Medical Engineering & Physics最新文献

筛选
英文 中文
Mechanical properties of decellularized porcine esophagus: Preliminary results
IF 1.7 4区 医学
Medical Engineering & Physics Pub Date : 2025-02-20 DOI: 10.1016/j.medengphy.2025.104294
Romane LESIEUR , Agnès DROCHON , Marlène DURAND
{"title":"Mechanical properties of decellularized porcine esophagus: Preliminary results","authors":"Romane LESIEUR ,&nbsp;Agnès DROCHON ,&nbsp;Marlène DURAND","doi":"10.1016/j.medengphy.2025.104294","DOIUrl":"10.1016/j.medengphy.2025.104294","url":null,"abstract":"<div><div>Esophageal tissue engineering is a promising approach to create an esophageal substitute after surgical resection of a part of the organ. Regeneration of esophageal tissue may be achieved using some synthetic or biological scaffolds. In the present study, scaffolds are obtained through the decellularization of porcine esophagi. In view of future implantation, it is important to test the mechanical properties of the decellularized matrices and to compare them with the data obtained for native pig esophagi. Results of longitudinal and circumferential traction experiments as well as inflation and burst tests are presented. The results obtained for the compliance of porcine decellularized matrices are novel. It is concluded that the decellularized matrices are suitable for use as esophageal substitutes.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"137 ","pages":"Article 104294"},"PeriodicalIF":1.7,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143444393","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
An FE model investigating the bone-implant interface of Osseointegrated prosthetics to better understand how forces are transferred under loading
IF 1.7 4区 医学
Medical Engineering & Physics Pub Date : 2025-02-10 DOI: 10.1016/j.medengphy.2025.104304
Tiereny McGuire , Arul Ramasamy , Anthony M J Bull
{"title":"An FE model investigating the bone-implant interface of Osseointegrated prosthetics to better understand how forces are transferred under loading","authors":"Tiereny McGuire ,&nbsp;Arul Ramasamy ,&nbsp;Anthony M J Bull","doi":"10.1016/j.medengphy.2025.104304","DOIUrl":"10.1016/j.medengphy.2025.104304","url":null,"abstract":"<div><h3>Background</h3><div>Osseointegrated prostheses (OIP) use is increasing for above-knee amputees who have difficulties with sockets. This study aims to simulate the bone-implant interface under loading using a 3D finite element (FE) model and quantify force distribution to produce hypotheses on bone remodelling and implant failure, informing implant and surgical design, and rehabilitation protocols.</div></div><div><h3>Methods</h3><div>Ten customised 3D femur FE models (5 female, 5 male) were generated from CT scans and bone-implant assemblies created. The bone was subdivided into seven Gruen Zones and four proximal femur regions. Boundary conditions were taken from the literature.</div></div><div><h3>Results</h3><div>The highest stresses were found in the implant (Max: 113.9 MPa), whilst highest strains were seen in the bone (Max: 4.89 %). Stress and strain were unevenly distributed, with distal regions experiencing stress shielding effects and areas around the implant tip experiencing significantly higher stresses and strains (<em>p</em> &lt; .001). Maximum stresses were higher in female bones (<em>p</em> &lt; .01), whilst shorter residuum lengths saw significantly lower stresses (<em>p</em> &lt; .05).</div></div><div><h3>Conclusion</h3><div>Sex, size and limb length are all important factors and these need to be accounted for when designing and implanting OIPs.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"137 ","pages":"Article 104304"},"PeriodicalIF":1.7,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143444391","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
Atomic-level insights into the adsorption of various biopolymers on Fe3O4 nanoparticles: A molecular dynamics study
IF 1.7 4区 医学
Medical Engineering & Physics Pub Date : 2025-02-08 DOI: 10.1016/j.medengphy.2025.104301
Farzad Pashmforoush, Shahram Ajori
{"title":"Atomic-level insights into the adsorption of various biopolymers on Fe3O4 nanoparticles: A molecular dynamics study","authors":"Farzad Pashmforoush,&nbsp;Shahram Ajori","doi":"10.1016/j.medengphy.2025.104301","DOIUrl":"10.1016/j.medengphy.2025.104301","url":null,"abstract":"<div><div>In this study, molecular dynamics simulations were implemented to investigate the atomic-level interactions of three different biopolymers (Gum Tragacanth, pectin, and carrageenan) on Fe<sub>3</sub>O<sub>4</sub> nanoparticles. The main purpose was to achieve a deep understanding of the adsorption dynamics between these biopolymers and magnetic nanoparticle. In this respect, initially, the adsorption models were simulated under NVT conditions, and consequently, in-depth analyses of interaction energies, concentration profiles, and radial distribution functions were conducted. According to the obtained results, a strong adsorption of all three biopolymers on nanoparticles surface was observed, caused mainly by hydrogen bonds and van der Waals forces. However, Fe<sub>3</sub>O<sub>4</sub>/carrageenan demonstrated the strongest binding affinity among the biopolymer-nanoparticle pairs. This research provides critical atomic-level insights into biopolymer-nanoparticle interactions, bridging a significant knowledge gap and enhancing the understanding and potential application of Fe<sub>3</sub>O<sub>4</sub>-based materials in cutting-edge biomedical technologies.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"137 ","pages":"Article 104301"},"PeriodicalIF":1.7,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143444392","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
Assessment of pre- and post-operative gait dynamics in total knee arthroplasty by a wearable capture system
IF 1.7 4区 医学
Medical Engineering & Physics Pub Date : 2025-02-08 DOI: 10.1016/j.medengphy.2025.104309
Zhuoxi Bi , Wenquan Cui , Luming Feng , Yaxin Liu , Xin Ma , Shihao Li , Changle Ren , Liming Shu
{"title":"Assessment of pre- and post-operative gait dynamics in total knee arthroplasty by a wearable capture system","authors":"Zhuoxi Bi ,&nbsp;Wenquan Cui ,&nbsp;Luming Feng ,&nbsp;Yaxin Liu ,&nbsp;Xin Ma ,&nbsp;Shihao Li ,&nbsp;Changle Ren ,&nbsp;Liming Shu","doi":"10.1016/j.medengphy.2025.104309","DOIUrl":"10.1016/j.medengphy.2025.104309","url":null,"abstract":"<div><h3>Background</h3><div>Walking function reconstruction is suboptimal after total knee arthroplasty. However, a comprehensive investigation of kinematic and kinetic parameters before and after total knee arthroplasty is lacking. This study aimed to quantitatively compare the differences in gait parameters before and after total knee arthroplasty with those of healthy control group.</div></div><div><h3>Methods</h3><div>This study utilized a wearable capture system to obtain gait parameters from pre- operative and one-year post- operative patients, as well as from the healthy control group. The parameters included walking speed, the stance phase percentage during the gait cycle, knee flexion angle, center of pressure trajectory, vertical ground reaction force, and its moment on the coronal plane of the knee joint.</div></div><div><h3>Results</h3><div>Post-total knee arthroplasty patients presented an averaged 12.5 % improvement in walking speed and an averaged 19.75 % increasement in the maximum knee flexion angle during the gait cycle, although both were still lower than those of the healthy control group. During the stance phase, the vertical ground reaction force exhibited a less pronounced double-hump feature, and compared to preoperative levels, the peak of the coronal plane moment of the knee was reduced by approximately half.</div></div><div><h3>Conclusion</h3><div>One-year post- total knee arthroplasty patients exhibited improved walking function compared to preoperative levels, but a gap remained compared to healthy control group. Additionally, preoperative gait abnormalities persisted postoperatively.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"137 ","pages":"Article 104309"},"PeriodicalIF":1.7,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143394474","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
A novel 3D lightweight model for COVID-19 lung CT Lesion Segmentation
IF 1.7 4区 医学
Medical Engineering & Physics Pub Date : 2025-02-08 DOI: 10.1016/j.medengphy.2025.104297
Jingdong Yang , Shaoyu Huang , Han Wang , Yuhang Lu , Wei liu , Yan Shen , Xiaohong Fu
{"title":"A novel 3D lightweight model for COVID-19 lung CT Lesion Segmentation","authors":"Jingdong Yang ,&nbsp;Shaoyu Huang ,&nbsp;Han Wang ,&nbsp;Yuhang Lu ,&nbsp;Wei liu ,&nbsp;Yan Shen ,&nbsp;Xiaohong Fu","doi":"10.1016/j.medengphy.2025.104297","DOIUrl":"10.1016/j.medengphy.2025.104297","url":null,"abstract":"<div><div>3D-based medical image segmentation, offering enhanced spatial information compared to 2D slice-based methods, encounters challenges arising from factors such as a restricted clinical sample size, imbalanced foreground-background pixel distribution, and suboptimal generalization performance. To address these challenges, we propose a lightweight segmentation model tailored to 3D medical images. Employing the K-means algorithm, our approach efficiently extracts the Region of Interest (ROI) from medical images, facilitating lung area segmentation while minimizing interference from background pixels. We address the risk of model overfitting by adopting the Focal loss in conjunction with the Dice coefficient as our loss function. Feature extraction capabilities are bolstered through the incorporation of a parallel attention mechanism at skip connections, aiming to enhance the representation of both shallow and deep layers. Moreover, we optimize computational efficiency and memory utilization by substituting 3 × 3 convolutions with depth-wise separable convolutions and integrating residual connections for improved gradient propagation. The introduction of Ghost-inspired 1 × 1 convolution ensures consistent feature dimensions before and after residual connections. Experimental evaluation, conducted on a dataset comprising 199 COVID-19-Seg cases through 5-fold cross-validation, underscores the superior performance of our proposed model. Evaluation metrics, including Average Surface Distance (ASD), accuracy, sensitivity, Dice coefficient, and Intersection over Union (IOU) accuracy, yield values of 19.880, 99.90 %, 58.90 %, 56.10 %, and 41.00 %, respectively. In comparison to the other state-of-the-art segmentation models, our approach achieves heightened segmentation accuracy and generalization performance while incurring only a marginal increase in parameters and computational complexity.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"137 ","pages":"Article 104297"},"PeriodicalIF":1.7,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143402751","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
A patient-matched prosthesis for thumb amputations: Design, mechanical and functional evaluation
IF 1.7 4区 医学
Medical Engineering & Physics Pub Date : 2025-02-08 DOI: 10.1016/j.medengphy.2025.104296
Federico Stacchiotti , Chiara Bregoli , Rubens Ferrari , Jacopo Fiocchi , Kavin Morellato , Carlo Alberto Biffi , Mattia Frascio , Matilde Minuto , Ausonio Tuissi , Emanuele Gruppioni
{"title":"A patient-matched prosthesis for thumb amputations: Design, mechanical and functional evaluation","authors":"Federico Stacchiotti ,&nbsp;Chiara Bregoli ,&nbsp;Rubens Ferrari ,&nbsp;Jacopo Fiocchi ,&nbsp;Kavin Morellato ,&nbsp;Carlo Alberto Biffi ,&nbsp;Mattia Frascio ,&nbsp;Matilde Minuto ,&nbsp;Ausonio Tuissi ,&nbsp;Emanuele Gruppioni","doi":"10.1016/j.medengphy.2025.104296","DOIUrl":"10.1016/j.medengphy.2025.104296","url":null,"abstract":"<div><div>Thumb amputations strongly affect hand functionality in daily activities. The currently available solutions, such as microsurgical treatments and external vacuum prostheses present disadvantages, which can be successfully addressed through the osseointegration technique. However, despite its widespread use in oral applications, only a few osseointegrated solutions for the treatment of hand-finger amputations are available. Bone remaining limbs may have different lengths, diameters, and conditions and no patient-matched osseointegrated medical devices are available on the market. The manuscript presents the first patient-matched medical device for the treatment of thumb amputations. The prosthesis mainly consists of three components: an osseointegrated fixture which is implanted into the medullary canal of the bone remaining limb, an abutment, and an external digital prosthesis. The design phase is followed by computational and experimental analysis to optimize the design of each component attached to the osseointegrated fixture in order to preserve the implant fixture and bone. The maximum force generated during the pinch test in a healthy subject is approximately 80 N. The mechanical performance required during daily activities is achieved by the novel proposed device and the obtained results confirm that, in case of loads greater than daily ones, the failure may occur in the abutment component which is external to the body. A limitation of the current study consists in the lack of analysis on the bone-implant interface for which specific investigations would be required: currently, the contact between bone and fixture is assumed to be fixed, i.e. no micro motions are considered. Research is ongoing to test the entire device in a clinical study to collect quantitative and qualitative information from patients and surgeons.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"137 ","pages":"Article 104296"},"PeriodicalIF":1.7,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143386771","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 surface type on outdoor gait parameters measured using an In-Shoe Motion Sensor System
IF 1.7 4区 医学
Medical Engineering & Physics Pub Date : 2025-02-08 DOI: 10.1016/j.medengphy.2025.104295
Hiroki Shimizu , Kyoma Tanigawa , Anuradhi Bandara , Shinichi Kawamoto , Shota Suzuki , Momoko Nagai-Tanima , Tomoki Aoyama
{"title":"Influence of surface type on outdoor gait parameters measured using an In-Shoe Motion Sensor System","authors":"Hiroki Shimizu ,&nbsp;Kyoma Tanigawa ,&nbsp;Anuradhi Bandara ,&nbsp;Shinichi Kawamoto ,&nbsp;Shota Suzuki ,&nbsp;Momoko Nagai-Tanima ,&nbsp;Tomoki Aoyama","doi":"10.1016/j.medengphy.2025.104295","DOIUrl":"10.1016/j.medengphy.2025.104295","url":null,"abstract":"<div><div>The objectives of this study were to measure outdoor gait parameters using an In-Shoe Motion Sensor System (IMS) and evaluate how different types of surfaces affect various gait dynamics. Accurate outdoor gait data are crucial for effective fall risk assessment because surface irregularities and tripping hazards often result in falls during walking. An IMS was used in this study to collect spatiotemporal, spatial, and foot parameters from 27 healthy adults walking on indoor asphalt, soil, and grass surfaces. Data were recorded during a 6-minute walk test, with measurements taken every 2 min and analyzed using the Statistical Package for the Social Sciences. The results showed significant differences in foot clearance, heel height, and gait cycle across surfaces. Walking on grass significantly increased foot height, swing time, and roll angle of heel contact. These findings may help develop interventions to prevent falls.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"137 ","pages":"Article 104295"},"PeriodicalIF":1.7,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143394473","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
ResGloTBNet: An interpretable deep residual network with global long-range dependency for tuberculosis screening of sputum smear microscopy images
IF 1.7 4区 医学
Medical Engineering & Physics Pub Date : 2025-02-08 DOI: 10.1016/j.medengphy.2025.104300
Taocui Yan , Yaqian Jin , Shangqing Liu , Qiuni Li , Guowei Zuo , Ziqian Ye , Jin Li , Baoru Han
{"title":"ResGloTBNet: An interpretable deep residual network with global long-range dependency for tuberculosis screening of sputum smear microscopy images","authors":"Taocui Yan ,&nbsp;Yaqian Jin ,&nbsp;Shangqing Liu ,&nbsp;Qiuni Li ,&nbsp;Guowei Zuo ,&nbsp;Ziqian Ye ,&nbsp;Jin Li ,&nbsp;Baoru Han","doi":"10.1016/j.medengphy.2025.104300","DOIUrl":"10.1016/j.medengphy.2025.104300","url":null,"abstract":"<div><div>Tuberculosis is a high-mortality infectious disease. Manual sputum smear microscopy is a common and effective method for screening tuberculosis. However, it is time-consuming, labor-intensive, and has low sensitivity. In this study, we propose ResGloTBNet, a framework that integrates convolutional neural network and graph convolutional network for sputum smear image classification with high discriminative power. In this framework, the global reasoning unit is introduced into the residual structure of ResNet to form the ResGloRe module, which not only fully extracts the local features of the image but also models the global relationship between different regions in the image. Furthermore, we applied activation maximization and class activation mapping to generate explanations for the model's predictions on the test sets. ResGloTBNet achieved remarkable results on a publicly available dataset, reaching 97.2 % accuracy and 99.0 % sensitivity. It also maintained a high level of performance on a private dataset, attaining 98.0 % accuracy and 96.6 % sensitivity. In addition, interpretable analysis demonstrated that ResGloTBNet can effectively identify the features and regions in the input images that contribute the most to the model's predictions, providing valuable insights into the decision-making process of the deep learning model.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"137 ","pages":"Article 104300"},"PeriodicalIF":1.7,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419036","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
A numerical simulation study of airway flow: Impact of bronchial stenosis 气道流动的数值模拟研究:支气管狭窄的影响
IF 1.7 4区 医学
Medical Engineering & Physics Pub Date : 2025-02-08 DOI: 10.1016/j.medengphy.2025.104303
Mingqian Mao , Zhichen Yang , Mengting Li , Xiaoyu Ni , Changwang Pan
{"title":"A numerical simulation study of airway flow: Impact of bronchial stenosis","authors":"Mingqian Mao ,&nbsp;Zhichen Yang ,&nbsp;Mengting Li ,&nbsp;Xiaoyu Ni ,&nbsp;Changwang Pan","doi":"10.1016/j.medengphy.2025.104303","DOIUrl":"10.1016/j.medengphy.2025.104303","url":null,"abstract":"<div><div>Obstructive lung diseases, marked by airway stenosis, are chronic and pose significant mortality risks. This study aims to analyze airflow patterns in obstructed bronchi, comparing them to healthy airways during tidal breathing to improve our comprehension of disease effects on respiratory function. The current studies mostly overlook the specific morphology of the patient's upper airway or the elastic deformation of the airway soft tissues, which results in the existing results not being sufficient to effectively guide surgical treatment. In this paper, a realistic model of bronchial stenosis was obtained by CT data from a 71-year-old female patient. Full consideration was given to the nonlinear elastic material properties of the tracheal wall cartilage and smooth muscle and the dynamic changes in intra-pulmonary pressure, which are significant factors affecting the airflow field within the airway. The dynamic mesh technology and the Fluid-Structure Interaction (FSI) method, in conjunction with Computational Fluid Dynamics (CFD), were employed to analyze the impact of bilateral bronchial stenosis on the airflow state and the nonlinear mechanical behavior of the airway wall under different respiratory intensities. The simulation results exposed the distribution pattern of key parameters, such as airflow velocity, pressure, wall shear stress, and turbulent kinetic energy, indicating that bronchial stenosis significantly influences the air-flow motion, resulting in increased pressure, wall shear stress, and deformation of the airway wall. The finding revealed that the maximum airflow velocity, pressure, and wall shear stress all occurred in the stenosis areas of the bronchi, while the maximum deformation occurred on the smooth muscle side of the middle part of the main trachea. Additionally, turbulence occurs near the main trachea and carina, potentially related to airflow separation and local geometric changes. These insights contribute to a deeper understanding of the effects of bronchial stenosis on airway airflow dynamics and provide a scientific basis for the determination of clinical treatment plans and the prediction of treatment outcomes.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"137 ","pages":"Article 104303"},"PeriodicalIF":1.7,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430089","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
A multi-attention deep architecture to stratify lung nodule malignancy from CT scans
IF 1.7 4区 医学
Medical Engineering & Physics Pub Date : 2025-02-07 DOI: 10.1016/j.medengphy.2025.104305
Alejandra Moreno , Andrea Rueda , Fabio Martínez
{"title":"A multi-attention deep architecture to stratify lung nodule malignancy from CT scans","authors":"Alejandra Moreno ,&nbsp;Andrea Rueda ,&nbsp;Fabio Martínez","doi":"10.1016/j.medengphy.2025.104305","DOIUrl":"10.1016/j.medengphy.2025.104305","url":null,"abstract":"<div><div>Lung cancer remains the principal cause of cancer-related deaths. Nodules are the main radiological finding, typically observed from low-dose CT scans. Nonetheless, the nodule characterization diagnosis remains subjective, reporting a moderate agreement among experts' observations, especially in identifying malignancy stratification. The proposed approach presents a deep multi-attention strategy, validated exhaustively to classify nodule masses according to four malignancy degrees. This work introduces a multi-attention architecture dedicated to stratifying nodules among malignancy stages. The architecture receives volumetric nodule regions and learns multi-scale saliency maps, focusing on determinant malignancy patterns of the observed masses. Specialized attention heads capture related patterns associated with lobulated, textural, and spiculated features. Validation includes an extensive analysis regarding multiple attention features, allowing to establish a correlation with other radiological findings. The proposed approach achieves an AUC of 85.35% for a classical multi-classification and a mean AUC of 82.90% in a one-vs-all validation methodology, showing competitive results in the state-of-the-art. The introduced architecture has capabilities to support nodule stratification and to classify nodule features. The exhaustive validation also suggests a proper generalization performance, which is a potential property to transfer this strategy in real scenarios.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"137 ","pages":"Article 104305"},"PeriodicalIF":1.7,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376673","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
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
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
确定
请完成安全验证×
相关产品
×
本文献相关产品
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信