{"title":"Automated Diagnosis of Lung Cancer with the Use of Deep Convolutional Neural Networks on Chest CT","authors":"Joongwon Kim, Hojun Lee, Taeseon Yoon","doi":"10.1145/3168776.3168798","DOIUrl":"https://doi.org/10.1145/3168776.3168798","url":null,"abstract":"For the past several decades, machine learning has greatly enhanced the process of image analysis. With the development of deep learning technologies in the 21st century, image recognition has gained applicability to various technologies such as automated driving system, face recognition and medical data processing. This research attempts to diagnose lung cancer using chest CT of patients and non-patients. A modified form of Deep Convolutional Neural Network is introduced, which involves using multiple 2D convolutional neural networks on individual slices and combining the results to diagnose patients and non-patients. Each patient/non-patient's chest CT data were first segmented for the lung features and stored into three-dimensional arrays. The preprocessed three-dimensional arrays were fed into the CNN framework, and the parameters of the network were trained. Many iterations of the process with enough data modified network parameters in a way that the network was able to diagnose CT scans of patients with accuracy between 70~80%.","PeriodicalId":253305,"journal":{"name":"Proceedings of the 2017 4th International Conference on Biomedical and Bioinformatics Engineering","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124104940","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}
{"title":"Improvement of Sentinel Lymph Node Detection after Radiopharmaceutical Injection of 99mTc Phytate Colloid","authors":"Yasuyuki Takahashi, Akiko Iriuchijima, Chihiro Ishii","doi":"10.1145/3168776.3168792","DOIUrl":"https://doi.org/10.1145/3168776.3168792","url":null,"abstract":"A sentinel lymph node (SLN) is defined as the lymph node to which it is most likely cancer cells will spread from a primary tumor. Although lymphoscintigraphy is a useful method of detecting malignancy in a sentinel node, conventional lympho-scintigraphy does not determine the exact anatomical location of that node. Breast cancer has the property of spreading to the whole body through the lymph nodes around the breast. If lymph node metastases are negative, a large lymphadenectomy is generally unnecessary. However, in lymphoscintigraphy with a radiopharmaceutical, the image may be less than ideal. We investigated three methods of image improvement for lympho-scintigraphy of breast cancer. Lymphoscintigraphy was performed 12 hours after injection of 37 MBq of 99mTc-phytate colloid into the peritumoral region. The particle size of 99mTc-phytate was 150-200 nm (labeling after 15 min). Images were obtained with dual-energy windows of 140±10 keV for the primary image and 90±20 keV for the scatter image. Image processing employed the Annular Background Subtraction (ABS) method and logarithmic analysis. In brief, first the dosage site was obliterated automatically, and then the background was removed. Next, the logarithm of each pixel value was taken to improve image contrast. Third, a binarization was employed for the pixels in the scatter image, and an outline was extracted. Three kinds of logarithmic processing were used in the three versions of image processing in attempting to improve the detection of the SLN. In addition, it was not necessary to cover the injection position with lead and metastasis of the injection position neighborhood was detected well.","PeriodicalId":253305,"journal":{"name":"Proceedings of the 2017 4th International Conference on Biomedical and Bioinformatics Engineering","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131266468","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}
{"title":"An In-Air Signature Verification System Using Wi-Fi Signals","authors":"Han Cheol Moon, Se-In Jang, Kangrok Oh, K. Toh","doi":"10.1145/3168776.3168799","DOIUrl":"https://doi.org/10.1145/3168776.3168799","url":null,"abstract":"This paper presents a Wi-Fi based system for in-air signature verification. The proposed system is able to authenticate in-air signatures which are captured through Wi-Fi signals. The system consists of four main stages namely, data acquisition, preprocessing, feature extraction and matching. The proposed system shows an average equal error rate of 4.31% on an in-house dataset which consists of 1040 samples collected from 13 subjects. This experiment shows that the Wi-Fi signals can be applied to in-air signature verification effectively.","PeriodicalId":253305,"journal":{"name":"Proceedings of the 2017 4th International Conference on Biomedical and Bioinformatics Engineering","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125489914","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}
{"title":"Study on Repositioning of Comminuted Fractured Bones for Computer-Aided Preoperative Planning","authors":"I. Idram, J. Lai, T. Essomba, P. Lee","doi":"10.1145/3168776.3168801","DOIUrl":"https://doi.org/10.1145/3168776.3168801","url":null,"abstract":"The objective of this study is to provide a virtual simulation of bone fracture reduction system for encouraging computer aided preoperative planning (CAPP) orthopedic surgery, by emphasizing the study into bone fracture registration algorithms to improve correctness and accuracy of bone reduction. A concept and application program for 3D simulation based on personal computer presented, enabling surgeons to relocate fracture fragments onto their original position. This laboratory default software, named PhysiGuide, employed to deal with a comminuted fracture fragments reduction. Four different registration techniques proposed: pairs point, mirrored-bone, anatomy landmarks and fracture line constraints. A proximal femoral fracture generated from CT scans used for evaluating the performance of the proposed registration. Displacements distant of fragments after reduction are calculated and compared to healthy bones as a ground truth. The translation and rotation errors in repositioning calculation and the contact between fracture fragments should be within a clinically acceptable range. The experimental results show the lowest displacement and good stability obtained by using the method of fracture line constraint. The root mean square error is ± 1.097 mm.","PeriodicalId":253305,"journal":{"name":"Proceedings of the 2017 4th International Conference on Biomedical and Bioinformatics Engineering","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121202404","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}
Danny Chin Wei-Kit, Steven Lim, Pang Yean-Ling, Wong Kam-Huei
{"title":"Application of Organosolv Pretreatment on Pennisetum Purpureum for Lignin Removal and Cellulose Recovery","authors":"Danny Chin Wei-Kit, Steven Lim, Pang Yean-Ling, Wong Kam-Huei","doi":"10.1145/3168776.3168781","DOIUrl":"https://doi.org/10.1145/3168776.3168781","url":null,"abstract":"Pennisetum Purpureum or Napier Grass, a native to African grass happened to be one of the most promising candidates for bioethanol production. However, literature studies on the organosolv pretreatment process for P. Purpureum were relatively rare. Therefore, in this research, organosolv pretreatment on P. Purpureum was studied and compared with different types of solvent (1-pentanol and ethylene glycol) and homogeneous catalysts (sodium hydroxide and sulfuric acid) in order to provide the feasibility study and filling the current research gap. The chemical composition of P. Purpureum was found to comprise of 21.50% lignin, 54.67% alpha cellulose and 23.83% of beta cellulose and hemicellulose. The substantial composition of cellulose and hemicellulose in P. Purpureum proved its promising potential as a raw material for bioethanol production. Ethylene glycol with concentration of 50.0 v/v% with addition of 2.0 v/v% of sodium hydroxide had proven to be the most effective organosolv pretreatment combination in removal of lignin (83.4%). In terms of lignocellulosic component recovery, this pretreatment solvent achieved up to 70.10% alpha cellulose recovery and 97.90% beta cellulose and hemicellulose recovery.","PeriodicalId":253305,"journal":{"name":"Proceedings of the 2017 4th International Conference on Biomedical and Bioinformatics Engineering","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124881483","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}
R. Saputra, Billy Muhamad Iqbal, examiner Amalia Suzianti, examiner Erlinda Muslim, examiner Romandhani Ardi
{"title":"Stress Emotion Evaluation in Multiplayer Online Battle Arena (MOBA) Video Game Related to Gaming Rules Using Electroencephalogram (EEG)","authors":"R. Saputra, Billy Muhamad Iqbal, examiner Amalia Suzianti, examiner Erlinda Muslim, examiner Romandhani Ardi","doi":"10.1145/3168776.3168797","DOIUrl":"https://doi.org/10.1145/3168776.3168797","url":null,"abstract":"One of the functions of playing video games is place for entertainment, but there are also people become stress while playing video games because of frustration (fail to achieve objective in video games). One of video games genre that nowadays is popular is Multi Player Online Battle Arena (MOBA). This MOBA games have high complexity and more challenging for player, so this genre is suitable for this research to see what in game events that makes player's stress. This research objective is to evaluate stress when playing video games using cognitive ergonomic approach to see what in-game characteristic that increase stress. Methods for this research are frequency analysis from average power, asymmetry, and alpha/beta ratio also theta/beta ratio. Frequency Analysis is conducted by using electroencephalogram data from respondent while playing DOTA 2. Based on result of this research, there are some conditions that affect and did not affect to player's stress to both experienced and first time player.","PeriodicalId":253305,"journal":{"name":"Proceedings of the 2017 4th International Conference on Biomedical and Bioinformatics Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130016846","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}
{"title":"Determination of Total Flavonoid Content in Flos Sophorae Immaturus Using Near Infrared Spectroscopy","authors":"Xiaoli Liu","doi":"10.1145/3168776.3168791","DOIUrl":"https://doi.org/10.1145/3168776.3168791","url":null,"abstract":"Near infrared spectroscopy combined with multivariate calibration methods was used to analyze the total flavonoid content in Flos Sophorae Immaturus in this paper. Principal component regression (PCR), partial least squares regression (PLSR) and support vector regression (SVR) were performed comparatively to develop calibration models. Data preprocessing methods and calibration model parameters were independently optimized for each case. The performance of SVR model was superior to PLSR and PCR models. The root mean square error of prediction (RMSEP) and correlation coefficient of prediction (Rp 2) of SVR model were 0.0025 and 0.9690, respectively. Results showed that NIR spectroscopy combined with SVR has significant potential in quantitative analysis of flavonoid content in Flos Sophorae Immaturus.","PeriodicalId":253305,"journal":{"name":"Proceedings of the 2017 4th International Conference on Biomedical and Bioinformatics Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129099241","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}
{"title":"Proceedings of the 2017 4th International Conference on Biomedical and Bioinformatics Engineering","authors":"","doi":"10.1145/3168776","DOIUrl":"https://doi.org/10.1145/3168776","url":null,"abstract":"","PeriodicalId":253305,"journal":{"name":"Proceedings of the 2017 4th International Conference on Biomedical and Bioinformatics Engineering","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125349224","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}