Medical Engineering & Physics最新文献_第7页

Validity and between-days reliability of two different metabolic systems for measuring gas exchange during walking 两种不同代谢系统在步行过程中测量气体交换的有效性和天间可靠性

IF 1.7 4区医学

Medical Engineering & Physics Pub Date : 2025-02-01 DOI: 10.1016/j.medengphy.2024.104281

Juan M.A. Alcantara , Fernando Alonso-Gonzalo , Antonio Clavero-Jimeno , Andres Marmol-Perez , Jose Antonio Suarez-Roman , Jonatan R. Ruiz

{"title":"Validity and between-days reliability of two different metabolic systems for measuring gas exchange during walking","authors":"Juan M.A. Alcantara , Fernando Alonso-Gonzalo , Antonio Clavero-Jimeno , Andres Marmol-Perez , Jose Antonio Suarez-Roman , Jonatan R. Ruiz","doi":"10.1016/j.medengphy.2024.104281","DOIUrl":"10.1016/j.medengphy.2024.104281","url":null,"abstract":"<div><h3>Background</h3><div>Portable metabolic systems for assessing gas exchange outside the laboratory and clinical settings are increasing their popularity. We aimed to determine the validity and the reliability of the K5 portable system (Cosmed, Rome, Italy) and the Omnical (Maastricht Instruments, Maastricht, The Netherlands) metabolic cart.</div></div><div><h3>Methods</h3><div>Gas exchange was measured, using the K5 and the Omnical in a randomised and counterbalanced order, in 35 participants (19 women; age: 26 ± 3 yrs.) using a walking protocol on 2 non-consecutive (48 h apart) days. The protocol consisted of a 5 min walk and 2.5 min rest cycle starting at 3.5 km/h and increasing in 1 km/h to 6.5 km/h. The protocol was repeated twice after a 10–15 min resting. To determine validity and reliability, we conducted two-factor repeated measures analysis of variance (ANOVA), intraclass correlation coefficients (ICC), coefficients of variation (CV) and Bland-Altman analyses.</div></div><div><h3>Results</h3><div>Repeated measures ANOVA showed that mean oxygen consumption, carbon dioxide production and energy expenditure were higher for the K5 compared to the Omnical on both visits (all <em>P</em> < 0.001). Respiratory exchange ratio (RER) was similar among systems at faster (≥4.5 km/h) walking speeds. ICC, CV and Bland-Altman showed a better reliability of the Omnical (ICCs ranged from 0.71 to 0.86, and CVs from 3.1 % to 7.1 %) compared to the K5 (ICCs ranged from 0.40 to 0.98, and CVs from 2.6 % to 6.3 %).</div></div><div><h3>Conclusions</h3><div>The K5 portable system provides similar RER values to the Omnical metabolic cart, although the Omnical reliability was better for most outcomes.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"136 ","pages":"Article 104281"},"PeriodicalIF":1.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143166646","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

Semi-supervised medical image segmentation with dual-branch mixup-decoupling confidence training 基于双分支混合解耦置信度训练的半监督医学图像分割

IF 1.7 4区医学

Medical Engineering & Physics Pub Date : 2025-02-01 DOI: 10.1016/j.medengphy.2025.104285

Jianwu Long, Yuanqin Liu, Yan Ren

{"title":"Semi-supervised medical image segmentation with dual-branch mixup-decoupling confidence training","authors":"Jianwu Long, Yuanqin Liu, Yan Ren","doi":"10.1016/j.medengphy.2025.104285","DOIUrl":"10.1016/j.medengphy.2025.104285","url":null,"abstract":"<div><div>Semi-supervised medical image segmentation algorithms hold significant research and practical value due to their ability to reduce labeling dependency and annotation costs. However, most current algorithms lack diverse regularization methods to effectively exploit robust knowledge from unlabeled data. The pseudo-label filtering methods employed are often overly simplistic, which exacerbates the serious category imbalance problem in medical images. Additionally, these algorithms fail to provide robust semantic representations for comparative learning in multi-scenario settings, making it challenging for the model to learn more discriminative semantic information. To address these issues, we propose a semi-supervised medical image segmentation algorithm that utilizes dual-branch mixup-decoupling confidence training to establish a dual-stream semantic link between labeled and unlabeled images, thereby alleviating semantic ambiguity. Furthermore, we design a bidirectional confidence contrast learning method to maximize the consistency between similar pixels and the distinction between dissimilar pixels in both directions across different feature embeddings in dual views. This enables the model to learn the key features of intra-class similarity and inter-class separability. We conduct a series of experiments on both 2D and 3D datasets, and the experimental results demonstrate that the proposed algorithm achieves notable segmentation performance, outperforming other recent state-of-the-art algorithms.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"136 ","pages":"Article 104285"},"PeriodicalIF":1.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143166645","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

Investigating the course and predictors of desire to void based on heart rate variability 研究基于心率变异性的欲望过程和预测因素

IF 1.7 4区医学

Medical Engineering & Physics Pub Date : 2025-02-01 DOI: 10.1016/j.medengphy.2025.104286

Shulian Tan, Yi Tang, Ping Shi

{"title":"Investigating the course and predictors of desire to void based on heart rate variability","authors":"Shulian Tan, Yi Tang, Ping Shi","doi":"10.1016/j.medengphy.2025.104286","DOIUrl":"10.1016/j.medengphy.2025.104286","url":null,"abstract":"<div><div>Urinary incontinence is closely related to the motor ability and toileting tasks. Some nursing home residents with limited mobility who cannot reach the bathroom in time highly depend on caregivers for toileting assistance. However, nursing home staffing is often insufficient to meet the needs of all residents. Monitoring the desire to urinate is vital to minimize functional dependence and improve the quality of life of older people. Improved reliability of the desire to void monitoring requires exploring more effective monitoring methods. In this paper, we observed the changes in heart rate variability (HRV) during bladder filling, established the mapping relationship between normal bladder filling degree and HRV, and evaluated the performance of different classification models in predicting the degree of desire to void using HRV characteristics at different bladder filling degrees. The results showed that the autonomic nervous system gradually shifted to sympathetic nerve activity with increased bladder filling. Meanwhile, the classification accuracy of the wide neural network model for the degree of desire to void was >98 %. HRV shows a significant application prospect in predicting the desire to void, which provides a new direction for the research and development of non-invasive voiding intention monitoring and intelligent rehabilitation equipment and is expected to promote technical progress and development in related fields.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"136 ","pages":"Article 104286"},"PeriodicalIF":1.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143196580","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

Fluid-structure interaction simulations for the prediction of fractional flow reserve in pediatric patients with anomalous aortic origin of a coronary artery 流固相互作用模拟预测冠状动脉异常起源地患儿血流储备分数

IF 1.7 4区医学

Medical Engineering & Physics Pub Date : 2025-02-01 DOI: 10.1016/j.medengphy.2025.104293

Charles Puelz , Craig G. Rusin , Dan Lior , Shagun Sachdeva , Tam T. Doan , Lindsay F. Eilers , Dana Reaves-O'Neal , Monisha Akula , Silvana Molossi

{"title":"Fluid-structure interaction simulations for the prediction of fractional flow reserve in pediatric patients with anomalous aortic origin of a coronary artery","authors":"Charles Puelz , Craig G. Rusin , Dan Lior , Shagun Sachdeva , Tam T. Doan , Lindsay F. Eilers , Dana Reaves-O'Neal , Monisha Akula , Silvana Molossi","doi":"10.1016/j.medengphy.2025.104293","DOIUrl":"10.1016/j.medengphy.2025.104293","url":null,"abstract":"<div><div>Computer simulations of blood flow in patients with anomalous aortic origin of a coronary artery (AAOCA) have the promise to provide insight into this complex disease. They provide an <em>in silico</em> experimental platform to explore possible mechanisms of myocardial ischemia, a potentially deadly complication for patients with this defect. This paper focuses on the question of model calibration for fluid-structure interaction models of pediatric AAOCA patients. Imaging and cardiac catheterization data provide partial information for model construction and calibration. However, parameters for downstream boundary conditions needed for these models are difficult to estimate. Further, important model predictions, like fractional flow reserve (FFR), are sensitive to these parameters. We describe an approach to calibrate downstream boundary condition parameters to clinical measurements of resting FFR. The calibrated models are then used to predict FFR at stress, an invasively measured quantity that can be used in the clinical evaluation of these patients. We find reasonable agreement between the model predicted and clinically measured FFR at stress, indicating the credibility of this modeling framework for predicting hemodynamics of pediatric AAOCA patients. This approach could lead to important clinical applications since it may serve as a tool for risk stratifying children with AAOCA.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"136 ","pages":"Article 104293"},"PeriodicalIF":1.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143196581","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

Low-cost graphite and double-gate FET-based label-free biosensor for dopamine sensing to detect neural diseases 低成本石墨双栅fet无标记生物传感器用于多巴胺传感检测神经疾病

IF 1.7 4区医学

Medical Engineering & Physics Pub Date : 2025-02-01 DOI: 10.1016/j.medengphy.2025.104282

Deepti , Anirban Kolay , Subrata Majumder , Amitesh Kumar

{"title":"Low-cost graphite and double-gate FET-based label-free biosensor for dopamine sensing to detect neural diseases","authors":"Deepti , Anirban Kolay , Subrata Majumder , Amitesh Kumar","doi":"10.1016/j.medengphy.2025.104282","DOIUrl":"10.1016/j.medengphy.2025.104282","url":null,"abstract":"<div><div>The manuscript proposes biosensors for detecting different concentrations of neurotransmitters named dopamine, which have a critical role in the human body's neurological, hormonal, and renal systems. In this work, the primary focus is to detect dopamine, whose disorder levels cause many neurological disabilities such as Alzheimer's and Parkinson's disease. In the present work, the simulation of two different structures has been studies: a) a graphite-based structure and b) a double gate TFET structure for detecting dopamine using TCAD Silvaco software. The proposed device utilizes a graphite-based structure with respective work functions of the used materials and studies the change in ON current (I<em><sub>ON</sub></em> sensing factor is calculated for simulation study for V<sub>GS</sub> = 0.8 V). The cavity is increased to 800 µm for graphite-based biosensors for improved sensitivity. The graphite-based biosensors can detect up to 13.3 nM concentration of dopamine. Experimental electrochemical analysis results verify the proposed graphite-based biosensors' sensitivity for different dopamine concentrations. Another double gate field effect transistor (FET) biosensor has also been investigated for the detection of dopamine. The effective dielectric constant has been calculated using Bruggeman's model to check the sensitivity of double gate FET-based sensors for varying dopamine and uric acid concentrations. The sensitivity is increased with the increase of dopamine concentration percentage.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"136 ","pages":"Article 104282"},"PeriodicalIF":1.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143166299","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

Benchmarking 2D human pose estimators and trackers for workflow analysis in the cardiac catheterization laboratory 基准二维人体姿态估计器和跟踪器的工作流程分析在心导管实验室

IF 1.7 4区医学

Medical Engineering & Physics Pub Date : 2025-02-01 DOI: 10.1016/j.medengphy.2025.104289

Rick M. Butler , Emanuele Frassini , Teddy S. Vijfvinkel , Sjors van Riel , Chavdar Bachvarov , Jan Constandse , Maarten van der Elst , John J. van den Dobbelsteen , Benno H.W. Hendriks

{"title":"Benchmarking 2D human pose estimators and trackers for workflow analysis in the cardiac catheterization laboratory","authors":"Rick M. Butler , Emanuele Frassini , Teddy S. Vijfvinkel , Sjors van Riel , Chavdar Bachvarov , Jan Constandse , Maarten van der Elst , John J. van den Dobbelsteen , Benno H.W. Hendriks","doi":"10.1016/j.medengphy.2025.104289","DOIUrl":"10.1016/j.medengphy.2025.104289","url":null,"abstract":"<div><div>Workflow insights can improve efficiency and safety in the Cardiac Catheterization Laboratory (Cath Lab). As manual analysis is labor-intensive, we aim for automation through camera monitoring. Literature shows that human poses are indicative of activities and therefore workflow. As a first exploration, we evaluate how marker-less multi-human pose estimators perform in the Cath Lab. We annotated poses in 2040 frames from ten multi-view coronary angiogram (CAG) recordings. Pose estimators AlphaPose, OpenPifPaf and OpenPose were run on the footage. Detection and tracking were evaluated separately for the Head, Arms, and Legs with Average Precision (AP), head-guided Percentage of Correct Keypoints (PCKh), Association Accuracy (AA), and Higher-Order Tracking Accuracy (HOTA). We give qualitative examples of results for situations common in the Cath Lab, with reflections in the monitor or occlusion of personnel. AlphaPose performed best on most mean Full-pose metrics with an AP from 0.56 to 0.82, AA from 0.55 to 0.71, and HOTA from 0.58 to 0.73. On PCKh OpenPifPaf scored highest, from 0.53 to 0.64. Arms, Legs, and the Head were detected best in that order, from the views which see the least occlusion. During tracking in the Cath Lab, AlphaPose tended to swap identities and OpenPifPaf merged different individuals. Results suggest that AlphaPose yields the most accurate confidence scores and limbs, and OpenPifPaf more accurate keypoint locations in the Cath Lab. Occlusions and reflection complicate pose tracking. The AP of up to 0.82 suggests that AlphaPose is a suitable pose detector for workflow analysis in the Cath Lab, whereas its HOTA of up to 0.73 here calls for another tracking solution.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"136 ","pages":"Article 104289"},"PeriodicalIF":1.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143166300","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

Mathematical representation and nonlinear modelling of the Wheatley mitral valve 惠特利二尖瓣的数学表示和非线性建模

IF 1.7 4区医学

Medical Engineering & Physics Pub Date : 2025-02-01 DOI: 10.1016/j.medengphy.2025.104283

H.L. Oliveira , G.C. Buscaglia , J.A. Cuminato , S. McKee , I.W. Stewart , M.M. Kerr , D.J. Wheatley

{"title":"Mathematical representation and nonlinear modelling of the Wheatley mitral valve","authors":"H.L. Oliveira , G.C. Buscaglia , J.A. Cuminato , S. McKee , I.W. Stewart , M.M. Kerr , D.J. Wheatley","doi":"10.1016/j.medengphy.2025.104283","DOIUrl":"10.1016/j.medengphy.2025.104283","url":null,"abstract":"<div><div>This study is concerned with the Wheatley design of the mitral valve. A mathematical description, in terms of elementary functions, is provided for the S-shaped leaflets. This is based on a level set containing symmetric circles (or more generally ellipses) which allow parametrisation. A geometric nonlinear mechanical model subjected to a uniform pressure gradient and in the absence of inertial forces is introduced. The model results in a system of nonlinear equations that is solved using iterative incremental techniques. Under normal pressure loads, the S-shaped geometries induce internal forces which manifest themselves in two combined effects: bending and torsion. As a consequence, the supports are subject to periodic bending actions that tend to deform the support frame towards the interior of the valve. Providing resistance becomes vital for maintaining stable equilibrium. It is also observed that for circular base shape geometries, the mechanism for transmitting the equilibrium forces remains unchanged when the height/diameter ratio is kept below 2.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"136 ","pages":"Article 104283"},"PeriodicalIF":1.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143166301","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 wired and wireless electromagnetic hand motion tracking in central venous access: Are they equivalent enough to cut the cord? 有线和无线电磁手部运动跟踪在中心静脉通路中的比较：它们是否足以切断脐带？

IF 1.7 4区医学

Medical Engineering & Physics Pub Date : 2025-02-01 DOI: 10.1016/j.medengphy.2024.104280

Hamza Ali , Oussama Metrouh , Muneeb Ahmed , John D. Mitchell , Vincent Baribeau , Matthew R. Palmer , Christopher MacLellan , Jeffrey Weinstein

{"title":"Comparison of wired and wireless electromagnetic hand motion tracking in central venous access: Are they equivalent enough to cut the cord?","authors":"Hamza Ali , Oussama Metrouh , Muneeb Ahmed , John D. Mitchell , Vincent Baribeau , Matthew R. Palmer , Christopher MacLellan , Jeffrey Weinstein","doi":"10.1016/j.medengphy.2024.104280","DOIUrl":"10.1016/j.medengphy.2024.104280","url":null,"abstract":"<div><h3>Purpose</h3><div>This study aims to compare a commercially available wired and wireless tracker in motion analysis of interventional radiologists performing simulated ultrasound-guided central venous access.</div></div><div><h3>Methods and material</h3><div>Interventional radiologists were asked to volunteer for the study. Participants were asked to place central venous lines on a commercially available, standardized manikin as their needle hand and ultrasound probe motion were recorded using electromagnetic trackers. Each participant performed a total of 10 trials, with 5 trials recorded using a wired tracker and 5 using a wireless tracker. Institution-developed software was used to calculate established motion metrics (path length and number of movements). The motion metrics from the two trackers were compared.</div></div><div><h3>Results</h3><div>Seven interventional radiologists participated in the study. Path length (wireless vs. wired: 773.1 cm ± 85.7 cm vs. 959.5 cm ± 303.6 cm, <em>p</em> < 0.001) and number of movements (193 ± 52 vs. 231 ± 50.5, <em>p</em> = 0.001) differed significantly between the two trackers; however, the time to complete the procedure (51.8 s ± 14.8 s vs. 49.8 s ± 10.5 s, <em>p</em> = 0.68) was similar across trackers.</div></div><div><h3>Conclusion</h3><div>The motion metrics of the same operators differ significantly between wired and wireless trackers. Accounting for the sampling frame rate and the frame efficiency of the wireless sensors can provide comparable motion data.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"136 ","pages":"Article 104280"},"PeriodicalIF":1.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143166667","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

DP-CLAM: A weakly supervised benign-malignant classification study based on dual-angle scanning ultrasound images of thyroid nodules DP-CLAM：基于甲状腺结节双角度超声扫描图像的弱监督良恶性分类研究

IF 1.7 4区医学

Medical Engineering & Physics Pub Date : 2025-02-01 DOI: 10.1016/j.medengphy.2025.104288

Shuhuan Wang , Shuangqingyue Zhang , Lingmin Liao , Chunquan Zhang , Debin Xu , Long Huang , He Ma

{"title":"DP-CLAM: A weakly supervised benign-malignant classification study based on dual-angle scanning ultrasound images of thyroid nodules","authors":"Shuhuan Wang , Shuangqingyue Zhang , Lingmin Liao , Chunquan Zhang , Debin Xu , Long Huang , He Ma","doi":"10.1016/j.medengphy.2025.104288","DOIUrl":"10.1016/j.medengphy.2025.104288","url":null,"abstract":"<div><div>In this paper, a two-stage task weakly supervised learning algorithm is proposed. It accurately achieved patient-level classification task of benign and malignant thyroid nodules based on ultrasound images from two scanning angles: long axis and short axis of the thyroid site. In the first stage, 68,208 ultrasound scanning images of 588 patients are used to train the underlying classification model. In the second stage, feature vectors of ultrasound images with dual scan angles are extracted using the classification model in the first stage. Then the feature vectors are assigned to position sequences in the order of visual reception by the physician. Finally, the location decision is made through a weakly supervised learning approach. Combined with the dual-angle difference information carried in the overall features, our method accurately achieved benign and malignant classification of thyroid nodules at the patient level. An accuracy of 93.81 % for benign and malignant classification of patients was obtained in our test set. The accuracy of benign and malignant classification of patients with thyroid nodules is improved by our weakly supervised learning method based on a two-stage classification task. It also reduced the pressure of imaging physicians in diagnosing a large number of images. In the clinical auxiliary diagnosis, it provides an effective reference for the timely determination of thyroid nodule patients.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"136 ","pages":"Article 104288"},"PeriodicalIF":1.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143166643","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

MSRMMP: Multi-scale residual module and multi-layer pseudo-supervision for weakly supervised segmentation of histopathological images 组织病理图像弱监督分割的多尺度残差模块和多层伪监督

IF 1.7 4区医学

Medical Engineering & Physics Pub Date : 2025-02-01 DOI: 10.1016/j.medengphy.2025.104284

Yuanchao Xue , Yangsheng Hu , Yu Yao , Jie Huang , Haitao Wang , Jianfeng He

{"title":"MSRMMP: Multi-scale residual module and multi-layer pseudo-supervision for weakly supervised segmentation of histopathological images","authors":"Yuanchao Xue , Yangsheng Hu , Yu Yao , Jie Huang , Haitao Wang , Jianfeng He","doi":"10.1016/j.medengphy.2025.104284","DOIUrl":"10.1016/j.medengphy.2025.104284","url":null,"abstract":"<div><div>Accurate semantic segmentation of histopathological images plays a crucial role in accurate cancer diagnosis. While fully supervised learning models have shown outstanding performance in this field, the annotation cost is extremely high. Weakly Supervised Semantic Segmentation (WSSS) reduces annotation costs due to the use of image-level labels. However, these WSSS models that rely on Class Activation Maps (CAM) focus only on the most salient parts of the image, which is challenging when dealing with semantic segmentation tasks involving multiple targets. We propose a two-stage weakly supervised segmentation framework (MSRMMP) to resolve the above problems, the generation of pseudo masks based on multi-scale residual networks (MSR-Net) and the semantic segmentation based on multi-layer pseudo-supervision. MSR-Net fully captures the local features of an image through multi-scale residual module (MSRM) and generates pseudo masks using image-level label. Additionally, we employ Transunet as the segmentation backbone, and uses multi-layer pseudo-supervision algorithms to solve the problem of pseudo-mask inaccuracy. Experiments performed on two publicly available histopathology image datasets show that our proposed method outperforms other state-of-the-art weakly supervised semantic segmentation methods. Additionally, it outperforms the fully-supervised model in mIoU and has a similar result in fwIoU when compared to fully-supervised models. Compared with manual labeling, our model can significantly save the labeling time from hours to minutes.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"136 ","pages":"Article 104284"},"PeriodicalIF":1.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143166644","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