Irbm最新文献

{"title":"Effects of the Printing Angle on the Properties of Titanium Devices Printed by Additive Manufacturing: a Systematic Review","authors":"Juliana Dias Corpa Tardelli ,&nbsp;Júlia Sacilotto ,&nbsp;Lucas Barcelos Otani ,&nbsp;Andréa Cândido dos Reis","doi":"10.1016/j.irbm.2025.100898","DOIUrl":"10.1016/j.irbm.2025.100898","url":null,"abstract":"<div><h3>Objectives</h3><div>The variation of the printing angle of metallic devices induces anisotropy. Thus, to understand the effects of this parameter on as-built samples, this review aimed to answer, “What is the state-of-the-art in the effect of the printing angle of titanium devices printed by additive manufacturing on the material properties?” to identify the best angle for biomedical application through the correlation of microstructural, mechanical properties and roughness.</div></div><div><h3>Material and Methods</h3><div>The PRISMA 2020 guidelines were followed. The protocol was registered in the Open Science Framework. The search strategy was applied to five databases. The selection process of the articles occurred in two phases by the reviewers independently according to the eligibility criteria, experimental studies that analyzed as-built Ti and its alloy samples printed at different angles characterized by microstructure, mechanical properties, and roughness. In the first, the title and abstract were analyzed. In the second, the articles selected in the first were read in full. The risk of bias was analyzed through a specific tool.</div></div><div><h3>Results</h3><div>Of the 668 articles found, six met the eligibility criteria. Five metal additive manufacturing techniques with printing angles ranging from 0^∘ to 90^∘ were evaluated. The microstructure of the samples was consistent with that expected for the alloy and printing technique, with no interference from the angle. For mechanical properties, greater strength was observed at 0^∘ for tensile, 90^∘ for compression, and Vickers hardness showed no significant differences. For roughness, 0^∘ was the most rough. All studies presented a low risk of bias.</div></div><div><h3>Conclusion</h3><div>The literature evaluated demonstrated that the variation of the printing angle causes the staircase effect that significantly affects the properties of the materials produced. Therefore, the choice of the angle of the biomedical device must be guided by its application, given its strong influence on mechanical performance and consequent durability.</div></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":"46 4","pages":"Article 100898"},"PeriodicalIF":5.6,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144480479","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}

{"title":"Monitoring and Sensing System for People's Behavior During Fall Events Based on Mobility Analysis","authors":"Laura Maligne ,&nbsp;Eric Campo ,&nbsp;Adrien van den Bossche ,&nbsp;Nadine Vigouroux ,&nbsp;Frédéric Vella ,&nbsp;Olivier Negro ,&nbsp;Dan Istrate ,&nbsp;Vincent Zalc ,&nbsp;Pierre Rumeau","doi":"10.1016/j.irbm.2025.100895","DOIUrl":"10.1016/j.irbm.2025.100895","url":null,"abstract":"<div><h3>Objectives</h3><div>Observing the activities of the elderly in natural life is a crucial issue nowadays to better understand their potential behavioral changes and predict risks. To this end, a comprehensive hardware and software infrastructure has been designed by a multidisciplinary team of researchers and pre-tested in a smart flat lab. It enables to collect relevant data and develop algorithms to analyze activities and detect changes such as falls, wandering or other risky situations. This study was carried out in a shared house by 12 independent elderly people. The study focuses on episodes of falls in the house, and analyzes mobility behavior before and after falls to observe the person's rehabilitation in the home.</div></div><div><h3>Materials and Methods</h3><div>Each resident's room and the two shared spaces were equipped with motion and magnetic contact sensors to record movements and entry/exit activities. 9 months of data were collected and analyzed, highlighting patterns of activity and changes in these behaviors, particularly when a fall occurred and then when the usual behavior returned, if at all. Two levels of analysis were implemented: the detection of deviation in activity indicators for each individual, and the detection of drift in the established behavior pattern over time. The classification technique used to extract the patterns is the K-means partitioning algorithm. We also used the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) method to validate the performance of the K-means method.</div></div><div><h3>Results</h3><div>Data analysis was carried out on the 4 falls recorded during the observation period, involving 4 of the house's occupants. The results highlight the relationship between model conduct and events related to falls and returns from hospitalization. Detection was validated by share house carers' annotations, acting as a ground truth, on the days when falls occurred. The first results of pattern recognition with clustering methods show that the K-means method provides more convincing results than the DBSCAN method. In this study, by observing the movement signals of residents who fell during the course of the study, we were able to identify characteristic post-fall behaviors.</div></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":"46 4","pages":"Article 100895"},"PeriodicalIF":5.6,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144212270","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}

{"title":"Effectiveness of 3D Technology-Assisted Minimally Invasive Surgery for Brainstem Hemorrhage","authors":"Xiaofeng Zhu ,&nbsp;Lei Xia ,&nbsp;Quan Chen ,&nbsp;Jin Shang,&nbsp;Qiang Tong,&nbsp;Jinlong Zheng,&nbsp;Xiangyang Tian,&nbsp;Xiu Yang,&nbsp;Qiu Han","doi":"10.1016/j.irbm.2025.100896","DOIUrl":"10.1016/j.irbm.2025.100896","url":null,"abstract":"<div><h3>Objective</h3><div>This single-center prospective cohort study compared the efficacy of 3D-printed guide plate-assisted minimally invasive puncture and drainage (MIPD) with conservative treatment in managing primary brainstem hemorrhage (PBH).</div></div><div><h3>Methods</h3><div>Between May 2018 to January 2024, 70 PBH patients undergoing 3D-printed guide plate-assisted MIPD at our institution were enrolled as the treatment cohort. Seventy propensity score-matched PBH patients receiving conservative treatment during the same period served as controls. The primary outcome was the proportion of patients achieving a modified Rankin Scale (mRS) score of 1 to 3 at the 90-day follow-up. Secondary outcomes comprised hematoma volume, National Institutes of Health Stroke Scale (NIHSS) scores assessed at admission and post-treatment, and incidence rates of complications (including hospital-acquired pneumonia [HAP], intracranial infection, rebleeding, hydrocephalus, and seizures).</div></div><div><h3>Results</h3><div>At 90 days, significantly more patients in the treatment cohort achieved favorable outcomes (mRS 1-3: 41.4% vs 22.9%, <span><math><mi>P</mi><mo>=</mo><mn>0.03</mn></math></span>). Postoperative hematoma volumes and NIHSS scores were significantly reduced in the treatment cohort compared to the control cohort (both <span><math><mi>P</mi><mo>&lt;</mo><mn>0.05</mn></math></span>). The treatment cohort had significantly lower incidence of HAP (11.4% vs 28.6%, <span><math><mi>P</mi><mo>=</mo><mn>0.02</mn></math></span>) and intracranial infection (1.4% vs 11.4%, <span><math><mi>P</mi><mo>=</mo><mn>0.039</mn></math></span>). No significant between-group differences were found in rebleeding, hydrocephalus, or seizure rates (all <span><math><mi>P</mi><mo>&gt;</mo><mn>0.05</mn></math></span>).</div></div><div><h3>Conclusion</h3><div>3D-printed guide plate-assisted MIPD demonstrates superior efficacy over conservative treatment for PBH. This approach provides rapid hematoma clearance, mitigates neurological deficits, and reduces HAP and intracranial infection risks, translating to lower mortality and disability, supporting broader clinical implementation pending multicenter validation.</div></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":"46 4","pages":"Article 100896"},"PeriodicalIF":5.6,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144203683","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}

{"title":"Characterization and In Vivo Evaluation of Phosphate-Based Glass/TiO2 for Skull Prosthetic Application","authors":"Ana Lucía Sánchez-Alfonso ,&nbsp;Lorena Gaytán-Tocavén ,&nbsp;Luz Elena Alcantara-Quintana ,&nbsp;Raul Gerardo Paredes ,&nbsp;Criseida Ruiz-Aguilar","doi":"10.1016/j.irbm.2025.100899","DOIUrl":"10.1016/j.irbm.2025.100899","url":null,"abstract":"<div><h3>Objectives</h3><div>Skull defects as a consequence of tumors, congenital anomalies, decompressive craniectomies, and skull fractures are a problem that led to the development of the present study. The need to find a biomaterial that can stimulate and promote the healing of skull bone tissue, thereby achieving rapid and complete recovery from the injury, helps improve the patient's quality of life. Bioactive glasses are materials with excellent biological characteristics, including bioactivity, biocompatibility, resorbability, and the ability to promote cell adhesion and osseointegration. The present investigation aimed to evaluate the chemical composition of phosphate-based bioactive glass (45P₂O₅<img>30CaO<img>24Na₂O<img>1TiO₂, mol%) in Wistar rats for skull prostheses applications.</div></div><div><h3>Materials and Methods</h3><div>The experimental methodology involves creating a cranial defect in two groups (control and experimental) by forming trephines in the skulls of Wistar rats and implanting the prosthesis in the trephines in the experimental group. Subjects underwent motor and cognitive-behavioral tests over a four-month period to analyze the prosthetic's potential side effects on the brain. The physical, chemical, and biological characterization techniques of both cranial and brain tissue were used, including X-ray diffraction, Scanning Electron Microscopy, Elemental analysis by energy dispersive spectroscopy, Histological evaluation of skull tissue, Alacian Blue Staining Method, and Histological evaluation of brain tissue.</div></div><div><h3>Results</h3><div>the authors found hydroxyapatite precipitations on the implant surface from the first-month post-surgery, contrary to the control group, where precipitations began to appear in the third month after surgery. The implant facilitated bone tissue regeneration without compromising motor capabilities or associative learning.</div></div><div><h3>Conclusions</h3><div>The present investigation supports the application of a skull prosthesis made of bioactive glass, which exhibits excellent physical, chemical, and biological properties, demonstrating adequate osteoinduction, osteoconduction, and bone cell adhesion, without presenting adverse reactions in the brain.</div></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":"46 4","pages":"Article 100899"},"PeriodicalIF":5.6,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144203684","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}

{"title":"Hydrodynamic Alterations Produced by Subaortic Membranes: An in Vitro Study","authors":"Sofia Di Leonardo ,&nbsp;Danila Vella ,&nbsp;Calogera Pisano ,&nbsp;Vincenzo Argano ,&nbsp;Gaetano Burriesci","doi":"10.1016/j.irbm.2025.100897","DOIUrl":"10.1016/j.irbm.2025.100897","url":null,"abstract":"<div><h3>Background</h3><div>Subaortic stenosis is an aortic disease characterised by the presence of a membrane located at the aortic valve inlet, that causes a sudden reduction of the inflow lumen. The membrane develops as a tissue growth of variable thickness that can cause a major increase in the pressure gradient. In this case, when diagnosed, it is removed by surgical resection.</div></div><div><h3>Methods</h3><div>To investigate the haemodynamic alteration introduced by subaortic membranes, an <em>in vitro</em> study was designed and performed. Stiff and flexible membranes were implanted at the inlet of a bioprosthetic control valve. These mock membranes had different radial and angular alignment, modelling concentric and eccentric orifice positions. For each configuration, a range of different membrane extensions was studied, progressively reducing the orifice area at the inlet of the control valve.</div></div><div><h3>Results</h3><div>Analysis of the hydrodynamic performances indicates that the detrimental effect of subaortic membranes becomes significant when the membrane orifice areas reduce below 75% of the unobstructed inflow lumen. Video analysis of the valve leaflets dynamics indicates that, together with a worsening in the systolic pressure gradient, the presence of subaortic membranes increases cusps fluttering. As the membrane orifice area reduces, leaflets experience faster oscillation frequencies at decreasing amplitudes.</div></div><div><h3>Conclusions</h3><div>The fibromuscular or thin nature of the membrane has a significant role on the severity of the pathology, with higher stiffnesses generally producing worse hydrodynamics. The orifice dimension and position are also important on the systolic performance and can determine potential structural degradation and haematic damage.</div></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":"46 4","pages":"Article 100897"},"PeriodicalIF":5.6,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144203678","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}

{"title":"Enhancing Precision and Personalization in Surgical Management of Osteogenesis Imperfecta Through Advanced Technologies: A Case Study","authors":"Yary Volpe ,&nbsp;Simone Lazzeri","doi":"10.1016/j.irbm.2025.100900","DOIUrl":"10.1016/j.irbm.2025.100900","url":null,"abstract":"<div><h3>Background and Objective</h3><div>The paper aims to demonstrate the integration of advanced technologies, including computed tomography (CT), computer-aided design (CAD), and additive manufacturing, for precise surgical planning and personalized solutions in the management of Osteogenesis Imperfecta (OI). The main research question is to determine how these technologies can be utilized to achieve successful surgical outcomes in severe cases of OI, such as the one presented in this study.</div></div><div><h3>Methods</h3><div>The study involved an 11-year-old child with OI who suffered from a closed right diaphyseal femur fracture and severe lower extremity abnormalities. Virtual and physical planning procedures were carried out using CAD software based on patient-specific CT models. The length of the proximal and distal segments, cutting planes, and osteotomies were precisely defined to achieve the desired surgical corrections. Additionally, 3D models of the bones and bony segments were manufactured using additive manufacturing to physically recreate the surgical procedure.</div></div><div><h3>Results</h3><div>The surgical treatment involved the correction of the right femur fracture and the left tibia and fibula in the first procedure, followed by the correction of the remaining segments in a second procedure. The Fassier-Duval telescopic intramedullary nail was used to stabilize the fracture and the osteotomy sites. The entire treatment course, from the first surgery to achieving partial weight-bearing, spanned approximately 15 weeks, including the two surgical procedures and staged rehabilitation. Post-surgery, the patient showed significant functional improvement, including the ability to stand and walk with assistance.</div></div><div><h3>Conclusion</h3><div>The integration of advanced technologies in surgical planning for OI patients has shown promising results, leading to improved patient outcomes and reduced complications. This approach has the potential to enhance the accuracy of preoperative planning and provide personalized and precise solutions, ultimately elevating the overall quality of healthcare for OI patients.</div></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":"46 4","pages":"Article 100900"},"PeriodicalIF":5.6,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144190184","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}

{"title":"Virtual Surgical Planning/3D Printing for the Management of Severely Comminuted Mandibular Fractures","authors":"Ning Zhao ,&nbsp;Fu-Chen Wang ,&nbsp;Hao-Ran Zhao ,&nbsp;Ling-Fa Xue ,&nbsp;Wen-Lin Xiao","doi":"10.1016/j.irbm.2025.100894","DOIUrl":"10.1016/j.irbm.2025.100894","url":null,"abstract":"<div><h3>Objectives</h3><div>Severely comminuted mandibular fractures present significant challenges due to the loss of spatial orientation of bone fragments, making precise reduction difficult. Traditional methods rely heavily on the surgeon's experience, often leading to suboptimal outcomes. Virtual surgical planning (VSP) and 3D printing have emerged as innovative tools to enhance surgical precision and efficiency in complex maxillofacial cases. This study aimed to evaluate the efficacy of VSP and 3D printing in achieving accurate reduction and fixation of severely comminuted mandibular fractures, using customized surgical guides and pre-bent titanium plates.</div></div><div><h3>Material and Methods</h3><div>Five patients with severely comminuted mandibular fractures were included. Preoperative computed tomography (CT) data were imported into MIMICS software for VSP, where fracture fragments were virtually aligned. Short-segment drilling guides (SSDGs) and a horseshoe-shaped reduction guide (HSRG) were designed using 3-Matic software and 3D printed. Intraoperatively, SSDGs were used to drill screw holes, and HSRG, along with pre-bent titanium plates, facilitated precise reduction and fixation of bone fragments. Postoperative outcomes were assessed using 3D CT scans, and mandibular parameters were compared between preoperative VSP and postoperative data.</div></div><div><h3>Results</h3><div>All five patients achieved successful reduction with satisfactory mandibular contour and occlusal relationships at three months postoperatively. There were no significant differences in mandibular parameters (CoD, GoL-GoR, ΔGo-Me, ∠GoL-Me-GoR, and Δ∠Co-Go-Me) between preoperative VSP and postoperative measurements (p &gt; 0.05). The average number of fracture fragments per patient was 8.8, with an average operation time of 169 minutes.</div></div><div><h3>Conclusions</h3><div>VSP combined with 3D printing offers a reliable and precise method for managing severely comminuted mandibular fractures. This approach reduces surgical complexity, enhances accuracy, and provides excellent functional and aesthetic outcomes, making it a valuable tool for complex mandibular fracture management.</div></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":"46 4","pages":"Article 100894"},"PeriodicalIF":5.6,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144083658","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}

{"title":"Finite Element Analysis of Knee Implant Materials Under Cyclic Loading Condition: An Analysis of Failures","authors":"Deepak Kumar,&nbsp;Rina Maiti","doi":"10.1016/j.irbm.2025.100893","DOIUrl":"10.1016/j.irbm.2025.100893","url":null,"abstract":"<div><h3>Objectives</h3><div>This study aims to evaluate the mechanical performance of knee implant materials under cyclic loading conditions using Finite Element Methods (FEM). The analysis focuses on three commonly used femoral and tibial component materials: Co-Cr-Mo alloy, Stainless Steel (ISO 5832-1), and Titanium alloy (ISO 5832-2). A plastic cushion of ultra-high molecular weight polyethylene (UHMWPE) is used consistently across all material combinations. The goal is to determine the optimal material for minimizing stress and deformation under n number (millions) of cyclic loading conditions.</div></div><div><h3>Methods</h3><div>Finite element analysis (FEA) was conducted using ABAQUS to simulate the mechanical performance of the knee implant materials under cyclic loading conditions. The applied loading conditions varied from 700 N to 3500 N, corresponding to the vertical ground reaction and gait cycle forces. The three metallic materials were analysed with UHMWPE to assess contact pressure distribution and wear of PE component after n numbers of cycles.</div></div><div><h3>Results</h3><div>The analysis showed that Co-Cr-Mo alloy exhibited the least stress 13 MPa and deformation 0.17 mm among the three materials. Paired with PE, it has the least contact pressure, 0.8 MPa, and the wear rate of PE is 0.116 mm/million cycles. Titanium alloy and Stainless Steel (ISO 5832-1) showed higher stress and deformation, indicating lower durability under cyclic loading.</div></div><div><h3>Conclusion</h3><div>These findings highlight Co-Cr-Mo alloy as the optimal material for knee implants, enhancing mechanical stability and longevity. This selection minimizes failure rates and revision surgeries.</div><div>Future work includes experimental validation and advanced modelling to refine computational findings and develop patient-specific implants.</div></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":"46 3","pages":"Article 100893"},"PeriodicalIF":5.6,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143917562","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}

{"title":"Multi-Task Hierarchical Model of Medical Images Based on Alternate Interaction","authors":"Yucheng Song ,&nbsp;Chenxi Li ,&nbsp;Kangxu Fan ,&nbsp;Lifeng Li ,&nbsp;Jia Guo ,&nbsp;Muhammad Ayoub ,&nbsp;Zhifang Liao ,&nbsp;Yitao Zuo","doi":"10.1016/j.irbm.2025.100892","DOIUrl":"10.1016/j.irbm.2025.100892","url":null,"abstract":"<div><div>In the field of medical image segmentation and classification, deep learning models can automatically extract features and perform high-performance inference, thus aiding physicians in efficient and accurate automated decision support. However, these models are typically trained for a single task, leading to limitations such as neglect of task relevance and poor scalability. To address these issues, we propose a novel Alternating Multi-Task Hierarchical Network (AMTH-Net) for medical image segmentation and classification. This model is divided into three hierarchical modules: Pathology Region Clarity (PRC) as an auxiliary module to enhance the capabilities of segmentation and classification, Multi-Resolution Attention (MRA) segmentation module that uses deep supervision to focus on image information at various resolution levels to improve segmentation accuracy, and Cascaded Multi-Scale Information (CMSI) classification module which employs a cascaded multi-scale mechanism to gradually integrate discrete information from different network layers, thereby enhancing classification performance. Additionally, we introduce a novel Alternating Interaction Loss (AI-Loss) based on Multi-Gradient Information Feedback (MGIF) algorithm to further enhance the model's segmentation and diagnostic performance. Our experiments on the COVID CXR and F BUSI Breast Ultrasound datasets show that AMTH-Net achieves superior performance in both segmentation and classification tasks. Specifically, on the COVID chest X-ray (COVID CXR) dataset, the Dice coefficient of AMTH-Net reaches 98.33%, the Intersection over Union (IOU) is 96.31%, and the accuracy rate is 91.49%, outperforming existing methods in terms of performance. On the F BUSI dataset, its Dice coefficient is 96.76%, the Intersection over Union (IOU) is 95.92%, and the accuracy rate is 95.87%, surpassing other methods once again. These results confirm the effectiveness and superiority of the model we proposed.</div></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":"46 3","pages":"Article 100892"},"PeriodicalIF":5.6,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143887945","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}

{"title":"MISA-Net: A Multi-Scale Feature Interaction Network for Brain Tumor Segmentation","authors":"Xiaobao Liu ,&nbsp;Junfeng Xia ,&nbsp;Wenjuan Gu ,&nbsp;Tingqiang Yao ,&nbsp;Jihong Shen ,&nbsp;Dan Tang","doi":"10.1016/j.irbm.2025.100891","DOIUrl":"10.1016/j.irbm.2025.100891","url":null,"abstract":"<div><h3>Background and Objective</h3><div>Accurate segmentation of brain tumor images is crucial in medical auxiliary diagnosis. However, the complex morphology and ambiguous boundary contours of brain tumors pose significant challenges to precise segmentation.</div></div><div><h3>Methods</h3><div>To address these issues, we developed MISA-Net, which is based on enhanced multi-scale feature interactions and selective feature fusion attention. Initially, a Multi-Scale Feature Interaction (MSFI) module was implemented to enhance the interaction between features at different scales, resolving issues of misclassification in regions with complex tumor morphologies. Subsequently, a Selective Feature Fusion Attention (SFFA) mechanism was introduced to reduce the interference of redundant information in skip connections on crucial features.</div></div><div><h3>Results</h3><div>Experiments on the BraTS 2019 dataset show that MISA-Net achieved Dice coefficients of 80.02%, 88.86%, and 86.02% in the enhancing, core, and whole tumor areas, respectively. Additionally, the Dice coefficient for the whole tumor area impressively reached 90.33% on the Kaggle LGG dataset; the Dice coefficient for the whole tumor area impressively reached 84.97% on the Figshare dataset.</div></div><div><h3>Conclusions</h3><div>Compared to existing mainstream models, MISA-Net demonstrates superior performance in brain tumor segmentation tasks, highlighting its potential and advantages in clinical diagnosis and treatment.</div></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":"46 3","pages":"Article 100891"},"PeriodicalIF":5.6,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143917561","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}