Medical image analysis最新文献_第9页

Tracking spatial temporal details in ultrasound long video via wavelet analysis and memory bank 基于小波分析和记忆库的超声长视频时空细节跟踪

IF 11.8 1区医学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Medical image analysis

Pub Date : 2025-12-09 DOI: 10.1016/j.media.2025.103904

Chenxiao Zhang , Runshi Zhang , Junchen Wang

Medical ultrasound videos are widely used for medical inspections, disease diagnosis and surgical planning. High-fidelity lesion area and target organ segmentation constitutes a key component of the computer-assisted surgery workflow. The low contrast levels and noisy backgrounds of ultrasound videos cause missegmentation of organ boundary, which may lead to small object losses and increase boundary segmentation errors. Object tracking in long videos also remains a significant research challenge. To overcome these challenges, we propose a memory bank-based wavelet filtering and fusion network, which adopts an encoder-decoder structure to effectively extract fine-grained detailed spatial features and integrate high-frequency (HF) information. Specifically, memory-based wavelet convolution is presented to simultaneously capture category, detailed information and utilize adjacent information in the encoder. Cascaded wavelet compression is used to fuse multiscale frequency-domain features and expand the receptive field within each convolutional layer. A long short-term memory bank using cross-attention and memory compression mechanisms is designed to track objects in long video. To fully utilize the boundary-sensitive HF details of feature maps, an HF-aware feature fusion module is designed via adaptive wavelet filters in the decoder. In extensive benchmark tests conducted on four ultrasound video datasets (two thyroid nodule, the thyroid gland, the heart datasets) compared with the state-of-the-art methods, our method demonstrates marked improvements in segmentation metrics. In particular, our method can more accurately segment small thyroid nodules, demonstrating its effectiveness for cases involving small ultrasound objects in long video. The code is available at https://github.com/XiAooZ/MWNet.

医学超声影像广泛应用于医学检查、疾病诊断和手术计划。高保真病变区域和靶器官分割是计算机辅助手术工作流程的关键组成部分。超声视频的低对比度和背景噪声会导致器官边界分割错误，导致小物体丢失，增加边界分割误差。长视频中的目标跟踪仍然是一个重大的研究挑战。为了克服这些挑战，我们提出了一种基于记忆库的小波滤波融合网络，该网络采用编码器-解码器结构，有效地提取细粒度的细节空间特征并整合高频（HF）信息。具体来说，基于记忆的小波卷积可以同时捕获编码器中的类别信息、详细信息和利用相邻信息。采用级联小波压缩融合多尺度频域特征，扩展每个卷积层内的接受域。利用交叉注意和记忆压缩机制，设计了一个长短期记忆库来跟踪长视频中的目标。为了充分利用特征图的边界敏感高频细节，在解码器中采用自适应小波滤波器设计了高频感知特征融合模块。在对四个超声视频数据集（两个甲状腺结节，甲状腺，心脏数据集）进行的广泛基准测试中，与最先进的方法相比，我们的方法在分割指标方面有显着改善。特别是，我们的方法可以更准确地分割甲状腺小结节，证明了它对长视频中涉及小超声物体的病例的有效性。代码可在https://github.com/XiAooZ/MWNet上获得。

{"title":"Tracking spatial temporal details in ultrasound long video via wavelet analysis and memory bank","authors":"Chenxiao Zhang , Runshi Zhang , Junchen Wang","doi":"10.1016/j.media.2025.103904","DOIUrl":"10.1016/j.media.2025.103904","url":null,"abstract":"<div><div>Medical ultrasound videos are widely used for medical inspections, disease diagnosis and surgical planning. High-fidelity lesion area and target organ segmentation constitutes a key component of the computer-assisted surgery workflow. The low contrast levels and noisy backgrounds of ultrasound videos cause missegmentation of organ boundary, which may lead to small object losses and increase boundary segmentation errors. Object tracking in long videos also remains a significant research challenge. To overcome these challenges, we propose a memory bank-based wavelet filtering and fusion network, which adopts an encoder-decoder structure to effectively extract fine-grained detailed spatial features and integrate high-frequency (HF) information. Specifically, memory-based wavelet convolution is presented to simultaneously capture category, detailed information and utilize adjacent information in the encoder. Cascaded wavelet compression is used to fuse multiscale frequency-domain features and expand the receptive field within each convolutional layer. A long short-term memory bank using cross-attention and memory compression mechanisms is designed to track objects in long video. To fully utilize the boundary-sensitive HF details of feature maps, an HF-aware feature fusion module is designed via adaptive wavelet filters in the decoder. In extensive benchmark tests conducted on four ultrasound video datasets (two thyroid nodule, the thyroid gland, the heart datasets) compared with the state-of-the-art methods, our method demonstrates marked improvements in segmentation metrics. In particular, our method can more accurately segment small thyroid nodules, demonstrating its effectiveness for cases involving small ultrasound objects in long video. The code is available at <span><span>https://github.com/XiAooZ/MWNet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"109 ","pages":"Article 103904"},"PeriodicalIF":11.8,"publicationDate":"2025-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145730676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

SAM-Swin: SAM-driven dual-swin transformers with adaptive lesion enhancement for Laryngo-Pharyngeal tumor detection SAM-Swin：基于自适应病灶增强的sam驱动双swin变压器，用于喉咽肿瘤检测

IF 11.8 1区医学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Medical image analysis

Pub Date : 2025-12-08 DOI: 10.1016/j.media.2025.103906

Jia Wei , Yun Li , Xiaomao Fan , Wenjun Ma , Meiyu Qiu , Hongyu Chen , Wenbin Lei

Laryngo-pharyngeal cancer (LPC) is a highly lethal malignancy in the head and neck region. Recent advancements in tumor detection, particularly through dual-branch network architectures, have significantly improved diagnostic accuracy by integrating global and local feature extraction. However, challenges remain in accurately localizing lesions and fully capitalizing on the complementary nature of features within these branches. To address these issues, we propose SAM-Swin, an innovative SAM-driven Dual-Swin Transformer for laryngo-pharyngeal tumor detection. This model leverages the robust segmentation capabilities of the Segment Anything Model 2 (SAM2) to achieve precise lesion segmentation. Meanwhile, we present a multi-scale lesion-aware enhancement module (MS-LAEM) designed to adaptively enhance the learning of nuanced complementary features across various scales, improving the quality of feature extraction and representation. Furthermore, we implement a multi-scale class-aware guidance (CAG) loss that delivers multi-scale targeted supervision, thereby enhancing the model’s capacity to extract class-specific features. To validate our approach, we compiled three LPC datasets from the First Affiliated Hospital (FAHSYSU), the Sixth Affiliated Hospital (SAHSYSU) of Sun Yat-sen University, and Nanfang Hospital of Southern Medical University (NHSMU). The FAHSYSU dataset is utilized for internal training, while the SAHSYSU and NHSMU datasets serve for external evaluation. Extensive experiments demonstrate that SAM-Swin outperforms state-of-the-art methods, showcasing its potential for advancing LPC detection and improving patient outcomes. The source code of SAM-Swin is available at the URL of https://github.com/VVJia/SAM-Swin.

喉咽癌（LPC）是头颈部高度致命的恶性肿瘤。肿瘤检测的最新进展，特别是通过双分支网络架构，通过整合全局和局部特征提取，显著提高了诊断准确性。然而，在准确定位病变和充分利用这些分支内特征的互补性方面仍然存在挑战。为了解决这些问题，我们提出了SAM-Swin，一种创新的sam驱动的双swin转换器，用于喉部肿瘤检测。该模型利用了SAM2 （Segment Anything model 2）的强大分割功能，实现了精确的病灶分割。同时，我们提出了一个多尺度的病灶感知增强模块（MS-LAEM），旨在自适应地增强对不同尺度的细微互补特征的学习，提高特征提取和表征的质量。此外，我们实现了一个多尺度类感知引导（CAG）损失，提供了多尺度目标监督，从而增强了模型提取类特定特征的能力。为了验证我们的方法，我们从中山大学第一附属医院（FAHSYSU）、中山大学第六附属医院（SAHSYSU）和南方医科大学南方医院（NHSMU）收集了三个LPC数据集。FAHSYSU数据集用于内部训练，而SAHSYSU和NHSMU数据集用于外部评估。广泛的实验表明，SAM-Swin优于最先进的方法，展示了其在推进LPC检测和改善患者预后方面的潜力。SAM-Swin的源代码可从https://github.com/VVJia/SAM-Swin获取。

{"title":"SAM-Swin: SAM-driven dual-swin transformers with adaptive lesion enhancement for Laryngo-Pharyngeal tumor detection","authors":"Jia Wei , Yun Li , Xiaomao Fan , Wenjun Ma , Meiyu Qiu , Hongyu Chen , Wenbin Lei","doi":"10.1016/j.media.2025.103906","DOIUrl":"10.1016/j.media.2025.103906","url":null,"abstract":"<div><div>Laryngo-pharyngeal cancer (LPC) is a highly lethal malignancy in the head and neck region. Recent advancements in tumor detection, particularly through dual-branch network architectures, have significantly improved diagnostic accuracy by integrating global and local feature extraction. However, challenges remain in accurately localizing lesions and fully capitalizing on the complementary nature of features within these branches. To address these issues, we propose SAM-Swin, an innovative SAM-driven Dual-Swin Transformer for laryngo-pharyngeal tumor detection. This model leverages the robust segmentation capabilities of the Segment Anything Model 2 (SAM2) to achieve precise lesion segmentation. Meanwhile, we present a multi-scale lesion-aware enhancement module (MS-LAEM) designed to adaptively enhance the learning of nuanced complementary features across various scales, improving the quality of feature extraction and representation. Furthermore, we implement a multi-scale class-aware guidance (CAG) loss that delivers multi-scale targeted supervision, thereby enhancing the model’s capacity to extract class-specific features. To validate our approach, we compiled three LPC datasets from the First Affiliated Hospital (FAHSYSU), the Sixth Affiliated Hospital (SAHSYSU) of Sun Yat-sen University, and Nanfang Hospital of Southern Medical University (NHSMU). The FAHSYSU dataset is utilized for internal training, while the SAHSYSU and NHSMU datasets serve for external evaluation. Extensive experiments demonstrate that SAM-Swin outperforms state-of-the-art methods, showcasing its potential for advancing LPC detection and improving patient outcomes. The source code of SAM-Swin is available at the URL of <span><span>https://github.com/VVJia/SAM-Swin</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"109 ","pages":"Article 103906"},"PeriodicalIF":11.8,"publicationDate":"2025-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145705009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Unsupervised anomaly detection in medical imaging using aggregated normative diffusion 基于聚合规范扩散的医学成像无监督异常检测

IF 11.8 1区医学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Medical image analysis

Pub Date : 2025-12-08 DOI: 10.1016/j.media.2025.103895

Alexander Frotscher , Jaivardhan Kapoor , Thomas Wolfers , Christian F. Baumgartner

Early detection of anomalies in medical images such as brain magnetic resonance imaging (MRI) is highly relevant for diagnosis and treatment of many medical conditions. Supervised machine learning methods are limited to a small number of pathologies where there is good availability of labeled data. In contrast, unsupervised anomaly detection (UAD) has the potential to identify a broader spectrum of anomalies by spotting deviations from normal patterns. Our research demonstrates that previous state-of-the-art UAD approaches do not generalise well to diverse types of anomalies in multi-modal MRI data. To overcome this, we introduce a new UAD method named Aggregated Normative Diffusion (ANDi). ANDi operates by aggregating differences between predicted denoising steps and ground truth backwards transitions in Denoising Diffusion Probabilistic Models (DDPMs) that have been trained on pyramidal Gaussian noise. We validate ANDi against four recent UAD baselines, and across three diverse brain MRI datasets. We show that ANDi, in some cases, substantially surpasses these baselines and shows increased robustness to varying types of anomalies. Particularly in detecting multiple sclerosis (MS) lesions, ANDi achieves improvements of up to 44 % (0.302 to 0.436 on Lubljana, +0.134) in terms of AUPRC.

早期发现异常的医学图像，如脑磁共振成像（MRI）是高度相关的诊断和治疗许多医疗条件。有监督的机器学习方法仅限于有标记数据可用的少数病理。相比之下，无监督异常检测（UAD）有可能通过发现与正常模式的偏差来识别更广泛的异常范围。我们的研究表明，以前最先进的UAD方法不能很好地推广到多模态MRI数据中不同类型的异常。为了克服这个问题，我们引入了一种新的UAD方法——聚合规范扩散（ANDi）。ANDi通过汇总在金字塔高斯噪声上训练的去噪扩散概率模型（ddpm）中预测去噪步骤和地面真值向后过渡之间的差异来操作。我们通过三个最近的UAD基线和三个不同的脑MRI数据集验证了ANDi。我们表明，在某些情况下，ANDi实质上超过了这些基线，并且对不同类型的异常表现出更高的鲁棒性。特别是在检测多发性硬化症（MS）病变方面，ANDi在AUPRC方面达到了高达73%的提高。

{"title":"Unsupervised anomaly detection in medical imaging using aggregated normative diffusion","authors":"Alexander Frotscher , Jaivardhan Kapoor , Thomas Wolfers , Christian F. Baumgartner","doi":"10.1016/j.media.2025.103895","DOIUrl":"10.1016/j.media.2025.103895","url":null,"abstract":"<div><div>Early detection of anomalies in medical images such as brain magnetic resonance imaging (MRI) is highly relevant for diagnosis and treatment of many medical conditions. Supervised machine learning methods are limited to a small number of pathologies where there is good availability of labeled data. In contrast, <em>unsupervised</em> anomaly detection (UAD) has the potential to identify a broader spectrum of anomalies by spotting deviations from normal patterns. Our research demonstrates that previous state-of-the-art UAD approaches do not generalise well to diverse types of anomalies in multi-modal MRI data. To overcome this, we introduce a new UAD method named Aggregated Normative Diffusion (<span>ANDi</span>). <span>ANDi</span> operates by aggregating differences between predicted denoising steps and ground truth backwards transitions in Denoising Diffusion Probabilistic Models (DDPMs) that have been trained on pyramidal Gaussian noise. We validate <span>ANDi</span> against four recent UAD baselines, and across three diverse brain MRI datasets. We show that <span>ANDi</span>, in some cases, substantially surpasses these baselines and shows increased robustness to varying types of anomalies. Particularly in detecting multiple sclerosis (MS) lesions, <span>ANDi</span> achieves improvements of up to 44 % (0.302 to 0.436 on Lubljana, +0.134) in terms of AUPRC.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"109 ","pages":"Article 103895"},"PeriodicalIF":11.8,"publicationDate":"2025-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145705010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Test-time generative augmentation for medical image segmentation 基于测试时间生成增强的医学图像分割

IF 11.8 1区医学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Medical image analysis

Pub Date : 2025-12-07 DOI: 10.1016/j.media.2025.103902

Xiao Ma , Yuhui Tao , Zetian Zhang , Yuhan Zhang , Xi Wang , Sheng Zhang , Zexuan Ji , Yizhe Zhang , Qiang Chen , Guang Yang

Medical image segmentation is critical for clinical diagnosis, treatment planning, and monitoring, yet segmentation models often struggle with uncertainties stemming from occlusions, ambiguous boundaries, and variations in imaging devices. Traditional test-time augmentation (TTA) techniques typically rely on predefined geometric and photometric transformations, limiting their adaptability and effectiveness in complex medical scenarios. In this study, we introduced Test-Time Generative Augmentation (TTGA), a novel augmentation strategy specifically tailored for medical image segmentation at inference time. Different from conventional augmentation strategies that suffer from excessive randomness or limited flexibility, TTGA leverages a domain-fine-tuned generative model to produce contextually relevant and diverse augmentations tailored to the characteristics of each test image. Built upon diffusion model inversion, a masked null-text inversion method is proposed to enable region-specific augmentations during sampling. Furthermore, a dual denoising pathway is designed to balance precise identity preservation with controlled variability. We demonstrate the efficacy of our TTGA through extensive experiments across three distinct segmentation tasks spanning nine datasets. Our results consistently demonstrate that TTGA not only improves segmentation accuracy (with DSC gains ranging from 0.1 % to 2.3 % over the baseline) but also offers pixel-wise error estimation (with DSC gains ranging from 1.1 % to 29.0 % over the baseline). The source code and demonstration are available at: https://github.com/maxiao0234/TTGA.

医学图像分割对于临床诊断、治疗计划和监测至关重要，但分割模型经常受到来自闭塞、模糊边界和成像设备变化的不确定性的困扰。传统的测试时间增强（TTA）技术通常依赖于预定义的几何和光度变换，限制了它们在复杂医疗场景中的适应性和有效性。在这项研究中，我们引入了测试时间生成增强（TTGA），这是一种专门针对推理时间医学图像分割的新型增强策略。与传统的增强策略不同，传统的增强策略具有过度的随机性或有限的灵活性，TTGA利用领域微调生成模型来根据每个测试图像的特征生成上下文相关和多样化的增强。在扩散模型反演的基础上，提出了一种屏蔽空文本反演方法，实现了采样过程中特定区域的增强。此外，设计了一种双重去噪途径来平衡精确的身份保持和可控的可变性。我们通过跨九个数据集的三个不同分割任务的广泛实验证明了我们的TTGA的有效性。我们的结果一致表明，TTGA不仅提高了分割精度（DSC增益范围从基线的0.1%到2.3%），而且还提供了像素级误差估计（DSC增益范围从基线的1.1%到29.0%）。源代码和演示可从https://github.com/maxiao0234/TTGA获得。

{"title":"Test-time generative augmentation for medical image segmentation","authors":"Xiao Ma , Yuhui Tao , Zetian Zhang , Yuhan Zhang , Xi Wang , Sheng Zhang , Zexuan Ji , Yizhe Zhang , Qiang Chen , Guang Yang","doi":"10.1016/j.media.2025.103902","DOIUrl":"10.1016/j.media.2025.103902","url":null,"abstract":"<div><div>Medical image segmentation is critical for clinical diagnosis, treatment planning, and monitoring, yet segmentation models often struggle with uncertainties stemming from occlusions, ambiguous boundaries, and variations in imaging devices. Traditional test-time augmentation (TTA) techniques typically rely on predefined geometric and photometric transformations, limiting their adaptability and effectiveness in complex medical scenarios. In this study, we introduced <strong>T</strong>est-<strong>T</strong>ime <strong>G</strong>enerative <strong>A</strong>ugmentation (<strong>TTGA</strong>), a novel augmentation strategy specifically tailored for medical image segmentation at inference time. Different from conventional augmentation strategies that suffer from excessive randomness or limited flexibility, TTGA leverages a domain-fine-tuned generative model to produce contextually relevant and diverse augmentations tailored to the characteristics of each test image. Built upon diffusion model inversion, a masked null-text inversion method is proposed to enable region-specific augmentations during sampling. Furthermore, a dual denoising pathway is designed to balance precise identity preservation with controlled variability. We demonstrate the efficacy of our TTGA through extensive experiments across three distinct segmentation tasks spanning nine datasets. Our results consistently demonstrate that TTGA not only improves segmentation accuracy (with DSC gains ranging from 0.1 % to 2.3 % over the baseline) but also offers pixel-wise error estimation (with DSC gains ranging from 1.1 % to 29.0 % over the baseline). The source code and demonstration are available at: <span><span>https://github.com/maxiao0234/TTGA</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"109 ","pages":"Article 103902"},"PeriodicalIF":11.8,"publicationDate":"2025-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Diagnostic text-guided representation learning in hierarchical classification for pathological whole slide image 诊断性文本引导表征学习在病理整片图像分层分类中的应用

IF 11.8 1区医学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Medical image analysis

Pub Date : 2025-12-07 DOI: 10.1016/j.media.2025.103894

Jiawen Li , Qiehe Sun , Renao Yan , Yizhi Wang , Yuqiu Fu , Yani Wei , Tian Guan , Huijuan Shi , Yonghong He , Anjia Han

With the development of digital imaging in medical microscopy, artificial intelligent-based analysis of pathological whole slide images (WSIs) provides a powerful tool for cancer diagnosis. Limited by the expensive cost of pixel-level annotation, current research primarily focuses on representation learning with slide-level labels, showing success in various downstream tasks. However, given the diversity of lesion types and the complex relationships between each other, these techniques still deserve further exploration in addressing advanced pathology tasks. To this end, we introduce the concept of hierarchical pathological image classification and propose a representation learning called PathTree. PathTree considers the multi-classification of diseases as a binary tree structure. Each category is represented as a professional pathological text description, which messages information with a tree-like encoder. The interactive text features are then used to guide the aggregation of hierarchical multiple representations. PathTree uses slide-text similarity to obtain probability scores and introduces two extra tree-specific losses to further constrain the association between texts and slides. Through extensive experiments on three challenging hierarchical classification datasets: in-house cryosectioned lung tissue lesion identification, public prostate cancer grade assessment, and public breast cancer subtyping, our proposed PathTree is consistently competitive compared to the state-of-the-art methods and provides a new perspective on the deep learning-assisted solution for more complex WSI classification.

随着数字成像技术在医学显微镜中的发展，基于人工智能的病理全切片图像分析为癌症诊断提供了有力的工具。受像素级标注昂贵成本的限制，目前的研究主要集中在使用幻灯片级标签的表示学习上，并在各种下游任务中取得了成功。然而，鉴于病变类型的多样性和彼此之间的复杂关系，这些技术在解决高级病理任务方面仍值得进一步探索。为此，我们引入了分层病理图像分类的概念，并提出了一种称为PathTree的表示学习方法。PathTree将疾病的多重分类视为二叉树结构。每个类别都表示为一个专业的病理文本描述，它用树状编码器传递信息。然后使用交互式文本特征来指导分层多表示的聚合。PathTree使用幻灯片-文本相似性来获得概率分数，并引入两个额外的树特定损失来进一步约束文本和幻灯片之间的关联。通过在三个具有挑战性的分层分类数据集上的广泛实验：内部冷冻切片肺组织病变识别、公共前列腺癌分级评估和公共乳腺癌亚型，我们提出的PathTree与最先进的方法相比始终具有竞争力，并为更复杂的WSI分类提供了深度学习辅助解决方案的新视角。

{"title":"Diagnostic text-guided representation learning in hierarchical classification for pathological whole slide image","authors":"Jiawen Li , Qiehe Sun , Renao Yan , Yizhi Wang , Yuqiu Fu , Yani Wei , Tian Guan , Huijuan Shi , Yonghong He , Anjia Han","doi":"10.1016/j.media.2025.103894","DOIUrl":"10.1016/j.media.2025.103894","url":null,"abstract":"<div><div>With the development of digital imaging in medical microscopy, artificial intelligent-based analysis of pathological whole slide images (WSIs) provides a powerful tool for cancer diagnosis. Limited by the expensive cost of pixel-level annotation, current research primarily focuses on representation learning with slide-level labels, showing success in various downstream tasks. However, given the diversity of lesion types and the complex relationships between each other, these techniques still deserve further exploration in addressing advanced pathology tasks. To this end, we introduce the concept of hierarchical pathological image classification and propose a representation learning called PathTree. PathTree considers the multi-classification of diseases as a binary tree structure. Each category is represented as a professional pathological text description, which messages information with a tree-like encoder. The interactive text features are then used to guide the aggregation of hierarchical multiple representations. PathTree uses slide-text similarity to obtain probability scores and introduces two extra tree-specific losses to further constrain the association between texts and slides. Through extensive experiments on three challenging hierarchical classification datasets: in-house cryosectioned lung tissue lesion identification, public prostate cancer grade assessment, and public breast cancer subtyping, our proposed PathTree is consistently competitive compared to the state-of-the-art methods and provides a new perspective on the deep learning-assisted solution for more complex WSI classification.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"109 ","pages":"Article 103894"},"PeriodicalIF":11.8,"publicationDate":"2025-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Immunocto: A massive immune cell database auto-generated for histopathology 免疫细胞：为组织病理学自动生成的大量免疫细胞数据库

IF 11.8 1区医学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Medical image analysis

Pub Date : 2025-12-07 DOI: 10.1016/j.media.2025.103905

Mikaël Simard , Zhuoyan Shen , Konstantin Bräutigam , Rasha Abu-Eid , Maria A. Hawkins , Charles-Antoine Collins Fekete

With the advent of novel cancer treatment options such as immunotherapy, studying the tumour immune micro-environment (TIME) is crucial to inform on prognosis and understand potential response to therapeutic agents. A key approach to characterising the TIME involves combining digitised images of haematoxylin and eosin (H&E) stained tissue sections obtained in routine histopathology examination with automated immune cell detection and classification methods. In this work, we introduce a workflow to automatically generate robust single cell contours and labels from dually stained tissue sections with H&E and multiplexed immunofluorescence (IF) markers. The approach harnesses the Segment Anything Model and requires minimal human intervention compared to existing single cell databases. With this methodology, we create Immunocto, a massive, multi-million automatically generated database of 6,848,454 human cells and objects, including 2,282,818 immune cells distributed across 4 subtypes: CD4

^{+}

T cell lymphocytes, CD8

^{+}

T cell lymphocytes, CD20

^{+}

B cell lymphocytes, and CD68

^{+}

/CD163

^{+}

macrophages. For each cell, we provide a 64 × 64 pixels² H&E image at 40 ×  magnification, along with a binary mask of the nucleus and a label. The database, which is made publicly available, can be used to train models to study the TIME on routine H&E slides. We show that deep learning models trained on Immunocto result in state-of-the-art performance for lymphocyte detection. The approach demonstrates the benefits of using matched H&E and IF data to generate robust databases for computational pathology applications.

随着免疫疗法等新型癌症治疗方案的出现，研究肿瘤免疫微环境（TIME）对于预测预后和了解治疗药物的潜在反应至关重要。表征TIME的关键方法包括将常规组织病理学检查中获得的血红素和伊红（H&；E）染色组织切片的数字化图像与自动免疫细胞检测和分类方法相结合。在这项工作中，我们引入了一个工作流程，可以自动生成具有H&；E和多重免疫荧光（IF）标记的双染色组织切片的鲁棒单细胞轮廓和标签。该方法利用分段任意模型，与现有的单细胞数据库相比，需要最少的人为干预。利用这种方法，我们创建了Immunocto，这是一个巨大的、数百万自动生成的数据库，包含6848454个人类细胞和物体，包括2282818个免疫细胞，分布在4个亚型：CD4+ T细胞淋巴细胞、CD8+ T细胞淋巴细胞、CD20+ B细胞淋巴细胞和CD68+/CD163+巨噬细胞。对于每个细胞，我们提供了一张64 × 64 pixels2的H&；E图像，放大倍数为40 ×，以及细胞核的二进制掩模和标签。该数据库是公开的，可用于训练模型来研究常规H&；E幻灯片上的TIME。我们表明，在Immunocto上训练的深度学习模型在淋巴细胞检测方面具有最先进的性能。该方法证明了使用匹配的H&；E和IF数据为计算病理学应用生成健壮的数据库的好处。

{"title":"Immunocto: A massive immune cell database auto-generated for histopathology","authors":"Mikaël Simard , Zhuoyan Shen , Konstantin Bräutigam , Rasha Abu-Eid , Maria A. Hawkins , Charles-Antoine Collins Fekete","doi":"10.1016/j.media.2025.103905","DOIUrl":"10.1016/j.media.2025.103905","url":null,"abstract":"<div><div>With the advent of novel cancer treatment options such as immunotherapy, studying the tumour immune micro-environment (TIME) is crucial to inform on prognosis and understand potential response to therapeutic agents. A key approach to characterising the TIME involves combining digitised images of haematoxylin and eosin (H&E) stained tissue sections obtained in routine histopathology examination with automated immune cell detection and classification methods. In this work, we introduce a workflow to automatically generate robust single cell contours and labels from dually stained tissue sections with H&E and multiplexed immunofluorescence (IF) markers. The approach harnesses the Segment Anything Model and requires minimal human intervention compared to existing single cell databases. With this methodology, we create Immunocto, a massive, multi-million automatically generated database of 6,848,454 human cells and objects, including 2,282,818 immune cells distributed across 4 subtypes: CD4<span><math><msup><mrow></mrow><mo>+</mo></msup></math></span> T cell lymphocytes, CD8<span><math><msup><mrow></mrow><mo>+</mo></msup></math></span> T cell lymphocytes, CD20<span><math><msup><mrow></mrow><mo>+</mo></msup></math></span> B cell lymphocytes, and CD68<span><math><msup><mrow></mrow><mo>+</mo></msup></math></span>/CD163<span><math><msup><mrow></mrow><mo>+</mo></msup></math></span> macrophages. For each cell, we provide a 64 × 64 pixels<sup>2</sup> H&E image at <strong>40</strong> ×  magnification, along with a binary mask of the nucleus and a label. The database, which is made publicly available, can be used to train models to study the TIME on routine H&E slides. We show that deep learning models trained on Immunocto result in state-of-the-art performance for lymphocyte detection. The approach demonstrates the benefits of using matched H&E and IF data to generate robust databases for computational pathology applications.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"109 ","pages":"Article 103905"},"PeriodicalIF":11.8,"publicationDate":"2025-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145705011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Perivascular space identification nnUNet for generalised usage (PINGU) 通用血管周围空间识别网（PINGU）

IF 11.8 1区医学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Medical image analysis

Pub Date : 2025-12-04 DOI: 10.1016/j.media.2025.103903

Benjamin Sinclair , William Pham , Lucy Vivash , Jasmine Moses , Miranda Lynch , Karina Dorfman , Cassandra Marotta , Shaun Koh , Jacob Bunyamin , Ella Rowsthorn , Alex Jarema , Himashi Peiris , Zhaolin Chen , Sandy R Shultz , David K Wright , Dexiao Kong , Sharon L. Naismith , Terence J. O’Brien , Meng Law

Perivascular spaces (PVSs) form a central component of the brain’s waste clearance system, the glymphatic system. These structures are visible on MRIs when enlarged, and their morphology is associated with aging and neurological disease. Manual quantification of PVS is time consuming and subjective. Numerous deep learning methods for PVS segmentation have been developed for automated segmentation. However, the majority of these algorithms have been developed and evaluated on homogenous datasets and high resolution scans, perhaps limiting their applicability for the wide range of image qualities acquired in clinical and research settings. In this work we train a nnUNet, a top-performing task driven biomedical image segmentation deep learning algorithm, on a heterogenous training sample of manually segmented MRIs of a range of different qualities and resolutions from 7 different datasets acquired on 6 different scanners. These are compared to the two currently publicly available deep learning methods for 3D segmentation of PVS, evaluated on scans with a range of resolutions and qualities. The resulting model, PINGU (Perivascular space Identification Nnunet for Generalised Usage), achieved voxel and cluster level dice scores of 0.50(SD=0.15) and 0.63(0.17) in the white matter (WM), and 0.54 (0.11) and 0.66(0.17) in the basal ganglia (BG). Performance on unseen “external” sites’ data was substantially lower for both PINGU (0.20-0.38 [WM, voxel], 0.29-0.58 [WM, cluster], 0.22-0.36 [BG, voxel], 0.46-0.60 [BG, cluster]) and the publicly available algorithms (0.18-0.30 [WM, voxel], 0.29-0.38 [WM cluster], 0.10-0.20 [BG, voxel], 0.15-0.37 [BG, cluster]). Nonetheless, PINGU strongly outperformed the publicly available algorithms, particularly in the BG. PINGU stands out as broad-use PVS segmentation tool, with particular strength in the BG, an area of PVS highly related to vascular disease and pathology.

血管周围空间（PVSs）是大脑废物清除系统（淋巴系统）的中心组成部分。这些结构放大后在mri上可见，其形态与衰老和神经系统疾病有关。人工量化pv既耗时又主观。为了实现自动分割，已经开发了许多用于pv分割的深度学习方法。然而，这些算法中的大多数都是在同质数据集和高分辨率扫描上开发和评估的，这可能限制了它们在临床和研究环境中获得的广泛图像质量的适用性。在这项工作中，我们训练了nnUNet，一种性能最好的任务驱动的生物医学图像分割深度学习算法，在来自6个不同扫描仪上获得的7个不同数据集的一系列不同质量和分辨率的手动分割mri的异构训练样本上。将这些方法与目前公开的两种用于pv 3D分割的深度学习方法进行比较，并对扫描结果进行一系列分辨率和质量的评估。所得模型PINGU（血管周围空间识别Nnunet for Generalised Usage）在白质（WM）中获得了0.50（SD=0.15）和0.63（0.17）的体素和聚类水平骰子分数，在基底节区（BG）中获得了0.54（0.11）和0.66（0.17）的分数。PINGU （0.20-0.38 [WM，体素]，0.29-0.58 [WM，聚类]，0.22-0.36 [BG，体素]，0.46-0.60 [BG，聚类]）和公开的算法（0.18-0.30 [WM，体素]，0.29-0.38 [WM聚类]，0.10-0.20 [BG，体素]，0.15-0.37 [BG，聚类]）在未见过的“外部”站点数据上的性能都明显较低。尽管如此，PINGU的表现仍然远远优于公开可用的算法，特别是在BG中。PINGU作为一种广泛使用的PVS分割工具，在与血管疾病和病理高度相关的PVS领域BG中具有特别的优势。

{"title":"Perivascular space identification nnUNet for generalised usage (PINGU)","authors":"Benjamin Sinclair , William Pham , Lucy Vivash , Jasmine Moses , Miranda Lynch , Karina Dorfman , Cassandra Marotta , Shaun Koh , Jacob Bunyamin , Ella Rowsthorn , Alex Jarema , Himashi Peiris , Zhaolin Chen , Sandy R Shultz , David K Wright , Dexiao Kong , Sharon L. Naismith , Terence J. O’Brien , Meng Law","doi":"10.1016/j.media.2025.103903","DOIUrl":"10.1016/j.media.2025.103903","url":null,"abstract":"<div><div>Perivascular spaces (PVSs) form a central component of the brain’s waste clearance system, the glymphatic system. These structures are visible on MRIs when enlarged, and their morphology is associated with aging and neurological disease. Manual quantification of PVS is time consuming and subjective. Numerous deep learning methods for PVS segmentation have been developed for automated segmentation. However, the majority of these algorithms have been developed and evaluated on homogenous datasets and high resolution scans, perhaps limiting their applicability for the wide range of image qualities acquired in clinical and research settings. In this work we train a nnUNet, a top-performing task driven biomedical image segmentation deep learning algorithm, on a heterogenous training sample of manually segmented MRIs of a range of different qualities and resolutions from 7 different datasets acquired on 6 different scanners. These are compared to the two currently publicly available deep learning methods for 3D segmentation of PVS, evaluated on scans with a range of resolutions and qualities. The resulting model, PINGU (Perivascular space Identification Nnunet for Generalised Usage), achieved voxel and cluster level dice scores of 0.50(SD=0.15) and 0.63(0.17) in the white matter (WM), and 0.54 (0.11) and 0.66(0.17) in the basal ganglia (BG). Performance on unseen “external” sites’ data was substantially lower for both PINGU (0.20-0.38 [WM, voxel], 0.29-0.58 [WM, cluster], 0.22-0.36 [BG, voxel], 0.46-0.60 [BG, cluster]) and the publicly available algorithms (0.18-0.30 [WM, voxel], 0.29-0.38 [WM cluster], 0.10-0.20 [BG, voxel], 0.15-0.37 [BG, cluster]). Nonetheless, PINGU strongly outperformed the publicly available algorithms, particularly in the BG. PINGU stands out as broad-use PVS segmentation tool, with particular strength in the BG, an area of PVS highly related to vascular disease and pathology.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"109 ","pages":"Article 103903"},"PeriodicalIF":11.8,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

AGFS-tractometry: A novel atlas-guided fine-scale tractometry approach for enhanced along-tract group statistical comparison using diffusion MRI tractography agfs - tractetry：一种新的阿特拉斯引导的精细尺度tractetry方法，用于增强沿束组统计比较，使用扩散MRI Tractography

IF 11.8 1区医学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Medical image analysis

Pub Date : 2025-12-03 DOI: 10.1016/j.media.2025.103892

Ruixi Zheng , Wei Zhang , Yijie Li , Xi Zhu , Zhou Lan , Jarrett Rushmore , Yogesh Rathi , Nikos Makris , Lauren J. O’Donnell , Fan Zhang

Diffusion MRI (dMRI) tractography is currently the only method for in vivo mapping of the brain’s white matter (WM) connections. Tractometry is an advanced tractography analysis technique for along-tract profiling to investigate the morphology and microstructural properties along the fiber tracts. Tractometry has become an essential tool for studying local along-tract differences between different populations (e.g., health vs disease). In this study, we propose a novel atlas-guided fine-scale tractometry method, namely AGFS-Tractometry, that leverages tract spatial information and permutation testing to enhance the along-tract statistical analysis between populations. There are two major contributions in AGFS-Tractometry. First, we create a novel atlas-guided tract profiling template that enables consistent, fine-scale, along-tract parcellation of subject-specific fiber tracts. Second, we propose a novel nonparametric permutation testing group comparison method to enable simultaneous analysis across all along-tract parcels while correcting for multiple comparisons. We perform experimental evaluations on synthetic datasets with known group differences and in vivo real data. We compare AGFS-Tractometry with two state-of-the-art tractometry methods, including Automated Fiber-tract Quantification (AFQ) and BUndle ANalytics (BUAN). Our results show that the proposed AGFS-Tractometry obtains enhanced sensitivity and specificity in detecting local WM differences. In the real data analysis experiments, AGFS-Tractometry can identify more regions with significant differences, which are anatomically consistent with the existing literature. Overall, these demonstrate the ability of AGFS-Tractometry to detect subtle or spatially localized WM group-level differences. The created tract profiling template and related code are available at: https://github.com/ZhengRuixi/AGFS-Tractometry.git.

扩散磁共振成像（dMRI）神经束成像是目前唯一的在体脑白质（WM）连接成像方法。纤维束法是一种先进的纤维束分析技术，用于研究纤维束的形态和微观结构特性。束测法已成为研究不同人群之间局部沿束差异（例如，健康vs疾病）的重要工具。在本研究中，我们提出了一种新的阿特拉斯引导的精细尺度tractometry方法，即AGFS-Tractometry，该方法利用通道空间信息和排列测试来增强种群间的沿通道统计分析。在AGFS-Tractometry中有两个主要贡献。首先，我们创建了一种新的图谱引导的纤维束分析模板，该模板可以实现一致的、精细的、沿着特定纤维束的束状分割。其次，我们提出了一种新的非参数排列测试组比较方法，以便在校正多重比较的同时对所有沿道包裹进行同时分析。我们对已知组差异和体内真实数据的合成数据集进行实验评估。我们将AGFS-Tractometry与两种最先进的tractometry方法进行比较，包括自动纤维束定量（AFQ）和束分析（BUAN）。我们的研究结果表明，所提出的AGFS-Tractometry在检测局部WM差异方面具有更高的灵敏度和特异性。在真实的数据分析实验中，AGFS-Tractometry能够识别出更多具有显著差异的区域，这在解剖学上与已有文献一致。总的来说，这些表明AGFS-Tractometry能够检测细微的或空间定位的WM组水平差异。创建的通道分析模板和相关代码可从https://github.com/ZhengRuixi/AGFS-Tractometry.git获得。

{"title":"AGFS-tractometry: A novel atlas-guided fine-scale tractometry approach for enhanced along-tract group statistical comparison using diffusion MRI tractography","authors":"Ruixi Zheng , Wei Zhang , Yijie Li , Xi Zhu , Zhou Lan , Jarrett Rushmore , Yogesh Rathi , Nikos Makris , Lauren J. O’Donnell , Fan Zhang","doi":"10.1016/j.media.2025.103892","DOIUrl":"10.1016/j.media.2025.103892","url":null,"abstract":"<div><div>Diffusion MRI (dMRI) tractography is currently the only method for in vivo mapping of the brain’s white matter (WM) connections. Tractometry is an advanced tractography analysis technique for along-tract profiling to investigate the morphology and microstructural properties along the fiber tracts. Tractometry has become an essential tool for studying local along-tract differences between different populations (e.g., health vs disease). In this study, we propose a novel atlas-guided fine-scale tractometry method, namely AGFS-Tractometry, that leverages tract spatial information and permutation testing to enhance the along-tract statistical analysis between populations. There are two major contributions in AGFS-Tractometry. First, we create a novel atlas-guided tract profiling template that enables consistent, fine-scale, along-tract parcellation of subject-specific fiber tracts. Second, we propose a novel nonparametric permutation testing group comparison method to enable simultaneous analysis across all along-tract parcels while correcting for multiple comparisons. We perform experimental evaluations on synthetic datasets with known group differences and in vivo real data. We compare AGFS-Tractometry with two state-of-the-art tractometry methods, including Automated Fiber-tract Quantification (AFQ) and BUndle ANalytics (BUAN). Our results show that the proposed AGFS-Tractometry obtains enhanced sensitivity and specificity in detecting local WM differences. In the real data analysis experiments, AGFS-Tractometry can identify more regions with significant differences, which are anatomically consistent with the existing literature. Overall, these demonstrate the ability of AGFS-Tractometry to detect subtle or spatially localized WM group-level differences. The created tract profiling template and related code are available at: <span><span>https://github.com/ZhengRuixi/AGFS-Tractometry.git</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"109 ","pages":"Article 103892"},"PeriodicalIF":11.8,"publicationDate":"2025-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689531","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Uncertainty estimates in pharmacokinetic modelling of DCE-MRI DCE-MRI药代动力学模型的不确定性估计

IF 11.8 1区医学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Medical image analysis

Pub Date : 2025-12-03 DOI: 10.1016/j.media.2025.103881

Jonas M. Van Elburg , Natalia V. Korobova , Mohammad M. Islam , Marian A. Troelstra , Oliver J. Gurney-Champion

Dynamic contrast-enhanced (DCE) MRI is a powerful technique for detecting and characterising various diseases by quantifying tissue perfusion. However, accurate perfusion quantification remains challenging due to noisy data and the complexity of pharmacokinetic modelling. Conventional non-linear least squares (NLLS) fitting often yields noisy parameter maps. Although deep-learning algorithms generate smoother, more visually appealing maps, these may lure clinicians into a false sense of security when the maps are incorrect. Hence, reliable uncertainty estimation is crucial for assessing model performance and ensuring clinical confidence.

Therefore, we implemented an ensemble of mean-variance estimation (MVE) neural networks to quantify perfusion parameters alongside aleatoric (data-driven) and epistemic (model-driven) uncertainties in DCE-MRI. We compared MVE with NLLS and a physics-informed neural network (PINN), both of which used conventional covariance matrix-based uncertainty estimation.

Simulations demonstrated that MVE achieved the highest accuracy in perfusion and uncertainty estimates. MVE’s aleatoric uncertainty strongly correlated with true errors, whereas NLLS and PINN tended to overestimate uncertainty. Epistemic uncertainty was significantly higher for the data deviating from what was encountered in training (out-of-distribution) in both MVE and PINN ensembles. In vivo, MVE produced smoother and more reliable uncertainty maps than NLLS and PINN, which exhibited outliers and overestimation. Within a liver region of interest, MVE’s uncertainty estimates matched the standard deviation of the data more closely than NLLS and PINN, making it the most accurate method.

In conclusion, an MVE enhances quantitative DCE-MRI by providing robust uncertainty estimates alongside perfusion parameters. This approach improves the reliability of AI-driven MRI analysis, supporting clinical translation.

动态对比增强（DCE） MRI是一种通过定量组织灌注来检测和表征各种疾病的强大技术。然而，由于数据嘈杂和药代动力学建模的复杂性，准确的灌注定量仍然具有挑战性。传统的非线性最小二乘（NLLS）拟合通常会产生噪声参数图。尽管深度学习算法生成的地图更平滑，视觉上更吸引人，但当地图不正确时，这些算法可能会诱使临床医生产生错误的安全感。因此，可靠的不确定性估计对于评估模型性能和确保临床置信度至关重要。因此，我们实现了均值方差估计（MVE）神经网络的集合，以量化灌注参数以及DCE-MRI中的任意（数据驱动）和认知（模型驱动）不确定性。我们将MVE与NLLS和物理信息神经网络（PINN）进行了比较，这两种方法都使用传统的基于协方差矩阵的不确定性估计。仿真结果表明，MVE在灌注和不确定性估计方面具有最高的准确性。MVE的任意不确定性与真实误差密切相关，而NLLS和PINN倾向于高估不确定性。在MVE和PINN集成中，对于偏离训练中遇到的数据（分布外），认知不确定性明显更高。在体内，与NLLS和PINN相比，MVE产生的不确定性图更平滑、更可靠，后者表现出异常值和高估。在感兴趣的肝脏区域内，MVE的不确定性估计比NLLS和PINN更接近数据的标准偏差，使其成为最准确的方法。总之，MVE通过提供可靠的不确定性估计和灌注参数来增强定量DCE-MRI。这种方法提高了人工智能驱动的MRI分析的可靠性，支持临床翻译。

{"title":"Uncertainty estimates in pharmacokinetic modelling of DCE-MRI","authors":"Jonas M. Van Elburg , Natalia V. Korobova , Mohammad M. Islam , Marian A. Troelstra , Oliver J. Gurney-Champion","doi":"10.1016/j.media.2025.103881","DOIUrl":"10.1016/j.media.2025.103881","url":null,"abstract":"<div><div>Dynamic contrast-enhanced (DCE) MRI is a powerful technique for detecting and characterising various diseases by quantifying tissue perfusion. However, accurate perfusion quantification remains challenging due to noisy data and the complexity of pharmacokinetic modelling. Conventional non-linear least squares (NLLS) fitting often yields noisy parameter maps. Although deep-learning algorithms generate smoother, more visually appealing maps, these may lure clinicians into a false sense of security when the maps are incorrect. Hence, reliable uncertainty estimation is crucial for assessing model performance and ensuring clinical confidence.</div><div>Therefore, we implemented an ensemble of mean-variance estimation (MVE) neural networks to quantify perfusion parameters alongside aleatoric (data-driven) and epistemic (model-driven) uncertainties in DCE-MRI. We compared MVE with NLLS and a physics-informed neural network (PINN), both of which used conventional covariance matrix-based uncertainty estimation.</div><div>Simulations demonstrated that MVE achieved the highest accuracy in perfusion and uncertainty estimates. MVE’s aleatoric uncertainty strongly correlated with true errors, whereas NLLS and PINN tended to overestimate uncertainty. Epistemic uncertainty was significantly higher for the data deviating from what was encountered in training (out-of-distribution) in both MVE and PINN ensembles. In vivo, MVE produced smoother and more reliable uncertainty maps than NLLS and PINN, which exhibited outliers and overestimation. Within a liver region of interest, MVE’s uncertainty estimates matched the standard deviation of the data more closely than NLLS and PINN, making it the most accurate method.</div><div>In conclusion, an MVE enhances quantitative DCE-MRI by providing robust uncertainty estimates alongside perfusion parameters. This approach improves the reliability of AI-driven MRI analysis, supporting clinical translation.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"109 ","pages":"Article 103881"},"PeriodicalIF":11.8,"publicationDate":"2025-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

D-EDL: Differential evidential deep learning for robust medical out-of-distribution detection D-EDL：基于差分证据深度学习的鲁棒医学非分布检测

IF 11.8 1区医学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Medical image analysis

Pub Date : 2025-11-30 DOI: 10.1016/j.media.2025.103888

Wei Fu , Yufei Chen , Yuqi Liu , Xiaodong Yue

In computer-aided diagnosis, the extreme imbalance in disease incidence rates often results in the omission of rare conditions, leading to out-of-distribution (OOD) samples during testing. To prevent unreliable diagnostic outputs, detecting these OOD samples becomes essential for clinical jnsafety. While Evidential Deep Learning (EDL) and its variants have shown great promise in detecting outliers, their clinical application remains challenging due to the variability in medical images. We find that when encountering samples with high data uncertainty, the Kullback-Leibler divergence (KL) in EDL tends to suppress inherent ambiguity, resulting in an over-penalty effect in evidence estimation that impairs discrimination between ambiguous in-distribution cases and true outliers. Motivated by the confirmatory and differential diagnostic process in clinical practice, we propose Differential Evidential Deep Learning (D-EDL), a simple but effective method for robust OOD detection. Specifically, we treat KL as a confirmatory restriction and innovatively replace it with a Ruling Out Module (ROM) for differential restriction, which reduces over-penalty on ambiguous ID samples while maintaining OOD sensitivity. Considering extreme testing scenarios, we introduce test-time Raw evidence Inference (RI) to bypass instability in uncertainty estimation with refined evidence and further improve robustness and precision. Finally, we propose the Balanced Detection Score (BDS) to quantify the potential on clinical performance when optimally balancing misdiagnoses and missed diagnoses across varying sensitivities. Experimental results on ISIC2019, Bone Marrow Cytomorphology datasets and EDDFS dataset demonstrate that our D-EDL outperforms state-of-the-art OOD detection methods, achieving significant improvements in robustness and clinical applicability. Code for D-EDL is available at https://github.com/KellaDoe/Differential_EDL.

在计算机辅助诊断中，由于疾病发病率的极度不平衡，往往会导致罕见疾病的遗漏，从而导致检测过程中的样本分布不均匀（OOD）。为了防止诊断结果不可靠，检测这些OOD样本对于临床安全至关重要。虽然证据深度学习（EDL）及其变体在检测异常值方面显示出巨大的希望，但由于医学图像的可变性，它们的临床应用仍然具有挑战性。我们发现，当遇到具有高数据不确定性的样本时，EDL中的Kullback-Leibler散度（KL）倾向于抑制固有的模糊性，从而导致证据估计中的过度惩罚效应，损害了分布中模糊性案例与真实异常值之间的区分。在临床实践的验证性和鉴别诊断过程的推动下，我们提出了差分证据深度学习（D-EDL），这是一种简单但有效的鲁棒性OOD检测方法。具体而言，我们将KL视为验证性限制，并创新地将其替换为排除模块（ROM）以进行差分限制，这减少了对模糊ID样本的过度惩罚，同时保持了OOD灵敏度。考虑到极端测试场景，我们引入了测试时间原始证据推断（RI）来绕过不确定性估计中的不稳定性，进一步提高了鲁棒性和精度。最后，我们提出了平衡检测评分（BDS）来量化在不同敏感性之间最佳平衡误诊和漏诊时临床表现的潜力。在ISIC2019、骨髓细胞形态学数据集和EDDFS数据集上的实验结果表明，我们的D-EDL优于最先进的OOD检测方法，在稳健性和临床适用性方面取得了显着提高。D-EDL的代码可从https://github.com/KellaDoe/Differential_EDL获得。

{"title":"D-EDL: Differential evidential deep learning for robust medical out-of-distribution detection","authors":"Wei Fu , Yufei Chen , Yuqi Liu , Xiaodong Yue","doi":"10.1016/j.media.2025.103888","DOIUrl":"10.1016/j.media.2025.103888","url":null,"abstract":"<div><div>In computer-aided diagnosis, the extreme imbalance in disease incidence rates often results in the omission of rare conditions, leading to out-of-distribution (OOD) samples during testing. To prevent unreliable diagnostic outputs, detecting these OOD samples becomes essential for clinical jnsafety. While Evidential Deep Learning (EDL) and its variants have shown great promise in detecting outliers, their clinical application remains challenging due to the variability in medical images. We find that when encountering samples with high data uncertainty, the Kullback-Leibler divergence (KL) in EDL tends to suppress inherent ambiguity, resulting in an over-penalty effect in evidence estimation that impairs discrimination between ambiguous in-distribution cases and true outliers. Motivated by the confirmatory and differential diagnostic process in clinical practice, we propose Differential Evidential Deep Learning (D-EDL), a simple but effective method for robust OOD detection. Specifically, we treat KL as a confirmatory restriction and innovatively replace it with a Ruling Out Module (ROM) for differential restriction, which reduces over-penalty on ambiguous ID samples while maintaining OOD sensitivity. Considering extreme testing scenarios, we introduce test-time Raw evidence Inference (RI) to bypass instability in uncertainty estimation with refined evidence and further improve robustness and precision. Finally, we propose the Balanced Detection Score (BDS) to quantify the potential on clinical performance when optimally balancing misdiagnoses and missed diagnoses across varying sensitivities. Experimental results on ISIC2019, Bone Marrow Cytomorphology datasets and EDDFS dataset demonstrate that our D-EDL outperforms state-of-the-art OOD detection methods, achieving significant improvements in robustness and clinical applicability. Code for D-EDL is available at <span><span>https://github.com/KellaDoe/Differential_EDL</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"109 ","pages":"Article 103888"},"PeriodicalIF":11.8,"publicationDate":"2025-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145619565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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