataset. The methodology used for seizure detection was also employed to automated epileptic focus localization. The features extracted for source localization were intended to characterize focal and non-focal signals. A scatter plot was generated using the features and simple thresholding was able to classify focal and non-focal EEGs with 84% sensitivity, 90.21% specificity and 88% accuracy. The proposed method uses fewer number of features resulting in smaller feature space which in turn makes it simple and robust compared to other schemes proposed in the literature.
  • No Thumbnail Available
    Item
    Statistically Modified Subset Order Subset Expectation Maximization (SMS-OSEM) SPECT Image Reconstruction
    (Addis Ababa University, 2021-12) Emebet, Hailu; Dawit, Assefa (PhD)
    Single photon emission computed tomography (SPECT) imaging is widely implemented in nuclear medicine as its clinical role in the diagnosis and management of several diseases is, many times, very helpful. The goal of reconstruction in tomographic images is as much as possible to recreate the exact image of an object being scanned. Nevertheless, the quality of the reconstructed image depends on the performance of the reconstruction algorithm. One of the most commonly used SPECT reconstruction algorithms in clinical practice is ordered subset expectation maximization (OSEM). It uses a subset of projections to shorten the reconstruction time to reach maximum reconstruction accuracy. However, only few studies are made on the use of statistical measurements to ordered subsets for better reconstruction performance. Hence, the aim of this thesis work is to develop a scheme for use in better SPECT image reconstruction in such a way that there will be improvement on the quality of the reconstructed image as well as reconstruction time. First the SPECT imaging system is simulated and projections of different phantoms (Shepp-Logan, Jaszczak, and Thorax) are calculated. Then the SPECT imaging system matrix is computed using main geometrical parameters of the SPECT instrument. Following this, the projections are grouped into subsets depending on the phantom used. The main contribution of the thesis work is that the subsets are ordered in decreasing order using statistical measurements such as variance, standard deviation and entropy. This measurement allows to find more information about the image being reconstructed. Consequently, a better and faster SPECT image reconstruction method known as Statistically Modified Subset OSEM (SMS-OSEM) is developed. The performance of the SMS-OSEM scheme was compared against the traditional OSEM by varying the number of iterations, the number of subsets and noise levels. The overall performance of the proposed algorithm was checked with different number of iterations (1, 10, 30, 50 and 100) using three different types of phantoms. Based on the phantoms tested using SMS-OSEM algorithm, it was observed that OSEM with variance based subset ordering was able to increase accuracy of the traditional OSEM reconstruction by 15.02% when the number of iterations is low between 1 and 20. For higher number of iterations, the accuracy was increased up to 67.88% depending of the phantom type. In addition, the reconstruction time was reduced by 12.52% for lower number of iterations and by 33.03% for higher number of iterations. The degree of tolerance of the SMS-OSEM method towards noise was tested by adding different amount of Gaussian noise and the algorithm offered better performance than the traditional OSEM scheme.
  • No Thumbnail Available
    Item
    Determination and optimization of Silver Nanoparticle Impregnated Porous Ceramic water filter for Point of Use Water Treatment
    (Addis Ababa University, 2020-11) Getachew, Amogne; Solomon, Kiros (PhD)
    Clean water is a necessity for healthy human beings so is its provision and access. The porous ceramic water filtration pot has been greatly improving the most contaminated tap water for drinking water in developing countries. This research was carried out to determine the efficiency of the AgNP impregnated porous ceramic water filter pots in improving water from bacterial coliforms. The study was undertaken to evaluate the performance of AgNP impregnated ceramic water filter pots in reducing the E. coli in contaminated water. The effect of firing temperature and volume porosity (P) of a pot-type ceramic water filter on the filtration and E. coli removal efficiency is presented. The raw materials used to make the porous ceramic pot are clay soil, sawdust and silver nitrate. Clay soil and sawdust were grinded and sieved with 1mm (clay soil), 0.2mm, 0.4mm, 0.6mm and 0.8mm (Sawdust) opening mesh size and then mixed with water and molded in a pot shape and fired at 900 °C, 1000 °C and 1100 °C. The porosity of the ceramic water filters was varied by changing the screen size of sawdust and percentage of sawdust added in the red clay and measured by the absorption test method using Archimedes’ principle and the E. coli were tested using the membrane filtration procedure. The porosity of the filters was found to be directly proportional to the screen size and percentage of the sawdust and slightly inversely proportional to firing temperatures. The filtration rate of water increased with the increase in the porosity of the AgNP impregnated ceramic water filters. Ceramic water filters designs (clay to sawdust mass ratio of 85:15, 90:10, and 95:5) fired at a temperature of 900 °C, 1000 °C, and 1100 °C for eight hours had total E. coli removal efficiency of 85.6 to 99.999% respectively. Changing in the filter’s design or raw materials and the firing temperature will affect the performance of the produced ceramic water filters pots. The results of this study suggest that the mean flow rate for a properly functioning filter (8.1% by mass sawdust and screen size in between 400μm and 600μm) fired at a temperature of 900 °C is 1.652 L/hr. This flow rate is more than the average liters per day for adults as recommended by World Health Organization (WHO). This filter also removed more than 99.96% of E. coli.
  • No Thumbnail Available
    Item
    Optimized Medical Equipment Replacement Planning
    (Addis Ababa University, 2021-02) Henok, Hussien; Dawit, Assefa (PhD)
    Owing to the limited hospital replacement budget, making selection concerning medical device substitution is a difficult task. If the selection is not planned, it could have a serious impact within the replacement process, which in turn could cause a possible hazard and accident or fatality to patients. This might result in operational and maintenance costs and premature substitution of medical device while failing to replace other devices that need urgent replacement. In this regard, developing a replacement framework that allows optimal use of the available budget is crucial. Managing non-optimized medical device replacement planning in hospitals is often time-consuming and expensive. Competent replacement planning allows a significant reduction in operational and other maintenance related costs. However, most hospitals often replace their medical devices after they have stopped working for an extended period. On the other hand, when a medical device is replaced too early, that involves additional cost to the procurer. Therefore, a technique has to consider the decision-makers to avoid any risk for patients and additional costs to the hospital. This thesis study proposes a comprehensive framework for an optimized replacement planning for medical devices based on the available budget. The system is supposed to take into account the ever-changing technologies in the field of medical devices thereby avoiding the traditional replacement paradigm. The proposed method uses the TFN-AHP model to set up the assessment criteria and evaluate them by contemplating qualitative/quantitative replacement criteria and a Tabu Search based optimization technique to generate a prioritized list of devices to be replaced. Data was collected at selected hospitals picked as pilots in the current study through structured questioners. The model architecture includes fourteen quantitative and qualitative factors descending as main and sub-criteria, which can affect the replacement decision. The proposed model was applied on thirty-five selected medical devices in several categories where devices with higher ERPW (Equipment Replacement Priority Weight) take higher order for replacement and devices with lower ERPW take lower order for replacement. The proposed model uses both relative and absolute measurements to determine score weight for all criteria. Following analysis of the questioners distributed to respondents, eight main factors and three sub-factors were identified for affecting the replacement process. From the distributed questioners, 85% of the participants agreed that there was a major gap in their hospital when medical device has to be replaced. Furthermore, 73% of the respondents agreed that medical device replacement does not consider the most influential replacement factors. In addition, 89% of the respondents agreed that no device replacement plans is practiced in their hospitals. Moreover, 81% of the respondents agreed that hospitals are not accustomed to efficient replacement techniques. About 85% of the respondents agreed that the available hospital budget affected the replacement process. In the proposed model, the identified eight main-factors and three sub-factors score weights were determined by using TFN-AHP technique. This technique combined with respondents scored criteria weights given for the 35 medical devices determined the ERPW for each individual device in order to prepare the priority list. The search for optimal/prioritized list of devices to be replaced was carried out using Tabu search algorithm based on TSPDC optimization setup. Results showed that the developed medical device replacement model quantitatively prioritized the medical devices.
  • No Thumbnail Available
    Item
    Cepstral Analysis of Wideband Ultrasound
    (Addis Ababa University, 2021-03) Eyob, Adugnaw; Dawit, Assefa (PhD)
    Ultrasound is a pressure wave with frequency beyond20 ������ . Wideband ultrasound is ultrasound pulse with mega range of frequency components. Most of the currently available ultrasound transducers are narrow banded and fail to provide better axially resolved images for tissues with multiple layers. The methodology used in this thesis models multi-layered biological medium based on linear acoustics of pulse-echo detection principle, normal incidence, longitudinal ultrasonic propagation and investigates the feasibility to detect periodicity. Ultrasound propagation data was generated synthetically and subjected to cepstral analysis to detect periodicity in a multilayered skin tissue model. Rectangular pulses with a center frequency of 16-30 MHz and pulse duration of 1.2 × 10−7s and 0.8 × 10−7s were applied to a 4-layered medium. The output is measured and cepstral analysis was applied to determine the feasibility of periodicity detection. For layers separated by equal thicknesses, the cepstral peaks existed at equal intervals where as in the case of different layer thicknesses, peaks existed at integer multiple of the thinnest layer thickness. In cepstral analysis, when the cepstral peaks exist at equal intervals or integer multiples of the shortest time of flight (time of flight to the thinnest layer), periodicity detection is guaranteed. It is concluded that periodicity is detected with wideband ultrasound pulses and the minimum and maximum bandwidth are determined based on the duration of the pulse. The possible limitations with the thesis are the assumption of normal incidence planar waveforms, linear ultrasound propagation, and parallel surfaces.