Irbm最新文献_第6页

Facial Palsy Characterization Using Dual Regression Trees 使用对偶回归树表征面瘫

IF 5.6 4区医学 Q1 ENGINEERING, BIOMEDICAL

Irbm

Pub Date : 2025-02-20 DOI: 10.1016/j.irbm.2025.100882

Soualmi Ameur , Mohd Saquib Khan , Régis Fournier , Marina Guihard , Laurent Chatelain , Marjolaine Baude , Amine Nait-ali

1) Objectives: The current facial recognition tools are inefficient in predicting landmarks for facial palsy patients. Noticeable asymmetry in the face results in inaccurate results as the prediction models are trained on symmetrical faces. In this study, a method is proposed which takes advantage of the existing powerful machine learning tools which are trained on datasets of healthy subjects with symmetric facial movements to create a system that can analyze and localize facial landmarks on both healthy as well as facial palsy subjects.

2) Methods: The task is accomplished by a simple image processing algorithm where two symmetric faces are generated from a non-symmetric face image representing the left and right sides of the original image. This method was tested against two other methods. One, which uses the cascade of regression trees (CRT) algorithm and the other which is a retrained version of the CRT algorithm on a dataset of facial palsy cases called Massachusetts Eye and Ear database and model (MEE).

3) Results: The methods were compared on 3 different types of test datasets containing a total 125 images. The proposed method outperforms other two methods in cases of asymmetrical faces from healthy people and palsy patients with approximately 7% lesser error compared to the CRT method and 39% lesser error than the MEE method.

4) Conclusion: The proposed method had a considerably better performance compared to the other two methods, which opens new perspectives to address the problem of face landmarks localization problem on facial palsy cases.

1)目的：目前的面部识别工具在面瘫患者地标预测方面效率低下。由于预测模型是在对称的面部上训练的，因此面部明显的不对称会导致预测结果不准确。在本研究中，我们提出了一种方法，利用现有强大的机器学习工具，在具有对称面部运动的健康受试者数据集上进行训练，创建一个可以分析和定位健康和面瘫受试者面部标志的系统。该任务通过一种简单的图像处理算法完成，该算法从非对称的人脸图像中生成两个对称的人脸，分别表示原始图像的左右两侧。这种方法与另外两种方法进行了对比试验。一种是使用级联回归树（CRT）算法，另一种是在面瘫病例数据集马萨诸塞州眼耳数据库和模型（MEE）上对CRT算法进行再训练。3)结果：在3种不同类型的测试数据集上进行比较，共包含125张图像。该方法在健康人群和瘫痪患者面部不对称情况下的定位误差比CRT法小约7%，比MEE法小39%，优于其他两种方法。4)结论：该方法的定位误差明显优于其他两种方法，为解决面瘫患者面部标志定位问题开辟了新的视角。

{"title":"Facial Palsy Characterization Using Dual Regression Trees","authors":"Soualmi Ameur , Mohd Saquib Khan , Régis Fournier , Marina Guihard , Laurent Chatelain , Marjolaine Baude , Amine Nait-ali","doi":"10.1016/j.irbm.2025.100882","DOIUrl":"10.1016/j.irbm.2025.100882","url":null,"abstract":"<div><div>1) Objectives: The current facial recognition tools are inefficient in predicting landmarks for facial palsy patients. Noticeable asymmetry in the face results in inaccurate results as the prediction models are trained on symmetrical faces. In this study, a method is proposed which takes advantage of the existing powerful machine learning tools which are trained on datasets of healthy subjects with symmetric facial movements to create a system that can analyze and localize facial landmarks on both healthy as well as facial palsy subjects.</div><div>2) Methods: The task is accomplished by a simple image processing algorithm where two symmetric faces are generated from a non-symmetric face image representing the left and right sides of the original image. This method was tested against two other methods. One, which uses the cascade of regression trees (CRT) algorithm and the other which is a retrained version of the CRT algorithm on a dataset of facial palsy cases called Massachusetts Eye and Ear database and model (MEE).</div><div>3) Results: The methods were compared on 3 different types of test datasets containing a total 125 images. The proposed method outperforms other two methods in cases of asymmetrical faces from healthy people and palsy patients with approximately 7% lesser error compared to the CRT method and 39% lesser error than the MEE method.</div><div>4) Conclusion: The proposed method had a considerably better performance compared to the other two methods, which opens new perspectives to address the problem of face landmarks localization problem on facial palsy cases.</div></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":"46 2","pages":"Article 100882"},"PeriodicalIF":5.6,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143455094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Complementary Split-Ring Resonator for Non-Invasive Diagnosis of Carotid Artery Atherosclerosis: Towards Future in-Vivo Measurements 用于颈动脉粥样硬化无创诊断的互补裂环谐振器：走向未来的体内测量

IF 5.6 4区医学 Q1 ENGINEERING, BIOMEDICAL

Irbm

Pub Date : 2025-02-14 DOI: 10.1016/j.irbm.2025.100883

Joséphine Dupeyron Masini , Frédérique Deshours , Georges Alquie , Rania Shahbaz , Sylvain Feruglio , Olivier Meyer , Dimitri Galayko , Hamid Kokabi , Jean-Michel Davaine

Objectives

The limited penetration depth of electromagnetic (EM) waves into biological tissues is a significant challenge for the use of microwave sensors in medical diagnostics. This study proposes a sensor based on a complementary split-ring resonator (CSRR) for the non-invasive detection of carotid atherosclerotic plaques, designed to be placed on the patient's neck.

Material and methods

The sensor employs a widened feed line and an optimized sensing area to concentrate the electric field and store a significant amount of energy within the biological tissue. Validation includes EM simulations and ex-vivo measurements on fresh animal tissues using monolayer and multilayer configurations to simulate human neck anatomy. A three-dimensional carotid artery model is also introduced to extend the analysis to deeper tissue layers and simulate different degrees of stenosis between 25% and 75%.

Results

The sensor demonstrates a sensitivity of 0.72% and a detection resolution of 14 MHz for a dielectric constant range from 1 to 52 in material measurements, which has contributed to enhancing the EM penetration depth in neck tissues. Simulation results for atherosclerotic plaques in the carotid artery revealed a frequency shift difference induced by stable and vulnerable plaques of around 1 to 2 MHz.

Conclusion

These findings highlight the sensor's potential for future use in the in- vivo diagnosis of carotid artery atherosclerosis.

目的电磁（EM）波对生物组织的穿透深度有限是微波传感器在医学诊断中应用的一个重大挑战。本研究提出了一种基于互补裂环谐振器（CSRR）的传感器，用于无创检测颈动脉粥样硬化斑块，设计用于患者颈部。材料和方法该传感器采用加宽的馈线和优化的传感区域来集中电场并在生物组织内存储大量能量。验证包括EM模拟和新鲜动物组织的离体测量，使用单层和多层配置来模拟人体颈部解剖。还引入了三维颈动脉模型，将分析扩展到更深的组织层，并模拟25%至75%之间不同程度的狭窄。结果该传感器在介电常数1 ~ 52范围内的材料测量灵敏度为0.72%，检测分辨率为14 MHz，有助于提高颈部组织的电磁穿透深度。对颈动脉粥样硬化斑块的模拟结果显示，稳定斑块和易损斑块引起的频移差异约为1至2 MHz。结论该传感器在颈动脉粥样硬化的体内诊断中具有广阔的应用前景。

{"title":"Complementary Split-Ring Resonator for Non-Invasive Diagnosis of Carotid Artery Atherosclerosis: Towards Future in-Vivo Measurements","authors":"Joséphine Dupeyron Masini , Frédérique Deshours , Georges Alquie , Rania Shahbaz , Sylvain Feruglio , Olivier Meyer , Dimitri Galayko , Hamid Kokabi , Jean-Michel Davaine","doi":"10.1016/j.irbm.2025.100883","DOIUrl":"10.1016/j.irbm.2025.100883","url":null,"abstract":"<div><h3>Objectives</h3><div>The limited penetration depth of electromagnetic (EM) waves into biological tissues is a significant challenge for the use of microwave sensors in medical diagnostics. This study proposes a sensor based on a complementary split-ring resonator (CSRR) for the non-invasive detection of carotid atherosclerotic plaques, designed to be placed on the patient's neck.</div></div><div><h3>Material and methods</h3><div>The sensor employs a widened feed line and an optimized sensing area to concentrate the electric field and store a significant amount of energy within the biological tissue. Validation includes EM simulations and ex-vivo measurements on fresh animal tissues using monolayer and multilayer configurations to simulate human neck anatomy. A three-dimensional carotid artery model is also introduced to extend the analysis to deeper tissue layers and simulate different degrees of stenosis between 25% and 75%.</div></div><div><h3>Results</h3><div>The sensor demonstrates a sensitivity of 0.72% and a detection resolution of 14 MHz for a dielectric constant range from 1 to 52 in material measurements, which has contributed to enhancing the EM penetration depth in neck tissues. Simulation results for atherosclerotic plaques in the carotid artery revealed a frequency shift difference induced by stable and vulnerable plaques of around 1 to 2 MHz.</div></div><div><h3>Conclusion</h3><div>These findings highlight the sensor's potential for future use in the in- vivo diagnosis of carotid artery atherosclerosis.</div></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":"46 2","pages":"Article 100883"},"PeriodicalIF":5.6,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143480547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Comparison of Different Sensor Locations on Freezing-of-Gait Ratio Results 不同传感器位置对步态冻结率结果的比较

IF 5.6 4区医学 Q1 ENGINEERING, BIOMEDICAL

Irbm

Pub Date : 2025-02-14 DOI: 10.1016/j.irbm.2025.100881

Slavka Netukova , Lucie Horakova , Evžen Růžička , Petr Dusek , Zoltan Szabo , Radim Krupička

Background

Freezing of gait (FoG) is a walking disturbance in the Parkinson's disease (PD). The freezing ratio (FoG-ratio) is a parameter used to quantify overall freezing severity rather than to assess single freezing episodes. Originally the FoG-ratio was designed to be computed from lower limb acceleration. However, some available measurement systems get their data from a single sensor located elsewhere, e.g. on the lower back.

Purpose

The objective of our paper is to analyse whether acceleration signals measured on different body locations result in a consistent FoG-ratio.

Methods

Eighty-four people with PD and 65 people without neurological disorders completed an instrumented Timed Up&Go Test (iTUG) twice. The FoG-ratios from inertial units placed on the chest, lower back, left and right lower limbs were calculated.

Findings

There were significant differences between the tested FoG-ratios in the control group as well as in the PD group for both segments. Four significant, but not consistent, correlations were revealed for the turn segment in the PD group. Eight correlations were revealed in the control group. The inter-trial reliability of all the tested cases for gait was good (rho>0.75) but only in one case for turning.

Conclusion

In conclusion, the placement of sensors affected the FoG-ratio parameter output. The different FoG-ratios reflect different amounts of power in the locomotion band of body segments. This could result in inconclusive validity and incomparability of freezing severity presented in studies when the sensor is placed somewhere other than on the lower limbs.

步态冻结（FoG）是帕金森病（PD）的一种行走障碍。冻结率（FoG-ratio）是一个用于量化整体冻结严重程度的参数，而不是评估单个冻结事件。最初设计的fog比率是根据下肢加速度计算的。然而，一些可用的测量系统从位于其他地方的单个传感器获得数据，例如在背部下部。本文的目的是分析在不同身体位置测量的加速度信号是否会产生一致的加速度加速度比。方法84例PD患者和65例非神经系统疾病患者分别进行了2次仪器定时起跳测试（iTUG）。计算了放置在胸部、下背部、左下肢和右下肢的惯性单元的fog -ratio。结果：在对照组和PD组的两个节段测试的fogg比率之间存在显著差异。PD组的转弯节段有四个显著但不一致的相关性。对照组有8项相关。所有测试病例的步态试验间信度都很好（rho>0.75），但只有一个病例的转弯试验间信度良好。结论传感器的放置位置影响FoG-ratio参数输出。不同的fog -ratio反映了身体各节段运动带的不同功率量。当传感器放置在下肢以外的其他地方时，这可能导致研究中提出的冻结严重程度的不确定性有效性和不可比较性。

{"title":"Comparison of Different Sensor Locations on Freezing-of-Gait Ratio Results","authors":"Slavka Netukova , Lucie Horakova , Evžen Růžička , Petr Dusek , Zoltan Szabo , Radim Krupička","doi":"10.1016/j.irbm.2025.100881","DOIUrl":"10.1016/j.irbm.2025.100881","url":null,"abstract":"<div><h3>Background</h3><div>Freezing of gait (FoG) is a walking disturbance in the Parkinson's disease (PD). The freezing ratio (FoG-ratio) is a parameter used to quantify overall freezing severity rather than to assess single freezing episodes. Originally the FoG-ratio was designed to be computed from lower limb acceleration. However, some available measurement systems get their data from a single sensor located elsewhere, e.g. on the lower back.</div></div><div><h3>Purpose</h3><div>The objective of our paper is to analyse whether acceleration signals measured on different body locations result in a consistent FoG-ratio.</div></div><div><h3>Methods</h3><div>Eighty-four people with PD and 65 people without neurological disorders completed an instrumented Timed Up&Go Test (iTUG) twice. The FoG-ratios from inertial units placed on the chest, lower back, left and right lower limbs were calculated.</div></div><div><h3>Findings</h3><div>There were significant differences between the tested FoG-ratios in the control group as well as in the PD group for both segments. Four significant, but not consistent, correlations were revealed for the turn segment in the PD group. Eight correlations were revealed in the control group. The inter-trial reliability of all the tested cases for gait was good (rho>0.75) but only in one case for turning.</div></div><div><h3>Conclusion</h3><div>In conclusion, the placement of sensors affected the FoG-ratio parameter output. The different FoG-ratios reflect different amounts of power in the locomotion band of body segments. This could result in inconclusive validity and incomparability of freezing severity presented in studies when the sensor is placed somewhere other than on the lower limbs.</div></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":"46 2","pages":"Article 100881"},"PeriodicalIF":5.6,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430227","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

IMU Calibration Effect on Lower Limbs Kinematics Against Optical Motion Capture in Post-Stroke Gait IMU标定对脑卒中后步态光学运动捕捉下肢运动学的影响

IF 5.6 4区医学 Q1 ENGINEERING, BIOMEDICAL

Irbm

Pub Date : 2025-02-01 DOI: 10.1016/j.irbm.2024.100873

Ariane P. Lallès , Geoffroy Moucheboeuf , Emilie Doat , Hélène Pillet , Xavier Bonnet

Background

Stroke is the most common cause of disabilities worldwide. Rehabilitation is central to restore functions. Inertial measurement units (IMU) can be used to ease goal settings and monitor progression. Contrary to optical motion capture (OMC), IMU are less expensive, portable, and allow large scale data collections in ambulatory settings. Although Xsens MVN system validity has been demonstrated in healthy participants, its validity among post-stroke (PS) patients is yet to be proven.

Research question

Computation methods being affected by the calibration type; the goal of this study is to compare lower limbs kinematics from Xsens system, after two calibrations against OMC in slow PS walkers exhibiting reduced ranges of movements.

Methods

Data was collected for six PS patients. They were equipped with 29 reflective markers and seven IMU. A minimum of two walks with a dynamic calibration and four walks with a static calibration were performed. All trials were accomplished at a self-selected walking speed and PS used their usual walking aids.

Results

Few interactions between the calibration type and side were found for the ankle abduction/adduction (A/A) bias, root mean square error (RMSE), and range of motion difference (ROMd) (p = 0.011, p = 0.048, p = 0.039). Few effects of the side on errors' values were found. We noticed some effects of the calibration type on errors' values, the dynamic calibration showing better results. In the sagittal plane, we reported RMSE values from 3.6 to 4.8°, 5.2 to 6.5°, and 5.0 to 5.9° for the hip, knee, and ankle dynamic calibration.

Significance

The calibration type, reduced range of movement, and slow walking speed does not seem to impact Xsens' accuracy to a great extent. Nevertheless, dynamic calibration provides slightly better results. Considering the patient's walking ability, we recommend using this calibration.

中风是全世界最常见的致残原因。康复是恢复功能的核心。惯性测量单元（IMU）可以用来简化目标设定和监测进展。与光学运动捕捉（OMC）相反，IMU更便宜，便携，并且允许在流动环境中进行大规模数据收集。虽然Xsens MVN系统的有效性已在健康参与者中得到证实，但其在脑卒中后（PS）患者中的有效性尚未得到证实。研究问题：标定类型对计算方法的影响本研究的目的是比较来自Xsens系统的下肢运动学，经过两次与OMC校准后，缓慢的PS步行者表现出运动范围缩小。方法收集6例PS患者的资料。他们配备了29个反射标记和7个IMU。进行了至少两次动态校准行走和四次静态校准行走。所有的试验都是在自己选择的步行速度下完成的，PS使用他们常用的步行辅助工具。结果踝关节外展/内收（A/A）偏差、均方根误差（RMSE）和活动范围差（ROMd）与校准类型和侧面之间的交互作用较小（p = 0.011, p = 0.048, p = 0.039）。研究发现，侧面对误差值的影响很小。我们注意到标定类型对误差值的影响，动态标定效果更好。在矢状面，我们报告了髋关节、膝关节和踝关节动态校准的RMSE值为3.6至4.8°、5.2至6.5°和5.0至5.9°。校准类型、缩小的运动范围和缓慢的行走速度似乎并没有在很大程度上影响Xsens的准确性。然而，动态校准提供了稍微好一些的结果。考虑到患者的行走能力，我们建议使用此校准。

{"title":"IMU Calibration Effect on Lower Limbs Kinematics Against Optical Motion Capture in Post-Stroke Gait","authors":"Ariane P. Lallès , Geoffroy Moucheboeuf , Emilie Doat , Hélène Pillet , Xavier Bonnet","doi":"10.1016/j.irbm.2024.100873","DOIUrl":"10.1016/j.irbm.2024.100873","url":null,"abstract":"<div><h3>Background</h3><div>Stroke is the most common cause of disabilities worldwide. Rehabilitation is central to restore functions. Inertial measurement units (IMU) can be used to ease goal settings and monitor progression. Contrary to optical motion capture (OMC), IMU are less expensive, portable, and allow large scale data collections in ambulatory settings. Although Xsens MVN system validity has been demonstrated in healthy participants, its validity among post-stroke (PS) patients is yet to be proven.</div></div><div><h3>Research question</h3><div>Computation methods being affected by the calibration type; the goal of this study is to compare lower limbs kinematics from Xsens system, after two calibrations against OMC in slow PS walkers exhibiting reduced ranges of movements.</div></div><div><h3>Methods</h3><div>Data was collected for six PS patients. They were equipped with 29 reflective markers and seven IMU. A minimum of two walks with a dynamic calibration and four walks with a static calibration were performed. All trials were accomplished at a self-selected walking speed and PS used their usual walking aids.</div></div><div><h3>Results</h3><div>Few interactions between the calibration type and side were found for the ankle abduction/adduction (A/A) bias, root mean square error (RMSE), and range of motion difference (ROMd) (p = 0.011, p = 0.048, p = 0.039). Few effects of the side on errors' values were found. We noticed some effects of the calibration type on errors' values, the dynamic calibration showing better results. In the sagittal plane, we reported RMSE values from 3.6 to 4.8°, 5.2 to 6.5°, and 5.0 to 5.9° for the hip, knee, and ankle dynamic calibration.</div></div><div><h3>Significance</h3><div>The calibration type, reduced range of movement, and slow walking speed does not seem to impact Xsens' accuracy to a great extent. Nevertheless, dynamic calibration provides slightly better results. Considering the patient's walking ability, we recommend using this calibration.</div></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":"46 1","pages":"Article 100873"},"PeriodicalIF":5.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143146009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Acknowledging our reviewers 感谢我们的审稿人

IF 5.6 4区医学 Q1 ENGINEERING, BIOMEDICAL

Irbm

Pub Date : 2025-02-01 DOI: 10.1016/S1959-0318(25)00003-X

引用次数: 0

Leveraging Action Unit Derivatives for Early-Stage Parkinson's Disease Detection 利用行动单元衍生工具检测早期帕金森病

IF 5.6 4区医学 Q1 ENGINEERING, BIOMEDICAL

Irbm

Pub Date : 2025-02-01 DOI: 10.1016/j.irbm.2024.100874

Anas Filali Razzouki , Laetitia Jeancolas , Graziella Mangone , Sara Sambin , Alizé Chalançon , Manon Gomes , Stéphane Lehéricy , Jean-Christophe Corvol , Marie Vidailhet , Isabelle Arnulf , Dijana Petrovska-Delacrétaz , Mounim A. El-Yacoubi

Objective

Hypomimia is a symptom of Parkinson's disease (PD), involving a decrease in facial movements and a loss of emotional expressions on the face. The objective of this study is to identify hypomimia in individuals in the early stage of PD by analyzing facial action units (AUs).

Methods

Our study included video recordings from 109 PD subjects and 45 healthy control (HC) subjects with an average of two videos per person (294 videos in total). The participants were requested to perform rapid syllable repetitions. For the purpose of discriminating between normal facial muscle movements and those specific to PD subjects experiencing hypomimia, we calculate the derivatives of the AUs. We derive global features based on the AUs intensities and their derivatives, and utilize XGBoost and Random Forest to perform the classification between PD and HC.

Results

We achieve subject-level classification scores of up to 73.7% for balanced accuracy (BA) and an area under the curve (AUC) of 81.39% using XGBoost, and a BA of 79.1% and an AUC of 83.7% with Random Forest. These findings show potential in identifying hypomimia during the early phases of PD. Moreover, this research could facilitate the continuous monitoring of hypomimia beyond hospital settings, enabled by telemedicine.

目的低贫血症是帕金森病（PD）的一种症状，包括面部运动减少和面部情绪表达的丧失。本研究的目的是通过分析面部动作单位（AUs）来识别早期PD患者的低贫血症。方法选取109名PD患者和45名健康对照（HC）患者的录像资料，平均每人2段，共294段。参与者被要求快速重复音节。为了区分正常的面部肌肉运动和那些特定的PD受试者经历低贫血症，我们计算了AUs的导数。我们基于AUs强度及其导数推导出全局特征，并利用XGBoost和Random Forest对PD和HC进行分类。结果使用XGBoost获得的学科水平分类分数的平衡精度（BA）和曲线下面积（AUC）分别为73.7%和81.39%，使用Random Forest获得的BA和AUC分别为79.1%和83.7%。这些发现显示了在PD早期阶段识别低血氧症的潜力。此外，通过远程医疗，这项研究可以促进在医院之外对低贫血症的持续监测。

{"title":"Leveraging Action Unit Derivatives for Early-Stage Parkinson's Disease Detection","authors":"Anas Filali Razzouki , Laetitia Jeancolas , Graziella Mangone , Sara Sambin , Alizé Chalançon , Manon Gomes , Stéphane Lehéricy , Jean-Christophe Corvol , Marie Vidailhet , Isabelle Arnulf , Dijana Petrovska-Delacrétaz , Mounim A. El-Yacoubi","doi":"10.1016/j.irbm.2024.100874","DOIUrl":"10.1016/j.irbm.2024.100874","url":null,"abstract":"<div><h3>Objective</h3><div>Hypomimia is a symptom of Parkinson's disease (PD), involving a decrease in facial movements and a loss of emotional expressions on the face. The objective of this study is to identify hypomimia in individuals in the early stage of PD by analyzing facial action units (AUs).</div></div><div><h3>Methods</h3><div>Our study included video recordings from 109 PD subjects and 45 healthy control (HC) subjects with an average of two videos per person (294 videos in total). The participants were requested to perform rapid syllable repetitions. For the purpose of discriminating between normal facial muscle movements and those specific to PD subjects experiencing hypomimia, we calculate the derivatives of the AUs. We derive global features based on the AUs intensities and their derivatives, and utilize XGBoost and Random Forest to perform the classification between PD and HC.</div></div><div><h3>Results</h3><div>We achieve subject-level classification scores of up to 73.7% for balanced accuracy (BA) and an area under the curve (AUC) of 81.39% using XGBoost, and a BA of 79.1% and an AUC of 83.7% with Random Forest. These findings show potential in identifying hypomimia during the early phases of PD. Moreover, this research could facilitate the continuous monitoring of hypomimia beyond hospital settings, enabled by telemedicine.</div></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":"46 1","pages":"Article 100874"},"PeriodicalIF":5.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143146011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluation of the Performance of Blueback Physio® Medical Device in the Management of Patients Suffering from Chronic Low Back Pain: Randomized Clinical Trial Blueback Physio®医疗器械治疗慢性腰痛的疗效评价：随机临床试验

IF 5.6 4区医学 Q1 ENGINEERING, BIOMEDICAL

Irbm

Pub Date : 2025-02-01 DOI: 10.1016/j.irbm.2024.100875

Ines Moudjari , Caroline Pautard , Clément Jouanneau , Anne-gaëlle Servel , Philippe Le Cavorzin , Benjamin Margo , Ophélie Flageul , Gwenvael Le Guicher , Régine Le Bouquin Jeannès

Background

Chronic low back pain (CLBP) is one of the leading causes of disability in the world population. In 2017, in central Europe and North America, prevalence of CLBP was 12.51% and 9.80% respectively. The rehabilitation of the abdominal muscles, and notably the deep transversus abdominis, plays an important role in the management of CLBP in physiotherapy.

Objectives

The main objective of this study is to prove that a biofeedback device of the transversus abdominis, named Blueback Physio

^{®}

, developed by the Blueback company, improves the management of patients suffering from this pain.

Design

The clinical trial is designed as a prospective, monocentric, comparative, open-label randomized and parallel group study.

Method

41 subjects were included in this study and divided into two groups, one control group, in which the subjects used the device without visual biofeedback, and one intervention group, where the subjects used the complete biofeedback. The study included patients cared in day or full hospitalization in FSEF Rennes-Beaulieu Clinic, France, as part of the PRESDO program (“programme de prévention secondaire des dorso-lombalgies”).

Results

We found that patients who use visual biofeedback of the transverse abdominis muscle are more likely to (i) quickly learn to voluntarily contract this muscle and (ii) have better control of this muscle compared to patients who do not use it. Finally, the PRESDO program improves overall patient well-being.

背景：慢性腰痛（CLBP）是世界人口致残的主要原因之一。2017年，中欧和北美CLBP患病率分别为12.51%和9.80%。在物理治疗中，腹肌，尤其是腹深横肌的康复在CLBP的治疗中起着重要的作用。本研究的主要目的是证明由Blueback公司开发的一种名为Blueback Physio®的横腹生物反馈装置可以改善患有这种疼痛的患者的管理。临床试验设计为前瞻性、单中心、比较、开放标签、随机、平行组研究。方法将41名受试者分为两组，对照组使用无视觉生物反馈装置，干预组使用完全生物反馈装置。该研究包括在法国FSEF Rennes-Beaulieu诊所接受日间或全面住院治疗的患者，作为PRESDO方案的一部分（“后腰痛预防方案”）。结果我们发现，使用腹横肌视觉生物反馈的患者更有可能(i)快速学会自愿收缩该肌肉，（ii）与不使用该肌肉的患者相比，对该肌肉有更好的控制。最后，PRESDO项目改善了患者的整体健康状况。

{"title":"Evaluation of the Performance of Blueback Physio® Medical Device in the Management of Patients Suffering from Chronic Low Back Pain: Randomized Clinical Trial","authors":"Ines Moudjari , Caroline Pautard , Clément Jouanneau , Anne-gaëlle Servel , Philippe Le Cavorzin , Benjamin Margo , Ophélie Flageul , Gwenvael Le Guicher , Régine Le Bouquin Jeannès","doi":"10.1016/j.irbm.2024.100875","DOIUrl":"10.1016/j.irbm.2024.100875","url":null,"abstract":"<div><h3>Background</h3><div>Chronic low back pain (CLBP) is one of the leading causes of disability in the world population. In 2017, in central Europe and North America, prevalence of CLBP was 12.51% and 9.80% respectively. The rehabilitation of the abdominal muscles, and notably the deep transversus abdominis, plays an important role in the management of CLBP in physiotherapy.</div></div><div><h3>Objectives</h3><div>The main objective of this study is to prove that a biofeedback device of the transversus abdominis, named Blueback Physio<span><math><msup><mrow></mrow><mrow><mi>®</mi></mrow></msup></math></span>, developed by the Blueback company, improves the management of patients suffering from this pain.</div></div><div><h3>Design</h3><div>The clinical trial is designed as a prospective, monocentric, comparative, open-label randomized and parallel group study.</div></div><div><h3>Method</h3><div>41 subjects were included in this study and divided into two groups, one control group, in which the subjects used the device without visual biofeedback, and one intervention group, where the subjects used the complete biofeedback. The study included patients cared in day or full hospitalization in FSEF Rennes-Beaulieu Clinic, France, as part of the PRESDO program (“programme de prévention secondaire des dorso-lombalgies”).</div></div><div><h3>Results</h3><div>We found that patients who use visual biofeedback of the transverse abdominis muscle are more likely to (i) quickly learn to voluntarily contract this muscle and (ii) have better control of this muscle compared to patients who do not use it. Finally, the PRESDO program improves overall patient well-being.</div></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":"46 1","pages":"Article 100875"},"PeriodicalIF":5.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143146012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The R-Vessel-X Project R-Vessel-X项目

IF 5.6 4区医学 Q1 ENGINEERING, BIOMEDICAL

Irbm

Pub Date : 2025-02-01 DOI: 10.1016/j.irbm.2025.100876

Abir Affane , Mohamed A. Chetoui , Jonas Lamy , Guillaume Lienemann , Raphaël Peron , Pierre Beaurepaire , Guillaume Dollé , Marie-Ange Lebre , Benoît Magnin , Odyssée Merveille , Mathilde Morvan , Phuc Ngo , Thibault Pelletier , Hugo Rositi , Stéphanie Salmon , Julien Finet , Bertrand Kerautret , Nicolas Passat , Antoine Vacavant

1) Objectives: This technical report presents a synthetic summary and the principal outcomes of the project R-Vessel-X (“Robust vascular network extraction and understanding within hepatic biomedical images”) funded by the French Agence Nationale de la Recherche, and developed between 2019 and 2023. 2) Material and methods: We used datasets and tools publicly available such as IRCAD, Bullitt or VascuSynth to obtain real or synthetic angiographic images. The main contributions lie in the field of 3D angiographic image analysis: filtering, segmentation, modeling and simulation, with a specific focus on the liver. 3) Results: We paid a particular attention to open-source software diffusion of the developed methods, by means of 3D Slicer plugins for the liver anatomy segmentation (SlicerRVXLiverSegmentation) and vesselness filtering (SlicerRVXVesselnessFilters), and an online demo for the generation of synthetic and realistic vessels in 2D and 3D (OpenCCO). 4) Conclusion: The R-Vessel-X project provided extensive research outcomes, covering various topics related to 3D angiographic image analysis, such as filtering, segmentation, modeling and simulation. We also developed open-source and free softwares so that the research communities in biomedical engineering can use these results in their future research.

1)目的：本技术报告介绍了R-Vessel-X项目（“肝脏生物医学图像中的稳健血管网络提取和理解”）的综合总结和主要成果，该项目由法国国家研究机构资助，在2019年至2023年之间开发。2)材料和方法：我们使用公开的数据集和工具，如IRCAD， Bullitt或VascuSynth来获得真实或合成的血管造影图像。主要贡献在于三维血管造影图像分析领域：滤波，分割，建模和仿真，特别关注肝脏。3)结果：我们特别关注所开发方法的开源软件传播，通过肝脏解剖分割（SlicerRVXLiverSegmentation）和血管滤波（SlicerRVXVesselnessFilters）的3D切片器插件，以及生成二维和三维合成和逼真血管的在线演示（OpenCCO）。4)结论：R-Vessel-X项目提供了广泛的研究成果，涵盖了与3D血管造影图像分析相关的各种主题，如滤波、分割、建模和仿真。我们还开发了开源和免费软件，以便生物医学工程的研究团体可以在他们未来的研究中使用这些结果。

{"title":"The R-Vessel-X Project","authors":"Abir Affane , Mohamed A. Chetoui , Jonas Lamy , Guillaume Lienemann , Raphaël Peron , Pierre Beaurepaire , Guillaume Dollé , Marie-Ange Lebre , Benoît Magnin , Odyssée Merveille , Mathilde Morvan , Phuc Ngo , Thibault Pelletier , Hugo Rositi , Stéphanie Salmon , Julien Finet , Bertrand Kerautret , Nicolas Passat , Antoine Vacavant","doi":"10.1016/j.irbm.2025.100876","DOIUrl":"10.1016/j.irbm.2025.100876","url":null,"abstract":"<div><div><strong>1) Objectives:</strong> This technical report presents a synthetic summary and the principal outcomes of the project R-Vessel-X (“Robust vascular network extraction and understanding within hepatic biomedical images”) funded by the French <em>Agence Nationale de la Recherche</em>, and developed between 2019 and 2023. <strong>2) Material and methods:</strong> We used datasets and tools publicly available such as IRCAD, Bullitt or VascuSynth to obtain real or synthetic angiographic images. The main contributions lie in the field of 3D angiographic image analysis: filtering, segmentation, modeling and simulation, with a specific focus on the liver. <strong>3) Results:</strong> We paid a particular attention to open-source software diffusion of the developed methods, by means of 3D Slicer plugins for the liver anatomy segmentation (SlicerRVXLiverSegmentation) and vesselness filtering (SlicerRVXVesselnessFilters), and an online demo for the generation of synthetic and realistic vessels in 2D and 3D (OpenCCO). <strong>4) Conclusion:</strong> The R-Vessel-X project provided extensive research outcomes, covering various topics related to 3D angiographic image analysis, such as filtering, segmentation, modeling and simulation. We also developed open-source and free softwares so that the research communities in biomedical engineering can use these results in their future research.</div></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":"46 1","pages":"Article 100876"},"PeriodicalIF":5.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143146010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Biomechanical Effects of Osteoporosis on the Sacroiliac Joint After Lumbosacral Fusion Surgery 腰骶融合术后骨质疏松对骶髂关节的生物力学影响

IF 5.6 4区医学 Q1 ENGINEERING, BIOMEDICAL

Irbm

Pub Date : 2025-01-30 DOI: 10.1016/j.irbm.2025.100877

Wei Fan , Chao Wang , Sheng-Nan Liu , Yu Zhang , Ming Zhang , Li-Xin Guo

Objective

Lumbar/lumbosacral fusion is a common surgical approach for treating lumbar degenerative disc disease, a condition that disproportionately affects a large portion of elderly population. Osteoporosis, another age-related disease, is also prevalent among the elderly. Previous studies have elucidated the biomechanical effects of osteoporosis on the postoperative lumbar spine. However, little attention has been paid to adjacent sacroiliac joints (SIJs), and it remains unclear whether or how osteoporosis impacts the SIJ biomechanics. The aim of this study was to determine the effects of osteoporosis on the range of motion (ROM) and stress distribution within the SIJs following lumbosacral fusion, and to identify potential implications for postoperative outcomes.

Methods

The previously validated, normal human lumbo-pelvic finite-element model was used to simulate the interbody fusion procedures at L5–S1, and an osteoporotic condition was simulated by reducing bone mechanical properties in the model. The ROM and stress distribution within the left and right SIJs were compared between the surgical models with and without osteoporosis in flexion, extension, lateral bending, and axial rotation motions.

Results

The presence of osteoporosis led to a significant increase in SIJ ROM: 38.9% and 36.5% in flexion, 19.5% and 15.9% in extension, 33.3% and 40.0% in lateral bending, and 26.38% and 20.0% in axial rotation, respectively, for left and right SIJs. Moreover, higher stress concentrations were observed at the SIJs in the osteoporotic model.

Conclusion

Osteoporosis exacerbates the SIJ motion and stress after lumbosacral fusion, indicating a potential increased risk of SIJ instability and degeneration among affected patients. The findings underscore the importance of considering osteoporosis in preoperative planning and postoperative management strategies for lumbosacral fusion procedures.

目的腰椎/腰骶融合术是治疗腰椎间盘退行性疾病的常用手术方法，这种疾病在很大一部分老年人中发病率很高。骨质疏松症，另一种与年龄有关的疾病，在老年人中也很普遍。先前的研究已经阐明了骨质疏松症对术后腰椎的生物力学影响。然而，对邻近骶髂关节（SIJ）的关注很少，骨质疏松症是否或如何影响SIJ的生物力学尚不清楚。本研究的目的是确定骨质疏松症对腰骶融合术后sij内活动范围（ROM）和应力分布的影响，并确定对术后结果的潜在影响。方法采用先前验证的正常人腰骨盆有限元模型模拟L5-S1椎间融合过程，并通过降低模型中的骨力学性能来模拟骨质疏松状况。比较有骨质疏松和无骨质疏松的手术模型在屈伸、侧屈和轴向旋转运动中左、右sij内的ROM和应力分布。结果骨质疏松的存在导致左、右SIJ的ROM明显增加：屈曲38.9%、36.5%，伸展19.5%、15.9%，侧弯33.3%、40.0%，轴向旋转26.38%、20.0%。此外，在骨质疏松模型中，sij处观察到较高的应力浓度。结论骨质疏松加剧了腰骶融合术后SIJ的运动和应激，提示患者SIJ不稳定和退变的风险增加。研究结果强调了在腰骶融合手术的术前计划和术后管理策略中考虑骨质疏松症的重要性。

{"title":"Biomechanical Effects of Osteoporosis on the Sacroiliac Joint After Lumbosacral Fusion Surgery","authors":"Wei Fan , Chao Wang , Sheng-Nan Liu , Yu Zhang , Ming Zhang , Li-Xin Guo","doi":"10.1016/j.irbm.2025.100877","DOIUrl":"10.1016/j.irbm.2025.100877","url":null,"abstract":"<div><h3>Objective</h3><div>Lumbar/lumbosacral fusion is a common surgical approach for treating lumbar degenerative disc disease, a condition that disproportionately affects a large portion of elderly population. Osteoporosis, another age-related disease, is also prevalent among the elderly. Previous studies have elucidated the biomechanical effects of osteoporosis on the postoperative lumbar spine. However, little attention has been paid to adjacent sacroiliac joints (SIJs), and it remains unclear whether or how osteoporosis impacts the SIJ biomechanics. The aim of this study was to determine the effects of osteoporosis on the range of motion (ROM) and stress distribution within the SIJs following lumbosacral fusion, and to identify potential implications for postoperative outcomes.</div></div><div><h3>Methods</h3><div>The previously validated, normal human lumbo-pelvic finite-element model was used to simulate the interbody fusion procedures at L5–S1, and an osteoporotic condition was simulated by reducing bone mechanical properties in the model. The ROM and stress distribution within the left and right SIJs were compared between the surgical models with and without osteoporosis in flexion, extension, lateral bending, and axial rotation motions.</div></div><div><h3>Results</h3><div>The presence of osteoporosis led to a significant increase in SIJ ROM: 38.9% and 36.5% in flexion, 19.5% and 15.9% in extension, 33.3% and 40.0% in lateral bending, and 26.38% and 20.0% in axial rotation, respectively, for left and right SIJs. Moreover, higher stress concentrations were observed at the SIJs in the osteoporotic model.</div></div><div><h3>Conclusion</h3><div>Osteoporosis exacerbates the SIJ motion and stress after lumbosacral fusion, indicating a potential increased risk of SIJ instability and degeneration among affected patients. The findings underscore the importance of considering osteoporosis in preoperative planning and postoperative management strategies for lumbosacral fusion procedures.</div></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":"46 2","pages":"Article 100877"},"PeriodicalIF":5.6,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143133000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

IF 4.2 4区医学 Q1 ENGINEERING, BIOMEDICAL

Irbm

Pub Date : 2025-01-01

引用次数: 0