Pub Date : 2018-11-01DOI: 10.1109/BMEICON.2018.8609991
Siriphan Phetnuam, C. Pintavirooj, S. Tungjitkusolmun
This paper describes design game and development exercise device for wrist and forearm of elder. In 2009, the number of the senior population has increased rapidly. The society has entered into an aging society. And senior population ages more than 80 years old have sickness, Organ degeneration and someone have a disability. Exercise is one of the important things that can keep the elderly have good health and reduce reliance should others. However, the senior population should not over the exercise. The design game and development of equipment for exercise wrist and forearm to the elderly person. To encourage older people to exercise more. Also, this device can apply to physical therapy for wrist and forearm of the patient. Results of goniometry, EMG and total earning score from playing games are increased due to more flexible effect to muscle after playing games. Furthermore, an extension of equipment and games will be developed for more exercise or physical therapy in other positions.
{"title":"Design and Development of Equipment Wrist and Forearm Physical Therapeutic in Elderly Persons","authors":"Siriphan Phetnuam, C. Pintavirooj, S. Tungjitkusolmun","doi":"10.1109/BMEICON.2018.8609991","DOIUrl":"https://doi.org/10.1109/BMEICON.2018.8609991","url":null,"abstract":"This paper describes design game and development exercise device for wrist and forearm of elder. In 2009, the number of the senior population has increased rapidly. The society has entered into an aging society. And senior population ages more than 80 years old have sickness, Organ degeneration and someone have a disability. Exercise is one of the important things that can keep the elderly have good health and reduce reliance should others. However, the senior population should not over the exercise. The design game and development of equipment for exercise wrist and forearm to the elderly person. To encourage older people to exercise more. Also, this device can apply to physical therapy for wrist and forearm of the patient. Results of goniometry, EMG and total earning score from playing games are increased due to more flexible effect to muscle after playing games. Furthermore, an extension of equipment and games will be developed for more exercise or physical therapy in other positions.","PeriodicalId":232271,"journal":{"name":"2018 11th Biomedical Engineering International Conference (BMEiCON)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126970019","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 : 2018-11-01DOI: 10.1109/BMEICON.2018.8609955
S. Umchid, Pitchaya Limhaprasert, Sitthichai Chumsoongnern, Tanun Petthong, T. Leeudomwong
In general, the people with physical disability come from many reasons such as injury from accident, age and health problems. Therefore, wheelchair is needed to use when handicapped people would like to travel to any places by themselves. However, hands and arms must be used to operate the wheelchair. Consequently, people with hands and arms impairment finds difficult to use a typical wheelchair. These people need to get help from other people around to control the wheelchair and it will create a big problem when these people would like to travel alone. Therefore, the objective of this work is to design, develop and construct a voice controlled automatic wheelchair. The developed wheelchair is able to operate by using the voice commands through the given input. The principle of the developed wheelchair consists of motor system, voice recognition module that would be controlled by the microcontroller. The automatic obstacle detection system is included to the developed wheelchair by using ultrasonic sensors in order to brake the developed wheelchair immediately when any obstacles suddenly come in the way of the developed wheelchair. Therefore, the developed voice controlled wheelchair can provide easy access for people with physical disability and also offer automatic protection from obstacle collision if the mistake of any voice commands occurs.
{"title":"Voice Controlled Automatic Wheelchair","authors":"S. Umchid, Pitchaya Limhaprasert, Sitthichai Chumsoongnern, Tanun Petthong, T. Leeudomwong","doi":"10.1109/BMEICON.2018.8609955","DOIUrl":"https://doi.org/10.1109/BMEICON.2018.8609955","url":null,"abstract":"In general, the people with physical disability come from many reasons such as injury from accident, age and health problems. Therefore, wheelchair is needed to use when handicapped people would like to travel to any places by themselves. However, hands and arms must be used to operate the wheelchair. Consequently, people with hands and arms impairment finds difficult to use a typical wheelchair. These people need to get help from other people around to control the wheelchair and it will create a big problem when these people would like to travel alone. Therefore, the objective of this work is to design, develop and construct a voice controlled automatic wheelchair. The developed wheelchair is able to operate by using the voice commands through the given input. The principle of the developed wheelchair consists of motor system, voice recognition module that would be controlled by the microcontroller. The automatic obstacle detection system is included to the developed wheelchair by using ultrasonic sensors in order to brake the developed wheelchair immediately when any obstacles suddenly come in the way of the developed wheelchair. Therefore, the developed voice controlled wheelchair can provide easy access for people with physical disability and also offer automatic protection from obstacle collision if the mistake of any voice commands occurs.","PeriodicalId":232271,"journal":{"name":"2018 11th Biomedical Engineering International Conference (BMEiCON)","volume":"72 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126104718","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 : 2018-11-01DOI: 10.1109/BMEICON.2018.8609999
Chadapa Boonyoung, A. Kwanyuang, S. Chatpun
The applying posteroanterior (PA) load through the spinous process of the vertebral bone is one of the methods for assessment and treatment for back pain in physical therapy. Central PA mobilization is crucial to be investigated the harmful effect on osteoporotic vertebral bone. Therefore, the objective of our study was to investigate the effect of PA load on elderly L1 lumbar vertebra geometry with different bone properties. The finite element model of L1 vertebra was generated from elderly computed tomography images. A 100 N PA load was applied at posterior aspect of spinous process of L1 vertebra in two different homogeneous material properties; (1) healthy L1, (2) osteoporotic L1. The distribution of von Mises stresses and minimum principal strains in mid-transverse sections of L1 vertebra was determined. The results revealed that PA load caused higher values of stresses and strains at pedicles and laminae in transverse section of L1 vertebra. Moreover, changing the elastic modulus influenced stresses and strains distributions in transverse sections of L1 vertebra. In conclusion, applying PA force through spinous process tends to cause a crack initiation at pedicles and laminae in L1 elderly vertebra.
通过椎体棘突施加后前路负荷是物理治疗中评估和治疗背痛的方法之一。中央PA移位对骨质疏松性椎体骨的危害研究至关重要。因此，我们的研究目的是探讨PA负荷对具有不同骨特性的老年L1腰椎几何形状的影响。L1椎体有限元模型由老年人计算机断层图像生成。采用两种不同均质材料对L1椎棘突后侧施加100 N PA载荷;(1)健康L1，(2)骨质疏松L1。测定了L1椎体中横截面von Mises应力和最小主应变的分布。结果表明，PA载荷使L1椎体横切面椎弓根和椎板处的应力和应变值升高。此外，改变弹性模量会影响L1椎体横截面的应力和应变分布。综上所述，通过棘突施加PA力容易导致L1老年性椎体椎弓根和椎板产生裂纹。
{"title":"A finite element study of posteroanterior lumbar mobilization on elderly vertebra geometry","authors":"Chadapa Boonyoung, A. Kwanyuang, S. Chatpun","doi":"10.1109/BMEICON.2018.8609999","DOIUrl":"https://doi.org/10.1109/BMEICON.2018.8609999","url":null,"abstract":"The applying posteroanterior (PA) load through the spinous process of the vertebral bone is one of the methods for assessment and treatment for back pain in physical therapy. Central PA mobilization is crucial to be investigated the harmful effect on osteoporotic vertebral bone. Therefore, the objective of our study was to investigate the effect of PA load on elderly L1 lumbar vertebra geometry with different bone properties. The finite element model of L1 vertebra was generated from elderly computed tomography images. A 100 N PA load was applied at posterior aspect of spinous process of L1 vertebra in two different homogeneous material properties; (1) healthy L1, (2) osteoporotic L1. The distribution of von Mises stresses and minimum principal strains in mid-transverse sections of L1 vertebra was determined. The results revealed that PA load caused higher values of stresses and strains at pedicles and laminae in transverse section of L1 vertebra. Moreover, changing the elastic modulus influenced stresses and strains distributions in transverse sections of L1 vertebra. In conclusion, applying PA force through spinous process tends to cause a crack initiation at pedicles and laminae in L1 elderly vertebra.","PeriodicalId":232271,"journal":{"name":"2018 11th Biomedical Engineering International Conference (BMEiCON)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124963173","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 : 2018-11-01DOI: 10.1109/BMEICON.2018.8609969
M. Nouman, S. Chatpun, Tulaya Prachgosin, W. Leelasamran
Overweight and obesity are growing health complications mostly associated with metabolic and musculoskeletal comorbidities. The knowledge about the effects of obesity on the plantar pressure distribution in diabetic population is lacking. The purpose of this study was to assess the differences regarding plantar pressure distribution in participants with diabetic neuropathic feet who had a different body mass index (BMI). Peak plantar pressure was measured in 12 participants during level walking. The subjects were classified into three categories, each containing 4 participants, as non-obese, overweight and obese according to their BMI values. Peak plantar pressure was determined for the hindfoot, midfoot and forefoot regions using Pedar-X® in-shoe pressure measurement system. Lower peak plantar pressure was observed in midfoot compared to the hindfoot and forefoot. There was no significant difference in peak plantar pressure between the groups for forefoot and hindfoot. However, the obese group showed a significant higher peak plantar pressure in midfoot compared to the non-obese and overweight diabetic foot with neuropathy. Therefore, the high peak plantar pressure at the midfoot can cause a foot pain in obese diabetic neuropathic foot.
{"title":"Plantar pressure distribution in non-obese, overweight and obese subjects with diabetic neuropathy while walking","authors":"M. Nouman, S. Chatpun, Tulaya Prachgosin, W. Leelasamran","doi":"10.1109/BMEICON.2018.8609969","DOIUrl":"https://doi.org/10.1109/BMEICON.2018.8609969","url":null,"abstract":"Overweight and obesity are growing health complications mostly associated with metabolic and musculoskeletal comorbidities. The knowledge about the effects of obesity on the plantar pressure distribution in diabetic population is lacking. The purpose of this study was to assess the differences regarding plantar pressure distribution in participants with diabetic neuropathic feet who had a different body mass index (BMI). Peak plantar pressure was measured in 12 participants during level walking. The subjects were classified into three categories, each containing 4 participants, as non-obese, overweight and obese according to their BMI values. Peak plantar pressure was determined for the hindfoot, midfoot and forefoot regions using Pedar-X® in-shoe pressure measurement system. Lower peak plantar pressure was observed in midfoot compared to the hindfoot and forefoot. There was no significant difference in peak plantar pressure between the groups for forefoot and hindfoot. However, the obese group showed a significant higher peak plantar pressure in midfoot compared to the non-obese and overweight diabetic foot with neuropathy. Therefore, the high peak plantar pressure at the midfoot can cause a foot pain in obese diabetic neuropathic foot.","PeriodicalId":232271,"journal":{"name":"2018 11th Biomedical Engineering International Conference (BMEiCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123946524","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 : 2018-11-01DOI: 10.1109/BMEICON.2018.8609939
Chih-Hsiang Chang, Kenta Simba, Takahiro Asahina, K. Kotani, Y. Jimbo
Temporal learning is one of the most basic ability within human brain, which enables people to perform complex tasks as playing and skilled works. However, the mechanism is not well understood. Recent studies have shown that neurons in whole cell recording in brain slices have ability to remember given time interval stimulation. However, the mechanism behind temporal memory and how the learned pattern changes performance within network spontaneous activity remains unknown. To understand the effect of temporal learning in network activity, our team uses in vitro models present as the simplest neuronal network for studying properties of network dynamics, and show how activity changes to learned stimulation in neuronal networks, which may imply long term learning also possess within cortical cultures.
{"title":"Spontaneous Activity and Evoked response change to 100ms temporal stimulation in Dissociated Neuronal Networks","authors":"Chih-Hsiang Chang, Kenta Simba, Takahiro Asahina, K. Kotani, Y. Jimbo","doi":"10.1109/BMEICON.2018.8609939","DOIUrl":"https://doi.org/10.1109/BMEICON.2018.8609939","url":null,"abstract":"Temporal learning is one of the most basic ability within human brain, which enables people to perform complex tasks as playing and skilled works. However, the mechanism is not well understood. Recent studies have shown that neurons in whole cell recording in brain slices have ability to remember given time interval stimulation. However, the mechanism behind temporal memory and how the learned pattern changes performance within network spontaneous activity remains unknown. To understand the effect of temporal learning in network activity, our team uses in vitro models present as the simplest neuronal network for studying properties of network dynamics, and show how activity changes to learned stimulation in neuronal networks, which may imply long term learning also possess within cortical cultures.","PeriodicalId":232271,"journal":{"name":"2018 11th Biomedical Engineering International Conference (BMEiCON)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127164747","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 : 2018-11-01DOI: 10.1109/BMEICON.2018.8609962
Syna Sreng, Noppadol Maneerat, Khin Yadanar Win, K. Hamamoto, Ronakorn Panjaphongse
Diabetic retinopathy is a complication of the eye damage and can lead to being blindness if it is late for treatment. Microaneurysms, exudates, hemorrhages and cotton wool spots are the lesions associated with diabetic retinopathy. Numerous studies have been done on the detection of microaneurysms, and hemorrhages, as well as exudates whereas only a few research works for detection of cotton wool spots, mainly because of the fact that its appearances are difficult to filter out from the background and not clearly visible. In this paper, an algorithm is proposed to detect cotton wool spots based on integrating principal components analysis and support vector machine. First, preprocessing is performed to enhance the retinal images. Then adaptive thresholding method is used to roughly extract the cotton wool spot from the background. Support vector machine and principal components analysis are further applied respectively to select the important features from morphologies, first-order statistics, gray level occurrence matrix and lacunarity. The proposed method was evaluated with local and DIARETDB1 datasets containing 289 images. Given a success rate of accuracy 90.47 %, sensitivity 85.29%, and specificity 90.12% with the average computational time 16.47 seconds per image on cotton wool spots detection, this system performed better by comparing to the previous research works.
{"title":"Classification of Cotton Wool Spots Using Principal Components Analysis and Support Vector Machine","authors":"Syna Sreng, Noppadol Maneerat, Khin Yadanar Win, K. Hamamoto, Ronakorn Panjaphongse","doi":"10.1109/BMEICON.2018.8609962","DOIUrl":"https://doi.org/10.1109/BMEICON.2018.8609962","url":null,"abstract":"Diabetic retinopathy is a complication of the eye damage and can lead to being blindness if it is late for treatment. Microaneurysms, exudates, hemorrhages and cotton wool spots are the lesions associated with diabetic retinopathy. Numerous studies have been done on the detection of microaneurysms, and hemorrhages, as well as exudates whereas only a few research works for detection of cotton wool spots, mainly because of the fact that its appearances are difficult to filter out from the background and not clearly visible. In this paper, an algorithm is proposed to detect cotton wool spots based on integrating principal components analysis and support vector machine. First, preprocessing is performed to enhance the retinal images. Then adaptive thresholding method is used to roughly extract the cotton wool spot from the background. Support vector machine and principal components analysis are further applied respectively to select the important features from morphologies, first-order statistics, gray level occurrence matrix and lacunarity. The proposed method was evaluated with local and DIARETDB1 datasets containing 289 images. Given a success rate of accuracy 90.47 %, sensitivity 85.29%, and specificity 90.12% with the average computational time 16.47 seconds per image on cotton wool spots detection, this system performed better by comparing to the previous research works.","PeriodicalId":232271,"journal":{"name":"2018 11th Biomedical Engineering International Conference (BMEiCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129794903","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 : 2018-11-01DOI: 10.1109/BMEICON.2018.8609944
K. Shimba, Y. Jimbo, K. Kotani
Brain is composed of a great number of neurons, which interconnect via axons. Although axons were regarded as digital cable in conventional view, recently that is thought as analogue cable and a computational unit. Here, we developed a microdevice to guide axons on multiple electrodes, and record response of axons to chemical reagent. Microfabrication based structural guidance and surface treatment with cell adherent and repellent reagent were combined to make a novel device. Then, changes in axonal conduction delay with various concentration of sodium channel blockers was recorded to evaluate suitability of our method. Axon showed different concentration dependent changes to tetrodotoxin and lidocaine, suggesting that our device is capable to detect dose-dependent response of axons.
{"title":"Microtunnel-Based Recording for Evaluating Axon Conduction Change after Chemical Treatment","authors":"K. Shimba, Y. Jimbo, K. Kotani","doi":"10.1109/BMEICON.2018.8609944","DOIUrl":"https://doi.org/10.1109/BMEICON.2018.8609944","url":null,"abstract":"Brain is composed of a great number of neurons, which interconnect via axons. Although axons were regarded as digital cable in conventional view, recently that is thought as analogue cable and a computational unit. Here, we developed a microdevice to guide axons on multiple electrodes, and record response of axons to chemical reagent. Microfabrication based structural guidance and surface treatment with cell adherent and repellent reagent were combined to make a novel device. Then, changes in axonal conduction delay with various concentration of sodium channel blockers was recorded to evaluate suitability of our method. Axon showed different concentration dependent changes to tetrodotoxin and lidocaine, suggesting that our device is capable to detect dose-dependent response of axons.","PeriodicalId":232271,"journal":{"name":"2018 11th Biomedical Engineering International Conference (BMEiCON)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123406827","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 : 2018-11-01DOI: 10.1109/BMEICON.2018.8609937
Hiromu Miyata, K. Shimba, Y. Miyamoto, T. Yagi
We report a cell patterning method using the magneto-Archimedes effect. With this method, we apply magnetic force to cells in an arbitrary direction at an arbitrary time, allowing patterning in two dimensions. To evaluate this method, we performed three experiments. First, we verified that cell-sized fluorescent particles are moved by the magneto-Archimedes effect. Second, we confirmed that nerve cells survive in paramagnetic solvent. Third, we then developed a setup to observe samples for 24 h while applying a magnetic force. Using this setup, we applied a magnetic force to nerve cells in the horizontal direction to move them. The results reveal that the magnetic force is sufficient to move suspended cell-sized particles.
{"title":"Method for controlling non-labeled cell migration using the magneto-Archimedes effect","authors":"Hiromu Miyata, K. Shimba, Y. Miyamoto, T. Yagi","doi":"10.1109/BMEICON.2018.8609937","DOIUrl":"https://doi.org/10.1109/BMEICON.2018.8609937","url":null,"abstract":"We report a cell patterning method using the magneto-Archimedes effect. With this method, we apply magnetic force to cells in an arbitrary direction at an arbitrary time, allowing patterning in two dimensions. To evaluate this method, we performed three experiments. First, we verified that cell-sized fluorescent particles are moved by the magneto-Archimedes effect. Second, we confirmed that nerve cells survive in paramagnetic solvent. Third, we then developed a setup to observe samples for 24 h while applying a magnetic force. Using this setup, we applied a magnetic force to nerve cells in the horizontal direction to move them. The results reveal that the magnetic force is sufficient to move suspended cell-sized particles.","PeriodicalId":232271,"journal":{"name":"2018 11th Biomedical Engineering International Conference (BMEiCON)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115557814","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 : 2018-11-01DOI: 10.1109/BMEICON.2018.8609954
Christina Gsaxner, Birgit Pfarrkirchner, L. Lindner, Antonio Pepe, P. Roth, J. Egger, J. Wallner
In this contribution, we propose an automatic ground truth generation approach that utilizes Positron Emission Tomography (PET) acquisitions to train neural networks for automatic urinary bladder segmentation in Computed Tomography (CT) images. We evaluated different deep learning architectures to segment the urinary bladder. However, deep neural networks require a large amount of training data, which is currently the main bottleneck in the medical field, because ground truth labels have to be created by medical experts on a time-consuming slice-by-slice basis. To overcome this problem, we generate the training data set from the PET data of combined PET/CT acquisitions. This can be achieved by applying simple thresholding to the PET data, where the radiotracer accumulates very distinct in the urinary bladder. However, the ultimate goal is to entirely skip PET imaging and its additional radiation exposure in the future, and only use CT images for segmentation.
{"title":"PET-Train: Automatic Ground Truth Generation from PET Acquisitions for Urinary Bladder Segmentation in CT Images using Deep Learning","authors":"Christina Gsaxner, Birgit Pfarrkirchner, L. Lindner, Antonio Pepe, P. Roth, J. Egger, J. Wallner","doi":"10.1109/BMEICON.2018.8609954","DOIUrl":"https://doi.org/10.1109/BMEICON.2018.8609954","url":null,"abstract":"In this contribution, we propose an automatic ground truth generation approach that utilizes Positron Emission Tomography (PET) acquisitions to train neural networks for automatic urinary bladder segmentation in Computed Tomography (CT) images. We evaluated different deep learning architectures to segment the urinary bladder. However, deep neural networks require a large amount of training data, which is currently the main bottleneck in the medical field, because ground truth labels have to be created by medical experts on a time-consuming slice-by-slice basis. To overcome this problem, we generate the training data set from the PET data of combined PET/CT acquisitions. This can be achieved by applying simple thresholding to the PET data, where the radiotracer accumulates very distinct in the urinary bladder. However, the ultimate goal is to entirely skip PET imaging and its additional radiation exposure in the future, and only use CT images for segmentation.","PeriodicalId":232271,"journal":{"name":"2018 11th Biomedical Engineering International Conference (BMEiCON)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115935092","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：