Journal of Medical Imaging最新文献

筛选
英文 中文
Evaluating GPT-5 as a generalist multimodal clinical model. 评估GPT-5作为多面手多模式临床模型。
IF 2.3
Journal of Medical Imaging Pub Date : 2027-01-01 Epub Date: 2026-11-03 DOI: 10.1117/1.JMI.14.S1.S12602
Alexandru Florea, Shansong Wang, Mingzhe Hu, Qiang Li, Zach Eidex, Luke Del Balzo, Mojtaba Safari, Xiaofeng Yang
{"title":"Evaluating GPT-5 as a generalist multimodal clinical model.","authors":"Alexandru Florea, Shansong Wang, Mingzhe Hu, Qiang Li, Zach Eidex, Luke Del Balzo, Mojtaba Safari, Xiaofeng Yang","doi":"10.1117/1.JMI.14.S1.S12602","DOIUrl":"10.1117/1.JMI.14.S1.S12602","url":null,"abstract":"<p><strong>Purpose: </strong>The transition from task-specific artificial intelligence toward general-purpose foundation models raises fundamental questions about their capacity to support the integrated reasoning required in clinical medicine, where diagnosis demands synthesis of ambiguous patient narratives, laboratory data, and multimodal imaging.</p><p><strong>Approach: </strong>We provide the first controlled, cross-sectional evaluation of the GPT-5 family (GPT-5, GPT-5 Mini, and GPT-5nano) against its predecessor GPT-4o across a diverse spectrum of clinically grounded tasks, grounded tasks, including the United States Medical Licensing Examination, text-based, text-based reasoning benchmarks (MedQA and MedXpertQA Text), and visual question answering (VQA) in neuroradiology (BraTS), digital pathology (PathVQA and BreakHis), and mammography (EMBED, InBreast, Chinese Mammography Database, and CBIS-DDSM) using a standardized zero-shot chain-of-thought protocol.</p><p><strong>Results: </strong>GPT-5 demonstrated substantial performance gains with absolute improvements exceeding 25 percentage points on MedXpertQA. When tasked with multimodal synthesis, GPT-5 effectively leveraged its enhanced training corpora to achieve state-of-the-art or competitive performance across most VQA benchmarks and outperformed GPT-4o by margins of 10% to 40% in mammography tasks requiring fine-grained lesion characterization. However, performance remained moderate in neuroradiology (44% macro-average accuracy) and lagged substantially behind domain-specific models in mammography, where specialized systems exceed 80% accuracy compared with GPT-5's 52% to 64%.</p><p><strong>Conclusions: </strong>These findings indicate that although GPT-5 represents a meaningful advance toward general, multimodal clinical inference, generalist models are still not yet substitutes for purpose-built systems in highly specialized, perception-critical tasks. We delineate the current VQA landscape, positioning GPT-5 as a powerful adjunct capable of holistic inference while underscoring that domain adaptation, rigorous validation, and guarantees of reasoning transparency remain essential prerequisites for clinical deployment.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"14 Suppl 1","pages":"S12602"},"PeriodicalIF":2.3,"publicationDate":"2027-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13730543/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149326115","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}
引用次数: 0
End-to-end deep learning for identifying Alzheimer's disease signatures in spectral fluorescence imaging of normal-appearing brain regions in 5xFAD mice. 端到端深度学习在5xFAD小鼠正常脑区光谱荧光成像中识别阿尔茨海默病特征
IF 2.3
Journal of Medical Imaging Pub Date : 2026-11-01 Epub Date: 2026-11-06 DOI: 10.1117/1.JMI.13.6.064001
Raissa Souza, Anastasiia A Stepanchuk, Paula J Brandt, Anthony J Winder, Mohammad Khazaei, Peter K Stys, Nils D Forkert
{"title":"End-to-end deep learning for identifying Alzheimer's disease signatures in spectral fluorescence imaging of normal-appearing brain regions in 5xFAD mice.","authors":"Raissa Souza, Anastasiia A Stepanchuk, Paula J Brandt, Anthony J Winder, Mohammad Khazaei, Peter K Stys, Nils D Forkert","doi":"10.1117/1.JMI.13.6.064001","DOIUrl":"10.1117/1.JMI.13.6.064001","url":null,"abstract":"<p><strong>Purpose: </strong>Alzheimer's disease (AD) is the leading cause of dementia, characterized by the accumulation of amyloid- <math><mrow><mi>β</mi></mrow> </math> and tau aggregates in the brain. Current diagnostic approaches primarily detect mature plaques, but growing evidence suggests that pre-fibrillar aggregates are present earlier in normal-appearing tissue and may provide a valuable window for intervention. We propose the first proof-of-concept end-to-end deep learning (DL) model to identify AD signatures directly from normal-appearing tissue (i.e., background parenchyma) of raw spectral fluorescence data.</p><p><strong>Approach: </strong>To develop and evaluate our DL model, we used one million signals extracted from spectral fluorescence images of brain cortex sections collected from wild-type and 5xFAD mice (a transgenic strain carrying five familial human AD mutations).</p><p><strong>Results: </strong>Our results demonstrate that AD-related signatures can indeed be detected in normal-appearing brain cortex regions. Experiments revealed that model performance depends on input dimensions, training set size, and the preprocessing kernel size. The optimal configuration used <math><mrow><mn>1000</mn> <mo>×</mo> <mn>32</mn></mrow> </math> input, 9000 training samples, and a <math><mrow><mn>3</mn> <mo>×</mo> <mn>3</mn></mrow> </math> kernel, achieving <math><mrow><mo>≥</mo> <mn>95</mn> <mo>%</mo></mrow> </math> accuracy, sensitivity, specificity, <math><mrow><mi>F</mi> <mn>1</mn></mrow> </math> -score, and area under the receiver operating characteristic curve. Importantly, no mice were misclassified, and saliency analysis indicated that a broad range of spectral fluorescence wavelengths contributed to the model's decisions.</p><p><strong>Conclusions: </strong>These findings highlight the potential of DL-based analysis of spectral fluorescence data to enable earlier detection of AD-related changes, supporting a shift toward a more proactive strategy for biomarker discovery.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 6","pages":"064001"},"PeriodicalIF":2.3,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13768351/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149411850","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}
引用次数: 0
OMAMA-DB: the Oregon-Massachusetts Mammography Database. OMAMA-DB:俄勒冈-马萨诸塞州乳房x光检查数据库。
IF 2.3
Journal of Medical Imaging Pub Date : 2026-11-01 Epub Date: 2026-05-25 DOI: 10.1117/1.JMI.13.6.062205
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
{"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":"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":2.3,"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}
引用次数: 0
Peer-Validated Resources for Medical Imaging: From Scientific Products to Scientific Infrastructure. 医学成像的同行验证资源:从科学产品到科学基础设施。
IF 2.3
Journal of Medical Imaging Pub Date : 2026-11-01 Epub Date: 2026-10-13 DOI: 10.1117/1.JMI.13.6.062201
Daniel Haehn, Daniel Moyer, Chris Rorden, Rudolph Pienaar
{"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":"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}
引用次数: 0
Noise2Flow: single-image conditional mean denoising flows from weak-anchor couplings. Noise2Flow:单图像条件平均去噪流弱锚耦合。
IF 2.3
Journal of Medical Imaging Pub Date : 2026-11-01 Epub Date: 2026-11-13 DOI: 10.1117/1.JMI.13.6.064002
Yipeng Sun, Linda-Sophie Schneider, Mingxuan Gu, Siyuan Mei, Chengze Ye, Linghan Cai, Jinhua Wang, Ge Hu, Daiqi Liu, Zijin Yang, Fei Wu, Siming Bayer, Lan Song, Andreas Maier
{"title":"Noise2Flow: single-image conditional mean denoising flows from weak-anchor couplings.","authors":"Yipeng Sun, Linda-Sophie Schneider, Mingxuan Gu, Siyuan Mei, Chengze Ye, Linghan Cai, Jinhua Wang, Ge Hu, Daiqi Liu, Zijin Yang, Fei Wu, Siming Bayer, Lan Song, Andreas Maier","doi":"10.1117/1.JMI.13.6.064002","DOIUrl":"https://doi.org/10.1117/1.JMI.13.6.064002","url":null,"abstract":"<p><strong>Purpose: </strong>Single-image denoising is needed when clean targets and repeated acquisitions are unavailable, as in low-dose computed tomography (CT) and fluorescence microscopy. Existing per-image methods often assume pixel-wise noise independence, which fails under spatially correlated noise, and imperfect single-image denoisers commonly leave residual noise. We learn a proxy mean-velocity direction field from one noisy image so that a single transport step exceeds the imperfect anchors used as supervision.</p><p><strong>Approach: </strong>Noise2Flow runs weak single-image denoisers on the noisy image to form source-target couplings. The displacement from input to anchor is a directional proxy for the mean restoration velocity. For each imposed linear segment, MeanFlow's finite-interval average velocity reduces exactly to a constant secant. A flow network is trained with a direction-normalized objective that regularizes predictions at states in a stochastic tube around the noisy-to-anchor segment toward a common secant direction. At inference, the weak denoisers are discarded; one update with a calibrated transport budget restores the image.</p><p><strong>Results: </strong>On the fluorescence microscopy denoising (FMD) test set of 48 images, Noise2Flow reaches 34.91 dB peak signal-to-noise ratio and 0.887 structural similarity, 0.52 dB above Filter2Noise, and 1.00 dB above Noise2Detail. On 1311 low-dose CT slices from 10 Mayo Clinic patients, it reaches 28.82 dB and 0.714, 0.91 dB above Filter2Noise and 1.23 dB above Noise2Detail. One-step inference is within 0.11 dB of 10-step Heun; tube sampling improves the 10-step Heun result relative to on-segment training; a calibrated extrapolation factor moves the flow past residual-noise anchors of varying quality.</p><p><strong>Conclusions: </strong>A proxy mean-velocity direction field can be learned from a single noisy medical image by treating weak-denoiser outputs as directional anchors rather than final targets. The straight proxy path defines the one-step endpoint update; tube regularization and calibrated extrapolation carry that update past residual-noise anchors. The learned flow exceeds residual-noise anchors and supports reference-free restoration in data-limited imaging.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 6","pages":"064002"},"PeriodicalIF":2.3,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13761232/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149411851","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}
引用次数: 0
MILU: a consensus ensemble benchmark for multimodal medical imaging lecture understanding. MILU:多模态医学影像讲座理解的共识集合基准。
IF 2.3
Journal of Medical Imaging Pub Date : 2026-11-01 Epub Date: 2026-04-15 DOI: 10.1117/1.JMI.13.6.062202
Md Motaleb Hossen Manik, Md Zabirul Islam, Ge Wang
{"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}
引用次数: 0
mach: ultrafast ultrasound beamforming. 马赫:超快超声波束形成。
IF 2.3
Journal of Medical Imaging Pub Date : 2026-11-01 Epub Date: 2026-04-06 DOI: 10.1117/1.JMI.13.6.062203
Charles Guan, Alexander P Rockhill, Masashi Sode, Gianmarco Pinton
{"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}
引用次数: 0
Representation geometry and task performance in vision-language modeling for computed tomography enterography. 计算机体层摄影术视觉语言建模中的表示几何和任务性能。
IF 2.3
Journal of Medical Imaging Pub Date : 2026-11-01 Epub Date: 2026-11-10 DOI: 10.1117/1.JMI.13.6.064501
Cristian Minoccheri, Emily Wittrup, Kayvan Najarian, Ryan Stidham
{"title":"Representation geometry and task performance in vision-language modeling for computed tomography enterography.","authors":"Cristian Minoccheri, Emily Wittrup, Kayvan Najarian, Ryan Stidham","doi":"10.1117/1.JMI.13.6.064501","DOIUrl":"10.1117/1.JMI.13.6.064501","url":null,"abstract":"<p><strong>Purpose: </strong>Computed tomography (CT) enterography is central to inflammatory bowel disease evaluation, but optimal representation choices for vision-language learning on this volumetric modality are unclear. We establish baseline performance and quantify how aggregation, slice encoding, and retrieval context affect classification, retrieval, and report generation.</p><p><strong>Approach: </strong>We fine-tuned vision-language models on abdominal CT enterography with parameter-efficient adapters and compared (i) mean versus attention pooling of slice embeddings, (ii) multiwindow red-green-blue Hounsfield-unit encoding versus multiplanar sampling for added spatial coverage, and (iii) report generation with versus without retrieval-augmented generation (RAG). A three-teacher pseudolabel framework enabled evaluation without expert annotations. Classification and retrieval comparisons used three training seeds.</p><p><strong>Results: </strong>Mean and attention pooling achieved the same mean three-class disease classification accuracy (55.7%; standard deviations of 2.0 and 2.4 percentage points) at the largest low-rank adaptation capacity. Neither consistently outperformed the other at matched capacity with central sampling. Sixteen slices at 20% to 80% had higher classification accuracy than 8 slices, 32 slices, and 10% to 90% sampling in all three seeds for both pooling methods. The tested multiplanar configurations had lower classification accuracy. For report generation, fine-tuning without retrieval performed at prevalence-matched chance for within-1 report-label agreement (70.4% versus 71.0% random). RAG improved within-1 report-label agreement by 7 to 14 points over chance and reduced ordinal mean absolute error from 0.98 to 0.80-0.89.</p><p><strong>Conclusions: </strong>Slice sampling and tissue-contrast-focused encoding affect performance in CT enterography vision-language systems, and RAG improved report-label agreement over the fine-tuned baseline. These results provide initial baselines and practical guidance for multimodal learning in volumetric CT.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 6","pages":"064501"},"PeriodicalIF":2.3,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13749121/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149388229","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}
引用次数: 0
Measured and synthetic rigid head motion datasets via generative model for motion simulation and compensation in medical imaging. 基于生成模型的测量和合成刚性头部运动数据集,用于医学成像中的运动仿真和补偿。
IF 2.3
Journal of Medical Imaging Pub Date : 2026-11-01 Epub Date: 2026-07-17 DOI: 10.1117/1.JMI.13.6.062206
Manuela Goldmann, Felix Damm, Florian Goldmann, Oliver Hornung, Michael Manhart, Alexander Preuhs, Markus Kowarschik, Andreas Maier
{"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}
引用次数: 0
In search of truth: evaluating concordance of AI-based anatomy segmentation models. 寻找真理:评估基于人工智能的解剖分割模型的一致性。
IF 2.3
Journal of Medical Imaging Pub Date : 2026-11-01 Epub Date: 2026-04-03 DOI: 10.1117/1.JMI.13.6.062204
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
{"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}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书