Sara Montagna, Angelo Croatti, A. Ricci, V. Agnoletti, Vittorio Albarello
The problem of tracking has gained a central role in healthcare research since it enables the acquisition of the information needed for improving healthcare management and efficiency, alongside patient safety. In literature, it is mainly discussed as an allocation problem that must deal with limited resources (rooms, physicians, equipment) to optimise workflows, and Real-Time Location Systems have been introduced with the main goal of locating and identifying assets and personnel in a healthcare facility. In this paper, we propose a novel perspective of pervasive tracking into Hospital 4.0, devised explicitly for time-dependent acute patient flow. The goal is to develop a tracking system that acquires not only the time and location of entities, exploiting state-of-the-art techniques, but also the main clinical events occurred. As an example application we describe TraumaTracker, a system developed to support the accurate and complete documentation of trauma resuscitation processes from pre-hospital care.
{"title":"Pervasive Tracking for Time-Dependent Acute Patient Flow: A Case Study in Trauma Management","authors":"Sara Montagna, Angelo Croatti, A. Ricci, V. Agnoletti, Vittorio Albarello","doi":"10.1109/CBMS.2019.00057","DOIUrl":"https://doi.org/10.1109/CBMS.2019.00057","url":null,"abstract":"The problem of tracking has gained a central role in healthcare research since it enables the acquisition of the information needed for improving healthcare management and efficiency, alongside patient safety. In literature, it is mainly discussed as an allocation problem that must deal with limited resources (rooms, physicians, equipment) to optimise workflows, and Real-Time Location Systems have been introduced with the main goal of locating and identifying assets and personnel in a healthcare facility. In this paper, we propose a novel perspective of pervasive tracking into Hospital 4.0, devised explicitly for time-dependent acute patient flow. The goal is to develop a tracking system that acquires not only the time and location of entities, exploiting state-of-the-art techniques, but also the main clinical events occurred. As an example application we describe TraumaTracker, a system developed to support the accurate and complete documentation of trauma resuscitation processes from pre-hospital care.","PeriodicalId":311634,"journal":{"name":"2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)","volume":"4564 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116566605","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}
Deep Learning, which involves powerful black box predictors, has achieved a state-of-the-art performance in medical image analysis such as segmentation and classification for diagnosis. However, in spite of these successes, these methods focus exclusively on improving the accuracy of point predictions without assessing the quality of their outputs. Knowing how much confidence there is in a prediction is essential for gaining clinicians' trust in the technology. Monte-Carlo dropout in neural networks is equivalent to a specific variational approximation in Bayesian neural networks and is simple to implement without any changes in the network architecture. It is considered state-of-the-art for estimating uncertainty. However, in classification, it does not model the predictive probabilities. This means that we are not capturing the true underlying uncertainty in the prediction. In this paper, we propose an uncertainty estimation framework for classification by decomposing predictive probabilities into two main types of uncertainty in Bayesian modelling: aleatoric and epistemic uncertainty (representing uncertainty in the quality of the data and in the model parameters, respectively). We demonstrate that the proposed uncertainty quantification framework using the Bayesian Residual U-Net (BRUNet) provides additional insight for clinicians when analysing images with help from deep learners. In addition, we demonstrate how the resulting uncertainty depends on the dropout rates using images from nuclei in divergent medical images.
{"title":"Estimating Uncertainty in Deep Learning for Reporting Confidence to Clinicians when Segmenting Nuclei Image Data","authors":"Biraja Ghoshal, A. Tucker, B. Sanghera, W. Wong","doi":"10.1109/CBMS.2019.00072","DOIUrl":"https://doi.org/10.1109/CBMS.2019.00072","url":null,"abstract":"Deep Learning, which involves powerful black box predictors, has achieved a state-of-the-art performance in medical image analysis such as segmentation and classification for diagnosis. However, in spite of these successes, these methods focus exclusively on improving the accuracy of point predictions without assessing the quality of their outputs. Knowing how much confidence there is in a prediction is essential for gaining clinicians' trust in the technology. Monte-Carlo dropout in neural networks is equivalent to a specific variational approximation in Bayesian neural networks and is simple to implement without any changes in the network architecture. It is considered state-of-the-art for estimating uncertainty. However, in classification, it does not model the predictive probabilities. This means that we are not capturing the true underlying uncertainty in the prediction. In this paper, we propose an uncertainty estimation framework for classification by decomposing predictive probabilities into two main types of uncertainty in Bayesian modelling: aleatoric and epistemic uncertainty (representing uncertainty in the quality of the data and in the model parameters, respectively). We demonstrate that the proposed uncertainty quantification framework using the Bayesian Residual U-Net (BRUNet) provides additional insight for clinicians when analysing images with help from deep learners. In addition, we demonstrate how the resulting uncertainty depends on the dropout rates using images from nuclei in divergent medical images.","PeriodicalId":311634,"journal":{"name":"2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)","volume":"222 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121680392","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}
T. Koutny, A. D. Cioppa, I. D. Falco, E. Tarantino, U. Scafuri, M. Krcma
A physiological model improves delivered healthcare, when constructing a medical device. Such a model comprises a number of parameters. While an analytical method determines model parameters, an evolutionary algorithm can improve them further. As evolutionary algorithms were designed on top of random-number generators, their results are not deterministic. This raises a concern about their applicability to medical devices. Medical-device algorithm must produce an output with a minimum guaranteed accuracy. Therefore, we applied de-randomized sequences to Meta-Differential Evolution instead of using a random-number generator. Eventually, we designed an optimization method based on zooming with derandomized sequences as an alternative to the Meta-Differential Evolution. As the experimental setup, we predicted glucose-level signal to cover a blind window of glucose-monitoring signal that results from a physiological lag in glucose transportation. Completely de-randomized differential evolution exhibited the same accuracy and precision as completely non-deterministic differential evolution. They produced 93% of glucose levels with relative error less than or equal to 15%.
{"title":"De–randomized Meta-Differential Evolution for Calculating and Predicting Glucose Levels","authors":"T. Koutny, A. D. Cioppa, I. D. Falco, E. Tarantino, U. Scafuri, M. Krcma","doi":"10.1109/CBMS.2019.00064","DOIUrl":"https://doi.org/10.1109/CBMS.2019.00064","url":null,"abstract":"A physiological model improves delivered healthcare, when constructing a medical device. Such a model comprises a number of parameters. While an analytical method determines model parameters, an evolutionary algorithm can improve them further. As evolutionary algorithms were designed on top of random-number generators, their results are not deterministic. This raises a concern about their applicability to medical devices. Medical-device algorithm must produce an output with a minimum guaranteed accuracy. Therefore, we applied de-randomized sequences to Meta-Differential Evolution instead of using a random-number generator. Eventually, we designed an optimization method based on zooming with derandomized sequences as an alternative to the Meta-Differential Evolution. As the experimental setup, we predicted glucose-level signal to cover a blind window of glucose-monitoring signal that results from a physiological lag in glucose transportation. Completely de-randomized differential evolution exhibited the same accuracy and precision as completely non-deterministic differential evolution. They produced 93% of glucose levels with relative error less than or equal to 15%.","PeriodicalId":311634,"journal":{"name":"2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128321806","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}
Jonathan S. Ramos, M. Cazzolato, Bruno S. Faiçal, M. Nogueira-Barbosa, C. Traina, A. Traina
Segmentation of medical images is critical for making several processes of analysis and classification more reliable. With the growing number of people presenting back pain and related problems, the semi-automatic segmentation and 3D reconstruction of vertebral bodies became even more important to support decision making. A 3D reconstruction allows a fast and objective analysis of each vertebrae condition, which may play a major role in surgical planning and evaluation of suitable treatments. In this paper, we propose 3DBGrowth, which develops a 3D reconstruction over the efficient Balanced Growth method for 2D images. We also take advantage of the slope coefficient from the annotation time to reduce the total number of annotated slices, reducing the time spent on manual annotation. We show experimental results on a representative dataset with 17 MRI exams demonstrating that our approach significantly outperforms the competitors and, on average, only 37% of the total slices with vertebral body content must be annotated without losing performance/accuracy. Compared to the state-of-the-art methods, we have achieved a Dice Score gain of over 5% with comparable processing time. Moreover, 3DBGrowth works well with imprecise seed points, which reduces the time spent on manual annotation by the specialist.
{"title":"3DBGrowth: Volumetric Vertebrae Segmentation and Reconstruction in Magnetic Resonance Imaging","authors":"Jonathan S. Ramos, M. Cazzolato, Bruno S. Faiçal, M. Nogueira-Barbosa, C. Traina, A. Traina","doi":"10.1109/CBMS.2019.00091","DOIUrl":"https://doi.org/10.1109/CBMS.2019.00091","url":null,"abstract":"Segmentation of medical images is critical for making several processes of analysis and classification more reliable. With the growing number of people presenting back pain and related problems, the semi-automatic segmentation and 3D reconstruction of vertebral bodies became even more important to support decision making. A 3D reconstruction allows a fast and objective analysis of each vertebrae condition, which may play a major role in surgical planning and evaluation of suitable treatments. In this paper, we propose 3DBGrowth, which develops a 3D reconstruction over the efficient Balanced Growth method for 2D images. We also take advantage of the slope coefficient from the annotation time to reduce the total number of annotated slices, reducing the time spent on manual annotation. We show experimental results on a representative dataset with 17 MRI exams demonstrating that our approach significantly outperforms the competitors and, on average, only 37% of the total slices with vertebral body content must be annotated without losing performance/accuracy. Compared to the state-of-the-art methods, we have achieved a Dice Score gain of over 5% with comparable processing time. Moreover, 3DBGrowth works well with imprecise seed points, which reduces the time spent on manual annotation by the specialist.","PeriodicalId":311634,"journal":{"name":"2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130602180","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}
Marjan Najafabadipour, M. Zanin, A. R. González, C. Gonzalo-Martín, B. García, V. Calvo, J. L. Cruz-Bermúdez, M. Provencio, Ernestina Menasalvas Ruiz
The widespread adoption of Electronic Health Records (EHRs) is generating an ever-increasing amount of unstructured clinical texts. Processing time expressions from these domain-specific-texts is crucial for the discovery of patterns that can help in the detection of medical events and building the patient's natural history. In medical domain, the recognition of time information from texts is challenging due to their lack of structure; usage of various formats, styles and abbreviations; their domain specific nature; writing quality; and the presence of ambiguous expressions. Furthermore, despite of Spanish occupying the second position in the world ranking of number of native speakers, to the best of our knowledge, no Natural Language Processing (NLP) tools have been introduced for the recognition of time expressions from clinical texts, written in this particular language. Therefore, in this paper, we propose a Temporal Tagger for identifying and normalizing time expressions appeared in Spanish clinical texts. We further compare our Temporal Tagger with the Spanish version of SUTime. By using a large dataset comprising EHRs of people suffering from lung cancer, we show that our developed Temporal Tagger, with an F1 score of 0.93, outperforms SUTime, with an F1 score of 0.797.
{"title":"Recognition of Time Expressions in Spanish Electronic Health Records","authors":"Marjan Najafabadipour, M. Zanin, A. R. González, C. Gonzalo-Martín, B. García, V. Calvo, J. L. Cruz-Bermúdez, M. Provencio, Ernestina Menasalvas Ruiz","doi":"10.1109/CBMS.2019.00025","DOIUrl":"https://doi.org/10.1109/CBMS.2019.00025","url":null,"abstract":"The widespread adoption of Electronic Health Records (EHRs) is generating an ever-increasing amount of unstructured clinical texts. Processing time expressions from these domain-specific-texts is crucial for the discovery of patterns that can help in the detection of medical events and building the patient's natural history. In medical domain, the recognition of time information from texts is challenging due to their lack of structure; usage of various formats, styles and abbreviations; their domain specific nature; writing quality; and the presence of ambiguous expressions. Furthermore, despite of Spanish occupying the second position in the world ranking of number of native speakers, to the best of our knowledge, no Natural Language Processing (NLP) tools have been introduced for the recognition of time expressions from clinical texts, written in this particular language. Therefore, in this paper, we propose a Temporal Tagger for identifying and normalizing time expressions appeared in Spanish clinical texts. We further compare our Temporal Tagger with the Spanish version of SUTime. By using a large dataset comprising EHRs of people suffering from lung cancer, we show that our developed Temporal Tagger, with an F1 score of 0.93, outperforms SUTime, with an F1 score of 0.797.","PeriodicalId":311634,"journal":{"name":"2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)","volume":"215 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133481025","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}
This paper reports a user study performed to assess the usability of a Web-based electronic informed consent application called DICE, which is aimed at supporting patients in the process of reading, understanding and using the informed consent as a trigger for further interaction with the team of care givers. In particular, we performed a questionnaire-based study and a series of individual semi-structured interviews to understand whether the application is usable and can be used in real-world settings, respectively. We found that patients could appreciate the availability of interactive tools like DICE, but health professionals believe that its actual adoption in current workflows and practices could be hampered by the chronic lack of time and health operators who could timely address the licit requests that such a tool could bring to light.
{"title":"Digitizing the Informed Consent: the Challenges to Design for Practices","authors":"Michela Assale, Erica Barbero, F. Cabitza","doi":"10.1109/CBMS.2019.00127","DOIUrl":"https://doi.org/10.1109/CBMS.2019.00127","url":null,"abstract":"This paper reports a user study performed to assess the usability of a Web-based electronic informed consent application called DICE, which is aimed at supporting patients in the process of reading, understanding and using the informed consent as a trigger for further interaction with the team of care givers. In particular, we performed a questionnaire-based study and a series of individual semi-structured interviews to understand whether the application is usable and can be used in real-world settings, respectively. We found that patients could appreciate the availability of interactive tools like DICE, but health professionals believe that its actual adoption in current workflows and practices could be hampered by the chronic lack of time and health operators who could timely address the licit requests that such a tool could bring to light.","PeriodicalId":311634,"journal":{"name":"2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)","volume":"75Suppl 2 Suppl 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129203538","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}
Millions of people worldwide suffer from neurological disorders such as epilepsy, movement disorders, and obsessive-compulsive disorder (OCD), depression, and delirium. To provide relief from these disorders, brain stimulation therapies have been shown to be effective at controlling onsets of seizures, tremors, dyskinesia, dystonia, and OCD episodes. Current development of brain stimulation therapies has pivoted toward closed-loop control of sensing onset events and correspondingly delivering adaptive stimulation. Development of closed-loop brain stimulation therapies for neurological disorders rely on the identification of neural biomarkers. As such, a brain signal monitoring system that can chronically record these neurological events is essential to the continued development of neuromodulation systems and therapies. Through analyzing clinical data, neural disorder biomarkers can be identified and novel therapies can be optimized. This paper outlines the development of a translational deep brain stimulation monitoring system utilizing Medtronic's RC+S System to help clinicians and patients accurately record and document neural disorder onset events. With this neural data, stimulation therapy parameters can be adjusted using the system without requiring an in-person office visit. The system is capable of wirelessly communicating with multiple implanted neurostimulators, monitoring disorder onset biomarkers, and periodically downloading real-time brain signal data as well as loop recordings triggered by device-detected disorder onset events. This translational system and neural disorder onset data can be used to optimize therapies, minimize symptom onsets, enable episodic care management, and improve chronic care management.
{"title":"A Translational Wireless Deep Brain Stimulation Monitoring System for Chronic Brain Signal Recording to Automate Neural Disorder Onset Recording","authors":"William Drew, T. Denison, S. Stanslaski","doi":"10.1109/CBMS.2019.00027","DOIUrl":"https://doi.org/10.1109/CBMS.2019.00027","url":null,"abstract":"Millions of people worldwide suffer from neurological disorders such as epilepsy, movement disorders, and obsessive-compulsive disorder (OCD), depression, and delirium. To provide relief from these disorders, brain stimulation therapies have been shown to be effective at controlling onsets of seizures, tremors, dyskinesia, dystonia, and OCD episodes. Current development of brain stimulation therapies has pivoted toward closed-loop control of sensing onset events and correspondingly delivering adaptive stimulation. Development of closed-loop brain stimulation therapies for neurological disorders rely on the identification of neural biomarkers. As such, a brain signal monitoring system that can chronically record these neurological events is essential to the continued development of neuromodulation systems and therapies. Through analyzing clinical data, neural disorder biomarkers can be identified and novel therapies can be optimized. This paper outlines the development of a translational deep brain stimulation monitoring system utilizing Medtronic's RC+S System to help clinicians and patients accurately record and document neural disorder onset events. With this neural data, stimulation therapy parameters can be adjusted using the system without requiring an in-person office visit. The system is capable of wirelessly communicating with multiple implanted neurostimulators, monitoring disorder onset biomarkers, and periodically downloading real-time brain signal data as well as loop recordings triggered by device-detected disorder onset events. This translational system and neural disorder onset data can be used to optimize therapies, minimize symptom onsets, enable episodic care management, and improve chronic care management.","PeriodicalId":311634,"journal":{"name":"2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133273348","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}
Available and objective clinical documents are important for research of assistant diagnosis, development of algorithms, and education. To facilitate the readability and variability of clinical documents, this paper presents a rule-based approach to develop a question-answer dataset for chest X-rays from a public collection of radiology examinations, including both images and radiologist narrative reports. Our method simplified the complicated reports via hand-selected keywords, generated more than 63 thousand question-answer pairs via hand-written patterns, and augmented the question-answer dataset to more than 130 thousand pairs via rule-based question answering. To the best of our knowledge, this is the first generated question-answer dataset for chest X-rays by rule-based method. The dataset is promising for future researches and applications such as visual question answering, computer-aided diagnosis and so on.
{"title":"Rule-Based Method to Develop Question-Answer Dataset from Chest X-Ray Reports","authors":"Jie Wang, Hairong Lv, R. Jiang, Zhen Xie","doi":"10.1109/CBMS.2019.00016","DOIUrl":"https://doi.org/10.1109/CBMS.2019.00016","url":null,"abstract":"Available and objective clinical documents are important for research of assistant diagnosis, development of algorithms, and education. To facilitate the readability and variability of clinical documents, this paper presents a rule-based approach to develop a question-answer dataset for chest X-rays from a public collection of radiology examinations, including both images and radiologist narrative reports. Our method simplified the complicated reports via hand-selected keywords, generated more than 63 thousand question-answer pairs via hand-written patterns, and augmented the question-answer dataset to more than 130 thousand pairs via rule-based question answering. To the best of our knowledge, this is the first generated question-answer dataset for chest X-rays by rule-based method. The dataset is promising for future researches and applications such as visual question answering, computer-aided diagnosis and so on.","PeriodicalId":311634,"journal":{"name":"2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132260957","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}
Allergic Reactions can range from mild rashes to severe conditions, sometimes even leading to anaphylaxis and sudden death. Lack of sufficient prior patient data and a need of physician's immediate supervision calls for a solution which can be deployed at large to prevent the sudden death occurring due to anaphylactic shocks and further collect data to enable fast detection in future situations. This paper describes an integrated ecosystem comprising of several on-body patient devices connected to a central server with a doctor at one of the client nodes. An on-body device consists of physiological signal acquiring sensors, abnormality detector, and smart-phone for uploading the anomalous data to a server for further classification. Gathering anomalous data from the patients, the cloud processes them through a binary adversarial classifier based on physician's annotation of anaphylaxis occurrence. The adversarial classifier has been incorporated to tackle data insufficiency because of its faster convergence.
{"title":"An Adaptive Anaphylaxis Detection and Emergency Response System","authors":"Gopabandhu Hota, Abhilash Nandy, Kshitiz Goel, Dishank Yadav, Saumo Pal, Ankush Roy","doi":"10.1109/CBMS.2019.00019","DOIUrl":"https://doi.org/10.1109/CBMS.2019.00019","url":null,"abstract":"Allergic Reactions can range from mild rashes to severe conditions, sometimes even leading to anaphylaxis and sudden death. Lack of sufficient prior patient data and a need of physician's immediate supervision calls for a solution which can be deployed at large to prevent the sudden death occurring due to anaphylactic shocks and further collect data to enable fast detection in future situations. This paper describes an integrated ecosystem comprising of several on-body patient devices connected to a central server with a doctor at one of the client nodes. An on-body device consists of physiological signal acquiring sensors, abnormality detector, and smart-phone for uploading the anomalous data to a server for further classification. Gathering anomalous data from the patients, the cloud processes them through a binary adversarial classifier based on physician's annotation of anaphylaxis occurrence. The adversarial classifier has been incorporated to tackle data insufficiency because of its faster convergence.","PeriodicalId":311634,"journal":{"name":"2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122985281","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}
Lucas M. Valério, D. Alves, L. F. Cruz, P. Bugatti, C. Oliveira, P. T. Saito
Recently, impressive results have been provided by pre-trained convolutional neural networks combined with the transfer learning technique. They have quickly become a great option to classify general image datasets. However, to the best of our knowledge, the majority of works do not explore if these pre-trained architectures are well-suited to specific contexts like the medical image domain (e.g. breast lesions). We focus on breast lesions, because it is one of the most common types of cancer affecting women worldwide, and its early diagnosis is crucial to the success of the treatment. In this paper, we propose a methodology capable of analyzing different approaches, regarding description (e.g through handcrafted and deep features) and classification (e.g. through end-to-end networks and traditional classifiers) to automatically answer the best tuning according to a given mammographic image dataset. Our methodology can also apply a data augmentation method to improve the learning of the networks. It increases the number of training samples to cope with unbalancing and overfitting problems that are intrinsic to the breast lesion classification task. We validate our methodology on public image datasets and our results show classification accuracies of up to 94.34%.
{"title":"DeepMammo: Deep Transfer Learning for Lesion Classification of Mammographic Images","authors":"Lucas M. Valério, D. Alves, L. F. Cruz, P. Bugatti, C. Oliveira, P. T. Saito","doi":"10.1109/CBMS.2019.00093","DOIUrl":"https://doi.org/10.1109/CBMS.2019.00093","url":null,"abstract":"Recently, impressive results have been provided by pre-trained convolutional neural networks combined with the transfer learning technique. They have quickly become a great option to classify general image datasets. However, to the best of our knowledge, the majority of works do not explore if these pre-trained architectures are well-suited to specific contexts like the medical image domain (e.g. breast lesions). We focus on breast lesions, because it is one of the most common types of cancer affecting women worldwide, and its early diagnosis is crucial to the success of the treatment. In this paper, we propose a methodology capable of analyzing different approaches, regarding description (e.g through handcrafted and deep features) and classification (e.g. through end-to-end networks and traditional classifiers) to automatically answer the best tuning according to a given mammographic image dataset. Our methodology can also apply a data augmentation method to improve the learning of the networks. It increases the number of training samples to cope with unbalancing and overfitting problems that are intrinsic to the breast lesion classification task. We validate our methodology on public image datasets and our results show classification accuracies of up to 94.34%.","PeriodicalId":311634,"journal":{"name":"2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127713290","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：