2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)最新文献_第10页

Can Multi-channel Heart Sounds Analysis improve Murmur Detection? 多通道心音分析能改善杂音检测吗?

2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI) Pub Date : 2022-09-27 DOI: 10.1109/BHI56158.2022.9926792

D. Nogueira, J. Oliveira, Carlos Gomes Ferreira, M. Coimbra, A. Jorge

{"title":"Can Multi-channel Heart Sounds Analysis improve Murmur Detection?","authors":"D. Nogueira, J. Oliveira, Carlos Gomes Ferreira, M. Coimbra, A. Jorge","doi":"10.1109/BHI56158.2022.9926792","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926792","url":null,"abstract":"Cardiac auscultation is still the most cost-effective screening procedure for cardiovascular diseases. The development of computer assisted methods can empower a large variety of health professionals and thus enable mass cardiac health low-cost screening. The procedure for correct cardiac auscultation includes listening to the heart sounds of the four main auscultation spots. Until recently, attempts to develop automatic heart sound analysis methods that explore the multi-channel richness of a real auscultation, were very difficult due to the lack of adequate public datasets. In this work, we use the CirCor Dataset which is characterized by the existence of more than one heart sound per patient (each patient has heart sounds collected at different auscultation spots). Using this dataset, we evaluate and quantify the comparative impact of using a single or a multi-channel approach. A single channel approach uses the sound from a single auscultation spot, whereas a multi-channel approach uses four auscultation spots in an asynchronous way. From the different classifiers tested, models that use four auscultation spots achieved a higher overall performance than those that search for abnormalities in a single heart sound spot. Our best result is a multi-channel SVM that analyzes four auscultation spots, with an overall performance of 87,4%. This opens the path to future research using a multi-channel approach.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"2021 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128045360","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}

引用次数: 0

The Stroop Competition: A Social-Evaluative Stroop Test for Acute Stress Induction Stroop竞赛:急性应激诱导的社会评价性Stroop测试

2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI) Pub Date : 2022-09-27 DOI: 10.1109/BHI56158.2022.9926835

Victoria Mueller, R. Richer, Lea Henrich, Leonie Berger, Antonia Gelardi, Katharina M. Jaeger, Bjoern M. Eskofier, N. Rohleder

{"title":"The Stroop Competition: A Social-Evaluative Stroop Test for Acute Stress Induction","authors":"Victoria Mueller, R. Richer, Lea Henrich, Leonie Berger, Antonia Gelardi, Katharina M. Jaeger, Bjoern M. Eskofier, N. Rohleder","doi":"10.1109/BHI56158.2022.9926835","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926835","url":null,"abstract":"The Stroop test is one of the most widely used protocols to induce cognitive stress and reliably activates the sympathetic nervous system (SNS). However, it only moderately activates the hypothalamic-pituitary-adrenal (HPA) axis, the stress axis responsible for cortisol secretion. In other well-known stress protocols, such as the cold pressor test, adding social-evaluative elements to the regular procedure has proven to cause increased HPA axis activation. For this reason, we introduce the “Stroop Competition”, a novel stress protocol based on the established Stroop test that adds social-evaluative feedback by conducting the test against a fake opponent with subsequent performance evaluation. We investigated the stress response of 22 participants performing either the “Stroop Competition” (Competition group) or the regular Stroop test (Control group) three consecutive times. Stress responses were assessed using ECG recordings to extract heart rate (HR) and heart rate variability (HRV) and saliva samples to extract salivary alpha-amylase (sAA) and cortisol. In the Competition group, participants experienced higher SNS activation indicated by significantly higher HR and lower HRV levels as well as higher sAA response to the stressor compared to the Control group. Additionally, overall cortisol levels were significantly higher in the Competition group supporting higher HPA axis activity. The findings of our pilot study confirm our hypothesis that adding social-evaluative elements to the Stroop test causes a more effective activation of both the SNS and HPA axis. We are convinced that our novel “Stroop Competition” protocol will provide a valuable addition to the already existing stress protocols in biopsychological research.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132315652","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}

引用次数: 1

Automating Treatment Recommendations for Children with Cerebral Palsy Based on Multi-Modal Clinical Data 基于多模式临床数据的脑瘫儿童自动化治疗建议

2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI) Pub Date : 2022-09-27 DOI: 10.1109/BHI56158.2022.9926836

A. Mahale, Yuanda Zhu, Sami Belhareth, A. Graf, K. Kruger, J. Krzak, May D. Wang

{"title":"Automating Treatment Recommendations for Children with Cerebral Palsy Based on Multi-Modal Clinical Data","authors":"A. Mahale, Yuanda Zhu, Sami Belhareth, A. Graf, K. Kruger, J. Krzak, May D. Wang","doi":"10.1109/BHI56158.2022.9926836","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926836","url":null,"abstract":"Physical disability of children caused by Cerebral Palsy has a prevalence of 2.5 per 1000 births and disrupts body movements such as gait that is essential for healthy pediatric development and overall well-being. Using a diagnostic matrix of clinical history, physical examination, imaging, and gait analysis data, clinicians can quantify how musculoskeletal impairments are impacting movement as evidence-based treatment planning. However, subjectivity and variability in gait analysis interpretation leads to low agreement among clinicians or institutions for cerebral palsy (CP) intervention. Consequently, the treatment planning process varies and takes years of expertise and significant effort to reach the level of competency necessary to synthesize data. In this study, we developed an evidence-based clinical decision support system (CDSS) that automatically recommends treatment options for CP pediatric patients based on an expert-verified clinical workflow. We integrated multi-modal clinical data such as patient demographic, physical exam, and gait analysis information. We validated the automated clinical workflow using de-identified patient data and achieved an accuracy of 0.612 for nine potential treatment options. We generated interpretable results to assist clinicians in using the automated clinical workflows. Our work serves as the foundation for evidence-based, data-driven treatment planning in pediatric CP clinical practice and clinical research, thereby enhancing the efficiency and accuracy in cerebral palsy patient care.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127309853","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}

引用次数: 0

Data-driven cardiovascular risk prediction and prognosis factor identification in diabetic patients 数据驱动的糖尿病患者心血管风险预测及预后因素识别

2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI) Pub Date : 2022-09-27 DOI: 10.1109/BHI56158.2022.9926871

Hugo Calero-Diaz, David Chushig-Muzo, H. Fabelo, I. Mora-Jiménez, C. Granja, C. Soguero-Ruíz

{"title":"Data-driven cardiovascular risk prediction and prognosis factor identification in diabetic patients","authors":"Hugo Calero-Diaz, David Chushig-Muzo, H. Fabelo, I. Mora-Jiménez, C. Granja, C. Soguero-Ruíz","doi":"10.1109/BHI56158.2022.9926871","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926871","url":null,"abstract":"The increase of patients diagnosed with non-communicable diseases (NCDs) has reached high levels, becoming an important global health issue. NCDs are the cause of decease of 41 million people yearly, accounting for 71% of all deaths world-wide. Among NCDs, cardiovascular diseases (CVDs) present an increasing prevalence, leading to severe complications and death. Patients with Type 1 diabetes are more prone to develop CVD events, and refer to greater mortality rates than the general population. An early risk prediction of developing CVD events in T1D patients could support clinicians in adequate interventions, including lifestyle changes or pharmacological and surgical treatments. In this work, we use feature selection techniques and data-driven models to identify relevant prognostic factors associated with the 10-year CVD risk, designing models for its earlier prediction. Demographic and clinical variables related to the patients' lifestyle were considered, including the interpretation of the variables' impact on the prediction models. Experimental results showed that linear data-driven models are best for CVD prediction, outperforming results of other techniques. Regarding the risk factors, the age was the most important variable for predicting CVD, being present in all the analyzed models. This work showed to be promising for predicting CVD, identifying risk factors, and paving the way for clinical decision-making.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126839960","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}

引用次数: 2

Pneumonia and COVID-19 Detection in Chest X-rays Using Faster Region-Based Convolutional Neural Networks (Faster R-CNN)* 基于更快区域卷积神经网络(Faster R-CNN)的胸部x线肺炎和COVID-19检测*

2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI) Pub Date : 2022-09-27 DOI: 10.1109/BHI56158.2022.9926872

Hanan Farhat, G. Sakr, R. Kilany

{"title":"Pneumonia and COVID-19 Detection in Chest X-rays Using Faster Region-Based Convolutional Neural Networks (Faster R-CNN)*","authors":"Hanan Farhat, G. Sakr, R. Kilany","doi":"10.1109/BHI56158.2022.9926872","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926872","url":null,"abstract":"The arising of SARS-CoV-2 or 2019 novel coron-avirus in December 2019 have prioritized research on pulmonary diseases diagnosis and prognosis, especially using artificial intelligence (AI) and Deep Learning (DL). Polymerase Chain Reaction (PCR) is the most widely used technique to detect SARS-CoV-2, with a 0.12% false negative rate. While 75% of the hospitalized cases develop pneumonia caused by the virus, patients can still develop bacterial pneumonia. COVID-19 pneumonia can be diagnosed based on clinical data and Computed Tomography (CT scan). However, Chest X-rays are faster, cheaper, emit less radiations, and can be performed on bed-side. In this article, we extend the application of VGG-16 based Faster Region-Based Convolutional Neural Network (Faster R-CNN) to the detection of Pneumonia and COVID-19 in Chest X-ray images using several public datasets of total images count ranging from 2122 to 18455 Chest X-rays, and study the impact of several hyper-parameters such as objectness threshold and epochs count and length, to optimize the model's performance. Our results comply with the state of the art of Faster R-CNN in pneumonia detection as the best accuracy achieved is 65%. For COVID-19 detection, Faster R-CNN achieves a 90% validation accuracy.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116852141","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}

引用次数: 0

Feasibility of Remote Pulse Transit Time Estimation Using Narrow-band Multi-wavelength Camera Photoplethysmography 窄带多波长相机光体积脉搏波远程估计脉冲传输时间的可行性

2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI) Pub Date : 2022-09-11 DOI: 10.1109/BHI56158.2022.9926828

Gašper Slapničar, Wenjin Wang, M. Luštrek

{"title":"Feasibility of Remote Pulse Transit Time Estimation Using Narrow-band Multi-wavelength Camera Photoplethysmography","authors":"Gašper Slapničar, Wenjin Wang, M. Luštrek","doi":"10.1109/BHI56158.2022.9926828","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926828","url":null,"abstract":"Contact-free remote sensing gained much traction in the past decade. While such monitoring of some vitals (heart rate) is approaching clinical levels of performance, others remain difficult to estimate (blood pressure) while being very valuable. In this paper we investigated the feasibility of estimating pulse transit time (PTT) - a marker known to be highly correlated with blood pressure - in a remote way from a single measuring site, using just a single modified RGB camera. The replacement of infrared (IR) filter with a narrow band triple bandpass filter allowed us to remotely measure the PTT between traditional wavelengths (green) and infrared (NIR) using a regular RGB camera. We measured PTT leveraging the fact that different wavelengths penetrate to different skin depths. Use of such a filter minimizes the inter-channel influence and band overlap and leverages NIR information not traditionally available from consumer RGB cameras. This way we obtained slightly delayed photoplethysmograms corresponding to each wavelength and skin depth. In our initial experiments with 5 subjects we observed relatively consistent temporal delays between waveforms from different wavelengths (especially near-infrared and green) in accordance with expectations and related work. These early results show promising fundamentals for further research in remote multi-wavelength PTT and blood pressure estimation, while also highlighting important fundamental and technical challenges to be considered.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125817331","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}

引用次数: 0

Clustering Egocentric Images in Passive Dietary Monitoring with Self-Supervised Learning 基于自监督学习的自我中心图像聚类被动饮食监测

2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI) Pub Date : 2022-08-25 DOI: 10.1109/BHI56158.2022.9926927

Jiachuan Peng, Peilun Shi, Jianing Qiu, Xinwei Ju, F. P. Lo, Xiao Gu, Wenyan Jia, T. Baranowski, M. Steiner-Asiedu, A. Anderson, M. McCrory, E. Sazonov, M. Sun, G. Frost, Benny P. L. Lo

{"title":"Clustering Egocentric Images in Passive Dietary Monitoring with Self-Supervised Learning","authors":"Jiachuan Peng, Peilun Shi, Jianing Qiu, Xinwei Ju, F. P. Lo, Xiao Gu, Wenyan Jia, T. Baranowski, M. Steiner-Asiedu, A. Anderson, M. McCrory, E. Sazonov, M. Sun, G. Frost, Benny P. L. Lo","doi":"10.1109/BHI56158.2022.9926927","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926927","url":null,"abstract":"In our recent dietary assessment field studies on passive dietary monitoring in Ghana, we have collected over 250k in-the-wild images. The dataset is an ongoing effort to facilitate accurate measurement of individual food and nutrient intake in low and middle income countries with passive monitoring camera technologies. The current dataset involves 20 households (74 subjects) from both the rural and urban regions of Ghana, and two different types of wearable cameras were used in the studies. Once initiated, wearable cameras continuously capture subjects' activities, which yield massive amounts of data to be cleaned and annotated before analysis is conducted. To ease the data post-processing and annotation tasks, we propose a novel self-supervised learning framework to cluster the large volume of egocentric images into separate events. Each event consists of a sequence of temporally continuous and contextually similar images. By clustering images into separate events, annotators and dietitians can examine and analyze the data more efficiently and facilitate the subsequent dietary assessment processes. Validated on a held-out test set with ground truth labels, the proposed framework outperforms baselines in terms of clustering quality and classification accuracy.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"145 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116727335","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}

引用次数: 3

Concurrent Validity of Automatic Speech and Pause Measures During Passage Reading in ALS 肌萎缩侧索硬化症患者阅读文章时自动语音和停顿措施的同步有效性

2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI) Pub Date : 2022-08-22 DOI: 10.1109/BHI56158.2022.9926862

S. Naeini, Leif E. R. Simmatis, Y. Yunusova, B. Taati

{"title":"Concurrent Validity of Automatic Speech and Pause Measures During Passage Reading in ALS","authors":"S. Naeini, Leif E. R. Simmatis, Y. Yunusova, B. Taati","doi":"10.1109/BHI56158.2022.9926862","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926862","url":null,"abstract":"The analysis of speech measures in individuals with amyotrophic lateral sclerosis (ALS) can provide essential information for early diagnosis and tracking disease progression. However, current methods for extracting speech and pause features are manual or semi-automatic, which makes them time-consuming and labour-intensive. The advent of speech-text alignment algorithms provides an opportunity for inex-pensive, automated, and accurate analysis of speech measures in individuals with ALS. There is a need to validate speech and pause features calculated by these algorithms against current gold standard methods. In this study, we extracted 8 speech/pause features from 646 audio files of individuals with ALS and healthy controls performing passage reading. Two pretrained forced alignment models - one using transformers and another using a Gaussian mixture / hidden Markov architecture - were used for automatic feature extraction. The results were then validated against semi-automatic speech/pause analysis software, with further subgroup analyses based on audio quality and disease severity. Features extracted using transformer-based forced alignment had the highest agreement with gold standards, including in terms of audio quality and disease severity. This study lays the groundwork for future intelligent diagnostic support systems for clinicians, and for novel methods of tracking disease progression remotely from home.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123537405","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}

引用次数: 0

Automated Temporal Segmentation of Orofacial Assessment Videos 口面部评估视频的自动时间分割

2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI) Pub Date : 2022-08-22 DOI: 10.1109/BHI56158.2022.9926863

S. Naeini, Leif E. R. Simmatis, D. Jafari, D. Guarin, Y. Yunusova, B. Taati

{"title":"Automated Temporal Segmentation of Orofacial Assessment Videos","authors":"S. Naeini, Leif E. R. Simmatis, D. Jafari, D. Guarin, Y. Yunusova, B. Taati","doi":"10.1109/BHI56158.2022.9926863","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926863","url":null,"abstract":"Computer vision techniques can help automate or partially automate clinical examination of orofacial impairments to provide accurate and objective assessments. Towards the development of such automated systems, we evaluated two approaches to detect and temporally segment (parse) repetitions in orofacial assessment videos. Recorded videos of participants with amyotrophic lateral sclerosis (ALS) and healthy control (HC) individuals were obtained from the Toronto NeuroFace Dataset. Two approaches for repetition detection and parsing were examined: one based on engineered features from tracked facial landmarks and peak detection in the distance between the vermilion-cutaneous junction of the upper and lower lips (baseline analysis), and another using a pre-trained transformer-based deep learning model called RepNet (Dwibedi et al, 2020), which automatically detects periodicity, and parses periodic and semi-periodic repetitions in video data. In experimental evaluation of two orofacial assessments tasks, - repeating maximum mouth opening (OPEN) and repeating the sentence “Buy Bobby a Puppy” (BBP) - RepNet provided better parsing than the landmark-based approach, quantified by higher mean intersection-over-union (IoU) with respect to ground truth manual parsing. Automated parsing using RepNet also clearly separated HC and ALS participants based on the duration of BBP repetitions, whereas the landmark-based method could not.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124158456","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}

引用次数: 0

Towards Graph Representation Learning Based Surgical Workflow Anticipation 基于图表示学习的手术工作流程预测

2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI) Pub Date : 2022-08-07 DOI: 10.1109/BHI56158.2022.9926801

Xiatian Zhang, N. A. Moubayed, Hubert P. H. Shum

{"title":"Towards Graph Representation Learning Based Surgical Workflow Anticipation","authors":"Xiatian Zhang, N. A. Moubayed, Hubert P. H. Shum","doi":"10.1109/BHI56158.2022.9926801","DOIUrl":"https://doi.org/10.1109/BHI56158.2022.9926801","url":null,"abstract":"Surgical workflow anticipation can give predictions on what steps to conduct or what instruments to use next, which is an essential part of the computer-assisted intervention system for surgery, e.g. workflow reasoning in robotic surgery. However, current approaches are limited to their insufficient expressive power for relationships between instruments. Hence, we propose a graph representation learning framework to comprehensively represent instrument motions in the surgical workflow anticipation problem. In our proposed graph representation, we maps the bounding box information of instruments to the graph nodes in the consecutive frames and build inter-frame/inter-instrument graph edges to represent the trajectory and interaction of the instruments over time. This design enhances the ability of our network on modeling both the spatial and temporal patterns of surgical instruments and their interactions. In addition, we design a multi-horizon learning strategy to balance the understanding of various horizons indifferent anticipation tasks, which significantly improves the model performance in anticipation with various horizons. Experiments on the Cholec80 dataset demonstrate the performance of our proposed method can exceed the state-of-the-art method based on richer backbones, especially in instrument anticipation (1.27 v.s. 1.48 for inMAE; 1.48 v.s. 2.68 for eMAE). To the best of our knowledge, we are the first to introduce a spatial-temporal graph representation into surgical workflow anticipation.","PeriodicalId":347210,"journal":{"name":"2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129095333","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}

引用次数: 0