Journal of Medical Imaging最新文献

{"title":"Ultrasound computer tomography using single-element directivity measurements.","authors":"Nathan Meulenbroek, Samuel Pichardo","doi":"10.1117/1.JMI.13.5.057001","DOIUrl":"https://doi.org/10.1117/1.JMI.13.5.057001","url":null,"abstract":"<p><strong>Purpose: </strong>Ultrasound computer tomography (UCT) is a promising medical imaging method for various applications such as the breast and brain. Current UCT image reconstruction methods fall broadly into two categories: time-of-flight (TOF)-based ray-tracing methods and full-waveform inversion (FWI) methods. Ray tracing methods are computationally efficient but often have blurred edges and low spatial resolution, whereas FWI methods demonstrate excellent image quality at high computational cost. To improve the image quality of ray-based methods without greatly increasing their computational cost, we propose bent-ray UCT reconstruction using direction of arrival (DOA) information rather than TOF information.</p><p><strong>Approach: </strong>DOA- and TOF-UCT methods are evaluated <i>in silico</i> using two-dimensional Shepp-Logan and breast tissue phantoms with speeds of sound ranging from 1460 to <math><mrow><mn>1580</mn> <mtext>  </mtext> <mi>m</mi> <mo>/</mo> <mi>s</mi></mrow> </math> . Both the Shepp-Logan and breast tissue phantoms were imaged with 128-element ring arrays with diameters of 38.5 and 21 cm, operating frequencies of 350 and 600 kHz, and resolutions of 0.71 and 0.41 mm, respectively. Initial measurements were derived from a finite-difference time-difference solution of the viscoelastic wave equation.</p><p><strong>Results: </strong>We demonstrate that DOA-UCT images have sharper edges and improved structural similarity to ground-truth images than conventional TOF-UCT. DOA-UCT reconstruction is also able to reconstruct images at multiple time points and with various window sizes, reducing the need to find an exact signal onset.</p><p><strong>Conclusions: </strong>To the best of our knowledge, this is the first demonstration of a bent-ray UCT algorithm that uses only DOA information, without TOF information.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 5","pages":"057001"},"PeriodicalIF":2.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13628646/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149116734","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":"Selective segmentation with rejection option: a machine reasoning approach and evaluation metrics in CT kidney segmentation.","authors":"Gabriel Melendez-Corres, Muhammad Wahi-Anwar, Jin Kim, Dallas Tada, John Hoffman, Joshua Genender, Matthew Brown","doi":"10.1117/1.JMI.13.5.054501","DOIUrl":"10.1117/1.JMI.13.5.054501","url":null,"abstract":"<p><strong>Purpose: </strong>Deep learning models for medical image segmentation achieve high average performance but can produce anatomically implausible errors that undermine trust and necessitate manual review. This work addresses this limitation through selective segmentation with a rejection option, enabling systems to accept plausible results while rejecting questionable ones.</p><p><strong>Approach: </strong>A nnUNet model trained for kidney segmentation on the KiTS23 dataset was integrated into the SimpleMind (SM) reasoning framework. Kidney segmentation candidates were evaluated and selected using SM reasoning methods fuzzy membership reasoning (FMR), adaptive reasoning (AR), and largest connected component analysis per side (LCCAPS), and performance was compared with the commonly used largest connected component analysis (LCCA). Performance was assessed via false positive rate and false negative rate across five validation folds. Candidate-level acceptance and rejection metrics were also introduced to evaluate selective performance. Robustness was further examined under added noise.</p><p><strong>Results: </strong>Reasoning-based approaches (FMR, AR, and LCCAPS) reduced false positives and anatomically invalid outputs more effectively than LCCA, while preserving acceptance of valid segmentation candidates. Results persisted under noise, avoiding acceptance of implausible results.</p><p><strong>Conclusions: </strong>Incorporating reasoning into DL segmentation supports selective acceptance of anatomically valid outputs and rejection of invalid ones, increasing reliability and autonomy in medical imaging workflows. This selective segmentation framework provides a practical path toward trusted, semi-autonomous clinical deployment.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 5","pages":"054501"},"PeriodicalIF":2.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13554113/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148921304","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":"Charting confidence in white matter brain charts: enabling study planning through stability validation.","authors":"Michael E Kim, Gaurav Rudravaram, Adam M Saunders, Chenyu Gao, Karthik Ramadass, Nancy R Newlin, Praitayini Kanakaraj, Sam Bogdanov, Angela L Jefferson, Victoria L Morgan, Alexandra Roche, Dario J Englot, Susan M Resnick, Lori L Beason Held, Murat Bilgel, Laurie E Cutting, Laura A Barquero, Micah A D'Archangel, Tin Q Nguyen, Kathryn L Humphreys, Yanbin Niu, Sophia Vinci-Booher, Carissa J Cascio, Kimberly R Pechman, Niranjana Shashikumar, The Habs-Hd Study Team, Alzheimer's Disease Neuroimaging Initiative, The Biocard Study Team, Zhiyuan Li, Panpan Zhang, John C Gore, Yihao Liu, Lianrui Zuo, Yuankai Huo, Derek B Archer, Timothy J Hohman, L Taylor Davis, Kurt G Schilling, Daniel C Moyer, Bennett A Landman","doi":"10.1117/1.JMI.13.5.054001","DOIUrl":"10.1117/1.JMI.13.5.054001","url":null,"abstract":"<p><strong>Purpose: </strong>Normative modeling of quantitative brain measurements is being widely adopted as a promising method for charting population-level developmental trajectories and identifying abnormalities in groups and individuals. Generalized additive models for location, scale, and shape (GAMLSS) are a statistical framework that has been identified by the World Health Organization as a robust method for large-scale population modeling. Validating the stability of normative models is essential for appropriate benchmarking and detecting anomalies, especially for patients with neurodegenerative or developmental disorders. As these models continue to expand in the number of features and amount of data, it becomes increasingly important to assess the stability of the models and their predictions.</p><p><strong>Approach: </strong>An analytic approach is extended from previous work to assess variability of the GAMLSS framework for normative modeling of white matter measurements across the lifespan. The analytic variance and bias are compared with empirical bootstrapping estimates and those of an analogous model that is a nonparametric, data-driven analog.</p><p><strong>Results: </strong>Across all models, the analytic approach showed low model variability ( <math><mrow><mo><</mo> <mn>0.5</mn> <mo>%</mo></mrow> </math> Coefficient of Variation) for lifespan trajectories that increased with age. Empirical variability of trajectories was slightly elevated by comparison, especially at the beginning of the lifespan. The trajectory variability for the data-driven analog was even larger, showing a ten-fold increase from the empirical GAMLSS variability. For individual centile prediction, the majority of data points for the analytic assessment had a mean absolute difference (MAD) in centile score prediction as <math><mrow><mi>z</mi></mrow> </math> -scores that was less than 0.003 with the standard deviation of these errors below 0.06. The empirical assessment showed an elevated standard deviation (0.15) and MAD of <math><mrow><mi>z</mi></mrow> </math> -score centile predictions (0.06) for the majority of datapoints. By contrast, when compared with the empirical assessment, the nonparametric, data-driven analog showed over a two-fold increase in the MAD of centile <math><mrow><mi>z</mi></mrow> </math> -score predictions (0.14) and a three-fold increase in standard deviation (0.45) for the majority of data points. The divergences in variability across assessments suggest that individual centile predictions are more sensitive to random fluctuations in the data, which the nonparametric data-driven approach exacerbates.</p><p><strong>Conclusions: </strong>Results suggest that the GAMLSS brain charts are a stable method of defining and charting normative white matter development as well as planning future clinical or research studies. Overall, this study provides an assessment of GAMLSS-derived brain chart variance in a large-scale population.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 5","pages":"054001"},"PeriodicalIF":2.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13601033/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149041245","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":"Incorporating synthetic data from diffusion models supports echocardiography downstream tasks.","authors":"Milad Yazdani, Pooria Ashrafian, Moein Heidari, Alireza Rafiei Sardouei, Dena Shahriari, Ilker Hacihaliloglu","doi":"10.1117/1.JMI.13.5.057002","DOIUrl":"https://doi.org/10.1117/1.JMI.13.5.057002","url":null,"abstract":"<p><strong>Purpose: </strong>Large labeled echocardiography datasets are costly to collect. We use diffusion models to generate synthetic training data for segmentation and cardiac phase classification.</p><p><strong>Approach: </strong>We study three generation approaches on CAMUS: an unconditional image space model, a latent model conditioned on plain English prompts or abstract tokens, and a ControlNet model conditioned on an abstract token and segmentation mask. We evaluate synthesis with Fréchet inception distance (FID) and augmentation using segmentation and classification of end diastole and end systole. We also evaluate segmentation within CardiacUDC and directly from CAMUS to CardiacUDC.</p><p><strong>Results: </strong>Conditioning on an abstract token and segmentation mask gives the lowest mean FID, 1.5, compared with 3.2 for the semantic diffusion model. Abstract token augmentation gives the highest classification accuracy, improving ResNet-18 from 83.8% to 87.2% and VGG-16 from 74.5% to 78.7%. Synthetic augmentation gives the highest mean Dice of 87.6% for the CAMUS 2D U-Net and 84.6% for the CardiacUDC nnU-Net. When nnU-Net models are trained on CAMUS and evaluated directly on CardiacUDC, augmentation raises mean Dice from 74.6% to 75.2%.</p><p><strong>Conclusions: </strong>Incorporating synthetic images into training gives modest gains in CAMUS phase classification, segmentation within CAMUS and CardiacUDC, and direct segmentation from CAMUS to CardiacUDC.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 5","pages":"057002"},"PeriodicalIF":2.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13661038/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149185252","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":"Clinical knowledge-guided attention for gait-based adult spinal deformity assessment from monocular video.","authors":"Kaixu Chen, Tomoyuki Asada, Kousei Miura, Hideki Kadone, Naoya Kikuchi, Yasuhiro Homma, Masashi Yamazaki, Itaru Kitahara, Yoshihiro Kuroda","doi":"10.1117/1.JMI.13.5.054002","DOIUrl":"10.1117/1.JMI.13.5.054002","url":null,"abstract":"<p><strong>Purpose: </strong>Adult spinal deformity (ASD) is associated with characteristic gait abnormalities, yet routine diagnosis relies mainly on radiographic assessment and physical examination, which can be time-consuming and may not reflect functional impairment during walking. Existing video-based gait models are often purely data-driven and difficult to interpret clinically. This study aims to develop an explainable, noninvasive ASD screening framework that integrates orthopedic clinical knowledge to guide model attention toward diagnostically meaningful gait cues.</p><p><strong>Approach: </strong>This paper proposes an anatomy-guided attention framework for ASD diagnosis from monocular gait videos. Human pose is extracted from videos and represented as spatiotemporal joint sequences. Orthopedic specialists provide clinical experience about anatomically important joints and motion patterns, which is encoded as clinician-informed attention maps. We then fuse these attention maps with the input videos to guide the classification model to focus on disease-relevant regions. The attention-guided maps are integrated with a three-dimensional (3D) CNN-based spatiotemporal backbone, and model visualization is used to assess interpretability.</p><p><strong>Results: </strong>Experiments on a gait dataset with 81 patients show that the proposed approach consistently outperforms conventional baselines. The proposed framework was evaluated using monocular gait videos from patients with adult spinal deformity, dropped head syndrome (DHS), lumbar canal stenosis (LCS), and hip osteoarthritis (HipOA). The proposed method achieves 71.35% accuracy, 75.51% precision, and 71.12% F1-score. In contrast, the model without attention achieves 62.09% accuracy, 64.55% precision, and 60.13% F1-score, corresponding to improvements of 9.26, 10.96, and 10.99 percentage points, respectively. Visualization analyses further show that anatomy-guided attention yields clearer and more stable focus on clinically meaningful body regions, producing explanations that better align with expert expectations.</p><p><strong>Conclusions: </strong>Incorporating clinician-derived priors as attention guidance improves both diagnostic accuracy and interpretability for gait-based ASD recognition from monocular videos. The proposed framework supports accessible, radiation-free screening and provides clinically informative visual evidence, facilitating translation of gait analysis models to real-world orthopedic practice.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 5","pages":"054002"},"PeriodicalIF":2.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13649287/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149138886","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":"Contrastive learning and advanced bundle metrics outperform fractional anisotropy for Alzheimer's disease diffusion MRI prediction: findings from the Beyond FA challenge.","authors":"Elyssa McMaster, Nancy Newlin, Trent Schwartz, Adam Saunders, Gaurav Rudravaram, Jiheng Li, André Hucke, Yehyun Suh, Jongyeon Yoon, Eleanor Liard, Michael Kim, Chenyu Gao, Karthik Ramadass, Chloe Cho, Sriram Gnana Sambanthan, Tomasz Pieciak, Dominika Ciupek, Santiago Aja-Fernández, Antonio Tristán-Vega, Maciej Malawski, Alex Caron, Antoine Théberg, Francois Reault, Arnaud Boré, Manon Edde, Ji Kim, Yihao Liu, Lianrui Zuo, Eleftherios Garyfallidis, Talia Nir, Neda Jahanshad, Kurt Schilling, Daniel Moyer, Bennett A Landman","doi":"10.1117/1.JMI.13.5.054003","DOIUrl":"10.1117/1.JMI.13.5.054003","url":null,"abstract":"<p><strong>Purpose: </strong>The inclusion of diffusion-weighted magnetic resonance imaging (DW-MRI) in major national studies has allowed for quantification and characterization of white matter macrostructure and microstructure in cases of disease and disorder. Diffusion tensor imaging (DTI) yields 3D scalar maps to summarize the DW-MRI signal with quantitative metrics. Fractional anisotropy (FA) is a DTI metric that describes the degree of anisotropy within diffusion and is frequently used to interpret white matter integrity, but it exhibits high sensitivity in pathological interpretation. These properties of FA make it difficult to use as a consistent candidate imaging biomarker, as it makes different ages, cognitive statuses, and pathologies difficult to discern. With the development of other white matter models and metrics, such as structural connectivity network measures and tractography bundle analyses, there are many combinations to analyze for white matter integrity analysis, especially in the context of lower-quality clinical data that FA's voxel-wise computation can be sensitive to. The widespread collection of DW-MRI data necessitates an analysis of these metrics to interpret white matter integrity beyond what FA can capture.</p><p><strong>Approach: </strong>We designed a challenge for the medical imaging community to compare crowdsourced DW-MRI candidate imaging biomarkers to a baseline relying on FA in an age, sex, and cognitive status classification task and variables unknown to teams during the challenge. After the challenge submission period ended, we evaluated methods based on sensitivity to environmental variables (humidity and temperature on the day of the scan), and we correlated features with known Alzheimer's disease (AD) pathology (amyloid beta 42, tau, and ptau cerebrospinal fluid/CSF readings) to evaluate if the methods collected in this study are robust to the limitations of FA. The key innovations are that we crowdsource DW-MRI feature representations for AD, we develop a framework to compare imaging feature representations in this context, we evaluate the sensitivity of DW-MRI imaging candidate biomarkers to environmental variables, and we correlate the novel features to known AD pathological measures.</p><p><strong>Results: </strong>We find that bundle-based methods outperform whole-brain methods in age classification tasks, but deep learning, computer vision-based methods show a new avenue for cognitive status prediction tasks.</p><p><strong>Conclusion: </strong>The submissions to our challenge show that there are many approaches to consider when developing new AD feature representations.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 5","pages":"054003"},"PeriodicalIF":2.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13671859/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149217082","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":"SNR-ST-Mix: sample-specific neighborhood regression mixup for augmented spatial transcriptomics imputation with deep neural network.","authors":"Hongyi Yu, Yaoyu Fang, Jiahe Qian, Xinkun Wang, Lee A Cooper, Bo Zhou","doi":"10.1117/1.JMI.13.4.047501","DOIUrl":"10.1117/1.JMI.13.4.047501","url":null,"abstract":"<p><strong>Purpose: </strong>Spatial transcriptomics (ST) enables gene-expression measurements within the tissue context. However, these measurements are often noisy, low-resolution, and sparsely sampled, which limits the recovery of fine spatial structure. Deep neural networks have become powerful tools for expression imputation from histology, but their performance remains constrained by limited sample sizes and a lack of biologically informed augmentation. Most of the existing augmentation strategies for learning are designed for classification tasks rather than regression, which neglect spatial and transcriptomic relationships, leading to biologically implausible interpolations that hinder prediction performance.</p><p><strong>Approach: </strong>To address these limitations, we propose SNR-ST-Mix, a geometry- and expression-aware data augmentation framework designed specifically for ST data. It constrains mixing to a spot's <math><mrow><mi>k</mi></mrow> </math> -nearest spatial neighbors and adaptively weights interpolation coefficients based on expression similarity, generating augmented samples that preserve local biological structure while ensuring spatial smoothness. This dual conditioning yields synthetic examples that expand the effective training manifold, promote generalization, and enhance prediction stability under sample-specific training.</p><p><strong>Results: </strong>Extensive experiments with various tissue types demonstrate that SNR-ST-Mix consistently outperforms conventional augmentation methods without requiring architectural changes or additional computation.</p><p><strong>Conclusions: </strong>SNR-ST-Mix provides an effective and biologically principled augmentation strategy for spatial transcriptomics regression tasks. By explicitly leveraging spatial geometry and transcriptomic similarity, it expands the effective training manifold and improves predictive performance without increasing model complexity.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 4","pages":"047501"},"PeriodicalIF":2.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13464387/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148727625","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":"Spectral micro-CT for quantitative analysis of calcification in fibrocartilage.","authors":"Vittoria Mazzini, Paolo Cardarelli, Andrew Coathup, Eleonora Olivotto, Francesco Grassi, Enrico Tassinari, Simone Velardita, Angelo Taibi, Luca Brombal","doi":"10.1117/1.JMI.13.4.043502","DOIUrl":"10.1117/1.JMI.13.4.043502","url":null,"abstract":"<p><strong>Purpose: </strong>We describe a method for the quantitative analysis of calcification structures in fibrocartilage samples from human hip acetabular labrum, using a lab-based spectral micro-computed tomography ( <math><mrow><mi>μ</mi> <mrow><mi>CT</mi></mrow> </mrow> </math> ) system.</p><p><strong>Approach: </strong>Tissue samples from 26 patients with osteoarthritis and femoroacetabular impingement were analyzed using a spectral <math><mrow><mi>μ</mi> <mrow><mi>CT</mi></mrow> </mrow> </math> system featuring photon-counting detector with a <math><mrow><mn>62</mn> <mtext>  </mtext> <mi>μ</mi> <mi>m</mi></mrow> </math> pixel size operating at two energy thresholds. Material decomposition was applied to the <math><mrow><mi>μ</mi> <mrow><mi>CT</mi></mrow> </mrow> </math> images to separate calcium and water-like components, resulting in the 3D spatial distribution and quantification of calcium deposits within the tissue. Results were compared with histological analysis using Alizarin Red™ staining. Two calcium crystal deposition scores on a four-grade scale were assigned based on histological and <math><mrow><mi>μ</mi> <mrow><mi>CT</mi></mrow> </mrow> </math> analysis, respectively.</p><p><strong>Results: </strong>This method provides 3D images with a voxel size of <math><mrow><mn>20</mn> <mtext>  </mtext> <mi>μ</mi> <mi>m</mi></mrow> </math> over a sample size up to 3 cm. The minimum detectable calcium concentration is <math><mrow><mn>0.24</mn> <mtext>  </mtext> <mrow><mi>g</mi></mrow> <mo>/</mo> <msup><mrow><mi>cm</mi></mrow> <mrow><mn>3</mn></mrow> </msup> </mrow> </math> , and calcified structures as small as <math><mrow><mn>49.6</mn> <mtext>  </mtext> <mi>μ</mi> <mi>m</mi></mrow> </math> in diameter were identified. The quantification accuracy was validated using a hydroxyapatite calibration phantom. Across the complete sample set, spectral µCT grading demonstrated significant correlation (Spearman correlation coefficient <math><mrow><mi>ρ</mi> <mo>=</mo> <mn>0.67</mn></mrow> </math> ) and substantial agreement (weighted Cohen's coefficient <math><mrow><mi>κ</mi> <mo>=</mo> <mn>0.70</mn></mrow> </math> ) with histological assessment. Moreover, the calcification spatial distribution exhibited very good consistency with histological results, supporting the method validity.</p><p><strong>Conclusions: </strong>This approach offers a nondestructive and reproducible alternative to histology for assessing calcification in joint tissue, providing quantitative 3D mapping of calcium concentration in intact samples without the need for staining or physical sectioning.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 4","pages":"043502"},"PeriodicalIF":2.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13464388/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148727683","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":"Development and evaluation of an anatomically guided system for ultrasound image acquisition in trauma assessment.","authors":"Robert S Armiger, Anna E Knight, Catherine M Carneal, Nathanael P Kuo, Kathleen M Perrino, Julia K Deanehan","doi":"10.1117/1.JMI.13.4.045001","DOIUrl":"10.1117/1.JMI.13.4.045001","url":null,"abstract":"<p><strong>Purpose: </strong>Medical care in battlefield and austere environments may require minimally trained personnel to perform complex diagnostic procedures such as ultrasound. We present a mixed reality (MR) guidance system that uses predictive anatomical modeling to assist novice operators in acquiring the extended Focused Assessment with Sonography in Trauma (eFAST).</p><p><strong>Approach: </strong>A morphable anatomical atlas of the torso was constructed from 180 CT scans using automated segmentation, deformable registration, and regression-based mapping between internal anatomy and external anthropometry. The atlas was integrated with a portable ultrasound system and an MR headset with probe tracking to provide subject-specific holographic guidance during scanning. System accuracy was validated using imaging phantoms and evaluated in a study involving 16 novice operators performing six-window eFAST examinations using both conventional ultrasound and MR guidance across four healthy volunteers. Ultrasound images were graded by an expert clinician, and operator workload was assessed using the NASA Task Load Index.</p><p><strong>Results: </strong>Atlas performance showed high segmentation accuracy (Dice score <math><mrow><mn>0.93</mn> <mo>±</mo> <mn>0.04</mn></mrow> </math> ) and in-atlas prediction errors below 10 mm using six anthropometric measures. Phantom testing demonstrated end-to-end image localization accuracy of <math><mrow><mn>2.2</mn> <mo>±</mo> <mn>0.6</mn> <mtext>  </mtext> <mi>mm</mi></mrow> </math> . MR guidance was associated with a nonsignificant increase in correct-window acquisition (48% to 60%) and a significant improvement in diagnostic sufficiency (13% to 25%) while reducing perceived cognitive workload.</p><p><strong>Conclusions: </strong>These results demonstrate the feasibility of anatomically informed MR guidance to support ultrasound acquisition by novice users and highlight its potential for trauma diagnostics in resource-limited or austere environments.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 4","pages":"045001"},"PeriodicalIF":2.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13537099/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148882098","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":"Radiomics-based machine learning to evaluate immunotherapy efficacy in non-small cell lung cancer patients with bone metastases.","authors":"Reza Kakavand, Nils D Forkert, Annalise Abbott, Joseph Kendal, Peter Connell, Hila Yashar, Michael J Monument, W Brent Edwards","doi":"10.1117/1.JMI.13.4.044503","DOIUrl":"10.1117/1.JMI.13.4.044503","url":null,"abstract":"<p><strong>Purpose: </strong>Assessing treatment response in bone metastases from non-small cell lung cancer (NSCLC) remains a major clinical challenge, particularly for patients receiving immune checkpoint inhibitors (ICIs). The existing response criteria are not optimized for osseous disease, leading to inconsistent evaluation. We aimed to develop and validate a radiomics-based machine learning (ML) framework to non-invasively distinguish immunotherapy response categories-progression, stable disease, and partial response-in NSCLC patients with bone metastases.</p><p><strong>Approach: </strong>Chest computed tomography (CT) scans from 99 NSCLC patients were analyzed before and during ICI therapy. Bone structures were automatically segmented using TotalSegmentator, and 1051 radiomic features were extracted per time point. Clinical variables were incorporated as optional features. Three ML classifiers-random forest, XGBoost, and support vector machine-were trained using fivefold cross-validation. A multistep feature selection pipeline (correlation filtering, mutual information, recursive feature elimination, and ReliefF ranking) was applied. Model performance was evaluated using area under the curve (AUC), <math><mrow><mi>F</mi> <mn>1</mn></mrow> </math> -score, accuracy, sensitivity, and specificity, with additional statistical testing using Kruskal-Wallis, Mann-Whitney <math><mrow><mi>U</mi></mrow> </math> , bootstrapping, and permutation analysis.</p><p><strong>Results: </strong>Inter-rater agreement for radiological response categories was high (Cohen's kappa = 0.91). Post-treatment radiomic features yielded the best performance. The random forest model achieved an AUC of 0.94, an <math><mrow><mi>F</mi> <mn>1</mn></mrow> </math> -score of 0.79, an accuracy of 0.79, a sensitivity of 0.80, and a specificity of 0.83. Clinical features did not meaningfully improve performance. Models based on the largest lesion showed lower accuracy than those using the overall response.</p><p><strong>Conclusions: </strong>Post-treatment CT radiomics captured therapy-induced skeletal changes and enabled differentiation of immunotherapy response categories in NSCLC bone metastases. These findings highlight radiomics as a non-invasive tool for response assessment and guiding personalized treatment strategies.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 4","pages":"044503"},"PeriodicalIF":2.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13389688/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148563052","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}