Journal of Medical Imaging最新文献

{"title":"MedPTQ: a practical pipeline for real post-training quantization in 3D medical image segmentation.","authors":"Chongyu Qu, Ritchie Zhao, Ye Yu, Bin Liu, Tianyuan Yao, Junchao Zhu, Bennett A Landman, Yucheng Tang, Yuankai Huo","doi":"10.1117/1.JMI.13.1.014006","DOIUrl":"10.1117/1.JMI.13.1.014006","url":null,"abstract":"<p><strong>Purpose: </strong>Quantizing deep neural networks, reducing the precision (bit-width) of their computations, can remarkably decrease memory usage and accelerate processing, making these models more suitable for large-scale medical imaging applications with limited computational resources. However, many existing methods studied \"simulated quantization,\" which simulates lower precision operations during inference but does not actually reduce model size or improve real-world inference speed. Moreover, the potential of deploying real three-dimensional (3D) low-bit quantization on modern graphics processing units (GPUs) is still unexplored.</p><p><strong>Approach: </strong>We introduce MedPTQ, an open-source pipeline for real post-training quantization that implements true 8-bit (INT8) inference on state-of-the-art (SOTA) 3D medical segmentation models, i.e., U-Net, SegResNet, SwinUNETR, nnU-Net, UNesT, TransUNet, ST-UNet, and VISTA3D. MedPTQ involves two main steps. First, we use TensorRT to perform simulated quantization for both weights and activations with an unlabeled calibration dataset. Second, we convert this simulated quantization into real quantization via the TensorRT engine on real GPUs, resulting in real-world reductions in model size and inference latency.</p><p><strong>Results: </strong>Extensive experiments benchmark MedPTQ across seven models and three datasets and demonstrate that it effectively performs INT8 quantization on GPUs, reducing model size by up to 3.83× and latency by up to 2.74×, while maintaining nearly identical Dice similarity coefficient (mDSC) performance to FP32 models. This advancement enables the deployment of efficient deep learning models in medical imaging applications where computational resources are constrained. The MedPTQ code and models have been released, including U-Net, TransUNet pretrained on the BTCV dataset for abdominal (13-label) segmentation, UNesT pretrained on the Whole Brain Dataset for whole brain (133-label) segmentation, and nnU-Net, SegResNet, SwinUNETR, and VISTA3D pretrained on TotalSegmentator V2 for full body (104-label) segmentation.</p><p><strong>Conclusions: </strong>We have introduced MedPTQ, a real post-training quantization pipeline that delivers INT8 inference for SOTA 3D artificial intelligence (AI) models in medical imaging segmentation. MedPTQ effectively reduces real-world model size, computational requirements, and inference latency without compromising segmentation accuracy on modern GPUs, as evidenced by mDSC comparable to full-precision baselines. We validate MedPTQ across a diverse set of AI architectures, ranging from convolutional-neural-network-based to transformer-based models, and a wide variety of medical imaging datasets. These datasets are collected from multiple hospitals with distinct imaging protocols, cover different body regions (such as the brain, abdomen, or full body), and include multiple imaging modalities [computed tomography (CT) and magne","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 1","pages":"014006"},"PeriodicalIF":2.3,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12912285/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146221578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing deep learning interpretability for hand-crafted feature-guided histologic image classification via weak-to-strong generalization.","authors":"Zong Fan, Changjie Lu, Jialin Yue, Mark Anastasio, Lulu Sun, Xiaowei Wang, Hua Li","doi":"10.1117/1.JMI.13.1.017502","DOIUrl":"10.1117/1.JMI.13.1.017502","url":null,"abstract":"<p><strong>Purpose: </strong>Deep learning (DL) models have achieved promising performance in histologic whole-slide image analysis for various clinical applications. However, their black-box nature hinders the interpretability of DL features for clinical adoption. By contrast, hand-crafted features (HCFs) directly calculated from images offer strong interpretability but with reduced predictive power of DL models. The relationship between DL features and HCFs remains insufficiently explored. We aim to enhance the interpretability and performance of DL models using a weak-to-strong generalization (WSG) framework that integrates HCFs into the learning process.</p><p><strong>Approach: </strong>The proposed WSG framework leverages an interpretable and HCF-based \"weak\" teacher model that supervises a \"strong\" DL student model to learn and improve itself by generalizing from weaker forms of reasoning to stronger ones, for classification tasks. An adaptive bootstrap WSG loss function is designed to optimize the transfer of knowledge from hand-crafted to deep-learned features, enabling systematic analysis of feature interactions. Innovatively, mutual information (MI) between HCFs and DL features learned by student models is analyzed to gain insights into their correlations and the interpretability of DL features. The framework is evaluated using extensive experiments on three public datasets with diverse combinations of teacher and student models for tumor classification.</p><p><strong>Results: </strong>The WSG framework achieves consistent improvements in classification performance across all evaluated models. Qualitative saliency-map analysis indicates that WSG supervision enables student models to concentrate on diagnostically relevant regions, thereby improving interpretability. Furthermore, quantitative analysis reveals a notable increase in MI between hand-crafted and deep-learned features following WSG training compared with that without WSG training, indicating more effective integration of expert knowledge into the learned representations.</p><p><strong>Conclusions: </strong>Our study elucidates the key HCFs that drive DL model predictions in histologic image classification. The findings demonstrate that integrating HCFs into DL model training via the WSG framework can enhance both the interpretability and the model's predictive performance, supporting their broader clinical adoption.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 1","pages":"017502"},"PeriodicalIF":2.3,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12818695/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146020152","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":"BAF-UNet: a boundary-aware segmentation model for skin lesion segmentation.","authors":"Menglei Zhang, Congwei Zhang, Zhibin Quan, Bing Guo, Wankou Yang","doi":"10.1117/1.JMI.13.1.014003","DOIUrl":"https://doi.org/10.1117/1.JMI.13.1.014003","url":null,"abstract":"<p><strong>Purpose: </strong>Skin lesion segmentation plays a significant role in the diagnosis and treatment of skin cancer. Accurate skin lesion segmentation is essential for skin cancer diagnosis and treatment but is challenged by ambiguous boundaries and diverse lesion shapes and sizes. We aim to improve segmentation performance with enhanced boundary preservation.</p><p><strong>Approach: </strong>We propose BAF-UNet, a boundary-aware segmentation network. It integrates a multiscale boundary-aware feature fusion (BFF) module to combine low-level boundary features with high-level semantic information, and a boundary-aware vision transformer (BAViT) that incorporates boundary guidance into MobileViT to capture local and global context. A boundary-focused loss function is also introduced to prioritize edge accuracy during training. The model is evaluated on ISIC2016, ISIC2017, and PH2 datasets.</p><p><strong>Results: </strong>Experiments demonstrate that BAF-UNet improves Dice scores and boundary accuracy compared to baseline models. The BFF and BAViT modules enhance boundary delineation while maintaining robustness across lesions of varying shapes and sizes.</p><p><strong>Conclusions: </strong>BAF-UNet effectively integrates boundary guidance into feature fusion and transformer-based context modeling, significantly improving segmentation accuracy, particularly along lesion edges, and shows potential for clinical application in automated skin cancer diagnosis.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 1","pages":"014003"},"PeriodicalIF":1.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12782429/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145953505","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":"Synthetic multi-inversion time magnetic resonance images for visualization of subcortical structures.","authors":"Savannah P Hays, Lianrui Zuo, Anqi Feng, Yihao Liu, Blake E Dewey, Jiachen Zhuo, Ellen M Mowry, Scott D Newsome, Jerry L Prince, Aaron Carass","doi":"10.1117/1.JMI.13.1.014002","DOIUrl":"10.1117/1.JMI.13.1.014002","url":null,"abstract":"<p><strong>Purpose: </strong>Visualization of subcortical gray matter is essential in neuroscience and clinical practice, particularly for disease understanding and surgical planning. Although multi-inversion time (multi-TI) <math> <mrow><msub><mi>T</mi> <mn>1</mn></msub> </mrow> </math> -weighted ( <math> <mrow><msub><mi>T</mi> <mn>1</mn></msub> </mrow> </math> -w) magnetic resonance (MR) imaging improves visualization, it is only acquired in specific clinical settings and not available in common public MR datasets.</p><p><strong>Approach: </strong>We present SyMTIC (synthetic multi-TI contrasts), a deep learning method that generates synthetic multi-TI images using routinely acquired <math> <mrow><msub><mi>T</mi> <mn>1</mn></msub> </mrow> </math> -w, <math> <mrow><msub><mi>T</mi> <mn>2</mn></msub> </mrow> </math> -weighted ( <math> <mrow><msub><mi>T</mi> <mn>2</mn></msub> </mrow> </math> -w), and fluid-attenuated inversion recovery (FLAIR) images. Our approach combines image translation via deep neural networks with imaging physics to estimate longitudinal relaxation time ( <math><mrow><mi>T</mi> <mn>1</mn></mrow> </math> ) and proton density ( <math><mrow><mi>ρ</mi></mrow> </math> ) maps. These maps are then used to compute multi-TI images with arbitrary inversion times.</p><p><strong>Results: </strong>SyMTIC was trained using paired magnetization prepared rapid acquisition with gradient echo (MPRAGE) and fast gray matter acquisition T1 inversion recovery (FGATIR) images along with <math> <mrow><msub><mi>T</mi> <mn>2</mn></msub> </mrow> </math> -w and FLAIR images. It accurately synthesized multi-TI images from standard clinical inputs, achieving image quality comparable to that from explicitly acquired multi-TI data. The synthetic images, especially for TI values between 400 to 800 ms, enhanced visualization of subcortical structures and improved segmentation of thalamic nuclei.</p><p><strong>Conclusion: </strong>SyMTIC enables robust generation of high-quality multi-TI images from routine MR contrasts. When paired with the HACA3 algorithm, it generalizes well to varied clinical datasets, including those without FLAIR or <math> <mrow><msub><mi>T</mi> <mn>2</mn></msub> </mrow> </math> -w images and unknown parameters, offering a practical solution for improving brain MR image visualization and analysis.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 1","pages":"014002"},"PeriodicalIF":1.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12770912/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145918841","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":"Ultrasound imaging using single-element biaxial beamforming.","authors":"Nathan Meulenbroek, Laura Curiel, Adam Waspe, Samuel Pichardo","doi":"10.1117/1.JMI.13.1.017001","DOIUrl":"https://doi.org/10.1117/1.JMI.13.1.017001","url":null,"abstract":"<p><strong>Purpose: </strong>Dynamic focusing of received ultrasound signals, or beamforming, is foundational for ultrasound imaging. Conventionally, it requires arrays of ultrasound sensors to estimate where sound came from using time-of-flight (TOF) measurements. We demonstrate passive beamforming with a single biaxial sensor and accurate passive acoustic mapping with two biaxial sensors using only direction of arrival (DOA) information.</p><p><strong>Approach: </strong>We introduce two single-element biaxial beamforming algorithms and four biaxial image reconstruction algorithms for a two-element biaxial piezoceramic transducer array. Imaging of a hemispherical acoustic source is characterized in an acoustic scanning tank within the region <math><mrow><mo>-</mo> <mn>30.29</mn> <mtext>  </mtext> <mi>mm</mi></mrow> </math> <math><mrow><mo>≤</mo> <mi>x</mi> <mo>≤</mo></mrow> </math> 29.94 mm and 50.11 mm <math><mrow><mo>≤</mo> <mi>z</mi> <mo>≤</mo></mrow> </math> 90.45 mm relative to the center of the array. Imaging performance is contrasted with delay, sum, and integrate (DSAI) and delay, multiply, sum, and integrate (DMSAI) algorithms.</p><p><strong>Results: </strong>Single-element biaxial beamforming can identify DOA with a median error (± interquartile range) of <math><mrow><mn>0.36</mn> <mo>±</mo> <mn>0.63</mn> <mtext>  </mtext> <mi>deg</mi></mrow> </math> and median full-width half-prominence of <math><mrow><mn>7.3</mn> <mo>±</mo> <mn>8.6</mn> <mtext>  </mtext> <mi>deg</mi></mrow> </math> . Using both array elements, DOA-only images demonstrate overall median localization error of 6.41 mm (lateral: 1.02 mm, axial: 5.85 mm, signal-to-noise ratio (SNR): 15.37) and DOA + TOF images demonstrate overall median error of 6.91 mm (lateral: 1.69 mm, axial: 6.11 mm, SNR: 18.37).</p><p><strong>Conclusions: </strong>To the best of our knowledge, we provide the first demonstration of single-element beamforming using a single stationary piezoceramic and the first demonstration of passive ultrasound imaging without the use of TOF information. These results enable simpler, smaller, more cost-effective arrays for passive ultrasound imaging.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"13 1","pages":"017001"},"PeriodicalIF":1.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12726554/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145828543","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":"Scribble-supervised method for cardiac tissue segmentation using position and temporal contrastive information.","authors":"Xiaoxuan Ma, Yingao Du, Kuncheng Lian","doi":"10.1117/1.JMI.12.6.064002","DOIUrl":"https://doi.org/10.1117/1.JMI.12.6.064002","url":null,"abstract":"<p><strong>Purpose: </strong>Accurate pixel-level segmentation is essential for medical image analysis, particularly in assisting diagnosis and treatment planning. However, fully supervised learning methods rely heavily on high-quality annotated data, which are often scarce due to the high cost of manual labeling, privacy concerns, and limited availability. We aim to reduce reliance on precise annotations and improve segmentation performance under weak supervision.</p><p><strong>Approach: </strong>We propose scribble position and temporal contrast learning (SPTCL), an innovative segmentation method that combines contrastive learning with weak supervision. Our method leverages the spatial continuity in 3D medical image volumes and the anatomical similarities across different cardiac phases to construct a contrastive learning task for robust feature representation from unlabeled data. To enhance the feature extraction capabilities, we employ a pre-trained encoder, which is initially trained on the ACDC dataset using contrastive learning to capture robust feature representations. This pre-trained encoder is then transferred to a weakly supervised segmentation network with a dual-branch decoder for further fine-tuning on the task. The predictions from both branches are fused to generate refined pseudo-labels, which are iteratively used to guide network training with only coarse scribble annotations.</p><p><strong>Results: </strong>Experiments on the ACDC dataset show that SPTCL outperforms existing models, achieving a Dice coefficient of 90.5%, with a 2.5% improvement over the baseline and a 1.7% improvement over the latest model. Furthermore, SPTCL reduces training time by <math><mrow><mo>∼</mo> <mn>33</mn> <mo>%</mo></mrow> </math> .</p><p><strong>Conclusions: </strong>SPTCL effectively addresses the challenges of limited annotation in medical image segmentation by uniting contrastive learning with weak supervision. It demonstrates strong potential for practical deployment in clinical settings where high-quality labels are difficult to obtain.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"12 6","pages":"064002"},"PeriodicalIF":1.7,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12640760/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145596901","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":"Benchmarking of deep learning methods for generic MRI multi-organ abdominal segmentation.","authors":"Deepa Krishnaswamy, Cosmin Ciausu, Steve Pieper, Ron Kikinis, Benjamin Billot, Andrey Fedorov","doi":"10.1117/1.JMI.12.6.064503","DOIUrl":"https://doi.org/10.1117/1.JMI.12.6.064503","url":null,"abstract":"<p><strong>Purpose: </strong>Recent advances in deep learning have led to robust automated tools for segmentation of abdominal computed tomography (CT). Meanwhile, segmentation of magnetic resonance imaging (MRI) is substantially more challenging due to the inherent signal variability and the increased effort required for annotating training datasets. Hence, existing approaches are trained on limited sets of MRI sequences, which might limit their generalizability.</p><p><strong>Approach: </strong>To characterize the landscape of MRI abdominal segmentation tools, we present a comprehensive benchmarking of three state-of-the-art and open-source models: <i>MRSegmentator</i>, <i>MRISegmentator-Abdomen</i>, and <i>TotalSegmentator MRI</i>. As these models are trained using labor-intensive manual annotation cycles, we also introduce and evaluate <i>ABDSynth</i>, a SynthSeg-based model purely trained on widely available CT segmentations (no real images). We assess accuracy and generalizability by leveraging three public datasets (not seen by any of the evaluated methods during their training), which span all major manufacturers, five MRI sequences, as well as a variety of subject conditions, voxel resolutions, and fields-of-view.</p><p><strong>Results: </strong>Our results reveal that <i>MRSegmentator</i> achieves the best performance and is most generalizable. By contrast, <i>ABDSynth</i> yields slightly less accurate results, but its relaxed requirements in training data make it an alternative when the annotation budget is limited.</p><p><strong>Conclusions: </strong>We perform benchmarking of four open-source models for abdominal MR segmentation on three datasets and demonstrate that models trained on real, heterogeneous, multimodal data yield the best overall performance. We provide evaluation code and datasets for future benchmarking at https://github.com/deepakri201/AbdoBench.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"12 6","pages":"064503"},"PeriodicalIF":1.7,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12680082/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145702382","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":"Breast tumor diagnosis via multimodal deep learning using ultrasound B-mode and Nakagami images.","authors":"Sabiq Muhtadi, Caterina M Gallippi","doi":"10.1117/1.JMI.12.S2.S22009","DOIUrl":"10.1117/1.JMI.12.S2.S22009","url":null,"abstract":"<p><strong>Purpose: </strong>We propose and evaluate multimodal deep learning (DL) approaches that combine ultrasound (US) B-mode and Nakagami parametric images for breast tumor classification. It is hypothesized that integrating tissue brightness information from B-mode images with scattering properties from Nakagami images will enhance diagnostic performance compared with single-input approaches.</p><p><strong>Approach: </strong>An EfficientNetV2B0 network was used to develop multimodal DL frameworks that took as input (i) numerical two-dimensional (2D) maps or (ii) rendered red-green-blue (RGB) representations of both B-mode and Nakagami data. The diagnostic performance of these frameworks was compared with single-input counterparts using 831 US acquisitions from 264 patients. In addition, gradient-weighted class activation mapping was applied to evaluate diagnostically relevant information utilized by the different networks.</p><p><strong>Results: </strong>The multimodal architectures demonstrated significantly higher area under the receiver operating characteristic curve (AUC) values ( <math><mrow><mi>p</mi> <mo><</mo> <mn>0.05</mn></mrow> </math> ) than their monomodal counterparts, achieving an average improvement of 10.75%. In addition, the multimodal networks incorporated, on average, 15.70% more diagnostically relevant tissue information. Among the multimodal models, those using RGB representations as input outperformed those that utilized 2D numerical data maps ( <math><mrow><mi>p</mi> <mo><</mo> <mn>0.05</mn></mrow> </math> ). The top-performing multimodal architecture achieved a mean AUC of 0.896 [95% confidence interval (CI): 0.813 to 0.959] when performance was assessed at the image level and 0.848 (95% CI: 0.755 to 0.903) when assessed at the lesion level.</p><p><strong>Conclusions: </strong>Incorporating B-mode and Nakagami information together in a multimodal DL framework improved classification outcomes and increased the amount of diagnostically relevant information accessed by networks, highlighting the potential for automating and standardizing US breast cancer diagnostics to enhance clinical outcomes.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"12 Suppl 2","pages":"S22009"},"PeriodicalIF":2.3,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12077846/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144081335","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":"Semi-supervised semantic segmentation of cell nuclei with diffusion model and collaborative learning.","authors":"Zhuchen Shao, Sourya Sengupta, Mark A Anastasio, Hua Li","doi":"10.1117/1.JMI.12.6.061403","DOIUrl":"10.1117/1.JMI.12.6.061403","url":null,"abstract":"<p><strong>Purpose: </strong>Automated segmentation and classification of the cell nuclei in microscopic images is crucial for disease diagnosis and tissue microenvironment analysis. Given the difficulties in acquiring large labeled datasets for supervised learning, semi-supervised methods offer alternatives by utilizing unlabeled data alongside labeled data. Effective semi-supervised methods to address the challenges of extremely limited labeled data or diverse datasets with varying numbers and types of annotations remain under-explored.</p><p><strong>Approach: </strong>Unlike other semi-supervised learning methods that iteratively use labeled and unlabeled data for model training, we introduce a semi-supervised learning framework that combines a latent diffusion model (LDM) with a transformer-based decoder, allowing for independent usage of unlabeled data to optimize their contribution to model training. The model is trained based on a sequential training strategy. LDM is trained in an unsupervised manner on diverse datasets, independent of cell nuclei types, thereby expanding the training data and enhancing training performance. The pre-trained LDM serves as a powerful feature extractor to support the transformer-based decoder's supervised training on limited labeled data and improve final segmentation performance. In addition, the paper explores a collaborative learning strategy to enhance segmentation performance on out-of-distribution (OOD) data.</p><p><strong>Results: </strong>Extensive experiments conducted on four diverse datasets demonstrated that the proposed framework significantly outperformed other semi-supervised and supervised methods for both in-distribution and OOD cases. Through collaborative learning with supervised methods, diffusion model and transformer decoder-based segmentation (DTSeg) achieved consistent performance across varying cell types and different amounts of labeled data.</p><p><strong>Conclusions: </strong>The proposed DTSeg framework addresses cell nuclei segmentation under limited labeled data by integrating unsupervised LDM training on diverse unlabeled datasets. Collaborative learning demonstrated effectiveness in enhancing the generalization capability of DTSeg to achieve superior results across diverse datasets and cases. Furthermore, the method supports multi-channel inputs and demonstrates strong generalization to both in-distribution and OOD scenarios.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"12 6","pages":"061403"},"PeriodicalIF":2.3,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11924957/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143694064","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":"Impact of menopause and age on breast density and background parenchymal enhancement in dynamic contrast-enhanced magnetic resonance imaging.","authors":"Grey Kuling, Jennifer D Brooks, Belinda Curpen, Ellen Warner, Anne L Martel","doi":"10.1117/1.JMI.12.S2.S22002","DOIUrl":"10.1117/1.JMI.12.S2.S22002","url":null,"abstract":"<p><strong>Purpose: </strong>Breast density (BD) and background parenchymal enhancement (BPE) are important imaging biomarkers for breast cancer (BC) risk. We aim to evaluate longitudinal changes in quantitative BD and BPE in high-risk women undergoing dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), focusing on the effects of age and transition into menopause.</p><p><strong>Approach: </strong>A retrospective cohort study analyzed 834 high-risk women undergoing breast DCE-MRI for screening between 2005 and 2020. Quantitative BD and BPE were derived using deep-learning segmentation. Linear mixed-effects models assessed longitudinal changes and the effects of age, menopausal status, weeks since the last menstrual period (LMP-wks), body mass index (BMI), and hormone replacement therapy (HRT) on these imaging biomarkers.</p><p><strong>Results: </strong>BD decreased with age across all menopausal stages, whereas BPE declined with age in postmenopausal women but remained stable in premenopausal women. HRT elevated BPE in postmenopausal women. Perimenopausal women exhibited decreases in both BD and BPE during the menopausal transition, though cross-sectional age at menopause had no significant effect on either measure. Fibroglandular tissue was positively associated with BPE in perimenopausal women.</p><p><strong>Conclusions: </strong>We highlight the dynamic impact of menopause on BD and BPE and correlate well with the known relationship between risk and age at menopause. These findings advance the understanding of imaging biomarkers in high-risk populations and may contribute to the development of improved risk assessment leading to personalized chemoprevention and BC screening recommendations.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"12 Suppl 2","pages":"S22002"},"PeriodicalIF":2.3,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11894108/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143617600","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}