Computerized Medical Imaging and Graphics最新文献_第3页

KWC-YOLO: An efficient YOLO architecture for lumbar spinal stenosis grading through dynamic convolution and spatially-aware gating KWC-YOLO：一种基于动态卷积和空间感知门控的腰椎管狭窄分级的高效YOLO架构

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2025-12-17 DOI: 10.1016/j.compmedimag.2025.102685

Wei Chen , Fan Wu , Yan Guo , Weiqing Zhuang , Hua Chen , Jie Feng , Jianfeng Wu

Lumbar spinal stenosis (LSS) represents a significant global health burden, and its diagnosis from Magnetic Resonance Imaging (MRI) is often subject to inter-observer variability and time-consuming interpretation. While deep learning (DL) models offer a promising solution, they are frequently constrained by the scarcity of annotated medical data, high computational demands, and challenges in representing subtle pathological features. To address these limitations, we propose KWC-YOLO, a novel and efficient object detection framework for the automated detection and classification of lumbar central canal stenosis (LCCS) severity according to the Schizas grading criteria. Our model enhances the YOLOv11n architecture through three core innovations: (1) the integration of KernelWarehouse (KWConv), a parameter-efficient dynamic convolution mechanism that improves the feature adaptability of the detection head; (2) the introduction of a FasterGATE activation unit in the backbone to enhance non-linear representation and accelerate convergence; and (3) the implementation of a lightweight Slim-Neck structure, which optimizes the trade-off between feature fusion quality and computational cost. On a clinical lumbar spine MRI dataset, KWC-YOLO demonstrates superior performance, achieving a mean Average Precision at an IoU of 0.5 (

A P_{50}

) of 86.7% and an

A P_{95}

of 63.0%. This represents a substantial improvement over the YOLOv11n baseline by 9.2 and 9.3 percentage points in

A P_{50}

and

A P_{95}

respectively, while simultaneously reducing the computational load by 36.5% to 4.0 GFLOPs. Conclusively, KWC-YOLO establishes a new benchmark for automated LCCS grading. Its compelling balance of high accuracy and computational efficiency holds the potential to alleviate the interpretative burden on radiologists, enhance reporting accuracy, and streamline clinical decision-making, ultimately leading to improved patient outcomes.

腰椎管狭窄症（LSS）是一项重大的全球健康负担，其磁共振成像（MRI）诊断往往受到观察者之间的差异和耗时的解释。虽然深度学习（DL）模型提供了一个很有前途的解决方案，但它们经常受到带注释的医疗数据稀缺、高计算需求以及在表示细微病理特征方面的挑战的限制。为了解决这些局限性，我们提出了KWC-YOLO，这是一种新颖高效的目标检测框架，用于根据Schizas分级标准自动检测和分类腰椎中央管狭窄（LCCS）的严重程度。我们的模型通过三个核心创新增强了YOLOv11n架构：(1)集成了KernelWarehouse (KWConv)，这是一种参数高效的动态卷积机制，提高了检测头的特征适应性；(2)在骨干网络中引入FasterGATE激活单元，增强非线性表示，加速收敛；(3)实现了轻量化的细颈结构，优化了特征融合质量和计算成本之间的权衡。在临床腰椎MRI数据集上，KWC-YOLO表现出优异的性能，在IoU为0.5 （AP50）时的平均平均精度为86.7%，AP95为63.0%。这在AP50和AP95中分别比YOLOv11n基线提高了9.2和9.3个百分点，同时将计算负载降低了36.5%，降至4.0 GFLOPs。最后，KWC-YOLO为LCCS自动分级建立了新的基准。它在高精度和计算效率之间取得了令人信服的平衡，有可能减轻放射科医生的解释负担，提高报告准确性，简化临床决策，最终改善患者的治疗效果。

{"title":"KWC-YOLO: An efficient YOLO architecture for lumbar spinal stenosis grading through dynamic convolution and spatially-aware gating","authors":"Wei Chen , Fan Wu , Yan Guo , Weiqing Zhuang , Hua Chen , Jie Feng , Jianfeng Wu","doi":"10.1016/j.compmedimag.2025.102685","DOIUrl":"10.1016/j.compmedimag.2025.102685","url":null,"abstract":"<div><div>Lumbar spinal stenosis (LSS) represents a significant global health burden, and its diagnosis from Magnetic Resonance Imaging (MRI) is often subject to inter-observer variability and time-consuming interpretation. While deep learning (DL) models offer a promising solution, they are frequently constrained by the scarcity of annotated medical data, high computational demands, and challenges in representing subtle pathological features. To address these limitations, we propose KWC-YOLO, a novel and efficient object detection framework for the automated detection and classification of lumbar central canal stenosis (LCCS) severity according to the Schizas grading criteria. Our model enhances the YOLOv11n architecture through three core innovations: (1) the integration of KernelWarehouse (KWConv), a parameter-efficient dynamic convolution mechanism that improves the feature adaptability of the detection head; (2) the introduction of a FasterGATE activation unit in the backbone to enhance non-linear representation and accelerate convergence; and (3) the implementation of a lightweight Slim-Neck structure, which optimizes the trade-off between feature fusion quality and computational cost. On a clinical lumbar spine MRI dataset, KWC-YOLO demonstrates superior performance, achieving a mean Average Precision at an IoU of 0.5 (<span><math><mrow><mi>A</mi><msub><mrow><mi>P</mi></mrow><mrow><mn>50</mn></mrow></msub></mrow></math></span>) of 86.7% and an <span><math><mrow><mi>A</mi><msub><mrow><mi>P</mi></mrow><mrow><mn>95</mn></mrow></msub></mrow></math></span> of 63.0%. This represents a substantial improvement over the YOLOv11n baseline by 9.2 and 9.3 percentage points in <span><math><mrow><mi>A</mi><msub><mrow><mi>P</mi></mrow><mrow><mn>50</mn></mrow></msub></mrow></math></span> and <span><math><mrow><mi>A</mi><msub><mrow><mi>P</mi></mrow><mrow><mn>95</mn></mrow></msub></mrow></math></span> respectively, while simultaneously reducing the computational load by 36.5% to 4.0 GFLOPs. Conclusively, KWC-YOLO establishes a new benchmark for automated LCCS grading. Its compelling balance of high accuracy and computational efficiency holds the potential to alleviate the interpretative burden on radiologists, enhance reporting accuracy, and streamline clinical decision-making, ultimately leading to improved patient outcomes.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"127 ","pages":"Article 102685"},"PeriodicalIF":4.9,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145840029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SAN-Wavelet cycleGAN for anatomical structure reinforcement and tissue detail preservation in abdominal CT synthesis 基于san -小波循环gan的腹部CT合成中解剖结构增强和组织细节保存。

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2025-12-08 DOI: 10.1016/j.compmedimag.2025.102686

Yueyu Huang , Lu Qiang , Wenyu Xing , Tao Jiang , Yucheng He , Yuan Liu , Gaobo Zhang , Jingxian Wang , Xiaojun Song , Yifang Li

Generating a CT image from an existing but unpaired MR image has recently become a promising objective in the radiotherapy treatment planning (RTP), whereas the unsatisfactory structure and detail accuracy of the outcome is still a challenge for its clinical application. To address this issue, this work proposed an unsupervised model called structure-adaptive normalization wavelet (SAN-Wavelet) cycleGAN for unpaired MR-to-CT image synthesis. This method not only developed a module called SAN to ensure the anatomically structural integrity, but also introduced a neighborhood detail loss (ND loss) for detail consistency penalization between different modalities. Furthermore, a high-frequency discriminator and wavelet-trans skip connection were designed to keep with the high-frequency tissue detail. Experimental findings on abdominal area demonstrated the effectiveness of SAN-Wavelet cycleGAN for unpaired MR-to-CT synthesis, with mean squared error (MSE) of 66.38, root mean squared error (RMSE) of 8.07, peak signal-to-noise ratio (PSNR) of 25.944 dB, structural similarity index (SSlM) of 0.895 and mixture perceptual similarity index (MPSIM) of 0.723. Compared to other unsupervised approaches (i.e., cycleGAN, gc-, cc-, and sc-cycleGAN), the performances of SAN-cycleGAN improved by 5–15 % in terms of the metrics above. Moreover, the dosimetric distributions of the synthesized CT and real CT in planning target volume (PTV-45Gy) and organ at risk area (bowel) were statistically consistent (Mann-Whitney U test, P > 0.05) with a mean relative error being 0.09 % and 0.24 %, showcasing a promising applicability for clinical application.

从现有的未配对的MR图像生成CT图像最近成为放射治疗计划（RTP）的一个有希望的目标，然而结果的结构和细节准确性不理想仍然是其临床应用的一个挑战。为了解决这个问题，本研究提出了一种称为结构自适应归一化小波（san -小波）循环gan的无监督模型，用于非成对的mr - ct图像合成。该方法不仅开发了一个称为SAN的模块来保证解剖结构的完整性，而且引入了邻域细节损失（ND loss）来对不同模态之间的细节一致性进行惩罚。此外，设计了高频鉴别器和小波变换跳变连接，以保持高频组织细节。在腹部区域的实验结果表明，san_wavelet - cycleGAN对非配对mr - ct合成的有效性，均方误差（MSE）为66.38，均方根误差（RMSE）为8.07，峰值信噪比（PSNR）为25.944 dB，结构相似指数（SSlM）为0.895，混合感知相似指数（MPSIM）为0.723。与其他无监督方法（即cycleGAN， gc-， cc-和sc-cycleGAN）相比，就上述指标而言，SAN-cycleGAN的性能提高了5- 15% %。此外，合成CT与真实CT在计划靶体积（PTV-45Gy）和危险器官（肠）的剂量学分布具有统计学上的一致性（Mann-Whitney U检验，P > 0.05），平均相对误差分别为0.09 %和0.24 %，具有良好的临床应用前景。

{"title":"SAN-Wavelet cycleGAN for anatomical structure reinforcement and tissue detail preservation in abdominal CT synthesis","authors":"Yueyu Huang , Lu Qiang , Wenyu Xing , Tao Jiang , Yucheng He , Yuan Liu , Gaobo Zhang , Jingxian Wang , Xiaojun Song , Yifang Li","doi":"10.1016/j.compmedimag.2025.102686","DOIUrl":"10.1016/j.compmedimag.2025.102686","url":null,"abstract":"<div><div>Generating a CT image from an existing but unpaired MR image has recently become a promising objective in the radiotherapy treatment planning (RTP), whereas the unsatisfactory structure and detail accuracy of the outcome is still a challenge for its clinical application. To address this issue, this work proposed an unsupervised model called structure-adaptive normalization wavelet (SAN-Wavelet) cycleGAN for unpaired MR-to-CT image synthesis. This method not only developed a module called SAN to ensure the anatomically structural integrity, but also introduced a neighborhood detail loss (ND loss) for detail consistency penalization between different modalities. Furthermore, a high-frequency discriminator and wavelet-trans skip connection were designed to keep with the high-frequency tissue detail. Experimental findings on abdominal area demonstrated the effectiveness of SAN-Wavelet cycleGAN for unpaired MR-to-CT synthesis, with mean squared error (MSE) of 66.38, root mean squared error (RMSE) of 8.07, peak signal-to-noise ratio (PSNR) of 25.944 dB, structural similarity index (SSlM) of 0.895 and mixture perceptual similarity index (MPSIM) of 0.723. Compared to other unsupervised approaches (i.e., cycleGAN, gc-, cc-, and sc-cycleGAN), the performances of SAN-cycleGAN improved by 5–15 % in terms of the metrics above. Moreover, the dosimetric distributions of the synthesized CT and real CT in planning target volume (PTV-45Gy) and organ at risk area (bowel) were statistically consistent (Mann-Whitney U test, P > 0.05) with a mean relative error being 0.09 % and 0.24 %, showcasing a promising applicability for clinical application.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"127 ","pages":"Article 102686"},"PeriodicalIF":4.9,"publicationDate":"2025-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145758295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A novel virtual patient approach for cross-patient multimodal fusion in enhanced breast cancer detection 一种新的虚拟患者方法，用于增强乳腺癌检测的跨患者多模式融合。

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2025-12-08 DOI: 10.1016/j.compmedimag.2025.102687

Younes Akbari , Faseela Abdullakutty , Somaya Al-Maadeed , Rafif Al Saady , Ahmed Bouridane , Rifat Hamoudi

<div><div>Multimodal medical imaging combining conventional imaging modalities such as mammography, ultrasound, and histopathology has shown significant promise for improving breast cancer detection accuracy. However, clinical implementation faces substantial challenges due to incomplete patient-matched multimodal datasets and resource constraints. Traditional approaches require complete imaging workups from individual patients, limiting their practical applicability. This study investigates whether cross-patient multimodal fusion combining imaging modalities from different patients, can provide additional diagnostic information beyond single-modality approaches. We hypothesize that leveraging complementary information from heterogeneous patient populations enhances cancer detection performance, even when modalities originate from separate individuals. We developed a novel virtual patient framework that systematically combines imaging modalities across different patients based on quality-driven selection strategies. Two training paradigms were evaluated: Fixed scenario with 1:1:1 cross-patient combinations (<span><math><mo>∼</mo></math></span>250 virtual patients), and Combinatorial scenario with systematic companion selection (<span><math><mo>∼</mo></math></span>20,000 virtual patients). Multiple fusion architectures (concatenation, attention, and averaging) were assessed, and we designed a novel co-attention mechanism that enables sophisticated cross-modal interaction through learned attention weights. These fusion networks were evaluated using histopathology (BCSS), mammography, and ultrasound (BUSI) datasets. External validation using the ICIAR2018 BACH Challenge dataset as an alternative histopathology source demonstrated the generalizability of our approach, achieving promising accuracy despite differences in staining protocols and acquisition procedures across institutions. All models were evaluated on consistent fixed test sets to ensure fair comparison. This dataset is well-suited for multiple breast cancer analysis tasks, including detection, segmentation, and Explainable Artificial Intelligence (XAI) applications. Cross-patient multimodal fusion demonstrated significant improvements over single-modality approaches. The best single modality achieved 75.36% accuracy (mammography), while the optimal fusion combination (histopathology-mammography) reached 97.10% accuracy, representing a 21.74 percentage point improvement. Comprehensive quantitative validation through silhouette analysis (score: 0.894) confirms that the observed performance improvements reflect genuine feature space structure rather than visualization artifacts. Cross-patient multimodal fusion demonstrates significant potential for enhancing breast cancer detection, particularly addressing real-world scenarios where complete patient-matched multimodal data is unavailable. This approach represents a paradigm shift toward leveraging heterogeneous information sources for impro

多模式医学成像结合传统成像方式，如乳房x线摄影、超声和组织病理学，已显示出显著的希望，以提高乳腺癌检测的准确性。然而，由于不完整的患者匹配多模式数据集和资源限制，临床实施面临着重大挑战。传统的方法需要对单个患者进行完整的影像学检查，这限制了它们的实际适用性。本研究探讨了跨患者多模态融合结合不同患者的成像模式是否可以提供单模态方法之外的额外诊断信息。我们假设，利用来自异质患者群体的互补信息可以提高癌症检测性能，即使模式来自不同的个体。我们开发了一种新的虚拟患者框架，基于质量驱动的选择策略，系统地结合不同患者的成像模式。评估了两种训练范式：固定情景与1:1:1的交叉患者组合（约250名虚拟患者），以及组合情景与系统同伴选择（约20,000名虚拟患者）。我们评估了多种融合架构（连接、注意和平均），并设计了一种新的共同注意机制，通过学习到的注意权重实现复杂的跨模态交互。使用组织病理学（BCSS）、乳房x光检查和超声（BUSI）数据集评估这些融合网络。使用ICIAR2018巴赫挑战数据集作为替代组织病理学来源的外部验证证明了我们的方法的通用性，尽管各机构的染色方案和获取程序存在差异，但仍取得了很好的准确性。所有模型都在一致的固定测试集上进行评估，以确保公平比较。该数据集非常适合多种乳腺癌分析任务，包括检测、分割和可解释人工智能（XAI）应用。与单模态入路相比，跨患者多模态融合表现出显著的改善。最佳单一模式（乳房x线摄影）的准确率为75.36%，而最佳融合组合（组织病理学-乳房x线摄影）的准确率为97.10%，提高21.74个百分点。通过剪影分析（得分：0.894）进行的综合定量验证证实，观察到的性能改进反映了真实的特征空间结构，而不是可视化伪影。跨患者多模态融合显示了增强乳腺癌检测的巨大潜力，特别是在无法获得完整的患者匹配多模态数据的现实情况下。这种方法代表了一种范式转变，即利用异构信息源来提高诊断性能。

{"title":"A novel virtual patient approach for cross-patient multimodal fusion in enhanced breast cancer detection","authors":"Younes Akbari , Faseela Abdullakutty , Somaya Al-Maadeed , Rafif Al Saady , Ahmed Bouridane , Rifat Hamoudi","doi":"10.1016/j.compmedimag.2025.102687","DOIUrl":"10.1016/j.compmedimag.2025.102687","url":null,"abstract":"<div><div>Multimodal medical imaging combining conventional imaging modalities such as mammography, ultrasound, and histopathology has shown significant promise for improving breast cancer detection accuracy. However, clinical implementation faces substantial challenges due to incomplete patient-matched multimodal datasets and resource constraints. Traditional approaches require complete imaging workups from individual patients, limiting their practical applicability. This study investigates whether cross-patient multimodal fusion combining imaging modalities from different patients, can provide additional diagnostic information beyond single-modality approaches. We hypothesize that leveraging complementary information from heterogeneous patient populations enhances cancer detection performance, even when modalities originate from separate individuals. We developed a novel virtual patient framework that systematically combines imaging modalities across different patients based on quality-driven selection strategies. Two training paradigms were evaluated: Fixed scenario with 1:1:1 cross-patient combinations (<span><math><mo>∼</mo></math></span>250 virtual patients), and Combinatorial scenario with systematic companion selection (<span><math><mo>∼</mo></math></span>20,000 virtual patients). Multiple fusion architectures (concatenation, attention, and averaging) were assessed, and we designed a novel co-attention mechanism that enables sophisticated cross-modal interaction through learned attention weights. These fusion networks were evaluated using histopathology (BCSS), mammography, and ultrasound (BUSI) datasets. External validation using the ICIAR2018 BACH Challenge dataset as an alternative histopathology source demonstrated the generalizability of our approach, achieving promising accuracy despite differences in staining protocols and acquisition procedures across institutions. All models were evaluated on consistent fixed test sets to ensure fair comparison. This dataset is well-suited for multiple breast cancer analysis tasks, including detection, segmentation, and Explainable Artificial Intelligence (XAI) applications. Cross-patient multimodal fusion demonstrated significant improvements over single-modality approaches. The best single modality achieved 75.36% accuracy (mammography), while the optimal fusion combination (histopathology-mammography) reached 97.10% accuracy, representing a 21.74 percentage point improvement. Comprehensive quantitative validation through silhouette analysis (score: 0.894) confirms that the observed performance improvements reflect genuine feature space structure rather than visualization artifacts. Cross-patient multimodal fusion demonstrates significant potential for enhancing breast cancer detection, particularly addressing real-world scenarios where complete patient-matched multimodal data is unavailable. This approach represents a paradigm shift toward leveraging heterogeneous information sources for impro","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"127 ","pages":"Article 102687"},"PeriodicalIF":4.9,"publicationDate":"2025-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145716425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

FAUDA-Net: Frequency-aware unsupervised domain adaptation network for multimodal medical image segmentation fada - net：用于多模态医学图像分割的频率感知无监督域自适应网络

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2025-12-08 DOI: 10.1016/j.compmedimag.2025.102684

Yan Liu , Yan Yang , Yongquan Jiang , Xiaole Zhao , Zhuyang Xie

Unsupervised domain adaptation (UDA) has achieved notable advances in medical image segmentation. However, the significant domain shifts between source and target data continue to pose fundamental challenges, driving an urgent demand for more robust cross-domain solutions. Current UDA methods often rely on static spatial alignment strategies that ignore the dynamic evolution of feature distributions during training, often resulting in blurred boundary delineation and loss of structural details. To address these issues, we propose a frequency-aware unsupervised domain adaptation network (FAUDA-Net), which dynamically adapts to feature distribution shifts and enhances boundary delineation in the target domain. Specifically, FAUDA-Net introduces dual-domain distribution disruption to encourage domain-invariant representations, along with frequency constraints, that leverage both phase and amplitude components to guide cross-domain adaptation. Furthermore, a frequency-aware contrastive learning mechanism aligns source and target features through channel self-attention matrices, enabling a shared pixel-wise decoder to achieve robust segmentation performance. Extensive experiments on three representative medical image datasets, MMWHS17, BraTS21, and PROMISE12, demonstrate that FAUDA-Net outperforms eight state-of-the-art methods in both overall segmentation accuracy (Dice) and boundary extraction precision (ASD), providing a reliable and effective solution for multi-modal and multi-center medical image segmentation.

无监督域自适应（UDA）在医学图像分割中取得了显著进展。然而，源数据和目标数据之间的重大领域转换继续构成根本性的挑战，推动了对更强大的跨领域解决方案的迫切需求。目前的UDA方法往往依赖于静态空间对齐策略，忽略了训练过程中特征分布的动态演变，往往导致边界描绘模糊和结构细节的丢失。为了解决这些问题，我们提出了一种频率感知的无监督域自适应网络（fada - net），该网络可以动态适应特征分布的变化，并增强目标域的边界描绘。具体来说，fada - net引入了双域分布中断，以鼓励域不变表示，以及频率约束，利用相位和幅度分量来指导跨域适应。此外，频率感知的对比学习机制通过信道自注意矩阵来对齐源和目标特征，使共享像素解码器能够实现稳健的分割性能。在MMWHS17、BraTS21和PROMISE12三个具有代表性的医学图像数据集上进行的大量实验表明，FAUDA-Net在整体分割精度（Dice）和边界提取精度（ASD）方面都优于8种最先进的方法，为多模态、多中心医学图像分割提供了可靠、有效的解决方案。

{"title":"FAUDA-Net: Frequency-aware unsupervised domain adaptation network for multimodal medical image segmentation","authors":"Yan Liu , Yan Yang , Yongquan Jiang , Xiaole Zhao , Zhuyang Xie","doi":"10.1016/j.compmedimag.2025.102684","DOIUrl":"10.1016/j.compmedimag.2025.102684","url":null,"abstract":"<div><div>Unsupervised domain adaptation (UDA) has achieved notable advances in medical image segmentation. However, the significant domain shifts between source and target data continue to pose fundamental challenges, driving an urgent demand for more robust cross-domain solutions. Current UDA methods often rely on static spatial alignment strategies that ignore the dynamic evolution of feature distributions during training, often resulting in blurred boundary delineation and loss of structural details. To address these issues, we propose a frequency-aware unsupervised domain adaptation network (FAUDA-Net), which dynamically adapts to feature distribution shifts and enhances boundary delineation in the target domain. Specifically, FAUDA-Net introduces dual-domain distribution disruption to encourage domain-invariant representations, along with frequency constraints, that leverage both phase and amplitude components to guide cross-domain adaptation. Furthermore, a frequency-aware contrastive learning mechanism aligns source and target features through channel self-attention matrices, enabling a shared pixel-wise decoder to achieve robust segmentation performance. Extensive experiments on three representative medical image datasets, MMWHS17, BraTS21, and PROMISE12, demonstrate that FAUDA-Net outperforms eight state-of-the-art methods in both overall segmentation accuracy (Dice) and boundary extraction precision (ASD), providing a reliable and effective solution for multi-modal and multi-center medical image segmentation.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"127 ","pages":"Article 102684"},"PeriodicalIF":4.9,"publicationDate":"2025-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145737505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Frequency-spatial synergistic network for accelerated multi-contrast MRI reconstruction 加速MRI多对比重建的频率-空间协同网络

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2025-12-04 DOI: 10.1016/j.compmedimag.2025.102682

Ke Li , Dong Liang , Guoqing Chen , Qiyu Jin , Tieyong Zeng

To accelerate the Magnetic Resonance Imaging (MRI) process, multi-contrast MRI reconstruction has emerged as a mainstream approach. This technique leverages readily available auxiliary modality information to guide the high-quality reconstruction of the target modality. The core challenge of this task lies in effectively capturing the global dependencies across different contrasts and efficiently integrating complementary information from multiple contrasts. To address these challenges, we propose the Multi-Contrast Dual-Domain (MCDD) network. It leverages frequency-domain information to capture global dependencies. Specifically, the network employs the Single-Contrast Learning (SCL) module as a prior to guide the Multi-Contrast Learning (MCL) module. Both modules extract complementary global and local features through Frequency (Fre) and Spatial (Spa) extraction blocks, which are fused via an Adaptive Fusion Mechanism (AFM). Experiments on BraTS, MRBrainS, and fastMRI demonstrate that MCDD outperforms state-of-the-art methods, achieving PSNR improvements of 2.42 dB (

4 \times

), 2.11 dB (

8 \times

), 1.63 dB (

16 \times

), and 0.82 dB (

32 \times

). Qualitative results further confirm enhanced structural fidelity and reduced artifacts, validating MCDD as an effective solution for accelerated MRI reconstruction.

为了加快磁共振成像（MRI）的进程，MRI多对比重建已成为一种主流方法。该技术利用易于获得的辅助模态信息来指导目标模态的高质量重建。该任务的核心挑战在于有效地捕获不同对比之间的全局依赖关系，并有效地整合来自多个对比的互补信息。为了解决这些挑战，我们提出了多对比度双域（MCDD）网络。它利用频域信息来捕获全局依赖项。具体来说，该网络采用单对比学习（Single-Contrast Learning， SCL）模块作为前置模块来指导多对比学习（Multi-Contrast Learning， MCL）模块。两个模块都通过频率（Fre）和空间（Spa）提取块提取互补的全局和局部特征，并通过自适应融合机制（AFM）进行融合。在brat、MRBrainS和fastMRI上的实验表明，MCDD优于最先进的方法，实现了2.42 dB（4倍）、2.11 dB（8倍）、1.63 dB（16倍）和0.82 dB（32倍）的PSNR改进。定性结果进一步证实了增强的结构保真度和减少的伪影，验证了MCDD是加速MRI重建的有效解决方案。

{"title":"Frequency-spatial synergistic network for accelerated multi-contrast MRI reconstruction","authors":"Ke Li , Dong Liang , Guoqing Chen , Qiyu Jin , Tieyong Zeng","doi":"10.1016/j.compmedimag.2025.102682","DOIUrl":"10.1016/j.compmedimag.2025.102682","url":null,"abstract":"<div><div>To accelerate the Magnetic Resonance Imaging (MRI) process, multi-contrast MRI reconstruction has emerged as a mainstream approach. This technique leverages readily available auxiliary modality information to guide the high-quality reconstruction of the target modality. The core challenge of this task lies in effectively capturing the global dependencies across different contrasts and efficiently integrating complementary information from multiple contrasts. To address these challenges, we propose the Multi-Contrast Dual-Domain (MCDD) network. It leverages frequency-domain information to capture global dependencies. Specifically, the network employs the Single-Contrast Learning (SCL) module as a prior to guide the Multi-Contrast Learning (MCL) module. Both modules extract complementary global and local features through Frequency (Fre) and Spatial (Spa) extraction blocks, which are fused via an Adaptive Fusion Mechanism (AFM). Experiments on BraTS, MRBrainS, and fastMRI demonstrate that MCDD outperforms state-of-the-art methods, achieving PSNR improvements of 2.42 dB (<span><math><mrow><mn>4</mn><mo>×</mo></mrow></math></span>), 2.11 dB (<span><math><mrow><mn>8</mn><mo>×</mo></mrow></math></span>), 1.63 dB (<span><math><mrow><mn>16</mn><mo>×</mo></mrow></math></span>), and 0.82 dB (<span><math><mrow><mn>32</mn><mo>×</mo></mrow></math></span>). Qualitative results further confirm enhanced structural fidelity and reduced artifacts, validating MCDD as an effective solution for accelerated MRI reconstruction.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"127 ","pages":"Article 102682"},"PeriodicalIF":4.9,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145685379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multimodal framework for TACE treatment response prediction in patients with hepatocellular carcinoma 肝癌患者TACE治疗反应预测的多模式框架。

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2025-12-02 DOI: 10.1016/j.compmedimag.2025.102679

Pietro Maria Marvulli , Domenico Buongiorno , Gian Maria Zaccaria, Antonio Brunetti, Francescomaria Marino, Vitoantonio Bevilacqua

Transarterial chemoembolization (TACE) is a first-line treatment for intermediate-stage hepatocellular carcinoma (HCC) that can cause side effects. An accurate prediction of TACE response is important to improve clinical outcomes and avoid unnecessary toxicity. This study pursues a dual objective: to propose a standardized evaluation pipeline that enables reproducible benchmarking of state-of-the-art approaches on publicly available datasets, including both internal and external validation with public dataset, and to introduce a novel multimodal framework that integrates clinical variables, radiomic and deep features extracted from CT scans using the Vision Transformer MedViT to predict treatment response. Experiments were conducted using two publicly available datasets, the HCC-TACE-Seg, used as training and internal validation sets, and the WAW-TACE cohort, used as external validation set. The results demonstrated that the proposed method outperforms existing approaches. Independent validation on the external WAW-TACE dataset achieved promising results, confirming the robustness of the model and its potential to support treatment planning.

经动脉化疗栓塞（TACE）是可引起副作用的中期肝细胞癌（HCC）的一线治疗方法。准确预测TACE反应对于改善临床结果和避免不必要的毒性非常重要。本研究追求双重目标：提出一个标准化的评估管道，使最先进的方法能够在公开可用的数据集上进行可重复的基准测试，包括使用公共数据集进行内部和外部验证，并引入一个新的多模式框架，该框架集成了临床变量，使用Vision Transformer MedViT从CT扫描中提取的放射学和深度特征，以预测治疗反应。实验使用两个公开的数据集进行，HCC-TACE-Seg作为训练和内部验证集，WAW-TACE队列作为外部验证集。结果表明，该方法优于现有方法。在外部WAW-TACE数据集上的独立验证取得了令人鼓舞的结果，证实了该模型的鲁棒性及其支持治疗计划的潜力。

{"title":"Multimodal framework for TACE treatment response prediction in patients with hepatocellular carcinoma","authors":"Pietro Maria Marvulli , Domenico Buongiorno , Gian Maria Zaccaria, Antonio Brunetti, Francescomaria Marino, Vitoantonio Bevilacqua","doi":"10.1016/j.compmedimag.2025.102679","DOIUrl":"10.1016/j.compmedimag.2025.102679","url":null,"abstract":"<div><div>Transarterial chemoembolization (TACE) is a first-line treatment for intermediate-stage hepatocellular carcinoma (HCC) that can cause side effects. An accurate prediction of TACE response is important to improve clinical outcomes and avoid unnecessary toxicity. This study pursues a dual objective: to propose a standardized evaluation pipeline that enables reproducible benchmarking of state-of-the-art approaches on publicly available datasets, including both internal and external validation with public dataset, and to introduce a novel multimodal framework that integrates clinical variables, radiomic and deep features extracted from CT scans using the Vision Transformer MedViT to predict treatment response. Experiments were conducted using two publicly available datasets, the HCC-TACE-Seg, used as training and internal validation sets, and the WAW-TACE cohort, used as external validation set. The results demonstrated that the proposed method outperforms existing approaches. Independent validation on the external WAW-TACE dataset achieved promising results, confirming the robustness of the model and its potential to support treatment planning.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"127 ","pages":"Article 102679"},"PeriodicalIF":4.9,"publicationDate":"2025-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145679264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Benchmarking pathology foundation models for predicting microsatellite instability in colorectal cancer histopathology 预测结直肠癌组织病理学微卫星不稳定性的基准病理学基础模型

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2025-12-02 DOI: 10.1016/j.compmedimag.2025.102680

Mohsin Bilal , Muhammad Aamir Gulzar , Nazish Jaffar , Abdulrahman Alabduljabbar , Youssef Altherwy , Anas Alsuhaibani , Fahdah Almarshad

The rapid evolution of pathology foundation models necessitates rigorous benchmarking for clinical tasks. We evaluated three leading foundation models, UNI, Virchow2, and CONCH, for predicting microsatellite instability status from colorectal cancer whole-slide images, an essential routine clinical test. Our comprehensive framework assessed stain, tissue, and resolution invariance using datasets from The Cancer Genome Atlas (TCGA, USA; n = 409) and Pathology Artificial Intelligence Platform (PAIP, South Korea; training n = 47, testing n = 21 and n = 78). We developed an efficient pipeline with minimal preprocessing, omitting stain normalization, color augmentation, and tumor segmentation. To improve contextual encoding, we applied a five-crop strategy per patch, averaging embeddings from the center and four peripheral crops. We compared three slide-level aggregation and four efficient adaptation strategies. CONCH, using 2-cluster aggregation and ProtoNet adaptation, achieved top balanced accuracies (0.775 and 0.778) in external validation on PAIP. Conversely, UNI, with mean-averaging aggregation and ANN adaptation, excelled in TCGA cross-validation (0.778) but not in external validation (0.764), suggesting potential overfitting. The proposed 5-Crop augmentation enhances robustness to scale in UNI and CONCH and reflects intrinsic invariance achieved by Virchow2 through large-scale pretraining. For prescreening, CONCH demonstrated specificity of 0.65 and 0.45 at sensitivities of 0.90 and 0.94, respectively, highlighting its effectiveness in identifying stable cases and minimizing number of rapid molecular tests needed. Interestingly, a fine-tuned ResNet34 adaptation achieved superior performance (0.836) in the smaller internal validation cohort, suggesting current pathology foundation models training recipes may not sufficiently generalize without task-specific fine-tuning. Interpretability analyses using CONCH’s multimodal embeddings identified plasma cells as key morphological features differentiating microsatellite instability from stability, validated by pathologists (accuracy up to 92.4 %). This study underscores the feasibility and clinical significance of adapting foundation models to enhance diagnostic efficiency and patient outcomes.

病理基础模型的快速发展需要对临床任务进行严格的基准测试。我们评估了三种主要的基础模型UNI、Virchow2和CONCH，用于预测结直肠癌全切片图像的微卫星不稳定状态，这是一项重要的常规临床测试。我们的综合框架使用来自癌症基因组图谱（TCGA，美国；n = 409）和病理学人工智能平台（PAIP，韩国；训练n = 47，测试n = 21和n = 78）的数据集评估染色、组织和分辨率不变性。我们开发了一个高效的流水线，减少了预处理，省略了染色归一化，颜色增强和肿瘤分割。为了改进上下文编码，我们应用了每个补丁的五种作物策略，平均中心和四个外围作物的嵌入。我们比较了三种幻灯片级聚合和四种有效的适应策略。CONCH采用2簇聚合和ProtoNet自适应，在PAIP的外部验证中获得了最高的平衡精度（0.775和0.778）。相反，具有平均聚合和人工神经网络适应的UNI在TCGA交叉验证中表现出色（0.778），但在外部验证中表现不佳（0.764），表明可能存在过拟合。提出的5-Crop增强方法增强了UNI和CONCH的规模鲁棒性，并反映了Virchow2通过大规模预训练实现的内在不变性。对于预筛选，CONCH的特异性分别为0.65和0.45，敏感性分别为0.90和0.94，突出了其在识别稳定病例和减少所需快速分子检测数量方面的有效性。有趣的是，经过微调的ResNet34自适应在较小的内部验证队列中获得了更好的表现（0.836），这表明如果没有针对特定任务的微调，目前的病理基础模型训练方法可能无法充分推广。使用CONCH多模态嵌入的可解释性分析确定了浆细胞是区分微卫星不稳定性和稳定性的关键形态学特征，经病理学家验证（准确率高达92.4 %）。本研究强调了调整基础模型以提高诊断效率和患者预后的可行性和临床意义。

{"title":"Benchmarking pathology foundation models for predicting microsatellite instability in colorectal cancer histopathology","authors":"Mohsin Bilal , Muhammad Aamir Gulzar , Nazish Jaffar , Abdulrahman Alabduljabbar , Youssef Altherwy , Anas Alsuhaibani , Fahdah Almarshad","doi":"10.1016/j.compmedimag.2025.102680","DOIUrl":"10.1016/j.compmedimag.2025.102680","url":null,"abstract":"<div><div>The rapid evolution of pathology foundation models necessitates rigorous benchmarking for clinical tasks. We evaluated three leading foundation models, UNI, Virchow2, and CONCH, for predicting microsatellite instability status from colorectal cancer whole-slide images, an essential routine clinical test. Our comprehensive framework assessed stain, tissue, and resolution invariance using datasets from The Cancer Genome Atlas (TCGA, USA; n = 409) and Pathology Artificial Intelligence Platform (PAIP, South Korea; training n = 47, testing n = 21 and n = 78). We developed an efficient pipeline with minimal preprocessing, omitting stain normalization, color augmentation, and tumor segmentation. To improve contextual encoding, we applied a five-crop strategy per patch, averaging embeddings from the center and four peripheral crops. We compared three slide-level aggregation and four efficient adaptation strategies. CONCH, using 2-cluster aggregation and ProtoNet adaptation, achieved top balanced accuracies (0.775 and 0.778) in external validation on PAIP. Conversely, UNI, with mean-averaging aggregation and ANN adaptation, excelled in TCGA cross-validation (0.778) but not in external validation (0.764), suggesting potential overfitting. The proposed 5-Crop augmentation enhances robustness to scale in UNI and CONCH and reflects intrinsic invariance achieved by Virchow2 through large-scale pretraining. For prescreening, CONCH demonstrated specificity of 0.65 and 0.45 at sensitivities of 0.90 and 0.94, respectively, highlighting its effectiveness in identifying stable cases and minimizing number of rapid molecular tests needed. Interestingly, a fine-tuned ResNet34 adaptation achieved superior performance (0.836) in the smaller internal validation cohort, suggesting current pathology foundation models training recipes may not sufficiently generalize without task-specific fine-tuning. Interpretability analyses using CONCH’s multimodal embeddings identified plasma cells as key morphological features differentiating microsatellite instability from stability, validated by pathologists (accuracy up to 92.4 %). This study underscores the feasibility and clinical significance of adapting foundation models to enhance diagnostic efficiency and patient outcomes.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"127 ","pages":"Article 102680"},"PeriodicalIF":4.9,"publicationDate":"2025-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145685281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Effective contextual feature fusion and individualized information for automated sleep staging 有效的上下文特征融合和个性化信息自动睡眠分期。

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2025-12-02 DOI: 10.1016/j.compmedimag.2025.102678

Jianguo Wei , Ronghe Chu , Wenhuan Lu , Yibing Chen

Polysomnography (PSG)-based sleep stage interpretation is crucial for diagnosing sleep disorders. Over the past decade, scholars have shown that machine learning offers a faster and more convenient alternative to manual visual interpretation of sleep stages and patterns. However, neglecting contextual features and individual case differences has hindered model application in new sleep staging cases. In this paper, we propose a sleep staging model that integrates contextual feature fusion and an individualized framework. The model incorporates weighted features from multiple epochs into the scoring process, enabling accurate scoring of 30-second epoch signals. Our individualized framework is tailored for emerging cases in real-world scenarios. It aggregates unique case information to derive individualized pseudo-labels, significantly enhancing automatic sleep staging accuracy through non-independent training. This strategy effectively addresses model degradation caused by differences between training cases and single new cases. To demonstrate our approach’s efficacy, we evaluated our automated sleep staging algorithm on the Sleep-EDF-20 and Sleep-EDF-78 datasets, achieving accuracy of 85.3% and 80.8%, respectively. Furthermore, our individualized framework achieved 79.1% accuracy on the UCD dataset. These results underscore its potential as an effective tool for sleep stage classification, supporting physicians and neurologists in diagnosing sleep disorders. The proposed framework is lightweight and suitable for integration into clinical decision support system for sleep medicine, with a clear pathway for collaboration with routine laboratory scoring processes to support practical deployment.

基于多导睡眠图（PSG）的睡眠阶段解释对于诊断睡眠障碍至关重要。在过去的十年里，学者们已经证明，机器学习提供了一种比人工视觉解释睡眠阶段和模式更快、更方便的选择。然而，忽视上下文特征和个体病例差异阻碍了模型在新的睡眠分期病例中的应用。在本文中，我们提出了一个结合上下文特征融合和个性化框架的睡眠分期模型。该模型将多个epoch的加权特征纳入评分过程，能够对30秒epoch信号进行准确评分。我们的个性化框架是为现实世界中的新情况量身定制的。它聚合独特的病例信息，得出个性化的伪标签，通过非独立训练显著提高自动睡眠分期的准确性。该策略有效地解决了由于训练案例和单个新案例之间的差异而导致的模型退化问题。为了证明我们的方法的有效性，我们在sleep - edf -20和sleep - edf -78数据集上评估了我们的自动睡眠分期算法，准确率分别达到85.3%和80.8%。此外，我们的个性化框架在UCD数据集上达到了79.1%的准确率。这些结果强调了它作为睡眠阶段分类的有效工具的潜力，支持医生和神经科医生诊断睡眠障碍。所提出的框架轻量级，适合集成到睡眠医学的临床决策支持系统中，并具有与常规实验室评分流程协作的明确途径，以支持实际部署。

{"title":"Effective contextual feature fusion and individualized information for automated sleep staging","authors":"Jianguo Wei , Ronghe Chu , Wenhuan Lu , Yibing Chen","doi":"10.1016/j.compmedimag.2025.102678","DOIUrl":"10.1016/j.compmedimag.2025.102678","url":null,"abstract":"<div><div>Polysomnography (PSG)-based sleep stage interpretation is crucial for diagnosing sleep disorders. Over the past decade, scholars have shown that machine learning offers a faster and more convenient alternative to manual visual interpretation of sleep stages and patterns. However, neglecting contextual features and individual case differences has hindered model application in new sleep staging cases. In this paper, we propose a sleep staging model that integrates contextual feature fusion and an individualized framework. The model incorporates weighted features from multiple epochs into the scoring process, enabling accurate scoring of 30-second epoch signals. Our individualized framework is tailored for emerging cases in real-world scenarios. It aggregates unique case information to derive individualized pseudo-labels, significantly enhancing automatic sleep staging accuracy through non-independent training. This strategy effectively addresses model degradation caused by differences between training cases and single new cases. To demonstrate our approach’s efficacy, we evaluated our automated sleep staging algorithm on the Sleep-EDF-20 and Sleep-EDF-78 datasets, achieving accuracy of 85.3% and 80.8%, respectively. Furthermore, our individualized framework achieved 79.1% accuracy on the UCD dataset. These results underscore its potential as an effective tool for sleep stage classification, supporting physicians and neurologists in diagnosing sleep disorders. The proposed framework is lightweight and suitable for integration into clinical decision support system for sleep medicine, with a clear pathway for collaboration with routine laboratory scoring processes to support practical deployment.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"127 ","pages":"Article 102678"},"PeriodicalIF":4.9,"publicationDate":"2025-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145670778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep spatiotemporal clutter filtering of transthoracic echocardiographic images: Leveraging contextual attention and residual learning 经胸超声心动图图像的深时空杂波滤波：利用上下文注意和残余学习。

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2025-11-28 DOI: 10.1016/j.compmedimag.2025.102665

Mahdi Tabassian , Somayeh Akbari , Sandro Queirós , Lamia Al Saikhan , Jan D’hooge

This study presents a deep autoencoder network for filtering reverberation clutter from transthoracic echocardiographic (TTE) images. Given the spatiotemporal nature of this type of clutter, the filtering network employs 3D convolutional layers to suppress it throughout the cardiac cycle. The design of the network incorporates two key features that contribute to the effectiveness of the filter: (1) an attention mechanism for focusing on cluttered regions and leveraging contextual information, and (2) residual learning for preserving fine image structures. A diverse set of artifact patterns was simulated and superimposed onto ultra-realistic synthetic TTE sequences from six ultrasound vendors, generating input for the filtering network. The corresponding artifact-free sequences served as ground-truth. The performance of the filtering network was evaluated using unseen synthetic and in vivo artifactual sequences. Results from the in vivo dataset confirmed the network’s strong generalization capabilities, despite being trained solely on synthetic data and simulated artifacts. The suitability of the filtered sequences for downstream processing was assessed by computing segmental strain curves. A significant reduction in the discrepancy between the strain profiles of the cluttered and clutter-free segments was observed after filtering. The trained network processes a TTE sequence in a fraction of a second, enabling real-time clutter filtering and potentially improving the precision of clinically relevant indices derived from TTE sequences. The source code of the proposed method and example video files of the filtering results are available at: https://github.com/MahdiTabassian/Deep-Clutter-Filtering/tree/main.

本研究提出了一种深度自编码器网络，用于过滤经胸超声心动图（TTE）图像中的混响杂波。考虑到这种杂波的时空性质，滤波网络采用3D卷积层在整个心脏周期内抑制它。该网络的设计包含两个关键特征，有助于过滤器的有效性：(1)关注混乱区域并利用上下文信息的注意机制，以及(2)残差学习以保留精细图像结构。不同的伪影模式被模拟并叠加到来自六个超声供应商的超逼真合成TTE序列上，为滤波网络生成输入。相应的无伪影序列作为基真值。使用未见的合成和活体人工序列来评估滤波网络的性能。活体数据集的结果证实了该网络强大的泛化能力，尽管仅在合成数据和模拟工件上进行训练。通过计算分段应变曲线来评估过滤序列对下游加工的适用性。过滤后，观察到杂乱和无杂乱段的应变曲线之间的差异显著减小。训练后的网络在不到一秒的时间内处理TTE序列，实现实时杂波过滤，并有可能提高从TTE序列中获得的临床相关指标的精度。所提出的方法的源代码和过滤结果的示例视频文件可在：https://github.com/MahdiTabassian/Deep-Clutter-Filtering/tree/main。

{"title":"Deep spatiotemporal clutter filtering of transthoracic echocardiographic images: Leveraging contextual attention and residual learning","authors":"Mahdi Tabassian , Somayeh Akbari , Sandro Queirós , Lamia Al Saikhan , Jan D’hooge","doi":"10.1016/j.compmedimag.2025.102665","DOIUrl":"10.1016/j.compmedimag.2025.102665","url":null,"abstract":"<div><div>This study presents a deep autoencoder network for filtering reverberation clutter from transthoracic echocardiographic (TTE) images. Given the spatiotemporal nature of this type of clutter, the filtering network employs 3D convolutional layers to suppress it throughout the cardiac cycle. The design of the network incorporates two key features that contribute to the effectiveness of the filter: (1) an <em>attention mechanism</em> for focusing on cluttered regions and leveraging contextual information, and (2) <em>residual learning</em> for preserving fine image structures. A diverse set of artifact patterns was simulated and superimposed onto ultra-realistic synthetic TTE sequences from six ultrasound vendors, generating input for the filtering network. The corresponding artifact-free sequences served as ground-truth. The performance of the filtering network was evaluated using unseen synthetic and <em>in vivo</em> artifactual sequences. Results from the <em>in vivo</em> dataset confirmed the network’s strong generalization capabilities, despite being trained solely on synthetic data and simulated artifacts. The suitability of the filtered sequences for downstream processing was assessed by computing segmental strain curves. A significant reduction in the discrepancy between the strain profiles of the cluttered and clutter-free segments was observed after filtering. The trained network processes a TTE sequence in a fraction of a second, enabling real-time clutter filtering and potentially improving the precision of clinically relevant indices derived from TTE sequences. The source code of the proposed method and example video files of the filtering results are available at: <span><span>https://github.com/MahdiTabassian/Deep-Clutter-Filtering/tree/main</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"127 ","pages":"Article 102665"},"PeriodicalIF":4.9,"publicationDate":"2025-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145662682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

BoneVisionNet: A deep learning approach for the classification of bone tumours from radiographs using a triple fusion attention network of transformer and CNNs with XAI visualizations BoneVisionNet：一种用于从x线照片中分类骨肿瘤的深度学习方法，使用变压器和cnn的三重融合关注网络与XAI可视化

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2025-11-19 DOI: 10.1016/j.compmedimag.2025.102668

Armaano Ajay , Karthik R , Akshaj Singh Bisht , Pranav Uppuluri

Diagnosis of bone tumours present numerous challenges due to the complexity of pathology and varying morphologies of bone tumours. Current methods rely on manual techniques that are time-consuming and prone to errors. Hence, there is a need for more accurate and automated methods to assist medical professionals. The proposed work aims to solve this challenge by developing a deep learning-based architecture for bone tumour classification using radiographs. The proposed BoneVisionNet is developed using a combination of three specialized DL networks. The proposed approach leverages Convolution-Enhanced Image Transformer for global feature extraction which is further refined using a Global Context Block (GCB). In parallel, the Attention Boosted Mid-Level Feature Extraction Network (ABMLFE-Net) targets mid-level features and DenseNet-169 focuses on local feature extraction. The feature maps from the ABMLFE-Net and DenseNet-169 are fused using element-wise multiplication and is followed by an Efficient Channel Attention (ECA) layer for feature refinement. The global features that are refined by GCB are concatenated with the enhanced feature maps from the ECA layer, resulting in an refined multi-scale feature map. The BoneVisionNet attained an accuracy of 84.35 % when tested on the BTXRD dataset, outperforming CNN and transformer-based networks for classifying bone tumours from radiographs. To the best of our knowledge, this study represents the first application of a triple-track architecture for the classification of bone tumours from X-ray images. XAI visualisations using Grad-CAM, LIME, and SHAP help to further validate the performance of the model by ensuring transparency in the decision-making process.

由于骨肿瘤的病理复杂性和不同的形态，骨肿瘤的诊断提出了许多挑战。目前的方法依赖于手工技术，既耗时又容易出错。因此，需要更准确和自动化的方法来协助医疗专业人员。提出的工作旨在通过开发基于深度学习的架构来解决这一挑战，该架构用于使用x射线片进行骨肿瘤分类。提出的BoneVisionNet是使用三个专门的深度学习网络的组合开发的。该方法利用卷积增强图像转换器进行全局特征提取，并使用全局上下文块（GCB）进一步细化。同时，注意力增强中级特征提取网络（ABMLFE-Net）针对中级特征，DenseNet-169侧重于局部特征提取。来自ABMLFE-Net和DenseNet-169的特征映射使用元素智能乘法进行融合，然后是高效通道注意（ECA）层进行特征细化。将经过GCB优化的全局特征与来自ECA层的增强特征映射相连接，得到精细化的多尺度特征映射。在BTXRD数据集上进行测试时，BoneVisionNet的准确率达到了84.35 %，优于CNN和基于变压器的网络，可以从x线照片中对骨肿瘤进行分类。据我们所知，这项研究代表了从x射线图像中对骨肿瘤进行分类的三轨道结构的首次应用。使用Grad-CAM、LIME和SHAP的XAI可视化有助于通过确保决策过程的透明度来进一步验证模型的性能。

{"title":"BoneVisionNet: A deep learning approach for the classification of bone tumours from radiographs using a triple fusion attention network of transformer and CNNs with XAI visualizations","authors":"Armaano Ajay , Karthik R , Akshaj Singh Bisht , Pranav Uppuluri","doi":"10.1016/j.compmedimag.2025.102668","DOIUrl":"10.1016/j.compmedimag.2025.102668","url":null,"abstract":"<div><div>Diagnosis of bone tumours present numerous challenges due to the complexity of pathology and varying morphologies of bone tumours. Current methods rely on manual techniques that are time-consuming and prone to errors. Hence, there is a need for more accurate and automated methods to assist medical professionals. The proposed work aims to solve this challenge by developing a deep learning-based architecture for bone tumour classification using radiographs. The proposed BoneVisionNet is developed using a combination of three specialized DL networks. The proposed approach leverages Convolution-Enhanced Image Transformer for global feature extraction which is further refined using a Global Context Block (GCB). In parallel, the Attention Boosted Mid-Level Feature Extraction Network (ABMLFE-Net) targets mid-level features and DenseNet-169 focuses on local feature extraction. The feature maps from the ABMLFE-Net and DenseNet-169 are fused using element-wise multiplication and is followed by an Efficient Channel Attention (ECA) layer for feature refinement. The global features that are refined by GCB are concatenated with the enhanced feature maps from the ECA layer, resulting in an refined multi-scale feature map. The BoneVisionNet attained an accuracy of 84.35 % when tested on the BTXRD dataset, outperforming CNN and transformer-based networks for classifying bone tumours from radiographs. To the best of our knowledge, this study represents the first application of a triple-track architecture for the classification of bone tumours from X-ray images. XAI visualisations using Grad-CAM, LIME, and SHAP help to further validate the performance of the model by ensuring transparency in the decision-making process.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"127 ","pages":"Article 102668"},"PeriodicalIF":4.9,"publicationDate":"2025-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145618356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0