首页 > 最新文献

2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS)最新文献

英文 中文
Wia-Spine: A CBIR environment with embedded radiomic features to assess fragility fractures Wia-Spine:一种具有嵌入式放射学特征的CBIR环境来评估脆性骨折
Pub Date : 2022-07-01 DOI: 10.1109/CBMS55023.2022.00020
M. Bedo, Jonathan S. Ramos, A. J. Traina, C. Traina, M. Nogueira-Barbosa, P. M. A. Marques
Osteoporosis is a systemic disorder that reduces the bone mineral density, increasing the vertebrae's fragility and proneness to fracture. Although the bone densitometry index t-Score is a solid marker for the osteoporosis diagnosis, its measure alone is insufficient to predict the future development of fragility fractures. A complementary approach to address vertebral bone characterization is the analysis of magnetic resonance imaging (MRI) by radiomic features, which model vertebral bodies' morphological properties after color and texture. Radiomic features have been employed for detecting fragility fractures in related work, but, to the best of our knowledge, no study has been conducted on their suitability to recover similar, diagnosed cases that could hint at future fractures. We fulfill this gap by designing a Content-based Image Retrieval (CBIR) tool with embedded radiomic features, which uses past cases recovered from an annotated database to (i) identify an existing fragility fracture in a query vertebra and (ii) predict a fracture to a query vertebra from an aging patient. The proposed CBIR was evaluated on a reference database of 273 vertebral bodies from sagittal T2-weighted MRIs. The results indicate our fine-tuned approach spotted fragility fractures accurately $(mathrm{F}1-text{Score} =0.83, text{Precision} =0.83, text{AUC} =0.81, text{CI} =95%)$. We also investigated the CBIR potential to predict fractures in a case study regarding three patients from the reference database (confirmed osteoporosis, MRI in [2012–2017]). The system correctly inferred the prediction of future fractures for query vertebrae, which were confirmed a few years later (MRI in [2018–2021]). Such empirical findings suggest CBIR can support a differential diagnosis in the assessment of local fragility fractures.
骨质疏松症是一种全身性疾病,它会降低骨密度,增加椎骨的脆弱性和骨折的可能性。虽然骨密度指数t-Score是骨质疏松症诊断的可靠指标,但仅凭其测量不足以预测脆性骨折的未来发展。解决椎体骨特征的补充方法是通过放射学特征对磁共振成像(MRI)进行分析,该分析模拟了椎体在颜色和纹理之后的形态特性。在相关工作中,放射学特征已被用于检测脆性骨折,但据我们所知,目前还没有研究表明放射学特征是否适合用于恢复类似的诊断病例,而这些病例可能暗示未来的骨折。我们通过设计一个嵌入放射学特征的基于内容的图像检索(CBIR)工具来填补这一空白,该工具使用从带注释的数据库中恢复的过去病例来(i)识别查询椎体中现有的脆性骨折,(ii)预测老年患者的查询椎体骨折。建议的CBIR在矢状面t2加权mri的273个椎体的参考数据库上进行评估。结果表明,我们的微调方法准确地发现了脆性骨折$( mathm {F}1-text{Score} =0.83, text{Precision} =0.83, text{AUC} =0.81, text{CI} =95%)$。我们还研究了CBIR预测骨折的潜力,该研究涉及来自参考数据库的三名患者(确诊骨质疏松症,MRI于[2012-2017])。该系统正确推断了查询椎体未来骨折的预测,并在几年后得到了证实(MRI于[2018-2021])。这些实证结果表明,CBIR可以支持局部脆性骨折评估的鉴别诊断。
{"title":"Wia-Spine: A CBIR environment with embedded radiomic features to assess fragility fractures","authors":"M. Bedo, Jonathan S. Ramos, A. J. Traina, C. Traina, M. Nogueira-Barbosa, P. M. A. Marques","doi":"10.1109/CBMS55023.2022.00020","DOIUrl":"https://doi.org/10.1109/CBMS55023.2022.00020","url":null,"abstract":"Osteoporosis is a systemic disorder that reduces the bone mineral density, increasing the vertebrae's fragility and proneness to fracture. Although the bone densitometry index t-Score is a solid marker for the osteoporosis diagnosis, its measure alone is insufficient to predict the future development of fragility fractures. A complementary approach to address vertebral bone characterization is the analysis of magnetic resonance imaging (MRI) by radiomic features, which model vertebral bodies' morphological properties after color and texture. Radiomic features have been employed for detecting fragility fractures in related work, but, to the best of our knowledge, no study has been conducted on their suitability to recover similar, diagnosed cases that could hint at future fractures. We fulfill this gap by designing a Content-based Image Retrieval (CBIR) tool with embedded radiomic features, which uses past cases recovered from an annotated database to (i) identify an existing fragility fracture in a query vertebra and (ii) predict a fracture to a query vertebra from an aging patient. The proposed CBIR was evaluated on a reference database of 273 vertebral bodies from sagittal T2-weighted MRIs. The results indicate our fine-tuned approach spotted fragility fractures accurately $(mathrm{F}1-text{Score} =0.83, text{Precision} =0.83, text{AUC} =0.81, text{CI} =95%)$. We also investigated the CBIR potential to predict fractures in a case study regarding three patients from the reference database (confirmed osteoporosis, MRI in [2012–2017]). The system correctly inferred the prediction of future fractures for query vertebrae, which were confirmed a few years later (MRI in [2018–2021]). Such empirical findings suggest CBIR can support a differential diagnosis in the assessment of local fragility fractures.","PeriodicalId":218475,"journal":{"name":"2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS)","volume":"182 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123290857","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
End-to-End Multi-task Learning Regression Network for Fovea Localization in Fundus Images 眼底图像中央凹定位的端到端多任务学习回归网络
Pub Date : 2022-07-01 DOI: 10.1109/CBMS55023.2022.00076
Limin Huang, Haijun Lei, Weixing Liu, Z. Li, Hai Xie, Baiying Lei
Macular fovea localization in fundus images is a critical stage for computer-aided diagnostic techniques of many retinal diseases. Due to its cluttered visual characteristics, it is difficult to accurately locate the fovea. Many previous methods obtain the location of macular fovea from pre-extracting image features extracted from surrounding structures, such as optic disc and vascular distribution. Deep learning-based regression techniques are promising due to their effective modeling of the relationship between the fovea and its surrounding structure for fovea localization. However, there are still many challenges to locate the fovea using deep learning accurately. To address these issues, we design a novel end-to-end multi-task learning regression network for fovea localization. Specifically, the proposed network consists of two regression networks. For the coordinate regression network, we introduce multi-scale fusion technology and a multi-head self-attention module to extract discriminative context information and capture long-term dependence, respectively. For the heatmap regression network, the generated heatmap according to the coordinates is utilized to supervise the output of the network. The experimental results on three public datasets demonstrate that our method achieves superior performance for the localization of macular fovea.
眼底图像中的黄斑中央凹定位是许多视网膜疾病计算机辅助诊断技术的关键阶段。由于其杂乱的视觉特征,很难准确定位中央窝。以往的许多方法都是通过提取视盘、血管分布等周围结构的预提取图像特征来获得黄斑中央窝的位置。基于深度学习的回归技术由于其对中央窝及其周围结构之间关系的有效建模而具有广阔的应用前景。然而,使用深度学习准确定位中央窝仍然存在许多挑战。为了解决这些问题,我们设计了一种新颖的端到端多任务学习回归网络,用于中央凹定位。具体来说,所提出的网络由两个回归网络组成。对于坐标回归网络,我们引入了多尺度融合技术和多头自关注模块,分别提取判别上下文信息和捕获长期依赖关系。对于热图回归网络,利用根据坐标生成的热图来监督网络的输出。在三个公开数据集上的实验结果表明,该方法对黄斑中央凹的定位有较好的效果。
{"title":"End-to-End Multi-task Learning Regression Network for Fovea Localization in Fundus Images","authors":"Limin Huang, Haijun Lei, Weixing Liu, Z. Li, Hai Xie, Baiying Lei","doi":"10.1109/CBMS55023.2022.00076","DOIUrl":"https://doi.org/10.1109/CBMS55023.2022.00076","url":null,"abstract":"Macular fovea localization in fundus images is a critical stage for computer-aided diagnostic techniques of many retinal diseases. Due to its cluttered visual characteristics, it is difficult to accurately locate the fovea. Many previous methods obtain the location of macular fovea from pre-extracting image features extracted from surrounding structures, such as optic disc and vascular distribution. Deep learning-based regression techniques are promising due to their effective modeling of the relationship between the fovea and its surrounding structure for fovea localization. However, there are still many challenges to locate the fovea using deep learning accurately. To address these issues, we design a novel end-to-end multi-task learning regression network for fovea localization. Specifically, the proposed network consists of two regression networks. For the coordinate regression network, we introduce multi-scale fusion technology and a multi-head self-attention module to extract discriminative context information and capture long-term dependence, respectively. For the heatmap regression network, the generated heatmap according to the coordinates is utilized to supervise the output of the network. The experimental results on three public datasets demonstrate that our method achieves superior performance for the localization of macular fovea.","PeriodicalId":218475,"journal":{"name":"2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS)","volume":"250 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115590004","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
Breast Cancer Diagnosis from Histopathology Images using Supervised Algorithms 使用监督算法从组织病理学图像中诊断乳腺癌
Pub Date : 2022-07-01 DOI: 10.1109/CBMS55023.2022.00025
Alberto Labrada, B. Barkana
Breast cancer is the most common cancer type worldwide. In cancer studies, histopathological breast images are used in the process of diagnosis. In this paper, we defined three sets of features to represent the characteristics of the cell nuclei to detect malignant cases. Geometric, directional, and intensity-based features, a total of 33, are derived and evaluated using breast cancer histopathological images from the BreaKHis database. Four machine learning algorithms, including Decision Tree, Support Vector Machines, K-Nearest Neighbor, and Narrow Neural Networks (NNN), are designed to assess the efficiency of the sets. The preliminary results showed that the proposed methodology achieved high performance in classifying cancerous cells as the directional feature set was the most effective set among the three sets. The combination of the sets achieved the best performance by the NNN, which reached an accuracy, recall, precision, AUC, and F1 score of 96.9%, 97.4%, 98%, 98.8%, and 97.7%, respectively.
乳腺癌是世界上最常见的癌症类型。在癌症研究中,组织病理学乳房图像用于诊断过程。在本文中,我们定义了三组特征来表示细胞核的特征,以检测恶性病例。基于几何、方向和强度的特征,共33个,使用BreaKHis数据库中的乳腺癌组织病理学图像进行导出和评估。四种机器学习算法,包括决策树、支持向量机、k近邻和窄神经网络(NNN),被设计用来评估集合的效率。初步结果表明,所提出的方法在癌细胞分类方面取得了较高的性能,其中方向特征集是三个集合中最有效的集合。这些集合的组合达到了NNN的最佳性能,准确率、召回率、精度、AUC和F1得分分别达到96.9%、97.4%、98%、98.8%和97.7%。
{"title":"Breast Cancer Diagnosis from Histopathology Images using Supervised Algorithms","authors":"Alberto Labrada, B. Barkana","doi":"10.1109/CBMS55023.2022.00025","DOIUrl":"https://doi.org/10.1109/CBMS55023.2022.00025","url":null,"abstract":"Breast cancer is the most common cancer type worldwide. In cancer studies, histopathological breast images are used in the process of diagnosis. In this paper, we defined three sets of features to represent the characteristics of the cell nuclei to detect malignant cases. Geometric, directional, and intensity-based features, a total of 33, are derived and evaluated using breast cancer histopathological images from the BreaKHis database. Four machine learning algorithms, including Decision Tree, Support Vector Machines, K-Nearest Neighbor, and Narrow Neural Networks (NNN), are designed to assess the efficiency of the sets. The preliminary results showed that the proposed methodology achieved high performance in classifying cancerous cells as the directional feature set was the most effective set among the three sets. The combination of the sets achieved the best performance by the NNN, which reached an accuracy, recall, precision, AUC, and F1 score of 96.9%, 97.4%, 98%, 98.8%, and 97.7%, respectively.","PeriodicalId":218475,"journal":{"name":"2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122893783","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: 4
Generative Adversarial Networks for Augmenting EEG Data in P300-based Applications: A Comparative Study 基于p300的脑电数据增强生成对抗网络的比较研究
Pub Date : 2022-07-01 DOI: 10.1109/CBMS55023.2022.00038
Yasmin Abdelghaffar, Ahmed Hashem, S. Eldawlatly
The performance of P300-based Brain-Computer Interface (BCI) applications is highly dependent on both the quality and quantity of the recorded Electroencephalography (EEG) signals. As recording extended datasets from users for calibration is often a difficult and tedious task, data augmentation can be used to help supplement the training data for machine learning classifiers that are typically used in P300-based BCI applications. In this paper, we analyze and compare the performance of three different generative adversarial networks (GANs) as data augmentation techniques; namely, deep convolutional GAN (DCGAN), conditional GAN (cGAN), and the auxiliary classifier GAN (ACGAN). We first investigated the effect of increasing the training data size using each of these GANs on the performance of P300 classification. Our results revealed that the cGAN increased the classification accuracy by up to 18% relative to the baseline data under the best conditions. We also investigated the effect of decreasing the training data size and compensating for the reduced data size using data generated from the GANs. Our analysis indicated that the training data size could be reduced by ~30% while maintaining the accuracy on par with the baseline accuracy. These results demonstrate the utility of GANs in addressing the challenges associated with the limited data typically available for BCI applications.
基于p300的脑机接口(BCI)应用程序的性能高度依赖于记录的脑电图(EEG)信号的质量和数量。由于记录来自用户的扩展数据集进行校准通常是一项困难而乏味的任务,因此可以使用数据增强来帮助补充机器学习分类器的训练数据,这些分类器通常用于基于p300的BCI应用程序。在本文中,我们分析和比较了三种不同的生成对抗网络(gan)作为数据增强技术的性能;即深度卷积GAN (DCGAN)、条件GAN (cGAN)和辅助分类器GAN (ACGAN)。我们首先研究了使用这些gan增加训练数据大小对P300分类性能的影响。我们的研究结果显示,在最佳条件下,相对于基线数据,cGAN将分类精度提高了18%。我们还研究了减少训练数据大小和使用gan生成的数据补偿减少的数据大小的效果。我们的分析表明,训练数据大小可以减少~30%,同时保持与基线精度相当的精度。这些结果证明了gan在解决与BCI应用程序通常可用的有限数据相关的挑战方面的实用性。
{"title":"Generative Adversarial Networks for Augmenting EEG Data in P300-based Applications: A Comparative Study","authors":"Yasmin Abdelghaffar, Ahmed Hashem, S. Eldawlatly","doi":"10.1109/CBMS55023.2022.00038","DOIUrl":"https://doi.org/10.1109/CBMS55023.2022.00038","url":null,"abstract":"The performance of P300-based Brain-Computer Interface (BCI) applications is highly dependent on both the quality and quantity of the recorded Electroencephalography (EEG) signals. As recording extended datasets from users for calibration is often a difficult and tedious task, data augmentation can be used to help supplement the training data for machine learning classifiers that are typically used in P300-based BCI applications. In this paper, we analyze and compare the performance of three different generative adversarial networks (GANs) as data augmentation techniques; namely, deep convolutional GAN (DCGAN), conditional GAN (cGAN), and the auxiliary classifier GAN (ACGAN). We first investigated the effect of increasing the training data size using each of these GANs on the performance of P300 classification. Our results revealed that the cGAN increased the classification accuracy by up to 18% relative to the baseline data under the best conditions. We also investigated the effect of decreasing the training data size and compensating for the reduced data size using data generated from the GANs. Our analysis indicated that the training data size could be reduced by ~30% while maintaining the accuracy on par with the baseline accuracy. These results demonstrate the utility of GANs in addressing the challenges associated with the limited data typically available for BCI applications.","PeriodicalId":218475,"journal":{"name":"2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121929450","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
Evaluation of Relevance-Driven Compression of Regular Cataract Surgery Videos 常规白内障手术视频的相关性驱动压缩评价
Pub Date : 2022-07-01 DOI: 10.1109/CBMS55023.2022.00083
Natalia Mathá, Klaus Schoeffmann, S. Sarny, Doris Putzgruber-Adamitsch, Y. El-Shabrawi
In recent years, the utilization intensity and thus the demand for storing cataract surgery videos for different purposes has increased. Hospitals continuously improve their technical recording equipment, i.e., cameras, to enhance the post-operative processing efficiency of the recordings. However, afterward, the videos are stored on hospitals' internal data servers in their original size, which leads to a massive storage consumption. In this paper, we propose a relevance-based compression scheme. First, we perform a user study with clinicians to define the relevance rates of regular cataract surgery phases. Then, we compress different phases based on the determined relevance rates, using different encoding parameters and two coding standards, namely H.264/AVC and AV1. Afterward, the medical experts evaluate the visual quality of the encoded videos. Our results show a storage-saving potential for H.264/AVC of up to 95.94% and up to 98.82% for AV1, excluding idle phases (no tools are visible).
近年来,白内障手术视频的使用强度和存储不同用途的需求不断增加。医院不断改进技术记录设备,如摄像机,以提高记录的术后处理效率。但是,之后,这些视频以原始大小存储在医院内部的数据服务器上,这导致了大量的存储消耗。在本文中,我们提出了一种基于相关性的压缩方案。首先,我们与临床医生进行了一项用户研究,以确定常规白内障手术阶段的相关性。然后,根据确定的相关率,使用不同的编码参数和H.264/AVC和AV1两种编码标准对不同的相位进行压缩。之后,医学专家评估编码视频的视觉质量。我们的研究结果表明,H.264/AVC的存储节省潜力高达95.94%,AV1的存储节省潜力高达98.82%,不包括空闲阶段(没有工具可见)。
{"title":"Evaluation of Relevance-Driven Compression of Regular Cataract Surgery Videos","authors":"Natalia Mathá, Klaus Schoeffmann, S. Sarny, Doris Putzgruber-Adamitsch, Y. El-Shabrawi","doi":"10.1109/CBMS55023.2022.00083","DOIUrl":"https://doi.org/10.1109/CBMS55023.2022.00083","url":null,"abstract":"In recent years, the utilization intensity and thus the demand for storing cataract surgery videos for different purposes has increased. Hospitals continuously improve their technical recording equipment, i.e., cameras, to enhance the post-operative processing efficiency of the recordings. However, afterward, the videos are stored on hospitals' internal data servers in their original size, which leads to a massive storage consumption. In this paper, we propose a relevance-based compression scheme. First, we perform a user study with clinicians to define the relevance rates of regular cataract surgery phases. Then, we compress different phases based on the determined relevance rates, using different encoding parameters and two coding standards, namely H.264/AVC and AV1. Afterward, the medical experts evaluate the visual quality of the encoded videos. Our results show a storage-saving potential for H.264/AVC of up to 95.94% and up to 98.82% for AV1, excluding idle phases (no tools are visible).","PeriodicalId":218475,"journal":{"name":"2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124647923","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
Ensemble Framework for Unsupervised Cervical Cell Segmentation 无监督子宫颈细胞分割的集成框架
Pub Date : 2022-07-01 DOI: 10.1109/CBMS55023.2022.00068
Agnimitra Sen, Shyamali Mitra, S. Chakraborty, Debashri Mondal, K. Santosh, N. Das
In medical image segmentation, preparing ground truths (or masks) is not trivial as it requires expert clinicians to manually label regions-of-interest. Cervical cytology image segmentation is no exception. In this paper, we propose an unsupervised segmentation framework for cervical cell and whole slide segmentation uses an ensemble of three clustering algorithms namely, K-means, K-means++ and Mean Shift clustering. The final cluster centers obtained from these algorithms are used to initialize cluster points for Fuzzy C-means clustering algorithm. The proposed method is evaluated on multiple standard datasets: HErlev Pap Smear dataset and SIPaKMeD Pap Smear dataset. We also evaluated on a whole slide image dataset (source: CMATER-JU laboratory) and our results are promising and comparable. Overall, our results on multiple benchmark datasets justify the viability of the proposed framework.
在医学图像分割中,准备基础真理(或掩模)不是微不足道的,因为它需要专家临床医生手动标记感兴趣的区域。宫颈细胞学图像分割也不例外。本文提出了一种基于K-means、k -means++和Mean Shift三种聚类算法的宫颈细胞和整个切片的无监督分割框架。这些算法得到的最终聚类中心用于模糊c均值聚类算法初始化聚类点。该方法在多个标准数据集上进行了评估:HErlev子宫颈抹片数据集和SIPaKMeD子宫颈抹片数据集。我们还对整个幻灯片图像数据集进行了评估(来源:CMATER-JU实验室),我们的结果是有希望的和可比较的。总的来说,我们在多个基准数据集上的结果证明了所提出框架的可行性。
{"title":"Ensemble Framework for Unsupervised Cervical Cell Segmentation","authors":"Agnimitra Sen, Shyamali Mitra, S. Chakraborty, Debashri Mondal, K. Santosh, N. Das","doi":"10.1109/CBMS55023.2022.00068","DOIUrl":"https://doi.org/10.1109/CBMS55023.2022.00068","url":null,"abstract":"In medical image segmentation, preparing ground truths (or masks) is not trivial as it requires expert clinicians to manually label regions-of-interest. Cervical cytology image segmentation is no exception. In this paper, we propose an unsupervised segmentation framework for cervical cell and whole slide segmentation uses an ensemble of three clustering algorithms namely, K-means, K-means++ and Mean Shift clustering. The final cluster centers obtained from these algorithms are used to initialize cluster points for Fuzzy C-means clustering algorithm. The proposed method is evaluated on multiple standard datasets: HErlev Pap Smear dataset and SIPaKMeD Pap Smear dataset. We also evaluated on a whole slide image dataset (source: CMATER-JU laboratory) and our results are promising and comparable. Overall, our results on multiple benchmark datasets justify the viability of the proposed framework.","PeriodicalId":218475,"journal":{"name":"2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121181045","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
Ultrasonic Carotid Blood Flow Velocimetry Based on Deep Complex Neural Network 基于深度复杂神经网络的超声颈动脉血流速度测量
Pub Date : 2022-07-01 DOI: 10.1109/CBMS55023.2022.00032
Jian Lei, Xun Lang, Bingbing He, Songhua Liu, Hao Tan, Yufeng Zhang
Precise measurement of carotid artery blood flow is of vital importance for studying thrombosis and early carotid atherosclerotic plaque. However, the traditional non-parametric methods are limited by the weak detection ability to low-velocity blood flow, and show problems including the large measurement deviation and long algorithm running time. Motivated by the above status quo, a novel method based on deep complex convolutional neural network (DCCNN) is proposed for carotid blood flow velocimetry. Based on supervised learning, DCCNN feeds the echo signals into complex convolutional layers for the purpose of rejecting clutter signals. Then, the outputs of complex convolutional layers are processed by the complex fully connected layers to estimate the blood flow velocity. The effectiveness of the proposed method is verified by simulation as well as in vivo data of healthy volunteers. Compared with typical velocimetry methods such as the high-pass filter and singular value decomposition, the normalized root mean square error (NRMSE) of the velocimetry result obtained from the proposed method is reduced by 47.20%) and 45.45%, and the goodness-of-fit is improved by 5.64%, 3.36%, respectively. In addition, the running time of DCCNN is reduced by 82.10% and 21.11%, respectively. Such results show that the proposed method is a promising tool for blood flow velocity measurement due to its higher velocity measurement accuracy and good real-time performance.
颈动脉血流的精确测量对于研究血栓形成和早期颈动脉粥样硬化斑块至关重要。然而,传统的非参数方法对低速血流的检测能力较弱,存在测量偏差大、算法运行时间长等问题。基于以上现状,本文提出了一种基于深度复杂卷积神经网络(DCCNN)的颈动脉血流速度测量方法。DCCNN基于监督学习,将回波信号送入复卷积层,以抑制杂波信号。然后,将复卷积层的输出经过复全连通层的处理来估计血流速度。通过仿真和健康志愿者的体内数据验证了该方法的有效性。与高通滤波和奇异值分解等典型测速方法相比,该方法得到的测速结果的归一化均方根误差(NRMSE)分别降低了47.20%和45.45%,拟合优度分别提高了5.64%和3.36%。此外,DCCNN的运行时间分别缩短了82.10%和21.11%。结果表明,该方法具有较高的测速精度和良好的实时性,是一种很有前途的血流速度测量工具。
{"title":"Ultrasonic Carotid Blood Flow Velocimetry Based on Deep Complex Neural Network","authors":"Jian Lei, Xun Lang, Bingbing He, Songhua Liu, Hao Tan, Yufeng Zhang","doi":"10.1109/CBMS55023.2022.00032","DOIUrl":"https://doi.org/10.1109/CBMS55023.2022.00032","url":null,"abstract":"Precise measurement of carotid artery blood flow is of vital importance for studying thrombosis and early carotid atherosclerotic plaque. However, the traditional non-parametric methods are limited by the weak detection ability to low-velocity blood flow, and show problems including the large measurement deviation and long algorithm running time. Motivated by the above status quo, a novel method based on deep complex convolutional neural network (DCCNN) is proposed for carotid blood flow velocimetry. Based on supervised learning, DCCNN feeds the echo signals into complex convolutional layers for the purpose of rejecting clutter signals. Then, the outputs of complex convolutional layers are processed by the complex fully connected layers to estimate the blood flow velocity. The effectiveness of the proposed method is verified by simulation as well as in vivo data of healthy volunteers. Compared with typical velocimetry methods such as the high-pass filter and singular value decomposition, the normalized root mean square error (NRMSE) of the velocimetry result obtained from the proposed method is reduced by 47.20%) and 45.45%, and the goodness-of-fit is improved by 5.64%, 3.36%, respectively. In addition, the running time of DCCNN is reduced by 82.10% and 21.11%, respectively. Such results show that the proposed method is a promising tool for blood flow velocity measurement due to its higher velocity measurement accuracy and good real-time performance.","PeriodicalId":218475,"journal":{"name":"2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS)","volume":"50 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114006000","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
Deep Learning Based Multi-Label Prediction of Hospitalization for COVID-19 Cases 基于深度学习的COVID-19住院病例多标签预测
Pub Date : 2022-07-01 DOI: 10.1109/CBMS55023.2022.00024
C. Leung, Thanh Huy Daniel Mai, N. D. Tran
Health informatics is an interdisciplinary area where computer science and related disciplines meet to address problems and support healthcare and medicine. In particular, computer has played an important role in medicine. Many existing computer-based systems (e.g., machine learning models) for healthcare applications produce binary prediction (e.g., whether a patient catches a disease or not). However, there are situations in which a non-binary prediction (e.g., what is hospitalization status of a patient) is needed. As a concrete example, over the past two years, people around the world have been affected by the coronavirus disease 2019 (COVID-19) pandemic. There have been works on binary prediction to determine whether a patient is COVID-19 positive or not. With availability of alternative methods (e.g., rapid test), such a binary prediction has become less important. Moreover, with the evolution of the disease (e.g., recent development of COVID-19 Omicron variant), multi-label prediction of the hospitalization status has become more important when compared with binary prediction on the confirmation of cases. Hence, in this paper, we present a multi-label prediction system for computer-based medical applications. Our system makes use of autoencoders (consisting of encoders and decoders) and few-shot learning to predict the hospitalization status (e.g., ICU, semi-ICU, regular wards, or no hospitalization). The prediction is important for allocation of medical resources (e.g., hospital facilities and medical staff), which in turn affect patient lives. Experimental results on real-life open datasets show that, when training with only a few data, our multilabel prediction system gave a high F1-score when predicting hospitalization status of COVID-19 cases.
健康信息学是一个跨学科领域,计算机科学和相关学科满足解决问题和支持医疗保健和医学。特别是,计算机在医学中发挥了重要作用。许多现有的基于计算机的医疗保健应用系统(例如,机器学习模型)产生二元预测(例如,患者是否患病)。然而,在某些情况下,需要非二元预测(例如,病人的住院情况如何)。作为一个具体的例子,在过去两年中,世界各地的人们都受到了2019年冠状病毒病(COVID-19)大流行的影响。已经有了二元预测的研究,以确定患者是否为COVID-19阳性。有了可用的替代方法(例如,快速测试),这种二元预测已经变得不那么重要了。此外,随着疾病的演变(如近期新出现的COVID-19 Omicron变体),与确诊病例的二元预测相比,住院状态的多标签预测变得更加重要。因此,在本文中,我们提出了一个基于计算机的医学应用的多标签预测系统。我们的系统利用自动编码器(由编码器和解码器组成)和少量学习来预测住院状态(例如,ICU,半ICU,普通病房或不住院)。这一预测对于医疗资源(例如医院设施和医务人员)的分配很重要,而医疗资源的分配反过来又会影响患者的生命。在现实开放数据集上的实验结果表明,当只使用少量数据进行训练时,我们的多标签预测系统在预测COVID-19病例住院情况时给出了很高的f1分。
{"title":"Deep Learning Based Multi-Label Prediction of Hospitalization for COVID-19 Cases","authors":"C. Leung, Thanh Huy Daniel Mai, N. D. Tran","doi":"10.1109/CBMS55023.2022.00024","DOIUrl":"https://doi.org/10.1109/CBMS55023.2022.00024","url":null,"abstract":"Health informatics is an interdisciplinary area where computer science and related disciplines meet to address problems and support healthcare and medicine. In particular, computer has played an important role in medicine. Many existing computer-based systems (e.g., machine learning models) for healthcare applications produce binary prediction (e.g., whether a patient catches a disease or not). However, there are situations in which a non-binary prediction (e.g., what is hospitalization status of a patient) is needed. As a concrete example, over the past two years, people around the world have been affected by the coronavirus disease 2019 (COVID-19) pandemic. There have been works on binary prediction to determine whether a patient is COVID-19 positive or not. With availability of alternative methods (e.g., rapid test), such a binary prediction has become less important. Moreover, with the evolution of the disease (e.g., recent development of COVID-19 Omicron variant), multi-label prediction of the hospitalization status has become more important when compared with binary prediction on the confirmation of cases. Hence, in this paper, we present a multi-label prediction system for computer-based medical applications. Our system makes use of autoencoders (consisting of encoders and decoders) and few-shot learning to predict the hospitalization status (e.g., ICU, semi-ICU, regular wards, or no hospitalization). The prediction is important for allocation of medical resources (e.g., hospital facilities and medical staff), which in turn affect patient lives. Experimental results on real-life open datasets show that, when training with only a few data, our multilabel prediction system gave a high F1-score when predicting hospitalization status of COVID-19 cases.","PeriodicalId":218475,"journal":{"name":"2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124489225","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
Fine-grained Encryption for Secure Research Data Sharing 细粒度加密安全研究数据共享
Pub Date : 2022-07-01 DOI: 10.1109/CBMS55023.2022.00089
L. Reis, M. T. D. Oliveira, S. Olabarriaga
Research data sharing requires provision of adequate security. The requirements for data privacy are extremely demanding for medical data that is reused for research purposes. To address these requirements, the research institutions must implement adequate security measurements, and this demands large effort and costs to do it properly. The usage of adequate access controls and data encryption are key approaches to effectively protect research data confidentiality; however, the management of the encryption keys is challenging. There are novel mechanisms that can be explored for managing access to the encryption keys and encrypted files. These mechanisms guarantee that data are accessed by authorised users and that auditing is possible. In this paper we explore these mechanisms to implement a secure research medical data sharing system. In the proposed system, the research data are stored on a secure cloud system. The data are partitioned into subsets, each one encrypted with a unique key. After the authorisation process, researchers are given rights to use one or more of the keys and to selectively access and decrypt parts of the dataset. Our proposed solution offers automated fine-grain access control to research data, saving time and work usually made manually. Moreover, it maximises and fortifies users' trust in data sharing through secure clouds solutions. We present an initial evaluation and conclude with a discussion about the limitations, open research questions and future work around this challenging topic.
研究数据共享需要提供足够的安全性。对于为了研究目的而重用的医疗数据,对数据隐私的要求非常高。为了满足这些需求,研究机构必须实现足够的安全度量,这需要大量的努力和成本来正确地完成。使用适当的访问控制和数据加密是有效保护研究数据机密性的关键方法;然而,加密密钥的管理具有挑战性。可以探索一些新的机制来管理对加密密钥和加密文件的访问。这些机制保证数据由授权用户访问,并且审计是可能的。在本文中,我们探讨了这些机制来实现一个安全的研究医疗数据共享系统。在该系统中,研究数据存储在一个安全的云系统上。数据被划分为子集,每个子集都用唯一的密钥加密。经过授权过程后,研究人员有权使用一个或多个密钥,并有选择地访问和解密部分数据集。我们提出的解决方案为研究数据提供了自动化的细粒度访问控制,节省了通常手工完成的时间和工作。此外,它还通过安全的云解决方案最大限度地提高和加强用户对数据共享的信任。我们提出了一个初步的评估,并以讨论的局限性,开放的研究问题和未来的工作围绕这一具有挑战性的主题结束。
{"title":"Fine-grained Encryption for Secure Research Data Sharing","authors":"L. Reis, M. T. D. Oliveira, S. Olabarriaga","doi":"10.1109/CBMS55023.2022.00089","DOIUrl":"https://doi.org/10.1109/CBMS55023.2022.00089","url":null,"abstract":"Research data sharing requires provision of adequate security. The requirements for data privacy are extremely demanding for medical data that is reused for research purposes. To address these requirements, the research institutions must implement adequate security measurements, and this demands large effort and costs to do it properly. The usage of adequate access controls and data encryption are key approaches to effectively protect research data confidentiality; however, the management of the encryption keys is challenging. There are novel mechanisms that can be explored for managing access to the encryption keys and encrypted files. These mechanisms guarantee that data are accessed by authorised users and that auditing is possible. In this paper we explore these mechanisms to implement a secure research medical data sharing system. In the proposed system, the research data are stored on a secure cloud system. The data are partitioned into subsets, each one encrypted with a unique key. After the authorisation process, researchers are given rights to use one or more of the keys and to selectively access and decrypt parts of the dataset. Our proposed solution offers automated fine-grain access control to research data, saving time and work usually made manually. Moreover, it maximises and fortifies users' trust in data sharing through secure clouds solutions. We present an initial evaluation and conclude with a discussion about the limitations, open research questions and future work around this challenging topic.","PeriodicalId":218475,"journal":{"name":"2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133087295","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
Explanations of Deep Networks on EEG Data via Interpretable Approaches 基于可解释方法的深度网络对EEG数据的解释
Pub Date : 2022-07-01 DOI: 10.1109/CBMS55023.2022.00037
Chen Cui, Y. Zhang, Shenghua Zhong
Despite achieving success in many domains, deep learning models remain mostly black boxes. However, understanding the reasons behind predictions is quite important in assessing trust, which is fundamental in the EEG analysis task. In this work, we propose to use two representative explanation approaches, including LIME and Grad-CAM, to explain the predictions of a simple convolutional neural network on an EEG-based emotional brain-computer interface. Our results demonstrate the interpretability approaches provide the understanding of which features better discriminate the target emotions and provide insights into the neural processes involved in the model learned behaviors.
尽管在许多领域取得了成功,但深度学习模型仍然大多是黑盒子。然而,理解预测背后的原因对于评估信任是非常重要的,这是脑电图分析任务的基础。在这项工作中,我们建议使用两种具有代表性的解释方法,包括LIME和Grad-CAM,来解释基于脑电图的情感脑机接口上简单卷积神经网络的预测。我们的研究结果表明,可解释性方法提供了对哪些特征更好地区分目标情绪的理解,并提供了对模型学习行为中涉及的神经过程的见解。
{"title":"Explanations of Deep Networks on EEG Data via Interpretable Approaches","authors":"Chen Cui, Y. Zhang, Shenghua Zhong","doi":"10.1109/CBMS55023.2022.00037","DOIUrl":"https://doi.org/10.1109/CBMS55023.2022.00037","url":null,"abstract":"Despite achieving success in many domains, deep learning models remain mostly black boxes. However, understanding the reasons behind predictions is quite important in assessing trust, which is fundamental in the EEG analysis task. In this work, we propose to use two representative explanation approaches, including LIME and Grad-CAM, to explain the predictions of a simple convolutional neural network on an EEG-based emotional brain-computer interface. Our results demonstrate the interpretability approaches provide the understanding of which features better discriminate the target emotions and provide insights into the neural processes involved in the model learned behaviors.","PeriodicalId":218475,"journal":{"name":"2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130689068","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
期刊
2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS)
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1