Medical & Biological Engineering & Computing最新文献_第8页

Ablation catheter-induced mechanical deformation in myocardium: computer modeling and ex vivo experiments. 消融导管诱发的心肌机械变形：计算机建模和体内外实验。

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2024-11-01 Epub Date: 2024-06-01 DOI: 10.1007/s11517-024-03135-7

Yukako Ijima, Kriengsak Masnok, Juan J Perez, Ana González-Suárez, Enrique Berjano, Nobuo Watanabe

{"title":"Ablation catheter-induced mechanical deformation in myocardium: computer modeling and ex vivo experiments.","authors":"Yukako Ijima, Kriengsak Masnok, Juan J Perez, Ana González-Suárez, Enrique Berjano, Nobuo Watanabe","doi":"10.1007/s11517-024-03135-7","DOIUrl":"10.1007/s11517-024-03135-7","url":null,"abstract":"Cardiac catheter ablation requires an adequate contact between myocardium and catheter tip. Our aim was to quantify the relationship between the contact force (CF) and the resulting mechanical deformation induced by the catheter tip using an ex vivo model and computational modeling. The catheter tip was inserted perpendicularly into porcine heart samples. CF values ranged from 10 to 80 g. The computer model was built to simulate the same experimental conditions, and it considered a 3-parameter Mooney-Rivlin model based on hyper-elastic material. We found a strong correlation between the CF and insertion depth (ID) (R2 = 0.96, P < 0.001), from 0.7 ± 0.3 mm at 10 g to 6.9 ± 0.1 mm at 80 g. Since the surface deformation was asymmetrical, two transversal diameters (minor and major) were identified. Both diameters were strongly correlated with CF (R2 ≥ 0.95), from 4.0 ± 0.4 mm at 20 g to 10.3 ± 0.0 mm at 80 g (minor), and from 6.4 ± 0.7 mm at 20 g to 16.7 ± 0.1 mm at 80 g (major). An optimal fit between computer and experimental results was achieved, with a prediction error of 0.74 and 0.86 mm for insertion depth and mean surface diameter, respectively.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"3283-3292"},"PeriodicalIF":2.6,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11485114/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141186994","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

Machine learning models' assessment: trust and performance. 机器学习模型评估：信任与性能。

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2024-11-01 Epub Date: 2024-06-08 DOI: 10.1007/s11517-024-03145-5

S Sousa, S Paredes, T Rocha, J Henriques, J Sousa, L Gonçalves

{"title":"Machine learning models' assessment: trust and performance.","authors":"S Sousa, S Paredes, T Rocha, J Henriques, J Sousa, L Gonçalves","doi":"10.1007/s11517-024-03145-5","DOIUrl":"10.1007/s11517-024-03145-5","url":null,"abstract":"The common black box nature of machine learning models is an obstacle to their application in health care context. Their widespread application is limited by a significant \"lack of trust.\" So, the main goal of this work is the development of an evaluation approach that can assess, simultaneously, trust and performance. Trust assessment is based on (i) model robustness (stability assessment), (ii) confidence (95% CI of geometric mean), and (iii) interpretability (comparison of respective features ranking with clinical evidence). Performance is assessed through geometric mean. For validation, in patients' stratification in cardiovascular risk assessment, a Portuguese dataset (N=1544) was applied. Five different models were compared: (i) GRACE score, the most common risk assessment tool in Portugal for patients with acute coronary syndrome; (ii) logistic regression; (iii) Naïve Bayes; (iv) decision trees; and (v) rule-based approach, previously developed by this team. The obtained results confirm that the simultaneous assessment of trust and performance can be successfully implemented. The rule-based approach seems to have potential for clinical application. It provides a high level of trust in the respective operation while outperformed the GRACE model's performance, enhancing the required physicians' acceptance. This may increase the possibility to effectively aid the clinical decision.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"3397-3410"},"PeriodicalIF":2.6,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11485107/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141288826","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

Influence of framing coil orientation and its shape on the hemodynamics of a basilar aneurysm model. 框架线圈方向及其形状对基底动脉瘤模型血液动力学的影响。

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2024-11-01 Epub Date: 2024-06-10 DOI: 10.1007/s11517-024-03146-4

Nisanth Kumar Panneerselvam, B J Sudhir, Santhosh K Kannath, B S V Patnaik

{"title":"Influence of framing coil orientation and its shape on the hemodynamics of a basilar aneurysm model.","authors":"Nisanth Kumar Panneerselvam, B J Sudhir, Santhosh K Kannath, B S V Patnaik","doi":"10.1007/s11517-024-03146-4","DOIUrl":"10.1007/s11517-024-03146-4","url":null,"abstract":"Aneurysms are bulges of an artery, which require clinical management solutions. Due to the inherent advantages, endovascular coil filling is emerging as the treatment of choice for intracranial aneurysms (IAs). However, after successful treatment of coil embolization, there is a serious risk of recurrence. It is well known that optimal packing density will enhance treatment outcomes. The main objective of endovascular coil embolization is to achieve flow stasis by enabling significant reduction in intra-aneurysmal flow and facilitate thrombus formation. The present study numerically investigates the effect of framing coil orientation on intra-aneurysmal hemodynamics. For the purpose of analysis, actual shape of the embolic coil is used, instead of simplified ideal coil shape. Typically used details of the framing coil are resolved for the analysis. However, region above the framing coil is assumed to be filled with a porous medium. Present simulations have shown that orientation of the framing coil loop (FCL) greatly influences the intra-aneurysmal hemodynamics. The FCLs which were placed parallel to the outlets of basilar tip aneurysm (Coil A) were found to reduce intra-aneurysmal flow velocity that facilitates thrombus formation. Involving the coil for the region is modeled using a porous medium model with a packing density of 20 <math><mo>%</mo></math> . The simulations indicate that the framing coil loop (FCL) has a significant influence on the overall outcome.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"3411-3432"},"PeriodicalIF":2.6,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141297183","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

Multi-modality multi-label ocular abnormalities detection with transformer-based semantic dictionary learning. 利用基于变换器的语义词典学习进行多模态多标签眼部异常检测。

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2024-11-01 Epub Date: 2024-06-11 DOI: 10.1007/s11517-024-03140-w

Anneke Annassia Putri Siswadi, Stéphanie Bricq, Fabrice Meriaudeau

{"title":"Multi-modality multi-label ocular abnormalities detection with transformer-based semantic dictionary learning.","authors":"Anneke Annassia Putri Siswadi, Stéphanie Bricq, Fabrice Meriaudeau","doi":"10.1007/s11517-024-03140-w","DOIUrl":"10.1007/s11517-024-03140-w","url":null,"abstract":"Blindness is preventable by early detection of ocular abnormalities. Computer-aided diagnosis for ocular abnormalities is built by analyzing retinal imaging modalities, for instance, Color Fundus Photography (CFP). This research aims to propose a multi-label detection of 28 ocular abnormalities consisting of frequent and rare abnormalities from a single CFP by using transformer-based semantic dictionary learning. Rare labels are usually ignored because of a lack of features. We tackle this condition by adding the co-occurrence dependency factor to the model from the linguistic features of the labels. The model learns the relation between spatial features and linguistic features represented as a semantic dictionary. The proposed method treats the semantic dictionary as one of the main important parts of the model. It acts as the query while the spatial features are the key and value. The experiments are conducted on the RFMiD dataset. The results show that the proposed method achieves the top 30% in Evaluation Set on the RFMiD dataset challenge. It also shows that treating the semantic dictionary as one of the strong factors in model detection increases the performance when compared with the method that treats the semantic dictionary as a weak factor.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"3433-3444"},"PeriodicalIF":2.6,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141301927","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

Session-independent subject-adaptive mental imagery BCI using selective filter-bank adaptive Riemannian features. 利用选择性滤波器库自适应黎曼特征，实现与会话无关的主体自适应心理意象 BCI。

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2024-11-01 Epub Date: 2024-06-03 DOI: 10.1007/s11517-024-03137-5

Jayasandhya Meenakshinathan, Vinay Gupta, Tharun Kumar Reddy, Laxmidhar Behera, Tushar Sandhan

{"title":"Session-independent subject-adaptive mental imagery BCI using selective filter-bank adaptive Riemannian features.","authors":"Jayasandhya Meenakshinathan, Vinay Gupta, Tharun Kumar Reddy, Laxmidhar Behera, Tushar Sandhan","doi":"10.1007/s11517-024-03137-5","DOIUrl":"10.1007/s11517-024-03137-5","url":null,"abstract":"The brain-computer interfaces (BCIs) facilitate the users to exploit information encoded in neural signals, specifically electroencephalogram (EEG), to control devices and for neural rehabilitation. Mental imagery (MI)-driven BCI predicts the user's pre-meditated mental objectives, which could be deployed as command signals. This paper presents a novel learning-based framework for classifying MI tasks using EEG-based BCI. In particular, our work focuses on the variation in inter-session data and the extraction of multi-spectral user-tailored features for robust performance. Thus, the goal is to create a calibration-free subject-adaptive learning framework for various mental imagery tasks not restricted to motor imagery alone. In this regard, critical spectral bands and the best temporal window are first selected from the EEG training trials of the subject based on the Riemannian user learning distance metric (Dscore) that checks for distinct and stable patterns. The filtered covariance matrices of the EEG trials in each spectral band are then transformed towards a reference covariance matrix using the Riemannian transfer learning, enabling the different sessions to be comparable. The evaluation of our proposed Selective Time-window and Multi-scale Filter-Bank with Adaptive Riemannian (STFB-AR) features on four public datasets, including disabled subjects, showed around 15% and 8% improvement in mean accuracy over baseline and fixed filter-bank models, respectively.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"3293-3310"},"PeriodicalIF":2.6,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141201048","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

Intelligent alert system for predicting invasive mechanical ventilation needs via noninvasive parameters: employing an integrated machine learning method with integration of multicenter databases. 通过非侵入性参数预测侵入性机械通气需求的智能警报系统：采用综合机器学习方法，整合多中心数据库。

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2024-11-01 Epub Date: 2024-06-11 DOI: 10.1007/s11517-024-03143-7

Guang Zhang, Qingyan Xie, Chengyi Wang, Jiameng Xu, Guanjun Liu, Chen Su

{"title":"Intelligent alert system for predicting invasive mechanical ventilation needs via noninvasive parameters: employing an integrated machine learning method with integration of multicenter databases.","authors":"Guang Zhang, Qingyan Xie, Chengyi Wang, Jiameng Xu, Guanjun Liu, Chen Su","doi":"10.1007/s11517-024-03143-7","DOIUrl":"10.1007/s11517-024-03143-7","url":null,"abstract":"The use of invasive mechanical ventilation (IMV) is crucial in rescuing patients with respiratory dysfunction. Accurately predicting the demand for IMV is vital for clinical decision-making. However, current techniques are invasive and challenging to implement in pre-hospital and emergency rescue settings. To address this issue, a real-time prediction method utilizing only non-invasive parameters was developed to forecast IMV demand in this study. The model introduced the concept of real-time warning and leveraged the advantages of machine learning and integrated methods, achieving an AUC value of 0.935 (95% CI 0.933-0.937). The AUC value for the multi-center validation using the AmsterdamUMCdb database was 0.727, surpassing the performance of traditional risk adjustment algorithms (OSI(oxygenation saturation index): 0.608, P/F(oxygenation index): 0.558). Feature weight analysis demonstrated that BMI, Gcsverbal, and age significantly contributed to the model's decision-making. These findings highlight the substantial potential of a machine learning real-time dynamic warning model that solely relies on non-invasive parameters to predict IMV demand. Such a model can provide technical support for predicting the need for IMV in pre-hospital and disaster scenarios.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"3445-3458"},"PeriodicalIF":2.6,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141301926","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

Classification of Parkinson's disease severity using gait stance signals in a spatiotemporal deep learning classifier. 利用时空深度学习分类器中的步态信号对帕金森病的严重程度进行分类。

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2024-11-01 Epub Date: 2024-06-17 DOI: 10.1007/s11517-024-03148-2

Brenda G Muñoz-Mata, Guadalupe Dorantes-Méndez, Omar Piña-Ramírez

{"title":"Classification of Parkinson's disease severity using gait stance signals in a spatiotemporal deep learning classifier.","authors":"Brenda G Muñoz-Mata, Guadalupe Dorantes-Méndez, Omar Piña-Ramírez","doi":"10.1007/s11517-024-03148-2","DOIUrl":"10.1007/s11517-024-03148-2","url":null,"abstract":"Parkinson's disease (PD) is a degenerative nervous system disorder involving motor disturbances. Motor alterations affect the gait according to the progression of PD and can be used by experts in movement disorders to rate the severity of the disease. However, this rating depends on the expertise of the clinical specialist. Therefore, the diagnosis may be inaccurate, particularly in the early stages of PD where abnormal gait patterns can result from normal aging or other medical conditions. Consequently, several classification systems have been developed to enhance PD diagnosis. In this paper, a PD gait severity classification algorithm was developed using vertical ground reaction force (VGRF) signals. The VGRF records used are from a public database that includes 93 PD patients and 72 healthy controls adults. The work presented here focuses on modeling each foot's gait stance phase signals using a modified convolutional long deep neural network (CLDNN) architecture. Subsequently, the results of each model are combined to predict PD severity. The classifier performance was evaluated using ten-fold cross-validation. The best-weighted accuracies obtained were 99.296(0.128)% and 99.343(0.182)%, with the Hoehn-Yahr and UPDRS scales, respectively, outperforming previous results presented in the literature. The classifier proposed here can effectively differentiate gait patterns of different PD severity levels based on gait signals of the stance phase.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"3493-3506"},"PeriodicalIF":2.6,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141332364","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

Deformable dose prediction network based on hybrid 2D and 3D convolution for nasopharyngeal carcinoma radiotherapy. 基于混合二维和三维卷积的可变形剂量预测网络用于鼻咽癌放射治疗

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2024-10-30 DOI: 10.1007/s11517-024-03231-8

Yanhua Liu, Wang Luo, Xiangchen Li, Min Liu

{"title":"Deformable dose prediction network based on hybrid 2D and 3D convolution for nasopharyngeal carcinoma radiotherapy.","authors":"Yanhua Liu, Wang Luo, Xiangchen Li, Min Liu","doi":"10.1007/s11517-024-03231-8","DOIUrl":"https://doi.org/10.1007/s11517-024-03231-8","url":null,"abstract":"Radiotherapy is recognized as the primary treatment for nasopharyngeal carcinoma (NPC). Rapid and accurate dose prediction is crucial for enhancing the quality and efficiency of radiotherapy planning. However, the current dose prediction model based on 2D architecture cannot effectively learn the spatial information among slices. Although some studies have explored the incorporation of interslice features through 3D architecture, the resolution properties of medical image anisotropy significantly limit the predictive performance. To address the issues, we propose a novel deformable dose prediction network based on hybrid 2D and 3D convolution for NPC radiotherapy. Specifically, the proposed model innovatively incorporates a 2.5D architecture based on hybrid 2D and 3D convolution, and effectively utilizes the directional information within anisotropic resolutions to achieve cross-scale feature extraction. Additionally, deformable convolution is introduced into the model to enhance the receptive field and effectively handle multi-scale spatial transformations. To improve channel correlation and reduce redundant features, we design a Residual Deformable Squeeze-and-Excitation Module. We conduct extensive experiments on an internal dataset, and the results show that the proposed model outperforms other existing methods in most dosimetric criteria. The proposed model has superior dose prediction performance in NPC radiotherapy, and has important clinical significance for assisting physicists to optimize the treatment plan and improve standardization of radiotherapy planning. The source code is available at https://github.com/CDUTJ102/2.5D-Deformable-UNet .","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142548607","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

Classification of breast cancer histopathology images using a modified supervised contrastive learning method. 使用改进的监督对比学习法对乳腺癌组织病理学图像进行分类。

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2024-10-30 DOI: 10.1007/s11517-024-03224-7

Matina Mahdizadeh Sani, Ali Royat, Mahdieh Soleymani Baghshah

{"title":"Classification of breast cancer histopathology images using a modified supervised contrastive learning method.","authors":"Matina Mahdizadeh Sani, Ali Royat, Mahdieh Soleymani Baghshah","doi":"10.1007/s11517-024-03224-7","DOIUrl":"https://doi.org/10.1007/s11517-024-03224-7","url":null,"abstract":"Deep neural networks have reached remarkable achievements in medical image processing tasks, specifically in classifying and detecting various diseases. However, when confronted with limited data, these networks face a critical vulnerability, often succumbing to overfitting by excessively memorizing the limited information available. This work addresses the challenge mentioned above by improving the supervised contrastive learning method leveraging both image-level labels and domain-specific augmentations to enhance model robustness. This approach integrates self-supervised pre-training with a two-stage supervised contrastive learning strategy. In the first stage, we employ a modified supervised contrastive loss that not only focuses on reducing false negatives but also introduces an elimination effect to address false positives. In the second stage, a relaxing mechanism is introduced that refines positive and negative pairs based on similarity, ensuring that only relevant image representations are aligned. We evaluate our method on the BreakHis dataset, which consists of breast cancer histopathology images, and demonstrate an increase in classification accuracy by 1.45% in the image level, compared to the state-of-the-art method. This improvement corresponds to 93.63% absolute accuracy, highlighting the effectiveness of our approach in leveraging properties of data to learn more appropriate representation space. The code implementation of this study is accessible on GitHub https://github.com/matinamehdizadeh/Breast-Cancer-Detection .","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142548606","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

Temporomandibular joint CBCT image segmentation via multi-view ensemble learning network. 通过多视角集合学习网络进行颞下颌关节 CBCT 图像分割。

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2024-10-28 DOI: 10.1007/s11517-024-03225-6

Piaolin Hu, Jupeng Li, Ruohan Ma, Kai Zhang, Yong Guo, Gang Li

{"title":"Temporomandibular joint CBCT image segmentation via multi-view ensemble learning network.","authors":"Piaolin Hu, Jupeng Li, Ruohan Ma, Kai Zhang, Yong Guo, Gang Li","doi":"10.1007/s11517-024-03225-6","DOIUrl":"https://doi.org/10.1007/s11517-024-03225-6","url":null,"abstract":"Accurate segmentation of the temporomandibular joint (TMJ) from cone beam CT (CBCT) images holds significant clinical value for diagnosing temporomandibular joint osteoarthrosis (TMJOA) and related conditions. Convolutional neural network-based medical image segmentation methods have achieved state-of-the-art performance in various segmentation tasks. However, 3D medical images segmentation requires substantial global context and rich spatial semantic information, demanding much more GPU memory and computational resources. To address these challenges in 3D medical image segmentation, we propose a novel network- the MVEL-Net (Multi-view Ensemble Learning Network) for TMJ CBCT image segmentation. By resampling images along three dimensions, we generate multiple weak learners with different spatial semantic information. A subsequent strong learning network effectively integrates the outputs from these weak learners to achieve more accurate segmentation results. We evaluated our network model using a clinical dataset comprising 88 subjects with TMJ CBCT images. The average Dice similarity coefficient (DSC) was 0.9817 ± 0.0049, the average surface distance was 0.0540 ± 0.0179 mm, and the 95% Hausdorff distance was 0.1743 ± 0.0550 mm. Our proposed MVEL-Net demonstrates excellent segmentation performance on TMJ from CBCT images, while using fewer GPU memory resources compared to other 3D networks. The effectiveness of this method in capturing spatial context could be leveraged for tasks like organ segmentation from volumetric scans. This may facilitate wider adoption of AI-based solutions for automated analysis of 3D medical images.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142511897","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