K. Mitsis, K. Zarkogianni, K. Dalakleidi, G. Mourkousis, K. Nikita
In this paper, preliminary results of the evaluation of a serious game promoting nutrition literacy (NL) and food literacy (FL) are presented. The serious game's effectiveness was evaluated in terms of educational value and user experience through a two-part evaluation strategy. In the first part, a quasi-experimental study was designed to assess the serious game's educational value compared to an alternative intervention based on the study of text-based material. Appropriate questionnaires were delivered prior to, immediately after, and one week after the intervention. In the second part of the evaluation strategy, the user experience was measured by means of the Game Experience Questionnaire (GEQ). Nineteen and 29 participants enrolled in the first and second part of the evaluation, respectively. The results of the study showed that both serious game and control intervention enhance user's NL and FL skills (p-value = 0.002, 0.025 respectively). Comparison between the two groups did not yield significant results (p-value = 0.25). Increased levels of competence, immersion, flow and positive affect were declared in the GEQ demonstrating the attractiveness of the serious game. Moreover, the study revealed an important association between the level of game interaction, as measured by the number of mouse clicks per second, and the user experience. Intermediate levels of mouse interaction indicate lower user engagement.
{"title":"Evaluation of a Serious Game Promoting Nutrition and Food Literacy: Experiment Design and Preliminary Results","authors":"K. Mitsis, K. Zarkogianni, K. Dalakleidi, G. Mourkousis, K. Nikita","doi":"10.1109/BIBE.2019.00096","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00096","url":null,"abstract":"In this paper, preliminary results of the evaluation of a serious game promoting nutrition literacy (NL) and food literacy (FL) are presented. The serious game's effectiveness was evaluated in terms of educational value and user experience through a two-part evaluation strategy. In the first part, a quasi-experimental study was designed to assess the serious game's educational value compared to an alternative intervention based on the study of text-based material. Appropriate questionnaires were delivered prior to, immediately after, and one week after the intervention. In the second part of the evaluation strategy, the user experience was measured by means of the Game Experience Questionnaire (GEQ). Nineteen and 29 participants enrolled in the first and second part of the evaluation, respectively. The results of the study showed that both serious game and control intervention enhance user's NL and FL skills (p-value = 0.002, 0.025 respectively). Comparison between the two groups did not yield significant results (p-value = 0.25). Increased levels of competence, immersion, flow and positive affect were declared in the GEQ demonstrating the attractiveness of the serious game. Moreover, the study revealed an important association between the level of game interaction, as measured by the number of mouse clicks per second, and the user experience. Intermediate levels of mouse interaction indicate lower user engagement.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114305380","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}
In the ubiquitin-proteasome system, E3 ubiquitin ligase (E3s for short) selectively recognize and bind specific regions of their substrate proteins. Sequence motifs whose sites are bound by E3 ubiquitin ligases are called degrons. Because much remains unclear about the relationship between substrate proteins of E3s and their binding sites, there is a need to computationally identify such binding sites from the substrate proteins. For this motif identification problem, in our previous works, we have proposed a series of collapsed Gibbs sampling algorithms, called DegSampler1 and DegSampler2, both of which use position-specific prior information. In this work, we propose a new collapsed Gibbs sampling algorithm, called DegSampler3, by integrating intra-motif pair-wise dependency model into the posterior probability distribution of DegSampler2. In our preliminary experiments, we found that DegSampler3 has the ability of finding more various degron sites than DegSampler2 while keeping the prediction accuracy almost the same as that of the previous method, DegSampler2.
{"title":"DegSampler3: Pairwise Dependency Model in Degradation Motif Site Prediction of Substrate Protein Sequences","authors":"O. Maruyama, Fumiko Matsuzaki","doi":"10.1109/BIBE.2019.00012","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00012","url":null,"abstract":"In the ubiquitin-proteasome system, E3 ubiquitin ligase (E3s for short) selectively recognize and bind specific regions of their substrate proteins. Sequence motifs whose sites are bound by E3 ubiquitin ligases are called degrons. Because much remains unclear about the relationship between substrate proteins of E3s and their binding sites, there is a need to computationally identify such binding sites from the substrate proteins. For this motif identification problem, in our previous works, we have proposed a series of collapsed Gibbs sampling algorithms, called DegSampler1 and DegSampler2, both of which use position-specific prior information. In this work, we propose a new collapsed Gibbs sampling algorithm, called DegSampler3, by integrating intra-motif pair-wise dependency model into the posterior probability distribution of DegSampler2. In our preliminary experiments, we found that DegSampler3 has the ability of finding more various degron sites than DegSampler2 while keeping the prediction accuracy almost the same as that of the previous method, DegSampler2.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123520044","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}
Dyslexia is a neurodevelopmental learning disorder that affects the acceleration and precision of word recognition, therefore obstructing the reading fluency, as well as text comprehension. Although it is not an oculomotor disease, readers with dyslexia have shown different eye movements than typically developing subjects during text reading. The majority of existing screening techniques for dyslexia's detection employ features associated with the aberrant visual scanning of reading text seen in dyslexia, whilst ignoring completely the behavior of the underlying data generating dynamical system. To address this problem, this work proposes a novel self-tuned architecture for feature extraction by modeling directly the inherent dynamics of wearable sensor data in higher-dimensional phase spaces via multidimensional recurrence quantification analysis (RQA) based on state matrices. Experimental evaluation on real data demonstrates the improved recognition accuracy of our method when compared against its state-of-the-art vector-based RQA counterparts.
{"title":"Automated Screening of Dyslexia via Dynamical Recurrence Analysis of Wearable Sensor Data","authors":"M. Zervou, G. Tzagkarakis, P. Tsakalides","doi":"10.1109/BIBE.2019.00144","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00144","url":null,"abstract":"Dyslexia is a neurodevelopmental learning disorder that affects the acceleration and precision of word recognition, therefore obstructing the reading fluency, as well as text comprehension. Although it is not an oculomotor disease, readers with dyslexia have shown different eye movements than typically developing subjects during text reading. The majority of existing screening techniques for dyslexia's detection employ features associated with the aberrant visual scanning of reading text seen in dyslexia, whilst ignoring completely the behavior of the underlying data generating dynamical system. To address this problem, this work proposes a novel self-tuned architecture for feature extraction by modeling directly the inherent dynamics of wearable sensor data in higher-dimensional phase spaces via multidimensional recurrence quantification analysis (RQA) based on state matrices. Experimental evaluation on real data demonstrates the improved recognition accuracy of our method when compared against its state-of-the-art vector-based RQA counterparts.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122810227","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}
Changlu Guo, Marton Szemenyei, Yang Pei, Yugen Yi, W. Zhou
At present, artificial visual diagnosis of fundus diseases has low manual reading efficiency and strong subjectivity, which easily causes false and missed detections. Automatic segmentation of retinal blood vessels in fundus images is very effective for early diagnosis of diseases such as the hypertension and diabetes. In this paper, we utilize the U-shaped structure to exploit the local features of the retinal vessels and perform retinal vessel segmentation in an end-to-end manner. Inspired by the recently DropBlock, we propose a new method called Structured Dropout U-Net (SD-Unet), which abandons the traditional dropout for convolutional layers, and applies the structured dropout to regularize U-Net. Compared to the state-of-the-art methods, we demonstrate the superior performance of the proposed approach.
{"title":"SD-Unet: A Structured Dropout U-Net for Retinal Vessel Segmentation","authors":"Changlu Guo, Marton Szemenyei, Yang Pei, Yugen Yi, W. Zhou","doi":"10.1109/BIBE.2019.00085","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00085","url":null,"abstract":"At present, artificial visual diagnosis of fundus diseases has low manual reading efficiency and strong subjectivity, which easily causes false and missed detections. Automatic segmentation of retinal blood vessels in fundus images is very effective for early diagnosis of diseases such as the hypertension and diabetes. In this paper, we utilize the U-shaped structure to exploit the local features of the retinal vessels and perform retinal vessel segmentation in an end-to-end manner. Inspired by the recently DropBlock, we propose a new method called Structured Dropout U-Net (SD-Unet), which abandons the traditional dropout for convolutional layers, and applies the structured dropout to regularize U-Net. Compared to the state-of-the-art methods, we demonstrate the superior performance of the proposed approach.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124946671","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}
Y. Petrakis, A. Kouroubali, Dimitrios G. Katehakis
Enabling data exchange between electronic medical records (EMRs) and personal health apps has the potential to boost the secondary usage of health data, eventually increasing the quality of life. In this paper, the authors present a mobile app architecture that enables the integration of legacy cross-enterprise document sharing (XDS) and next generation fast healthcare interoperability resources (FHIR) compatible electronic medical record (EMR) systems with personal mobile applications. The realization of this architecture is achieved by linking EMR information from multiple providers at the point of care, with a personal health app for citizens, combining the benefits and potential of both XDS and FHIR.
{"title":"A Mobile App Architecture for Accessing EMRs Using XDS and FHIR","authors":"Y. Petrakis, A. Kouroubali, Dimitrios G. Katehakis","doi":"10.1109/BIBE.2019.00057","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00057","url":null,"abstract":"Enabling data exchange between electronic medical records (EMRs) and personal health apps has the potential to boost the secondary usage of health data, eventually increasing the quality of life. In this paper, the authors present a mobile app architecture that enables the integration of legacy cross-enterprise document sharing (XDS) and next generation fast healthcare interoperability resources (FHIR) compatible electronic medical record (EMR) systems with personal mobile applications. The realization of this architecture is achieved by linking EMR information from multiple providers at the point of care, with a personal health app for citizens, combining the benefits and potential of both XDS and FHIR.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"475 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123284694","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}
A. Martínez-Torteya, Alejandro I. Trejo-Castro, J. Celaya-Padilla, Jose Gerardo Tamez-Peña
An early diagnosis of Alzheimer's disease (AD) is important for both support and therapeutic planning. Predicting who will progress from mild cognitive impairment (MCI) to AD would yield the same clinical benefits. However, it has been shown that the MCI to AD progression varies depending on certain demographic characteristics. AD is highly associated with the apolipoprotein E type 4 allele expressing the protein isoform APOE4. This study aimed at identifying features associated with the MCI to AD progression whose temporal evolution significantly differs between APOE4 carriers and non-carriers. Longitudinal information from 336 subjects (64.58% carriers) who progressed from MCI to AD was gathered, including laboratory assays, information from MRI and PET analyses, and neuropsychological tests. Longitudinal models identified 11 features with significant differences in their behavior between carriers and non-carriers, demonstrating that the way in which carriers and non-carriers progress from MCI to AD is significantly different.
{"title":"Differences in the Progression from Mild Cognitive Impairment to Alzheimer's Disease between APOE4 Carriers and Non-Carriers","authors":"A. Martínez-Torteya, Alejandro I. Trejo-Castro, J. Celaya-Padilla, Jose Gerardo Tamez-Peña","doi":"10.1109/BIBE.2019.00043","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00043","url":null,"abstract":"An early diagnosis of Alzheimer's disease (AD) is important for both support and therapeutic planning. Predicting who will progress from mild cognitive impairment (MCI) to AD would yield the same clinical benefits. However, it has been shown that the MCI to AD progression varies depending on certain demographic characteristics. AD is highly associated with the apolipoprotein E type 4 allele expressing the protein isoform APOE4. This study aimed at identifying features associated with the MCI to AD progression whose temporal evolution significantly differs between APOE4 carriers and non-carriers. Longitudinal information from 336 subjects (64.58% carriers) who progressed from MCI to AD was gathered, including laboratory assays, information from MRI and PET analyses, and neuropsychological tests. Longitudinal models identified 11 features with significant differences in their behavior between carriers and non-carriers, demonstrating that the way in which carriers and non-carriers progress from MCI to AD is significantly different.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129622869","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}
A fundamental drawback of traditional Intelligent Tutoring Systems (ITS) is that, unlike human tutors, they are not able to understand the emotional state of their users and adapt the learning process accordingly. This work explores the potential use of affective computing techniques for providing an affect detection mechanism for ITS. Electrocardiography (ECG) and electromyography (EMG) signals were recorded from 45 individuals that undertook a computerised English language test and provided feedback on the difficulty of the test's questions. Features extracted from the ECG and EMG signals were then used in order to train machine learning models for the task of predicting the self-perceived difficulty level of the questions. The conducted supervised classification experiments provided promising results for the suitability of this approach for enhancing ITS with information relating to the affective state of the learners, reaching an average classification F1-score of 75.49% for the personalised single-participant models and a classification F1-score of 64.10% for the global models.
{"title":"On the use of ECG and EMG Signals for Question Difficulty Level Prediction in the Context of Intelligent Tutoring Systems","authors":"Fehaid Alqahtani, Stamos Katsigiannis, N. Ramzan","doi":"10.1109/BIBE.2019.00077","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00077","url":null,"abstract":"A fundamental drawback of traditional Intelligent Tutoring Systems (ITS) is that, unlike human tutors, they are not able to understand the emotional state of their users and adapt the learning process accordingly. This work explores the potential use of affective computing techniques for providing an affect detection mechanism for ITS. Electrocardiography (ECG) and electromyography (EMG) signals were recorded from 45 individuals that undertook a computerised English language test and provided feedback on the difficulty of the test's questions. Features extracted from the ECG and EMG signals were then used in order to train machine learning models for the task of predicting the self-perceived difficulty level of the questions. The conducted supervised classification experiments provided promising results for the suitability of this approach for enhancing ITS with information relating to the affective state of the learners, reaching an average classification F1-score of 75.49% for the personalised single-participant models and a classification F1-score of 64.10% for the global models.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"49 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128965394","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}
The micro-electrodes of a pair of concentric cylinders have been designed to estimate the local cell configuration in biological tissues. The micro-electrodes consist with the outer and the inner concentric cylindrical needles of stainless-steel: the diameters of the outer and the inner cylindrical needles are 1.20 mm and 0.60 mm, respectively. The electrodes were inserted into the several types of the normal bovine tissues: the heart, the lever, the kidney, the fatty tissue, or the intestinal mucous membrane, alternatively. The electric voltage between electrodes was measured, while the sinusoidal alternating electric current at the frequency between 1 Hz to 1 MHz flew between the electrodes. The cell density in the tissue was counted at the microscopic image of each tissue. The results show that the capacity component increases with the density of cells. The study demonstrates the designed system of the measurement is effective to estimate the local cell configuration in biological tissues.
{"title":"Impedance between Micro-Electrodes of a Pair of Concentric Cylinders for Estimation of Local Cell Configuration","authors":"S. Hashimoto","doi":"10.1109/BIBE.2019.00149","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00149","url":null,"abstract":"The micro-electrodes of a pair of concentric cylinders have been designed to estimate the local cell configuration in biological tissues. The micro-electrodes consist with the outer and the inner concentric cylindrical needles of stainless-steel: the diameters of the outer and the inner cylindrical needles are 1.20 mm and 0.60 mm, respectively. The electrodes were inserted into the several types of the normal bovine tissues: the heart, the lever, the kidney, the fatty tissue, or the intestinal mucous membrane, alternatively. The electric voltage between electrodes was measured, while the sinusoidal alternating electric current at the frequency between 1 Hz to 1 MHz flew between the electrodes. The cell density in the tissue was counted at the microscopic image of each tissue. The results show that the capacity component increases with the density of cells. The study demonstrates the designed system of the measurement is effective to estimate the local cell configuration in biological tissues.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125349384","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}
Panagiotis A. Bonotis, Dimosthenis C. Tsouros, Panagiotis N. Smyrlis, A. Tzallas, N. Giannakeas, E. Glavas, M. Tsipouras
Objective characterization of pain intensity is necessary under certain clinical conditions. The portable electroencephalogram (EEG) is a cost-effective assessment tool and lately, new methods using efficient analysis of related dynamic changes in brain activity in the EEG recordings proved that these can reflect the dynamic changes of pain intensity. In this paper, a novel method for automated assessment of pain intensity using EEG data is presented. EEG recordings from twenty-two (22) healthy volunteers are recorded with the Emotiv EPOC+ using the Cold Pressor Test (CPT) protocol. The relative power of each brain band's energy for each channel is extracted and the stochastic forest algorithm is employed for discrimination across five classes, depicting the pain intensity. Obtained results in terms of classification accuracy reached high levels (72.7%), which renders the proposed method suitable for automated pain detection and quantification of its intensity.
{"title":"Automated Assessment of Pain Intensity Based on EEG Signal Analysis","authors":"Panagiotis A. Bonotis, Dimosthenis C. Tsouros, Panagiotis N. Smyrlis, A. Tzallas, N. Giannakeas, E. Glavas, M. Tsipouras","doi":"10.1109/BIBE.2019.00111","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00111","url":null,"abstract":"Objective characterization of pain intensity is necessary under certain clinical conditions. The portable electroencephalogram (EEG) is a cost-effective assessment tool and lately, new methods using efficient analysis of related dynamic changes in brain activity in the EEG recordings proved that these can reflect the dynamic changes of pain intensity. In this paper, a novel method for automated assessment of pain intensity using EEG data is presented. EEG recordings from twenty-two (22) healthy volunteers are recorded with the Emotiv EPOC+ using the Cold Pressor Test (CPT) protocol. The relative power of each brain band's energy for each channel is extracted and the stochastic forest algorithm is employed for discrimination across five classes, depicting the pain intensity. Obtained results in terms of classification accuracy reached high levels (72.7%), which renders the proposed method suitable for automated pain detection and quantification of its intensity.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116168973","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}
Cervical cancer affects 570,000 women globally and is among the most common causes of cancer-related deaths. Cervical cancer is caused due to the Human Papilloma Virus (HPV) which leads to abnormal growth of cells in the cervix region. Regular testing for HPV in women has helped reduce the death rate in developed countries. However, developing nations are still struggling to provide low-cost solutions due to the lack of affordable medical facilities. The skewed ratio of the oncologists to patients has also aggravated the problem. Motivated by the Deep Learning solutions in Bio-medical imaging, we propose a novel CervixNet methodology which performs image enhancement on cervigrams followed by Segmenting the Region of Interest (RoI) and then classifying the RoI to determine the appropriate treatment. For the classification task, a novel Hierarchical Convolutional Mixture of Experts (HCME) algorithm is proposed. HCME is capable of tackling the problem of overfitting, given that small datasets are an inherent problem in the field of biomedical imaging. Our proposed methodology has outperformed all the existing methodologies on publicly available Intel and Mobile-ODT Kaggle dataset giving an Accuracy of 96.77% and kappa score of 0.951. Hence, the results obtained validate our approach to provide first level screening at a low cost.
{"title":"Cervical Cancer Diagnosis using CervixNet - A Deep Learning Approach","authors":"R. Gorantla, R. Singh, Rohan Pandey, Mayank Jain","doi":"10.1109/BIBE.2019.00078","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00078","url":null,"abstract":"Cervical cancer affects 570,000 women globally and is among the most common causes of cancer-related deaths. Cervical cancer is caused due to the Human Papilloma Virus (HPV) which leads to abnormal growth of cells in the cervix region. Regular testing for HPV in women has helped reduce the death rate in developed countries. However, developing nations are still struggling to provide low-cost solutions due to the lack of affordable medical facilities. The skewed ratio of the oncologists to patients has also aggravated the problem. Motivated by the Deep Learning solutions in Bio-medical imaging, we propose a novel CervixNet methodology which performs image enhancement on cervigrams followed by Segmenting the Region of Interest (RoI) and then classifying the RoI to determine the appropriate treatment. For the classification task, a novel Hierarchical Convolutional Mixture of Experts (HCME) algorithm is proposed. HCME is capable of tackling the problem of overfitting, given that small datasets are an inherent problem in the field of biomedical imaging. Our proposed methodology has outperformed all the existing methodologies on publicly available Intel and Mobile-ODT Kaggle dataset giving an Accuracy of 96.77% and kappa score of 0.951. Hence, the results obtained validate our approach to provide first level screening at a low cost.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116548249","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：