International Journal of Biomedical Imaging最新文献

{"title":"Generative AI-Driven CNN Framework for Enhanced Lung Cancer Detection, Prediction, and Treatment: A Novel Approach to Overcoming AI Limitations.","authors":"Siva Sankar Bodicherla, D Natarajasivan, M Purushotham Reddy","doi":"10.1155/ijbi/8726222","DOIUrl":"10.1155/ijbi/8726222","url":null,"abstract":"<p><p>Lung cancer remains one of the most common and deadly diseases globally, necessitating swift and precise detection to enhance patient prognosis. Conventional radiological techniques, including CT scans and X-rays, often exhibit high false positive rates, low sensitivity, and reliance on radiologist interpretation, leading to potential diagnostic inconsistencies. This research presents a generative AI-driven convolutional neural network (CNN) framework aimed at improving lung cancer detection, risk prediction, and treatment planning. The proposed approach integrates deep learning, CNN-based feature extraction, and generative adversarial networks (GANs) for data augmentation, effectively overcoming limitations in AI-powered diagnostics. A dataset comprising lung cancer-patient information, CT scan characteristics, and cancer risk scores was utilized for model training and evaluation. The abstract has been updated to clearly highlight the quantitative improvements, showing an increase in accuracy from 94.5% to 100% and an improvement in AUC from 0.95 to 1.00 compared with existing models. The CNN model extracts crucial features from medical images, whereas GAN-generated synthetic data enhances learning efficiency and robustness. The model was implemented using TensorFlow and Keras, optimized with Adam and trained over 30 epochs, achieving an unparalleled 100% accuracy, precision, recall, and F1-score on the validation dataset. A comparative analysis with state-of-the-art AI methodologies, including Transformers and hybrid deep learning architectures, demonstrated the superior efficacy of the proposed framework. The findings highlight that generative AI significantly refines lung cancer diagnostics by minimizing false positives and optimizing treatment recommendations. The novelty of this work lies in its unified framework that brings together synthetic data generation, advanced feature extraction, attention-based classification, and a probabilistic risk prediction approach into a single system, an integration that has not been comprehensively explored in existing studies. The ROC-AUC score of 1.00 further validates the model's ability to accurately differentiate between malignant and benign cases. Future advancements will focus on clinical deployment, explainable AI (XAI) for improved interpretability, and integration into real-world healthcare systems.</p>","PeriodicalId":47063,"journal":{"name":"International Journal of Biomedical Imaging","volume":"2026 ","pages":"8726222"},"PeriodicalIF":2.3,"publicationDate":"2026-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13191821/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148018023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing the Generalizability of Deep Learning-Based Models for Lung Field Segmentation in Chest Radiographs Using Edge-Assisted Multiscale Feature Fusion.","authors":"Tairah Andrabi, Sajid Yousuf Bhat","doi":"10.1155/ijbi/6566262","DOIUrl":"10.1155/ijbi/6566262","url":null,"abstract":"<p><strong>Introduction: </strong>Lung field segmentation (LFS) in chest x-rays (CXR) is a key step for the computer-assisted diagnosis of respiratory diseases. However, achieving precise delineation remains challenging in images with poor contrast and superimposed anatomical structures, often resulting in imprecise lung outlines in deep learning (DL) models. Furthermore, existing models often lack generalizability, performing well on specific datasets but failing on unseen domains due to variations in imaging equipment, acquisition protocols, and patient demographics.</p><p><strong>Methods: </strong>To overcome these limitations, we propose a two-phase hybrid approach for robust and generalizable LFS in CXR. The first phase employs a heuristic approach to extract and refine multiscale edge features: The Laplacian of Gaussian (LoG) filter detects closed contours that effectively highlight the overall lung shape, whereas the Canny detector captures the finer, high-frequency edge details that preserve the lung outlines often missed by DL models due to overlapping structures. In the second phase, the enriched multiscale feature maps are fused along with the original contrast inputs and then used to train and evaluate various U-Net architectures.</p><p><strong>Results: </strong>The proposed approach is evaluated on three benchmark datasets: Montgomery County (MC), Shenzhen Hospital (SH), and Japanese Society of Radiological Technology (JSRT). Experiments conducted on individual datasets using five-fold cross-validation and testing on a completely unseen separate test set to simulate real-world settings revealed that the proposed edge-assisted filters, especially the Canny filter, significantly improve segmentation performance metrics. Among all U-Net variants, deep attention U-Net achieved the highest performance using a consistent channel combination, attaining a dice coefficient of 0.9815, a Jaccard score of 0.9624 on the JSRT dataset. The proposed approach achieved a dice gain of +0.0011 to +0.0034 and an IoU gain of +0.009 to +0.0034 across the three datasets compared with the baseline configuration using original images. Furthermore, cross-dataset validation also depicted improvement gains in dice, IoU, and other metrics, demonstrating the generalizability of the proposed approach.</p><p><strong>Conclusion: </strong>Further cross-dataset validation confirmed the framework's strong generalization capabilities, demonstrating stable performance even on unseen domains. These findings validate the proposed method as a reliable and effective solution for LFS in diverse and clinically challenging environments, offering promising benefits for respiratory diagnosis and patient care.</p>","PeriodicalId":47063,"journal":{"name":"International Journal of Biomedical Imaging","volume":"2026 ","pages":"6566262"},"PeriodicalIF":2.3,"publicationDate":"2026-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13150971/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147870003","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Personalized PET Imaging in Gastric Cancer: An Umbrella Review of Meta-Analyses to Guide Radiopharmaceutical Selection and Clinical Indication.","authors":"Aiganym Amrenova, Alma Shukirbekova, Sholpan Akhelova, Jamilya Assilbayeva, Andrey Gurin, Maira Mukazhanova, Bibigul Kaliyaskarova, Asset Sarsekeyev, Nadiar M Mussin, Amin Tamadon","doi":"10.1155/ijbi/3450212","DOIUrl":"10.1155/ijbi/3450212","url":null,"abstract":"<p><strong>Background: </strong>Gastric cancer remains a leading cause of cancer-related morbidity and mortality worldwide, and accurate imaging is critical for diagnosis, staging, recurrence detection, and prognostic assessment. Positron emission tomography (PET), traditionally performed using ¹⁸F-fluorodeoxyglucose (FDG), has demonstrated variable performance in gastric cancer, particularly for nodal and peritoneal disease. Recently, ⁶⁸Ga-labeled fibroblast activation protein inhibitor (FAPI) PET has emerged as a promising alternative, prompting multiple systematic reviews and meta-analyses with heterogeneous findings.</p><p><strong>Objective: </strong>We are aimed at synthesizing and appraise meta-analytic evidence on PET imaging in gastric cancer, with a focus on radiopharmaceutical-specific performance by clinical indication and certainty of evidence to inform personalized tracer selection.</p><p><strong>Methods: </strong>An umbrella review was conducted in accordance with PRISMA 2020. The protocol was prospectively registered in the Open Science Framework (OSF). PubMed, Scopus, and Web of Science were searched from inception to December 2025 for systematic reviews and meta-analyses evaluating PET imaging in gastric cancer. Outcomes included diagnostic accuracy, staging and restaging performance, recurrence detection, prognostic associations, methodological quality (AMSTAR-2), and certainty of evidence (GRADE).</p><p><strong>Results: </strong>Eleven meta-analyses published between 2011 and 2025 were included. FDG PET/CT demonstrated moderate diagnostic performance overall, with high specificity but limited sensitivity for lymph node and peritoneal metastases, while retaining moderate certainty for prognostic assessment based on standardized uptake value (SUV)-derived metrics. In contrast, ⁶⁸Ga-FAPI PET generally showed higher pooled sensitivity than FDG for primary tumor detection, nodal disease, peritoneal metastases, and recurrence detection across available meta-analyses, although the certainty of evidence ranged from low to moderate and some findings were derived from mixed-population reviews.</p><p><strong>Conclusions: </strong>Available meta-analytic evidence suggests an indication-driven, personalized approach to PET imaging in gastric cancer. FDG PET remains useful for prognostic stratification and selected recurrence settings, whereas FAPI PET appears to offer higher diagnostic sensitivity for staging and restaging, particularly for peritoneal disease. Nevertheless, the overall certainty of evidence remains limited by heterogeneity, indirectness, and the absence of updated de novo pooled analyses.</p>","PeriodicalId":47063,"journal":{"name":"International Journal of Biomedical Imaging","volume":"2026 ","pages":"3450212"},"PeriodicalIF":2.3,"publicationDate":"2026-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13131056/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147822086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clinician-Centric Explainable Artificial Intelligence Framework for Medical Imaging Diagnostics: A Systematic Review.","authors":"Charles Ikerionwu, Ikenna Arungwa, Tochukwu Maduike Emelogu, Chidinma Esther Nwabuike, Elochukwu Ukwandu","doi":"10.1155/ijbi/6366492","DOIUrl":"10.1155/ijbi/6366492","url":null,"abstract":"<p><p>Medical imaging has evolved from conventional x-rays to advanced digital modalities, with artificial intelligence (AI), particularly deep learning, showing an increasingly central role in diagnostic support. This study presents a systematic literature review (SLR) of AI-driven medical imaging research focusing on classification-based models and explainability approaches in pneumonia detection. Using predefined inclusion criteria and PRISMA-guided screening, 95 studies were synthesized to identify dominant architectures, dataset trends, performance patterns, and persistent challenges. The analysis shows that convolutional neural networks (CNNs) and their variants remain the most frequently adopted models, accounting for the largest proportion of applications across x-ray, computed tomography scan (CT scan), and magnetic resonance imaging (MRI). Reported diagnostic performance across reviewed studies commonly exceeded 90% in accuracy and AUC, with models such as DeepMediX, XNet, Wavelet-CNN, and RadCLIP demonstrating strong predictive capability in their respective experimental settings. However, the review identifies significant gaps in explainability, clinical workflow integration, ethical compliance, and trust evaluation. Thus, this paper proposes a clinician-centric explainable artificial intelligence (CC-XAI) framework derived from literature synthesis. The framework integrates multilevel explainability, contextual clinical alignment, and human-in-the-loop feedback mechanisms to bridge the gap between black-box AI systems and real-world clinical practice. Rather than introducing a new predictive model, the framework provides a structured design blueprint for embedding explainability into medical imaging diagnostics. The findings highlight the continued dominance of deep learning in medical imaging while emphasizing the urgent need for clinician-oriented XAI frameworks to support transparency, trust, and responsible AI deployment in healthcare.</p>","PeriodicalId":47063,"journal":{"name":"International Journal of Biomedical Imaging","volume":"2026 ","pages":"6366492"},"PeriodicalIF":2.3,"publicationDate":"2026-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13107166/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147785551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Digital Pathology-Based Comparison of PyRadiomics and HistomicsTK for Nuclei Classification in Melanoma Whole Slide Images.","authors":"Alessia Finti, Franco Marinozzi, Giovanni Pasini, Giorgio Russo, Alessandro Stefano, Fabiano Bini","doi":"10.1155/ijbi/7419529","DOIUrl":"10.1155/ijbi/7419529","url":null,"abstract":"<p><strong>Background: </strong>The analysis of histopathological characteristics from biopsy whole slide images (WSI) is a standard procedure in current diagnostic workflows. For instance, malignancies such as melanoma often require the execution of biopsy to be accurately identified. However, diagnosis can be difficult because of variability in clinical scenarios and in microscopic pictures, as well as the lack of biomarkers availability. In this context, the extraction of shape, texture, and intensity-based features from medical images has proven to be a very promising strategy to uncover latent patterns that may be helpful for diagnosis and prediction of several pathologies.</p><p><strong>Methods: </strong>This study proposes radiomics as a powerful tool for extracting nuclei features and enabling nuclei classification of PUMa dataset melanoma WSIs. More specifically, it evaluates the extraction of radiomics features through PyRadiomics, in comparison with the pathomics tool, namely HistomicsTK, in terms of classification performance. To systematically compare these approaches, three supervised classifiers were trained and tested using the same training/testing splits and usual classification metrics: one on radiomics features, one on histomic features, and one on the merged feature set.</p><p><strong>Results: </strong>The results illustrate an improved performance of the radiomics model compared with both the histomic model and the hybrid radiomics and histomics model, suggesting that radiomics can extract valuable phenotypic information from histological images.</p><p><strong>Conclusions: </strong>Radiomics-based feature extraction, as implemented in PyRadiomics, may be a valid and robust alternative to histomics/pathomics descriptors implemented in HistomicsTK in computational pathology pipelines for melanoma analysis.</p>","PeriodicalId":47063,"journal":{"name":"International Journal of Biomedical Imaging","volume":"2026 ","pages":"7419529"},"PeriodicalIF":2.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13042341/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147610193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Learning Framework for Automated MRI Planimetry in Multiple Sclerosis.","authors":"Stephanie Mangesius, Daniela Schiefeneder, Matthias Schwab, Markus Tiefenthaler, Florian Deisenhammer, Markus Haltmeier, Elke R Gizewski","doi":"10.1155/ijbi/4456355","DOIUrl":"10.1155/ijbi/4456355","url":null,"abstract":"<p><p>Brain volume changes and infratentorial involvement are key predictors of disability in multiple sclerosis (MS) and can be assessed using magnetic resonance imaging (MRI) planimetry. Although MRI planimetry is less susceptible to methodological and patient-related confounders than volumetry, it currently depends on manual measurements by unblinded experts, an approach that is time-consuming and vulnerable to bias. In this study, we present a fully automated deep learning framework for deriving brainstem planimetric measurements from MRI. The pipeline integrates an automated midsagittal plane (MSP) detection algorithm with a convolutional neural network trained to perform the segmentations required for planimetry. The automated method shows strong agreement with manual measurements and remains robust across scanners and acquisition protocols. These findings suggest that the proposed framework enables reliable, reproducible, and scalable MRI planimetry, supporting objective assessment of disease progression and treatment response in patients with MS.</p>","PeriodicalId":47063,"journal":{"name":"International Journal of Biomedical Imaging","volume":"2026 ","pages":"4456355"},"PeriodicalIF":2.3,"publicationDate":"2026-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12964314/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147379093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated <i>Mycobacterium tuberculosis</i> Detection in Multivariant Digitized Ziehl-Neelsen Staining Using Faster R-CNN Method.","authors":"Riries Rulaningtyas, Fashalli Giovi Bilhaq, Deby Kusumaningrum, Ronald Eric, Sayyidul Istighfar Ittaqillah, Herri Trilaksana, Dicky Bagus Widhyatmoko, Annie Anak Joseph","doi":"10.1155/ijbi/6692222","DOIUrl":"10.1155/ijbi/6692222","url":null,"abstract":"<p><p>Tuberculosis (TB) is an infectious disease caused by <i>Mycobacterium tuberculosis</i> and remains a major public health concern in Indonesia. One of the most widely used diagnostic methods is the microscopic examination of sputum smears stained using the Ziehl-Neelsen technique. However, manual identification of TB bacteria presents significant challenges, particularly due to staining thickness variations that lead to inconsistent color intensities, making visual detection difficult and often subjective. This study is aimed at developing an automated TB bacteria detection system using deep learning, specifically the Faster R-CNN algorithm with ResNet-50 layers. The system is implemented using the Python programming language and the TensorFlow Object Detection API. We incorporated data augmentation in the form of random rotation, random flipping, and color processing such as hue variation, saturation stretching, brightness stretching, and exposure stretching. Experimental results show that the proposed model achieves an accuracy of 88%, with a precision of 94%, recall of 93%, and an F1-score of 94%. The model outputs annotated images indicating the locations of TB bacteria, which can assist medical professionals in the diagnostic process. These findings demonstrate the potential of deep learning-based approaches in automating TB detection, particularly in healthcare settings with limited human resources.</p>","PeriodicalId":47063,"journal":{"name":"International Journal of Biomedical Imaging","volume":"2026 ","pages":"6692222"},"PeriodicalIF":2.3,"publicationDate":"2026-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12820789/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146031303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Impact of CT Reconstruction Parameters on Emphysema Index Quantification, HU-Based Measurements, and Goddard Score in COPD Assessment: A Prospective Study.","authors":"Rahma Saad Mohamed, Ahmed Sayed Abd El Bassset, Ahmed A G El-Shahawy","doi":"10.1155/ijbi/7436511","DOIUrl":"10.1155/ijbi/7436511","url":null,"abstract":"<p><strong>Background: </strong>Quantitative computed tomography (CT) plays a crucial role in assessing emphysema severity in chronic obstructive pulmonary disease (COPD). However, variations in CT reconstruction parameters-slice thickness (ST), kernel selection, field of view (FOV), and reconstruction gaps-can affect emphysema index (EI) quantification, impacting diagnostic accuracy and study comparability.</p><p><strong>Objective: </strong>This study examines how CT reconstruction parameters influence EI quantification using Hounsfield Unit (HU)-based measurements and the Goddard Score (GS) to refine imaging protocols for emphysema assessment.</p><p><strong>Methods: </strong>Low-dose CT scans were performed on 31 subjects, with images reconstructed using ST (0.6-10 mm), kernel settings (Br and Hr series), FOV ranges (250-370 mm), and reconstruction gaps (0.25-3 mm). EI was defined as the percentage of lung volume with attenuation values below - 950 HU, while GS provided a semi-quantitative assessment of emphysema severity. Statistical analyses evaluated the effects of reconstruction parameters on EI and GS.</p><p><strong>Results: </strong>Variations in FOV, kernel selection, and reconstruction gaps had negligible effects on the GS (<i>p</i> > 0.05), suggesting that these parameters do not introduce structural distortions in pulmonary imaging. However, ultra-thin slices (0.6 mm) enhanced the detection of subtle emphysematous changes, slightly increasing GS, though higher image noise may affect interpretation. Additionally, ST significantly influenced EI values due to partial volume effects, with thinner slices yielding lower attenuation values.</p><p><strong>Conclusion: </strong>These findings confirm the reliability of CT-based emphysema quantification and highlight the importance of optimizing ST to balance sensitivity and image clarity. Standardized imaging protocols and AI-driven texture analysis could further enhance quantitative emphysema assessment, improving disease monitoring and therapeutic decision-making in COPD management.</p>","PeriodicalId":47063,"journal":{"name":"International Journal of Biomedical Imaging","volume":"2026 ","pages":"7436511"},"PeriodicalIF":2.3,"publicationDate":"2026-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12789179/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145953407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Classification of Mammography Images Based on Multifractal Analysis of BIMFs.","authors":"Fatima Ghazi, Khalil Ibrahimi, Fouad Ayoub, Aziza Benkuider, Mohamed Zraidi","doi":"10.1155/ijbi/5940783","DOIUrl":"10.1155/ijbi/5940783","url":null,"abstract":"<p><p>Breast cancer is a real public health problem. Several women with this disease have died from it. Breast cancer is one of the deadliest cancers. Currently, the only way to combat this scourge is the early detection of breast masses. Mammography is a breast x-ray that allows images of the inside of the breast to be obtained using x-rays, thereby detecting possible abnormalities. Computer-aided diagnosis provides significant support in this direction. This work introduces a new system called MF-BIMFs for computer-aided diagnosis that automatically analyzes digital mammograms to discover areas of interest in breast images and offers experts a second opinion. This system was based on the combination of two steps. The first step is the image preprocessing which was based on the bidimensional empirical mode decomposition (BEMD) of breast mammographic images, and their objective is to decompose the image into several BIMF modes and the residual, while the second step is the extraction of features and irregularity properties of the preprocessed images from the multifractal spectrum on each BIMF and the residual and to extract a better representation of each mode and provide details capable of differentiating the two healthy and cancerous states, using these properties as characteristic attributes to evaluate their performance in characterizing two conditions objectively. The rate of this classification is given by SVM. The experimental results indicate that the BIMF₁ mode provided the best classification rate, approximately 97.32%. The interest of this new approach was applied to real mammographic image data from the Reference Center for Reproductive Health of Kenitra, Morocco (RCRHKM), which contains normal and pathological mammographic images.</p>","PeriodicalId":47063,"journal":{"name":"International Journal of Biomedical Imaging","volume":"2025 ","pages":"5940783"},"PeriodicalIF":2.3,"publicationDate":"2025-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12752853/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145879168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Alveolar Bone Segmentation Methods in Assessing the Effectiveness of Periodontal Defect Regeneration Through Machine Learning of CBCT Data: A Systematic Review.","authors":"Mahmud Mohammed, Tulio Fernandez-Medina, Manjunath Rajashekhar, Stephanie Baker, Ernest Jennings","doi":"10.1155/ijbi/9065572","DOIUrl":"10.1155/ijbi/9065572","url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate various segmentation methods used for cone-beam computed tomography (CBCT) images of alveolar bone, assessing their effectiveness and potential benefits in digital workflows for periodontal defect regeneration.</p><p><strong>Data: </strong>This review adheres to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) Checklist.</p><p><strong>Source: </strong>A comprehensive literature search was conducted from May 2024 to June 2025 using MeSH terms on PubMed, Scopus, Web of Science, and Medline databases, with publication date restricted to 5 years. The PRISMA guidelines were followed to ensure a systematic review process, and the review protocol was registered with Prospero. The QUADAS-2 checklist was used to evaluate the risk of bias in the included studies.</p><p><strong>Study selection: </strong>The initial search yielded 834 articles, which were systematically filtered down to 23 eligible studies. Deep learning methods, particularly U-Net, were the most frequently employed segmentation techniques. Four studies utilized semi-automated methods, while the remaining studies relied on manual or other segmentation methods. The Dice similarity (DC) index, ranging from 76% to 98%, was the primary metric used to assess segmentation performance.</p><p><strong>Conclusions: </strong>Significant differences were observed between the segmentation of healthy and defective alveolar bone, underscoring the need to enhance deep learning-based methods. Accurate segmentation of periodontal defects in DICOM images is a crucial first step in the scaffold workflow, as it enables precise assessment of defect morphology and volume. This information directly informs scaffold design, ensuring that the scaffold geometry is tailored to the patient-specific defect.</p><p><strong>Prospero registration: </strong>CRD42024590957.</p>","PeriodicalId":47063,"journal":{"name":"International Journal of Biomedical Imaging","volume":"2025 ","pages":"9065572"},"PeriodicalIF":2.3,"publicationDate":"2025-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12752843/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145879138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}