Computer methods and programs in biomedicine最新文献

{"title":"Reducing the spring-back force of the aortic stent graft — decreasing the risk of stent graft-induced new entry","authors":"Meixuan Li ,&nbsp;Tao Ma ,&nbsp;Jianming Li ,&nbsp;Zhuangyuan Meng ,&nbsp;Yunhan Cai ,&nbsp;Chen Peng ,&nbsp;Shengzhang Wang","doi":"10.1016/j.cmpb.2025.108993","DOIUrl":"10.1016/j.cmpb.2025.108993","url":null,"abstract":"<div><h3>Objective</h3><div>This study utilized patient-specific model to quantitatively analyze, from a mechanical perspective, the impact of reducing the spring-back force of the stent graft on the proximal and distal landing zones of the aorta after thoracic endovascular aortic repair (TEVAR).</div></div><div><h3>Methods</h3><div>A patient-specific aortic dissection (AD) model was established based on preoperative computed tomography angiogram (CTA) images. The stent graft structure, according to the stent graft actually used by the patient, was optimized to reduce spring-back force using the Isight (Dassault Systèmes, France) optimization design platform, in combination with the Kriging model and Non-dominated sorting genetic algorithm (NSGA-II). The final optimized stent graft was virtually implanted into the patient’s aorta and compared with the original stent graft to analyze, from a mechanical perspective, the impact of reducing the spring-back force of the stent graft on the proximal and distal landing zones after TEVAR.</div></div><div><h3>Results</h3><div>In the proximal landing zone, the peak value of maximum principal stress caused by the final optimized stent graft was 257.0 KPa, a 1.5 % reduction compared to the original stent graft. In the distal landing zone, the peak value of maximum principal stress was 148.7 KPa, a 19.9 % reduction compared to the original stent graft. The reduction in peak maximum principal stress in the distal landing zone was much greater than in the proximal landing zone. Before and after optimization, the location of the peak value of maximum principal stress in the distal landing zone remained at the boundary of the intima flap and was located on the greater curvature of the aorta.</div></div><div><h3>Conclusion</h3><div>Reducing the spring-back force of the stent graft can decrease the stress on the proximal and distal landing zones of the aorta, thereby reducing the risk of stent graft-induced new entry.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"271 ","pages":"Article 108993"},"PeriodicalIF":4.8,"publicationDate":"2025-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144750544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Combining tumor habitat radiomics and circulating tumor cell data for predicting high-grade pathological components in lung adenocarcinoma","authors":"Hongchang Wang ,&nbsp;Yan Gu ,&nbsp;Gao Wu ,&nbsp;Yunqiang Yang ,&nbsp;Wenhao Zhang ,&nbsp;Guang Mu ,&nbsp;Wentao Xue ,&nbsp;Chenghao Fu ,&nbsp;Yang Xia ,&nbsp;Liang Chen ,&nbsp;Mei Yuan ,&nbsp;Jun Wang","doi":"10.1016/j.cmpb.2025.108986","DOIUrl":"10.1016/j.cmpb.2025.108986","url":null,"abstract":"<div><h3>Objectives</h3><div>Lung cancer is the leading cause of cancer incidence and mortality. Early surgical resection significantly improves patient prognosis. Studies have shown that high-grade components in lung adenocarcinoma (LUAD) severely impact patient outcomes. Therefore, early prediction of these high-grade components is crucial for clinical surgical decision-making.</div></div><div><h3>Methods</h3><div>We delineated tumor subregions using k-means clustering and excluded features with low reproducibility by calculating the intraclass correlation coefficient (ICC). Stratified sampling ensured a consistent sample distribution between the training and testing datasets, and Borderline synthetic minority over-sampling technique (BorderlineSMOTE) addressed the data imbalance in the training dataset. Normality tests were conducted, followed by feature selection using independent sample t tests, Mann‒Whitney U tests, and Spearman rank correlation. Principal component analysis (PCA) of reduced dimensionality and model integration were performed using a stacking approach. Model predictive performance was evaluated using the area under the curve (AUC), and significant differences between models were assessed using the DeLong test.</div></div><div><h3>Results</h3><div>The combined Habitat-circulating tumor cell (CTC) model showed the best predictive performance for high-grade components in both the training and validation datasets, achieving AUCs of 0.98 [95 % CI: 0.95–1.00] and 0.91 [95 % CI: 0.82–1.00], respectively. In the training dataset, the combined model's AUC of 0.98 [95 % CI: 0.95–1.00] was notably higher than that of the single CTC model, which achieved an AUC of 0.75 [95 % CI: 0.64–0.85], and the single sub-region model, which had an AUC of 0.94 [95 % CI: 0.88–1.00]. Decision-curve analysis demonstrated maximal net benefit at threshold probabilities of 0.2–0.4. In the independent cohort (n = 29), AUC reached 1.00 [95 % CI: 1.00–1.00].</div></div><div><h3>Conclusion</h3><div>Combining habitat radiomics and CTC-related clinical models allows for more precise prediction of high-grade pathological components, aiding in clinical preoperative decision-making.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"271 ","pages":"Article 108986"},"PeriodicalIF":4.8,"publicationDate":"2025-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144780797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interpretable epidemic state estimation via rule based modeling","authors":"Giulio Pisaneschi ,&nbsp;Francesco Paolo Salzo ,&nbsp;Pierpaolo Serio ,&nbsp;Witold Pedrycz","doi":"10.1016/j.cmpb.2025.108963","DOIUrl":"10.1016/j.cmpb.2025.108963","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>Epidemiological data is, by its very own nature, associated with noise and incompleteness, posing a significant challenge to extracting meaningful insights. To address this limitation, we propose a novel framework that seamlessly integrates fuzzy logic and machine learning techniques to provide a reliable understanding of the aforementioned data. Fuzzy logic, with its inherent ability to handle vagueness and imprecision, proves invaluable in interpreting noisy epidemiological data.</div></div><div><h3>Methods:</h3><div>Our approach introduces a novel perspective by departing from a dynamical epidemic model, which encodes comprehensive prior knowledge of epidemic dynamics, to create a credible context for our predictive task. This facilitates model’s outputs interpretability, while maintaining its credibility. Within this environment, we aim to detect relevant parts of the system state that are implicitly encoded in other state variables, by looking at observable variables of the epidemic state.</div></div><div><h3>Results:</h3><div>The Takagi–Sugeno model demonstrated robust predictive accuracy across varying Signal-Noise Ratio levels, achieving comparable performance to neural networks while maintaining interpretability, with significant advantages in noisy data scenarios, as evidenced by lower Root Mean Squared Errors under worst-case conditions (low SNRs).</div></div><div><h3>Conclusions:</h3><div>This study introduces a robust and interpretable hybrid framework for epidemic forecasting, demonstrating reliable estimation of the effective reproduction number through fuzzy clustering and Takagi–Sugeno modeling, even under noisy conditions. The method effectively addresses data uncertainty and demonstrates strong performance under noisy conditions, offering a promising approach for applications requiring both transparency and reliability in predictive modeling.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"271 ","pages":"Article 108963"},"PeriodicalIF":4.8,"publicationDate":"2025-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144720885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TEANet: Automated tooth extraction and arrangement with tooth-level graph spatial transformation network","authors":"Xiaoshuang Li ,&nbsp;Miri Chung ,&nbsp;Lei Bi ,&nbsp;Jialiang Huang ,&nbsp;Yichen Pan ,&nbsp;Dagan Feng ,&nbsp;Dong Chen ,&nbsp;Bin Sheng ,&nbsp;Jinman Kim ,&nbsp;Lingyong Jiang","doi":"10.1016/j.cmpb.2025.108985","DOIUrl":"10.1016/j.cmpb.2025.108985","url":null,"abstract":"<div><h3>Background and objective</h3><div>Orthodontic treatment is a process that involves tooth extraction and arrangement achieved via mesh-based analysis and rigid deformation of teeth. The aim is to achieve balanced relationship in physiologic and aesthetic harmony among cranial structures and occlusion. Existing automated treatment planning methods elaborated point cloud for 3D analysis and utilized Graph Convolutional Network (GCN) for feature propagation. However, these techniques were designed specifically for cases not requiring extraction therefore have limited accuracy for dentition crowding cases that require tooth extraction.</div></div><div><h3>Methods</h3><div>Motivated by these challenges, we propose Tooth Extraction &amp; Arrangement Network (TEANet), an automated treatment planning method that enables tooth arrangement including cases requiring tooth extraction. The novelty we introduce is a double-coordinate classifier for tooth extraction and an adaptive graph for tooth arrangement. Our method makes the following contributions: (1) We introduce an orthodontic extraction classification for full-mouth point cloud that includes multiple tooth subsets; (2) We design a node-erasable adaptive graph to represent interactions (edges) among teeth (nodes) for feature propagation in GCN; and (3) We introduce a learning-based 3D spatial transformer model with GCN to produce tooth arrangement planning for extraction cases.</div></div><div><h3>Results</h3><div>We evaluated our method on three tasks in orthodontic treatment (tooth classification, extraction classification and tooth arrangement regression) with a total of 304 clinical cases. Our method achieved consistent and better performance than the state-of-the-art methods. The dataset will be released upon publication.</div></div><div><h3>Conclusion</h3><div>TEANet offers a novel and robust framework for orthodontic treatment planning, particularly in cases that require tooth extraction. By leveraging a double-coordinate classifier, an adaptive graph, and a learning-based spatial transformer with GCN, TEANet outperforms existing methods and provides an efficient solution for handling complex orthodontic cases.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"271 ","pages":"Article 108985"},"PeriodicalIF":4.8,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144739485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computational fluid dynamics analysis of the effect of ureteral access sheath positioning on stone clearance rates","authors":"Yujun Chen,&nbsp;Heng Yang,&nbsp;Xiaofeng Cheng,&nbsp;Haibo Xi,&nbsp;Yue Yu,&nbsp;Wen Deng,&nbsp;Gongxian Wang,&nbsp;Xiaochen Zhou","doi":"10.1016/j.cmpb.2025.108978","DOIUrl":"10.1016/j.cmpb.2025.108978","url":null,"abstract":"<div><h3>Background and objective</h3><div>Standardized protocols for optimal ureteral access sheath (UAS) positioning during flexible ureterorenoscopy (f-URS) lithotripsy have yet to be established. This study utilizes computational fluid dynamics (CFD) techniques to analyze the impact of varying UAS positions on stone clearance rates, aiming to identify the optimal UAS position for enhanced stone fragment evacuation.</div></div><div><h3>Materials and methods</h3><div>Various f-URS models were created using ANSYS SpaceClaim software. These models were then imported into ANSYS Fluent for meshing and computational simulation. The study evaluated the impact on stone clearance rates as the UAS was incrementally advanced towards the distal end of the f-URS, also observing the effects on local irrigation flow velocity at different UAS positions.</div></div><div><h3>Results</h3><div>Three models were constructed to simulate stone positions within the renal pelvis, lower calyx, and middle calyx. Each model generated 80 stone particles. In the middle calyx model, the numbers of particles evacuated were 32, 53, 58, and 67 for UAS positions A, B, C, and D, respectively. In the lower calyx model, particle clearance was 15, 21, 37, and 46 for UAS positions A, B, C, and D, respectively. In the renal pelvis model, particle evacuation was 14, 18, 31, and 61 for UAS positions A, B, C, and D, respectively. Position D represents the alignment of the UAS tip flush with the f-URS tip. Stones were deposited in the lower calyx by gravity. Contour plots and vector displays showed the highest irrigation velocity in the UAS and f-URS channels, with a relative low-flow region between the UAS and f-URS tips. When the UAS and f-URS tips were aligned, this low-flow region substantially disappeared.</div></div><div><h3>Conclusions</h3><div>Ureteral access sheath positioning significantly correlates with stone clearance rates. Maximal stone particle evacuation occurred when the distal tips of the UAS and f-URS were aligned. Variations in UAS position resulted in changes in local irrigation velocity.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"271 ","pages":"Article 108978"},"PeriodicalIF":4.8,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144739484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An EIT-based assessment of regional ventilation delay under incremental PEEP: Influence of sex, smoking, vaping, asthma, and BMI","authors":"Rongqing Chen ,&nbsp;Ella F.S. Guy ,&nbsp;Jaimey A. Clifton ,&nbsp;J. Geoffrey Chase ,&nbsp;Stefan J. Rupitsch ,&nbsp;Knut Moeller","doi":"10.1016/j.cmpb.2025.108992","DOIUrl":"10.1016/j.cmpb.2025.108992","url":null,"abstract":"<div><h3>Background and Objective</h3><div>Therapies such as positive airway pressure (PAP), which maintain positive end-expiratory pressure (PEEP) settings, are widely used in the management of respiratory diseases. However, most research has focused on patient outcomes, such as oxygenation, mortality rates, or ventilator-free days. There is a lack of focus on lung-specific responses, for example, atelectasis rate or aeration heterogeneities. This study aims to use Electrical Impedance Tomography (EIT) to investigate variations in lung aeration heterogeneity with increasing PEEP and how factors such as sex, smoking/vaping history, asthma, and BMI influence lung aeration dynamics.</div></div><div><h3>Methods</h3><div>Eighty participants were recruited and categorized into four groups: asthmatics, smokers, vapers, and healthy individuals. Each group comprises 20 subjects evenly distributed by sex (10 females and 10 males). Varying PEEP was applied on each subject during the trial, which began at zero end-expiratory pressure (ZEEP) and subsequently increased from 4 to 12 cmH₂O on non-invasive ventilation (NIV). EIT data were collected at each pressure level. Lung aeration heterogeneity was assessed using regional ventilation delay (RVD), a promising metric derived from EIT data for evaluating lung-specific responses to mechanical ventilation. RVD and its standard deviation (SDRVD) of each subject were calculated accordingly at ZEEP and the highest PEEP level.</div></div><div><h3>Results</h3><div>Results demonstrated that female participants exhibited a significant increase in RVD when pressure was elevated from ZEEP to higher levels, whereas male participants showed no such significant change. Overweight subjects experienced no significant alterations in RVD under highest PEEP, whereas non-overweight subjects showed significantly increased RVD under higher pressure levels. Vaping was associated with a statistically significant increase in RVD when pressure was at the highest PEEP level, whereas no significant RVD changes were observed among smokers or subjects with mild asthma within this relatively young population.</div></div><div><h3>Conclusions</h3><div>These findings emphasize the importance of considering individualized factors when optimizing respiratory therapy, including sex and BMI. These factors significantly influence regional lung aeration and ventilation dynamics, and play important roles in optimising mechanical ventilation settings, which could potentially enhance therapeutic effectiveness and patient outcomes.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"271 ","pages":"Article 108992"},"PeriodicalIF":4.8,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144723020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrative approach for early detection of Parkinson’s disease and atypical Parkinsonian syndromes leveraging hemodynamic parameters, motion data & advanced AI models","authors":"Rishit Singh ,&nbsp;Yugnanda Malhotra ,&nbsp;Jolly Parikh","doi":"10.1016/j.cmpb.2025.108989","DOIUrl":"10.1016/j.cmpb.2025.108989","url":null,"abstract":"<div><h3>Background and objective</h3><div>Parkinson's disease (PD) and other atypical Parkinsonian syndromes, including Multiple Systems Atrophies (MSAs) and Progressive Supranuclear Palsies (PSPs) are progressive neurodegenerative disorders that are often present with motor and non-motor symptoms. Early stage diagnosis is crucial to initiate timely intervention and manage disease progression while mitigating patient health. This study proposes a wearable, multi-modal sensor driven framework integrated with AI models for accurate classification of PD.</div></div><div><h3>Methods</h3><div>A multi sensor hardware platform is developed incorporating photoplethysmography (PPG), Heart Rate Variability (HRV) using MAX30102 for peripheral oxygen saturation and perfusion along with, temperature sensor (DS18B20) and inertial sensor (MPU6050), to detect tremor amplitudes, rigidity and bradykinesia. Data is collected from real time recording and publicly available datasets. Using a set of preprocessing filters, relevant temporal and statistical features are extracted to train a Multi-Layer Perceptron (MLP) &amp; ensemble model enabling AI and deep learning classifiers. The model is trained using deep learning techniques and evaluated using stratified k-fold class validation. Model performance is assessed using accuracy, precision, sensitivity and specificity metrics.</div></div><div><h3>Results</h3><div>The proposed model demonstrated high diagnostic performance. The ensemble classifier achieved over 96% accuracy in identifying early stage PD symptoms, while the ensemble classifier presented with an accuracy of over 96.7%. The models consistently reported over 95% accuracy with minimal variance across folds, confirming robustness across datasets and sensor modalities.</div></div><div><h3>Conclusion</h3><div>The novel integration of multi modal physiological and hemodynamic parameters amalgamating AI algorithms offer a scalable, remote and non-invasive approach to early detection of Parkinson’s disease and other atypical Parkinsonian syndromes. The proposed framework demonstrated key potential for clinical transition with implication for improving timeline of patient diagnoses, reduction in healthcare burden and costs along with enhancing patient quality of life and outcome.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"271 ","pages":"Article 108989"},"PeriodicalIF":4.8,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144750696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Shape-aware inference scheme for selective extraction of head-neck arteries on computer tomography angiography images","authors":"Markus Tiefenthaler ,&nbsp;Stephanie Mangesius ,&nbsp;Sergiy Pereverzyev Jr. ,&nbsp;Elke Ruth Gizewski ,&nbsp;Lukas Neumann","doi":"10.1016/j.cmpb.2025.108952","DOIUrl":"10.1016/j.cmpb.2025.108952","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>The extraction of head-neck blood vessels from 3D medical images plays a vital role in diagnosing vascular diseases. While many existing methods rely on convolutional neural networks (CNNs), they can encounter challenges in maintaining the continuity of extracted vessels, particularly when segmenting these slender tubular structures within 3D images. This study aims to address these challenges by introducing a novel inference method that preserves vessel continuity taking into consideration the global geometry of vascular structures, while also reducing the number of high resolution patches being processed.</div></div><div><h3>Methods:</h3><div>The proposed approach employs a two-stage CNN process complimented by a centerline-aware thresholding step. First, a CNN performs preliminary localization of arteries within a highly downsampled volume, identifying seed points. These seed points serve as input for a second CNN, specialized in capturing local artery appearances, to perform precise segmentation. A centerline-based artery tracking algorithm is then applied to guide patch segmentation along the artery until the entire vascular structure is segmented. Physical connectivity is ensured by our novel centerline-aware thresholding strategy which is used to construct the final segmentation mask.</div></div><div><h3>Results:</h3><div>The proposed method effectively reduces the number of high-resolution patches processed by the neural network, thereby not only addressing the issue of class imbalance by primarily concentrating on patches containing arteries but also reducing computational complexity. The performance is comparable to state of the art methods across various metrics, while the algorithm additionally recovers missing segments of falsely interrupted arteries, thereby facilitating automatic extraction of medically relevant quantities like for example artery length. The method requires significantly less memory and performs approximately one-tenth of the computations needed to segment a patient.</div></div><div><h3>Conclusion:</h3><div>The proposed approach offers an effective solution for extracting blood vessels from 3D medical images, overcoming the limitations of traditional CNN-based methods by preserving vessel continuity and addressing the challenge of class imbalance. This approach enables the selective segmentation of specific arteries in a resource-efficient manner, thereby enhancing the diagnosis and treatment of vascular diseases by providing more accurate vascular segmentations.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"270 ","pages":"Article 108952"},"PeriodicalIF":4.9,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144714108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of T2/T3 Staging in Patients with Volume-Equivalent Esophageal Squamous Cell Carcinoma on the Basis of PET/CT Radiomics","authors":"Ang Li ,&nbsp;Junqing Lin ,&nbsp;Lili Lin ,&nbsp;Jianqiang Ye ,&nbsp;Zhongyou Ji ,&nbsp;Han Jiang","doi":"10.1016/j.cmpb.2025.108988","DOIUrl":"10.1016/j.cmpb.2025.108988","url":null,"abstract":"<div><h3>Objectives</h3><div>To develop and externally validate PET/CT-based radiomic models for predicting tumor invasion depth (≤T2 vs. ≥T3) in patients with esophageal squamous cell carcinoma (ESCC) with volume-matched tumors.</div></div><div><h3>Methods</h3><div>Semiautomatic segmentation was performed on ¹⁸F-FDG PET images, and radiomic features were extracted from PET and coregistered CT scans. Feature reproducibility was evaluated with the intraclass correlation coefficient (ICC), which showed excellent agreement (ICC &gt; 0.95). Propensity score matching (PSM) was applied to control for tumor volume and patient demographics. Dimensionality reduction was conducted using principal component analysis (PCA), followed by feature selection via LASSO and MRMR. Logistic regression (LR), linear discriminant analysis (LDA), support vector machine (SVM), and random forest (RF) models were constructed. Model performance was assessed on internal and independent external cohorts.</div></div><div><h3>Results</h3><div>In the internal validation, the PET and combined PET/CT radiomic models outperformed the CT-alone models, with the LDA and LR classifiers achieving area under the ROC curve (AUC) greater than 0.97. In the external validation, only the models based on PET features maintained good predictive performance (LR AUC 0.8438, accuracy 81.25 %; LDA AUC 0.8281, accuracy 87.5 %). Models built on CT or combined PET/CT features failed to produce valid results, defaulting to single-class predictions. PET feature-based models demonstrated stable generalizability across datasets.</div></div><div><h3>Conclusions</h3><div>Radiomic models based on PET features and LDA or LR classifiers can accurately predict tumor invasion depth in patients with volume-equivalent ESCC and show strong external generalizability. CT or combined feature models may not be reliable under stringent tumor volume constraints.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"271 ","pages":"Article 108988"},"PeriodicalIF":4.8,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144720887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Semantic consistency-guided patch-wise relation graph reasoning scheme for lung cancer organoid segmentation in brightfield microscopy","authors":"Tianxu Lv ,&nbsp;Jiansong Fan ,&nbsp;Zexin Chen ,&nbsp;Yuan Liu ,&nbsp;Jianming Ni ,&nbsp;Wei Chu ,&nbsp;Xiang Pan","doi":"10.1016/j.cmpb.2025.108964","DOIUrl":"10.1016/j.cmpb.2025.108964","url":null,"abstract":"<div><h3>Background and Objective</h3><div>: Patient-derived organoids (PDOs) have recently opened new possibilities for personalized precision medicine. Specifically, the segmentation of live PDOs in brightfield microscopy is essential for organoid morphological evaluation, cell viability assays, and drug screening. However, accurately and automatically annotating live organoids remains challenging due to factors such as low contrast, varying organoid characteristics, imaging artifacts, and the scarcity of large-scale annotated datasets. This study aims to address these challenges by proposing an advanced method for live PDOs segmentation even with limited training data.</div></div><div><h3>Methods:</h3><div>We propose a semantic consistency-guided patch-wise relation graph reasoning scheme, which allows local–global semantics extraction, multi-task-based representation refinement and semantic consistency constraint for live PDOs segmentation. Specifically, our approach consists of two input-specific streams designed to extract high-level whole-image local and patch-wise semantic representations. Then a patch-wise relation graph convolution module (PRGCM) is devised to exploit global prior morphological properties by integrating low-level spatial relatedness into patch-wise high-level semantic representations using graph convolution. Subsequently, a local–global semantics fusion module (LGSFM) is deployed to enable local–global contextual semantic fusion. In the decoding stage, we develop two auxiliary learning tasks, with a patch segmentation decoder to guarantee semantic homogeneity by a novel loss function, called stream consistency (SC) loss, along with a reconstruction decoder to capture powerful and discriminative representation without additional annotations.</div></div><div><h3>Results:</h3><div>We introduce LiveOrganoid, a large-scale dataset of manually annotated lung cancer brightfield images, consisting of lung PDOs with diverse morphologies. Our scheme demonstrates superior performance on LiveOrganoid, achieving state-of-the-art results compared to recent methods, even with fewer training data. Additionally, we evaluate our method’s generalization for different imaging modality and other cell-culture segmentation tasks, including cell and nuclear segmentation in tissue images.</div></div><div><h3>Conclusions:</h3><div>Our proposed semantic consistency-guided patchwise relation graph reasoning scheme addresses the challenges in live PDOs segmentation, paving the way for improved organoid morphological evaluation, cell viability assays, and drug screening. The method’s generalizability to other cell-culture segmentation tasks highlights its potential for broader applications in precision medicine.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"271 ","pages":"Article 108964"},"PeriodicalIF":4.8,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144720991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}