Journal of Medical Imaging最新文献

{"title":"OMAMA-DB: the Oregon-Massachusetts Mammography Database.","authors":"Avanith Kanamarlapudi, Ryan Zurrin, Edward Gaibor, Benjamin Bendiksen Gutierrez, Neha Goyal, Vidhya Sree Narayanapa, Dan Simovici, Nurit Haspel, Marc Pomplun, Hyunkwang Lee, Mack Bandler, Greg Sorensen, Daniel Haehn","doi":"10.1117/1.JMI.13.6.062205","DOIUrl":"https://doi.org/10.1117/1.JMI.13.6.062205","url":null,"abstract":"<p><strong>Purpose: </strong>Public datasets for training artificial intelligence (AI) models in breast cancer screening are limited in size and quality, making it difficult to develop reliable systems. We introduce OMAMA-DB, an extensive publicly available collection of two-dimensional (2D) mammograms and three-dimensional (3D) tomosynthesis volumes.</p><p><strong>Approach: </strong>Starting from 967,991 images, we created a curated set of 231,080 images using a multi-stage filtering process that removes missing labels, uncommon dimensions, rare scanner types, duplicate studies, and invalid DICOM files. All 2D images then undergo additional outlier detection using histogram filtering and a variational autoencoder to remove low-quality outliers. OMAMA-DB includes pathology-based cancer labels and automated lesion annotations generated using DeepSight. We also provide a web-based annotation tool for expert validation. To demonstrate usability, we fine-tuned MedGemma on a balanced subset of OMAMA-DB. We conducted a preliminary user study comparing human and automated classification of real and synthetic mammograms.</p><p><strong>Results: </strong>OMAMA-DB contains 231,080 images, including 7351 2D and 374 3D cancer cases. Fine-tuned MedGemma achieved 0.989 accuracy, 0.997 sensitivity, and an <math><mrow><mi>F</mi> <mn>1</mn></mrow> </math> score of 0.989 on a balanced validation set of 2942 images. In real-versus-synthetic classification, humans achieved 0.485 accuracy, and logistic regression and convolutional neural network achieved 0.972 and 0.997, respectively.</p><p><strong>Conclusions: </strong>OMAMA-DB provides a large mammography dataset with pathology-based labels and automated lesion annotations to support medical imaging research. Fine-tuned foundation models demonstrate strong cancer classification performance, and the gap between human and automated detection of synthetic images highlights the importance of real clinical data. All data, models, and parameters are openly available for research use.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 6","pages":"062205"},"PeriodicalIF":1.7,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13210887/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148043893","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":"Peer-Validated Resources for Medical Imaging: From Scientific Products to Scientific Infrastructure.","authors":"Daniel Haehn, Daniel Moyer, Chris Rorden, Rudolph Pienaar","doi":"10.1117/1.JMI.13.6.062201","DOIUrl":"https://doi.org/10.1117/1.JMI.13.6.062201","url":null,"abstract":"<p><p>The editorial provides an overview of the JMI Special Section, Peer-Validated Resources for Medical Imaging.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 6","pages":"062201"},"PeriodicalIF":2.3,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13660627/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149185284","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":"MILU: a consensus ensemble benchmark for multimodal medical imaging lecture understanding.","authors":"Md Motaleb Hossen Manik, Md Zabirul Islam, Ge Wang","doi":"10.1117/1.JMI.13.6.062202","DOIUrl":"10.1117/1.JMI.13.6.062202","url":null,"abstract":"<p><strong>Purpose: </strong>Vision-language models (VLMs) are increasingly used to interpret multimodal educational materials, yet their reliability on diagram-, equation-, and text-dense scientific lecture slides remains poorly understood. This work introduces Medical Imaging Lecture Understanding (MILU), a large-scale benchmark designed to characterize cross-model variability in structured understanding of real medical imaging lectures.</p><p><strong>Approach: </strong>MILU includes 23 lecture sets with 1117 slides. LLaVA-OneVision, InternVL3-14B, Qwen2-VL-7B, and Qwen3-VL-4B were evaluated using unified prompts to generate structured JSON. We assessed parsing coverage, pairwise agreement, lecture-level patterns, and how outputs aligned with a simple consensus ensemble to identify shared concepts and relations across slides and models effectively.</p><p><strong>Results: </strong>All models produced valid JSON for most slides (92% to 99% coverage), but semantic agreement was extremely low. Pairwise concept Jaccard indices ranged from 0.03 to 0.09, and triple-level <math><mrow><mi>F</mi> <mn>1</mn></mrow> </math> scores from 0.001 to 0.033. Lecture-level patterns revealed higher stability in mathematically structured lectures and lower stability in diagram-heavy content. The consensus ensemble showed modest alignment with individual models (concept Jaccard 0.056 to 0.179; triple <math><mrow><mi>F</mi> <mn>1</mn></mrow> </math> 0.014 to 0.044), exposing areas of consistent convergence while also highlighting systematic disagreement.</p><p><strong>Conclusions: </strong>MILU provides the first comprehensive benchmark for evaluating structured understanding of scientific lecture slides. The results show that current VLMs achieve high formatting reliability but low semantic consistency. MILU establishes a foundation for future expert-annotated benchmarks, diagram- and math-aware modeling, and improved methods for scientific lecture interpretation.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 6","pages":"062202"},"PeriodicalIF":2.3,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13082354/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147700301","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":"mach: ultrafast ultrasound beamforming.","authors":"Charles Guan, Alexander P Rockhill, Masashi Sode, Gianmarco Pinton","doi":"10.1117/1.JMI.13.6.062203","DOIUrl":"10.1117/1.JMI.13.6.062203","url":null,"abstract":"<p><strong>Purpose: </strong>Volumetric ultrafast ultrasound produces massive datasets with high frame rates, dense reconstruction grids, and large channel counts. Beamforming computational demands limit research throughput and prevent real-time applications in emerging modalities such as elastography, functional neuroimaging, and microscopy.</p><p><strong>Approach: </strong>We developed mach, an open-source, GPU-accelerated beamformer with a highly optimized delay-and-sum CUDA kernel and an accessible Python interface. mach uses a hybrid delay computation strategy that substantially reduces memory overhead compared with fully precomputed approaches. The CUDA implementation optimizes memory layout for coalesced access and reuses delay computations across frames via shared memory. We benchmarked mach on the PyMUST rotating disk dataset and validated numerical accuracy against existing open-source beamformers.</p><p><strong>Results: </strong>mach processes 1.1 trillion points per second on a consumer-grade GPU, achieving > <math><mrow><mn>10</mn> <mo>×</mo></mrow> </math> faster performance than existing open-source GPU beamformers. On the PyMUST rotating disk benchmark, mach completes reconstruction in 0.23 ms, 6× faster than the acoustic round-trip time to the imaging depth. Validation against other beamformers confirms numerical accuracy with errors below <math><mrow><mo>-</mo> <mn>60</mn> <mtext>  </mtext> <mi>dB</mi></mrow> </math> for Power Doppler and <math><mrow><mo>-</mo> <mn>120</mn> <mtext>  </mtext> <mi>dB</mi></mrow> </math> for B-mode.</p><p><strong>Conclusions: </strong>mach achieves 1.1 trillion points per second throughput, enabling real-time 3D ultrafast ultrasound reconstruction for the first time on consumer-grade hardware. By eliminating the beamforming bottleneck, mach enables real-time applications such as 3D functional neuroimaging, intraoperative guidance, and ultrasound localization microscopy. mach is freely available at https://github.com/Forest-Neurotech/mach.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 6","pages":"062203"},"PeriodicalIF":2.3,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13053060/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147634858","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":"Measured and synthetic rigid head motion datasets via generative model for motion simulation and compensation in medical imaging.","authors":"Manuela Goldmann, Felix Damm, Florian Goldmann, Oliver Hornung, Michael Manhart, Alexander Preuhs, Markus Kowarschik, Andreas Maier","doi":"10.1117/1.JMI.13.6.062206","DOIUrl":"10.1117/1.JMI.13.6.062206","url":null,"abstract":"<p><strong>Purpose: </strong>Rigid head motion during interventional C-arm cone-beam CT (CBCT) is a major source of image degradation. Learning-based motion estimation requires realistic training data, but ground-truth motion is scarce, limiting direct validation of compensation trajectories. We address this gap with an open resource consisting of tracked real motion and pregenerated synthetic motion, along with a pretrained variational autoencoder (VAE) to generate larger ground-truth datasets.</p><p><strong>Approach: </strong>Using stereo optical tracking, we recorded rigid 6-DoF head motion trajectories from 25 volunteers lying head-first supine on an examination table, resembling a clinical setting. After data preprocessing, we trained a VAE on 120 sequences of 10 s at 30 Hz. Motion is represented in patient-centered coordinates to support transformation to arbitrary scan geometries. Similarity between measured and generated data is assessed via distributional distances, correlation metrics, low-dimensional embeddings, and a posthoc analysis of the learned latent space.</p><p><strong>Results: </strong>Evaluated based on 120 generated sequences, the trained VAE is capable of producing diverse 6-DoF trajectories that preserve real-world data correlation structure. Distributional and frequency-domain metrics, along with t-SNE embeddings, show overlap between real and synthetic samples without evidence of mode collapse or training data replication.</p><p><strong>Conclusions: </strong>This work provides an openly released resource comprising measured trajectories, a synthetic dataset, and pretrained VAE weights together with full training and evaluation code, combining rigid 6-DoF head motion measured in a realistic C-arm setting with a retrainable generative model. It is intended to support reproducible development, benchmarking, and comparison of head motion estimation methods in medical imaging modalities.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 6","pages":"062206"},"PeriodicalIF":2.3,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13377625/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148580674","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":"In search of truth: evaluating concordance of AI-based anatomy segmentation models.","authors":"Lena Giebeler, Deepa Krishnaswamy, David Clunie, Jakob Wasserthal, Lalith Kumar Shiyam Sundar, Andres Diaz-Pinto, Klaus H Maier-Hein, Murong Xu, Bjoern Menze, Steve Pieper, Ron Kikinis, Andrey Fedorov","doi":"10.1117/1.JMI.13.6.062204","DOIUrl":"10.1117/1.JMI.13.6.062204","url":null,"abstract":"<p><strong>Purpose: </strong>Artificial intelligence based methods for anatomy segmentation can help automate characterization of large imaging datasets. The growing number of similar functionality models raises the challenge of evaluating them on datasets that do not contain ground truth annotations. We introduce a practical framework to assist in this task.</p><p><strong>Approach: </strong>We harmonize the segmentation results into a standard, interoperable representation, which enables consistent, terminology-based labeling of the structures. We extend 3D Slicer to streamline loading and comparison of these harmonized segmentations and demonstrate how standard representation simplifies review of the results using interactive summary plots and browser-based visualization using the OHIF Viewer. To demonstrate the utility of the approach, we apply it to evaluating segmentation of 31 anatomical structures (lungs, vertebrae, ribs, and heart) by 6 open-source models-TotalSegmentator 1.5 and 2.6, Auto3DSeg, MOOSE, MultiTalent, and CADS-for a sample of computed tomography scans from the publicly available National Lung Screening Trial dataset.</p><p><strong>Results: </strong>We demonstrate the utility of the framework in enabling automating loading, structure-wise inspection, and comparison across models. Preliminary results ascertain the practical utility of the approach in allowing quick detection and review of problematic results. The comparison shows excellent agreement segmenting some (e.g., lung) but not all structures (e.g., some models produce invalid vertebrae or rib segmentations).</p><p><strong>Conclusions: </strong>The open-source resources developed include segmentation harmonization scripts, interactive summary plots, and visualization tools. These resources assist in segmentation model evaluation in the absence of ground truth, ultimately enabling informed model selection.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 6","pages":"062204"},"PeriodicalIF":2.3,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13050620/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147634872","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":"Limits of CNR and MSE in medical image quality.","authors":"Matthew A Kupinski","doi":"10.1117/1.JMI.13.S2.S22402","DOIUrl":"10.1117/1.JMI.13.S2.S22402","url":null,"abstract":"<p><strong>Purpose: </strong>Contrast-to-noise ratio (CNR) and mean-squared error (MSE) are often treated as compact surrogates for image quality. The purpose of this tutorial is to revisit why these scalar summaries are incomplete for detection and decision tasks unless the task, ensemble, and observer that make them meaningful are stated.</p><p><strong>Approach: </strong>We use reproducible numerical demonstrations, beginning with simple examples where CNR agrees with visual intuition and then showing how CNR fails when signal size changes. The Rose model is used as an intermediary between CNR and task-based assessment because it includes contrast, noise, and signal area while explicitly stating its assumptions. We then discuss failures caused by background variability, signal variability, noise correlation, and reconstruction-dependent texture and relate these failures to observer-based figures of merit.</p><p><strong>Results: </strong>CNR agrees with detectability only under restrictive conditions: a specified detection task, fixed known signal support, known background, effectively white noise, and an observer matched to the relevant image features. The Rose model corrects the most immediate omission by including signal area, and under its assumptions, it is ideal-observer-like. When signal extent, spatial frequency content, noise correlation, anatomical variability, location uncertainty, nonlinear processing, or distortion type changes, images can have equal CNR or equal MSE and substantially different detectability.</p><p><strong>Conclusions: </strong>CNR and MSE are useful descriptive statistics, but they are not general image quality figures of merit in the Barrett sense unless the task, ensemble, and observer that make them meaningful are stated. In particular, low-contrast detectability should not be used as a synonym for CNR unless the detection task and observer model that make the equivalence valid have been specified. For medical imaging optimization, CNR and MSE should be interpreted alongside, or replaced by, task-based measures such as ideal observer, Hotelling observer, channelized Hotelling observer, receiver operating characteristic, or estimation-task performance.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 Suppl 2","pages":"S22402"},"PeriodicalIF":2.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13615865/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149065205","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":"Constructing efficient channels for ideal observers using the conjugate gradient method.","authors":"Weimin Zhou","doi":"10.1117/1.JMI.13.S2.S22403","DOIUrl":"10.1117/1.JMI.13.S2.S22403","url":null,"abstract":"<p><strong>Purpose: </strong>Task-based assessment of image quality is critically important for the design and optimization of medical imaging systems. Ideal observers, including the Bayesian ideal observer (IO) and the ideal linear observer, i.e., the Hotelling observer (HO), provide objective figures of merit that quantify system performance on signal detection tasks. However, the application of ideal observers to high-dimensional image data is often computationally intractable. Channel mechanisms provide an effective framework for dimensionality reduction that can facilitate the computation of ideal observers. We present a conjugate gradient (CG)-based method to construct efficient channels for approximating the IO and HO performance.</p><p><strong>Approach: </strong>The channels are constructed using the CG method associated with the optimization of linear discriminant for signal detection tasks. The proposed method is capable of incorporating prior information about the objects being imaged. Numerical studies are conducted for a binary signal detection task involving type I lumpy backgrounds. The proposed CG-based channels are compared with partial least squares (PLS) channels in terms of their ability to preserve task-relevant information for approximating the IO and HO performance. The effects of channel number and training dataset size on signal detection performance are systematically investigated.</p><p><strong>Results: </strong>For the considered signal-known-exactly and background-known-statistically binary detection task, the CG-based channels provide efficient low-dimensional representations of images that preserve task-relevant information and enable accurate estimation of the IO and HO performance. Compared with the PLS channels, the proposed method that incorporates prior information about the objects being imaged produces cleaner channels and improved detection performance, particularly under limited training data conditions.</p><p><strong>Conclusion: </strong>The proposed CG-based channelization approach provides a principled and efficient way for extracting task-relevant features that enable accurate approximation of the IO and HO performance. By incorporating prior information about the objects being imaged, the proposed method can effectively construct efficient channels using a limited training dataset.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 Suppl 2","pages":"S22403"},"PeriodicalIF":2.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13668019/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149197185","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":"Utility of photon-counting CT localizer radiograph in opportunistic bone densitometry.","authors":"Katie Olivas, George Ibrahim, Cindy McCabe, Nicholas Felice, Tristan Nowak, Michael Grasruck, Steve Bache, Leah Waldman, Erin Macdonald, Richard Lee, Ehsan Samei, Ehsan Abadi","doi":"10.1117/1.JMI.13.5.053501","DOIUrl":"10.1117/1.JMI.13.5.053501","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Purpose: &lt;/strong&gt;Dual-energy X-ray absorptiometry (DXA) is the clinical gold standard for areal bone mineral density (aBMD) assessment for the detection of osteoporosis. The advancement of photon-counting CT (PCCT) provides an opportunity to use spectral localizer radiographs (LRs) for opportunistic aBMD assessment. This study explored that feasibility.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Approach: &lt;/strong&gt;The study used a combination of virtual imaging trials (VITs) and physical phantom experiments. For the VIT experiment, a 50th percentile BMI patient model was conditioned to represent three bone health statuses (normal, osteopenic, and osteoporotic) and was imaged with PCCT LR at six different tube currents (30, 60, 80, 100, 120, and 140 mAs). The simulation was repeated for two additional body sizes at BMI of 20 and &lt;math&gt;&lt;mrow&gt;&lt;mn&gt;31&lt;/mn&gt; &lt;mtext&gt;  &lt;/mtext&gt; &lt;mi&gt;kg&lt;/mi&gt; &lt;mo&gt;/&lt;/mo&gt; &lt;msup&gt;&lt;mrow&gt;&lt;mi&gt;m&lt;/mi&gt;&lt;/mrow&gt; &lt;mrow&gt;&lt;mn&gt;2&lt;/mn&gt;&lt;/mrow&gt; &lt;/msup&gt; &lt;/mrow&gt; &lt;/math&gt; . All datasets were evaluated for aBMD quantification derived from PCCT LRs. To confirm accuracy, a lumbar spine phantom was scanned on a clinical PCCT system and on a DXA device, and aBMD was measured for the L1 to L4 vertebrae.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The VIT study demonstrated stable aBMD accuracy across varying tube current settings, with fluctuations in error limited to &lt;math&gt;&lt;mrow&gt;&lt;mo&gt;∼&lt;/mo&gt; &lt;mn&gt;0.046&lt;/mn&gt; &lt;mtext&gt;  &lt;/mtext&gt; &lt;mrow&gt;&lt;mi&gt;g&lt;/mi&gt;&lt;/mrow&gt; &lt;mo&gt;/&lt;/mo&gt; &lt;msup&gt;&lt;mrow&gt;&lt;mi&gt;cm&lt;/mi&gt;&lt;/mrow&gt; &lt;mrow&gt;&lt;mn&gt;2&lt;/mn&gt;&lt;/mrow&gt; &lt;/msup&gt; &lt;/mrow&gt; &lt;/math&gt; across varying dose levels, within the range of reported lumbar spine DXA variability. Average mean absolute error (MAE) across all dose levels and vertebrae was &lt;math&gt;&lt;mrow&gt;&lt;mn&gt;0.031&lt;/mn&gt; &lt;mtext&gt;  &lt;/mtext&gt; &lt;mrow&gt;&lt;mi&gt;g&lt;/mi&gt;&lt;/mrow&gt; &lt;mo&gt;/&lt;/mo&gt; &lt;msup&gt;&lt;mrow&gt;&lt;mi&gt;cm&lt;/mi&gt;&lt;/mrow&gt; &lt;mrow&gt;&lt;mn&gt;2&lt;/mn&gt;&lt;/mrow&gt; &lt;/msup&gt; &lt;mo&gt;±&lt;/mo&gt; &lt;mn&gt;0.012&lt;/mn&gt;&lt;/mrow&gt; &lt;/math&gt; , &lt;math&gt;&lt;mrow&gt;&lt;mn&gt;0.047&lt;/mn&gt; &lt;mtext&gt;  &lt;/mtext&gt; &lt;mrow&gt;&lt;mi&gt;g&lt;/mi&gt;&lt;/mrow&gt; &lt;mo&gt;/&lt;/mo&gt; &lt;msup&gt;&lt;mrow&gt;&lt;mi&gt;cm&lt;/mi&gt;&lt;/mrow&gt; &lt;mrow&gt;&lt;mn&gt;2&lt;/mn&gt;&lt;/mrow&gt; &lt;/msup&gt; &lt;mo&gt;±&lt;/mo&gt; &lt;mn&gt;0.016&lt;/mn&gt;&lt;/mrow&gt; &lt;/math&gt; , and &lt;math&gt;&lt;mrow&gt;&lt;mn&gt;0.069&lt;/mn&gt; &lt;mtext&gt;  &lt;/mtext&gt; &lt;mrow&gt;&lt;mi&gt;g&lt;/mi&gt;&lt;/mrow&gt; &lt;mo&gt;/&lt;/mo&gt; &lt;msup&gt;&lt;mrow&gt;&lt;mi&gt;cm&lt;/mi&gt;&lt;/mrow&gt; &lt;mrow&gt;&lt;mn&gt;2&lt;/mn&gt;&lt;/mrow&gt; &lt;/msup&gt; &lt;mo&gt;±&lt;/mo&gt; &lt;mn&gt;0.020&lt;/mn&gt;&lt;/mrow&gt; &lt;/math&gt; for normal, osteopenic, and osteoporotic bone, corresponding to percent errors of &lt;math&gt;&lt;mrow&gt;&lt;mn&gt;2.77&lt;/mn&gt; &lt;mo&gt;%&lt;/mo&gt; &lt;mrow&gt;&lt;mo&gt;±&lt;/mo&gt;&lt;/mrow&gt; &lt;mn&gt;0.40&lt;/mn&gt; &lt;mo&gt;%&lt;/mo&gt;&lt;/mrow&gt; &lt;/math&gt; , &lt;math&gt;&lt;mrow&gt;&lt;mn&gt;4.85&lt;/mn&gt; &lt;mo&gt;%&lt;/mo&gt; &lt;mrow&gt;&lt;mo&gt;±&lt;/mo&gt;&lt;/mrow&gt; &lt;mn&gt;0.31&lt;/mn&gt; &lt;mo&gt;%&lt;/mo&gt;&lt;/mrow&gt; &lt;/math&gt; , and &lt;math&gt;&lt;mrow&gt;&lt;mn&gt;8.36&lt;/mn&gt; &lt;mo&gt;%&lt;/mo&gt; &lt;mrow&gt;&lt;mo&gt;±&lt;/mo&gt;&lt;/mrow&gt; &lt;mn&gt;0.57&lt;/mn&gt; &lt;mo&gt;%&lt;/mo&gt;&lt;/mrow&gt; &lt;/math&gt; . Patient size influenced aBMD quantification accuracy, with mean MAE across bone-density conditions increasing from &lt;math&gt;&lt;mrow&gt;&lt;mn&gt;0.053&lt;/mn&gt; &lt;mtext&gt;  &lt;/mtext&gt; &lt;mrow&gt;&lt;mi&gt;g&lt;/mi&gt;&lt;/mrow&gt; &lt;mo&gt;/&lt;/mo&gt; &lt;msup&gt;&lt;mrow&gt;&lt;mi&gt;cm&lt;/mi&gt;&lt;/mrow&gt; &lt;mrow&gt;&lt;mn&gt;2&lt;/mn&gt;&lt;/mrow&gt; &lt;/msup&gt; &lt;/mrow&gt; &lt;/math&gt; at BMI 20 to &lt;math&gt;&lt;mrow&gt;&lt;mn&gt;0.113&lt;/mn&gt; &lt;mtext&gt;  &lt;/mtext&gt; &lt;mrow&gt;&lt;mi&gt;g&lt;/mi&gt;&lt;/mrow&gt; &lt;mo&gt;/","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 5","pages":"053501"},"PeriodicalIF":2.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13588485/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149008469","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":"SoftSpot3D: prospective study of mobile 3D reconstruction for infants' cranial conditions.","authors":"Bo Wu, Can Kocabalkanli, Fereshteh Aalamifar, Marius George Linguraru, Athena Zhang, Robert Francis Keating, Angela Myers, Mario Blondin, Mary Kathryn Hederick, Christopher Michael Runyan, Gary Francis Rogers, Reza Seifabadi","doi":"10.1117/1.JMI.13.5.054502","DOIUrl":"10.1117/1.JMI.13.5.054502","url":null,"abstract":"<p><strong>Purpose: </strong>Deformational plagiocephaly and craniosynostosis require early detection for effective and less invasive interventions. Although 3D imaging and automated analysis allow for image-based assessment by nonspecialists, current 3D imaging systems are often costly and immobile. We present SoftSpot3D, a mobile three-dimensional head reconstruction framework designed as an accessible, low-cost screening solution for infant cranial assessment.</p><p><strong>Approach: </strong>The system is independent of marker placement, leveraging a patterned cap strictly for feature-based tracking rather than geometric registration. Developed for iPad using consumer-grade RGB-D sensors, our pipeline mitigates infant motion through RGB-D odometry and generalized iterative closest point refinement to generate accurate cranial models. Clinical metrics are then automatically extracted by analyzing cross-sectional contours at the standardized measurement plane.</p><p><strong>Results: </strong>Validated against the 3dMD (3dMD LLC, Atlanta, Georgia, United States) medical-grade stereophotogrammetry system on 143 infants (mean age: <math><mrow><mn>5.73</mn> <mo>±</mo> <mn>2.99</mn></mrow> </math> months; 98 males, 45 females), the system achieved an average cranial Hausdorff distance of <math><mrow><mn>2.94</mn> <mo>±</mo> <mn>1.32</mn> <mtext>  </mtext> <mi>mm</mi></mrow> </math> compared with 3dMD reference meshes. Key diagnostic shape indices demonstrated high clinical agreement, with mean absolute errors of <math><mrow><mn>2.18</mn> <mo>±</mo> <mn>1.63</mn></mrow> </math> for cranial index and <math><mrow><mn>2.16</mn> <mo>±</mo> <mn>1.90</mn></mrow> </math> for cranial vault asymmetry index (both unitless ratios).</p><p><strong>Conclusion: </strong>These results establish the clinical accuracy of the system as an accessible, low-cost screening solution, providing the evidence base for its integration into routine pediatric care to enable more efficient early detection and referrals. Furthermore, the framework automatically generates a structured clinical report incorporating quantitative metrics and multiview visualizations, facilitating immediate point-of-care decision-making.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 5","pages":"054502"},"PeriodicalIF":2.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13673180/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149217087","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}