Computerized Medical Imaging and Graphics最新文献_第2页

VLFATRollout: Fully transformer-based classifier for retinal OCT volumes VLFATRollout：完全基于变换器的视网膜 OCT 容量分类器。

IF 5.4 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2024-10-29 DOI: 10.1016/j.compmedimag.2024.102452

Marzieh Oghbaie , Teresa Araújo , Ursula Schmidt-Erfurth , Hrvoje Bogunović

Background and Objective:

Despite the promising capabilities of 3D transformer architectures in video analysis, their application to high-resolution 3D medical volumes encounters several challenges. One major limitation is the high number of 3D patches, which reduces the efficiency of the global self-attention mechanisms of transformers. Additionally, background information can distract vision transformers from focusing on crucial areas of the input image, thereby introducing noise into the final representation. Moreover, the variability in the number of slices per volume complicates the development of models capable of processing input volumes of any resolution while simple solutions like subsampling may risk losing essential diagnostic details.

Methods:

To address these challenges, we introduce an end-to-end transformer-based framework, variable length feature aggregator transformer rollout (VLFATRollout), to classify volumetric data. The proposed VLFATRollout enjoys several merits. First, the proposed VLFATRollout can effectively mine slice-level fore-background information with the help of transformer’s attention matrices. Second, randomization of volume-wise resolution (i.e. the number of slices) during training enhances the learning capacity of the learnable positional embedding (PE) assigned to each volume slice. This technique allows the PEs to generalize across neighboring slices, facilitating the handling of high-resolution volumes at the test time.

Results:

VLFATRollout was thoroughly tested on the retinal optical coherence tomography (OCT) volume classification task, demonstrating a notable average improvement of 5.47% in balanced accuracy over the leading convolutional models for a 5-class diagnostic task. These results emphasize the effectiveness of our framework in enhancing slice-level representation and its adaptability across different volume resolutions, paving the way for advanced transformer applications in medical image analysis. The code is available at https://github.com/marziehoghbaie/VLFATRollout/.

背景和目的：尽管三维变压器架构在视频分析中的应用前景广阔，但将其应用于高分辨率三维医疗卷却面临着一些挑战。其中一个主要限制是三维斑块数量较多，这降低了变换器全局自我关注机制的效率。此外，背景信息会分散视觉转换器的注意力，使其无法聚焦于输入图像的关键区域，从而在最终表示中引入噪声。此外，每个体的切片数的变化使得开发能够处理任何分辨率的输入体的模型变得更加复杂，而简单的解决方案（如子采样）可能会丢失重要的诊断细节：为了应对这些挑战，我们引入了一种基于变压器的端到端框架--可变长度特征聚合变压器推出（VLFATRollout），用于对体积数据进行分类。所提出的 VLFATRollout 有几个优点。首先，拟议的 VLFATRollout 可借助变换器的注意力矩阵有效挖掘切片级前景信息。其次，在训练过程中对体积分辨率（即切片数）进行随机化，可增强分配给每个体积切片的可学习位置嵌入（PE）的学习能力。这种技术可以让位置嵌入在相邻切片之间进行泛化，从而在测试时更容易处理高分辨率的容积：VLFATRollout 在视网膜光学相干断层扫描（OCT）容积分类任务中进行了全面测试，在 5 类诊断任务中，与领先的卷积模型相比，平均平衡准确率显著提高了 5.47%。这些结果凸显了我们的框架在增强切片级表示方面的有效性及其对不同体分辨率的适应性，为医学图像分析中的高级变换器应用铺平了道路。代码见 https://github.com/marziehoghbaie/VLFATRollout/。

{"title":"VLFATRollout: Fully transformer-based classifier for retinal OCT volumes","authors":"Marzieh Oghbaie , Teresa Araújo , Ursula Schmidt-Erfurth , Hrvoje Bogunović","doi":"10.1016/j.compmedimag.2024.102452","DOIUrl":"10.1016/j.compmedimag.2024.102452","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>Despite the promising capabilities of 3D transformer architectures in video analysis, their application to high-resolution 3D medical volumes encounters several challenges. One major limitation is the high number of 3D patches, which reduces the efficiency of the global self-attention mechanisms of transformers. Additionally, background information can distract vision transformers from focusing on crucial areas of the input image, thereby introducing noise into the final representation. Moreover, the variability in the number of slices per volume complicates the development of models capable of processing input volumes of any resolution while simple solutions like subsampling may risk losing essential diagnostic details.</div></div><div><h3>Methods:</h3><div>To address these challenges, we introduce an end-to-end transformer-based framework, variable length feature aggregator transformer rollout (VLFATRollout), to classify volumetric data. The proposed VLFATRollout enjoys several merits. First, the proposed VLFATRollout can effectively mine slice-level fore-background information with the help of transformer’s attention matrices. Second, randomization of volume-wise resolution (i.e. the number of slices) during training enhances the learning capacity of the learnable positional embedding (PE) assigned to each volume slice. This technique allows the PEs to generalize across neighboring slices, facilitating the handling of high-resolution volumes at the test time.</div></div><div><h3>Results:</h3><div>VLFATRollout was thoroughly tested on the retinal optical coherence tomography (OCT) volume classification task, demonstrating a notable average improvement of 5.47% in balanced accuracy over the leading convolutional models for a 5-class diagnostic task. These results emphasize the effectiveness of our framework in enhancing slice-level representation and its adaptability across different volume resolutions, paving the way for advanced transformer applications in medical image analysis. The code is available at <span><span>https://github.com/marziehoghbaie/VLFATRollout/</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"118 ","pages":"Article 102452"},"PeriodicalIF":5.4,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142570320","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

WISE: Efficient WSI selection for active learning in histopathology WISE：组织病理学主动学习的高效 WSI 选择

IF 5.4 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2024-10-28 DOI: 10.1016/j.compmedimag.2024.102455

Hyeongu Kang , Mujin Kim , Young Sin Ko , Yesung Cho , Mun Yong Yi

Deep neural network (DNN) models have been applied to a wide variety of medical image analysis tasks, often with the successful performance outcomes that match those of medical doctors. However, given that even minor errors in a model can impact patients’ life, it is critical that these models are continuously improved. Hence, active learning (AL) has garnered attention as an effective and sustainable strategy for enhancing DNN models for the medical domain. Extant AL research in histopathology has primarily focused on patch datasets derived from whole-slide images (WSIs), a standard form of cancer diagnostic images obtained from a high-resolution scanner. However, this approach has failed to address the selection of WSIs, which can impede the performance improvement of deep learning models and increase the number of WSIs needed to achieve the target performance. This study introduces a WSI-level AL method, termed WSI-informative selection (WISE). WISE is designed to select informative WSIs using a newly formulated WSI-level class distance metric. This method aims to identify diverse and uncertain cases of WSIs, thereby contributing to model performance enhancement. WISE demonstrates state-of-the-art performance across the Colon and Stomach datasets, collected in the real world, as well as the public DigestPath dataset, significantly reducing the required number of WSIs by more than threefold compared to the one-pool dataset setting, which has been dominantly used in the field.

深度神经网络（DNN）模型已被广泛应用于各种医学影像分析任务中，其成功的性能结果往往与医生不相上下。然而，鉴于模型中的微小错误都可能影响患者的生命，因此不断改进这些模型至关重要。因此，主动学习（AL）作为增强医疗领域 DNN 模型的一种有效且可持续的策略备受关注。组织病理学领域的现有主动学习研究主要集中在从全切片图像（WSI）中获得的补丁数据集上，全切片图像是一种从高分辨率扫描仪中获得的标准癌症诊断图像。然而，这种方法未能解决 WSI 的选择问题，这可能会阻碍深度学习模型性能的提高，并增加实现目标性能所需的 WSI 数量。本研究引入了一种 WSI 级 AL 方法，称为 WSI 信息选择（WISE）。WISE 旨在使用新制定的 WSI 级类距离度量来选择有信息量的 WSI。该方法旨在识别 WSI 的多样性和不确定性情况，从而有助于提高模型性能。WISE 在现实世界中收集的结肠和胃数据集以及公共 DigestPath 数据集上表现出了最先进的性能，与该领域中主要使用的单数据集设置相比，所需的 WSI 数量显著减少了三倍以上。

{"title":"WISE: Efficient WSI selection for active learning in histopathology","authors":"Hyeongu Kang , Mujin Kim , Young Sin Ko , Yesung Cho , Mun Yong Yi","doi":"10.1016/j.compmedimag.2024.102455","DOIUrl":"10.1016/j.compmedimag.2024.102455","url":null,"abstract":"<div><div>Deep neural network (DNN) models have been applied to a wide variety of medical image analysis tasks, often with the successful performance outcomes that match those of medical doctors. However, given that even minor errors in a model can impact patients’ life, it is critical that these models are continuously improved. Hence, active learning (AL) has garnered attention as an effective and sustainable strategy for enhancing DNN models for the medical domain. Extant AL research in histopathology has primarily focused on patch datasets derived from whole-slide images (WSIs), a standard form of cancer diagnostic images obtained from a high-resolution scanner. However, this approach has failed to address the selection of WSIs, which can impede the performance improvement of deep learning models and increase the number of WSIs needed to achieve the target performance. This study introduces a WSI-level AL method, termed WSI-informative selection (WISE). WISE is designed to select informative WSIs using a newly formulated WSI-level class distance metric. This method aims to identify diverse and uncertain cases of WSIs, thereby contributing to model performance enhancement. WISE demonstrates state-of-the-art performance across the Colon and Stomach datasets, collected in the real world, as well as the public DigestPath dataset, significantly reducing the required number of WSIs by more than threefold compared to the one-pool dataset setting, which has been dominantly used in the field.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"118 ","pages":"Article 102455"},"PeriodicalIF":5.4,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142553819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

RPDNet: A reconstruction-regularized parallel decoders network for rectal tumor and rectum co-segmentation RPDNet：用于直肠肿瘤和直肠共同分割的重建正则化并行解码器网络。

IF 5.4 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2024-10-28 DOI: 10.1016/j.compmedimag.2024.102453

WenXiang Huang , Ye Xu , Yuanyuan Wang , Hongtu Zheng , Yi Guo

Accurate segmentation of rectal cancer tumor and rectum in magnetic resonance imaging (MRI) is significant for tumor precise diagnosis and treatment plans determination. Variable shapes and unclear boundaries of rectal tumors make this task particularly challenging. Only a few studies have explored deep learning networks in rectal tumor segmentation, which mainly adopt the classical encoder-decoder structure. The frequent downsampling operations during feature extraction result in the loss of detailed information, limiting the network's ability to precisely capture the shape and boundary of rectal tumors. This paper proposes a Reconstruction-regularized Parallel Decoder network (RPDNet) to address the problem of information loss and obtain accurate co-segmentation results of both rectal tumor and rectum. RPDNet initially establishes a shared encoder and parallel decoders framework to fully utilize the common knowledge between two segmentation labels while reducing the number of network parameters. An auxiliary reconstruction branch is subsequently introduced by calculating the consistency loss between the reconstructed and input images to preserve sufficient anatomical structure information. Moreover, a non-parameter target-adaptive attention module is proposed to distinguish the unclear boundary by enhancing the feature-level contrast between rectal tumors and normal tissues. The experimental results indicate that the proposed method outperforms state-of-the-art approaches in rectal tumor and rectum segmentation tasks, with Dice coefficients of 84.91 % and 90.36 %, respectively, demonstrating its potential application value in clinical practice.

在磁共振成像（MRI）中准确分割直肠癌肿瘤和直肠对肿瘤的精确诊断和治疗方案的确定具有重要意义。直肠肿瘤形状多变、边界不清，使得这项任务尤其具有挑战性。只有少数研究探索了深度学习网络在直肠肿瘤分割中的应用，这些研究主要采用经典的编码器-解码器结构。在特征提取过程中频繁的降采样操作会导致细节信息的丢失，从而限制了网络精确捕捉直肠肿瘤形状和边界的能力。本文提出了一种重构正则化并行解码器网络（RPDNet）来解决信息丢失问题，并获得直肠肿瘤和直肠的精确协同分割结果。RPDNet 首先建立了一个共享编码器和并行解码器框架，以充分利用两个分割标签之间的共同知识，同时减少网络参数的数量。随后，通过计算重建图像与输入图像之间的一致性损失，引入辅助重建分支，以保留足够的解剖结构信息。此外，还提出了一个非参数目标自适应注意力模块，通过增强直肠肿瘤与正常组织之间的特征级对比来区分不清晰的边界。实验结果表明，所提出的方法在直肠肿瘤和直肠分割任务中的表现优于最先进的方法，Dice系数分别为84.91%和90.36%，证明了其在临床实践中的潜在应用价值。

{"title":"RPDNet: A reconstruction-regularized parallel decoders network for rectal tumor and rectum co-segmentation","authors":"WenXiang Huang , Ye Xu , Yuanyuan Wang , Hongtu Zheng , Yi Guo","doi":"10.1016/j.compmedimag.2024.102453","DOIUrl":"10.1016/j.compmedimag.2024.102453","url":null,"abstract":"<div><div>Accurate segmentation of rectal cancer tumor and rectum in magnetic resonance imaging (MRI) is significant for tumor precise diagnosis and treatment plans determination. Variable shapes and unclear boundaries of rectal tumors make this task particularly challenging. Only a few studies have explored deep learning networks in rectal tumor segmentation, which mainly adopt the classical encoder-decoder structure. The frequent downsampling operations during feature extraction result in the loss of detailed information, limiting the network's ability to precisely capture the shape and boundary of rectal tumors. This paper proposes a Reconstruction-regularized Parallel Decoder network (RPDNet) to address the problem of information loss and obtain accurate co-segmentation results of both rectal tumor and rectum. RPDNet initially establishes a shared encoder and parallel decoders framework to fully utilize the common knowledge between two segmentation labels while reducing the number of network parameters. An auxiliary reconstruction branch is subsequently introduced by calculating the consistency loss between the reconstructed and input images to preserve sufficient anatomical structure information. Moreover, a non-parameter target-adaptive attention module is proposed to distinguish the unclear boundary by enhancing the feature-level contrast between rectal tumors and normal tissues. The experimental results indicate that the proposed method outperforms state-of-the-art approaches in rectal tumor and rectum segmentation tasks, with Dice coefficients of 84.91 % and 90.36 %, respectively, demonstrating its potential application value in clinical practice.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"118 ","pages":"Article 102453"},"PeriodicalIF":5.4,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142570317","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

Robust brain MRI image classification with SIBOW-SVM 利用 SIBOW-SVM 进行稳健的脑部 MRI 图像分类。

IF 5.4 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2024-10-24 DOI: 10.1016/j.compmedimag.2024.102451

Liyun Zeng , Hao Helen Zhang

Primary Central Nervous System tumors in the brain are among the most aggressive diseases affecting humans. Early detection and classification of brain tumor types, whether benign or malignant, glial or non-glial, is critical for cancer prevention and treatment, ultimately improving human life expectancy. Magnetic Resonance Imaging (MRI) is the most effective technique for brain tumor detection, generating comprehensive brain scans. However, human examination can be error-prone and inefficient due to the complexity, size, and location variability of brain tumors. Recently, automated classification techniques using machine learning methods, such as Convolutional Neural Networks (CNNs), have demonstrated significantly higher accuracy than manual screening. However, deep learning-based image classification methods, including CNNs, face challenges in estimating class probabilities without proper model calibration (Guo et al., 2017; Minderer et al., 2021). In this paper, we propose a novel brain tumor image classification method called SIBOW-SVM, which integrates the Bag-of-Features model with SIFT feature extraction and weighted Support Vector Machines. This new approach can effectively extract hidden image features, enabling differentiation of various tumor types, provide accurate label predictions, and estimate probabilities of images belonging to each class, offering high-confidence classification decisions. We have also developed scalable and parallelable algorithms to facilitate the practical implementation of SIBOW-SVM for massive image datasets. To benchmark our method, we apply SIBOW-SVM to a public dataset of brain tumor MRI images containing four classes: glioma, meningioma, pituitary, and normal. Our results demonstrate that the new method outperforms state-of-the-art techniques, including CNNs, in terms of uncertainty quantification, classification accuracy, computational efficiency, and data robustness.

脑部原发性中枢神经系统肿瘤是影响人类最严重的疾病之一。无论是良性还是非良性、神经胶质还是非神经胶质的脑肿瘤，其早期检测和分类对于癌症的预防和治疗都至关重要，最终将提高人类的预期寿命。磁共振成像（MRI）是检测脑肿瘤最有效的技术，可生成全面的脑部扫描图像。然而，由于脑肿瘤的复杂性、大小和位置的可变性，人工检查容易出错且效率低下。最近，使用卷积神经网络（CNN）等机器学习方法的自动分类技术已证明其准确性明显高于人工筛查。然而，基于深度学习的图像分类方法，包括 CNN，在没有适当模型校准的情况下，在估计类概率方面面临挑战（Guo 等人，2017 年；Minderer 等人，2021 年）。在本文中，我们提出了一种名为 SIBOW-SVM 的新型脑肿瘤图像分类方法，它将特征袋模型与 SIFT 特征提取和加权支持向量机整合在一起。这种新方法能有效提取隐藏的图像特征，从而区分各种肿瘤类型，提供准确的标签预测，并估算图像属于每一类的概率，从而做出高置信度的分类决策。我们还开发了可扩展、可并行的算法，以促进 SIBOW-SVM 在海量图像数据集上的实际应用。为了对我们的方法进行基准测试，我们将 SIBOW-SVM 应用于脑肿瘤 MRI 图像的公共数据集，其中包含四个类别：胶质瘤、脑膜瘤、垂体瘤和正常。结果表明，新方法在不确定性量化、分类准确性、计算效率和数据鲁棒性方面都优于包括 CNN 在内的最先进技术。

{"title":"Robust brain MRI image classification with SIBOW-SVM","authors":"Liyun Zeng , Hao Helen Zhang","doi":"10.1016/j.compmedimag.2024.102451","DOIUrl":"10.1016/j.compmedimag.2024.102451","url":null,"abstract":"<div><div>Primary Central Nervous System tumors in the brain are among the most aggressive diseases affecting humans. Early detection and classification of brain tumor types, whether benign or malignant, glial or non-glial, is critical for cancer prevention and treatment, ultimately improving human life expectancy. Magnetic Resonance Imaging (MRI) is the most effective technique for brain tumor detection, generating comprehensive brain scans. However, human examination can be error-prone and inefficient due to the complexity, size, and location variability of brain tumors. Recently, automated classification techniques using machine learning methods, such as Convolutional Neural Networks (CNNs), have demonstrated significantly higher accuracy than manual screening. However, deep learning-based image classification methods, including CNNs, face challenges in estimating class probabilities without proper model calibration (Guo et al., 2017; Minderer et al., 2021). In this paper, we propose a novel brain tumor image classification method called SIBOW-SVM, which integrates the Bag-of-Features model with SIFT feature extraction and weighted Support Vector Machines. This new approach can effectively extract hidden image features, enabling differentiation of various tumor types, provide accurate label predictions, and estimate probabilities of images belonging to each class, offering high-confidence classification decisions. We have also developed scalable and parallelable algorithms to facilitate the practical implementation of SIBOW-SVM for massive image datasets. To benchmark our method, we apply SIBOW-SVM to a public dataset of brain tumor MRI images containing four classes: glioma, meningioma, pituitary, and normal. Our results demonstrate that the new method outperforms state-of-the-art techniques, including CNNs, in terms of uncertainty quantification, classification accuracy, computational efficiency, and data robustness.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"118 ","pages":"Article 102451"},"PeriodicalIF":5.4,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142607468","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

Active learning based on multi-enhanced views for classification of multiple patterns in lung ultrasound images 基于多增强视图的主动学习，用于肺部超声图像中多种模式的分类。

IF 5.4 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2024-10-24 DOI: 10.1016/j.compmedimag.2024.102454

Yuanlu Ni , Yang Cong , Chengqian Zhao , Jinhua Yu , Yin Wang , Guohui Zhou , Mengjun Shen

There are several main patterns in lung ultrasound (LUS) images, including A-lines, B-lines, consolidation and pleural effusion. LUS images of healthy lungs typically only exhibit A-lines, while other patterns may emerge or coexist in LUS images associated with different lung diseases. The accurate categorization of these primary patterns is pivotal for effective lung disease screening. However, two challenges complicate the classification task: the first is the inherent blurring of feature differences between main patterns due to ultrasound imaging properties; and the second is the potential coexistence of multiple patterns in a single case, with only the most dominant pattern being clinically annotated. To address these challenges, we propose the active learning based on multi-enhanced views (MEVAL) method to achieve more precise pattern classification in LUS. To accentuate feature differences between multiple patterns, we introduce a feature enhancement module by applying vertical linear fitting and k-means clustering. The multi-enhanced views are then employed in parallel with the original images, thus enhancing MEVAL’s awareness of feature differences between multiple patterns. To tackle the patterns coexistence issue, we propose an active learning strategy based on confidence sets and misclassified sets. This strategy enables the network to simultaneously recognize multiple patterns by selectively labeling of a small number of images. Our dataset comprises 5075 LUS images, with approximately 4% exhibiting multiple patterns. Experimental results showcase the effectiveness of the proposed method in the classification task, with accuracy of 98.72%, AUC of 0.9989, sensitivity of 98.76%, and specificity of 98.16%, which outperforms than the state-of-the-art deep learning-based methods. A series of comprehensive ablation studies suggest the effectiveness of each proposed component and show great potential in clinical application.

肺部超声（LUS）图像有几种主要模式，包括 A 线、B 线、合并和胸腔积液。健康肺部的 LUS 图像通常只显示 A 线，而与不同肺部疾病相关的 LUS 图像中可能会出现或同时出现其他模式。对这些主要模式进行准确分类是有效筛查肺部疾病的关键。然而，有两个挑战使分类任务变得复杂：一是由于超声成像特性，主要模式之间的固有特征差异变得模糊；二是在一个病例中可能同时存在多种模式，而临床上只对最主要的模式进行注释。为了应对这些挑战，我们提出了基于多增强视图（MEVAL）的主动学习方法，以实现更精确的 LUS 模式分类。为了突出多个模式之间的特征差异，我们通过垂直线性拟合和 k-means 聚类引入了一个特征增强模块。然后，多重增强视图与原始图像并行使用，从而增强了 MEVAL 对多种模式之间特征差异的感知。为解决模式共存问题，我们提出了一种基于置信集和错误分类集的主动学习策略。这种策略通过选择性地标记少量图像，使网络能够同时识别多种模式。我们的数据集包括 5075 幅 LUS 图像，其中约 4% 呈现出多种模式。实验结果表明，所提出的方法在分类任务中非常有效，准确率为 98.72%，AUC 为 0.9989，灵敏度为 98.76%，特异度为 98.16%，优于基于深度学习的最先进方法。一系列全面的消融研究表明，所提出的每个组件都很有效，在临床应用中显示出巨大的潜力。

{"title":"Active learning based on multi-enhanced views for classification of multiple patterns in lung ultrasound images","authors":"Yuanlu Ni , Yang Cong , Chengqian Zhao , Jinhua Yu , Yin Wang , Guohui Zhou , Mengjun Shen","doi":"10.1016/j.compmedimag.2024.102454","DOIUrl":"10.1016/j.compmedimag.2024.102454","url":null,"abstract":"<div><div>There are several main patterns in lung ultrasound (LUS) images, including A-lines, B-lines, consolidation and pleural effusion. LUS images of healthy lungs typically only exhibit A-lines, while other patterns may emerge or coexist in LUS images associated with different lung diseases. The accurate categorization of these primary patterns is pivotal for effective lung disease screening. However, two challenges complicate the classification task: the first is the inherent blurring of feature differences between main patterns due to ultrasound imaging properties; and the second is the potential coexistence of multiple patterns in a single case, with only the most dominant pattern being clinically annotated. To address these challenges, we propose the active learning based on multi-enhanced views (MEVAL) method to achieve more precise pattern classification in LUS. To accentuate feature differences between multiple patterns, we introduce a feature enhancement module by applying vertical linear fitting and k-means clustering. The multi-enhanced views are then employed in parallel with the original images, thus enhancing MEVAL’s awareness of feature differences between multiple patterns. To tackle the patterns coexistence issue, we propose an active learning strategy based on confidence sets and misclassified sets. This strategy enables the network to simultaneously recognize multiple patterns by selectively labeling of a small number of images. Our dataset comprises 5075 LUS images, with approximately 4% exhibiting multiple patterns. Experimental results showcase the effectiveness of the proposed method in the classification task, with accuracy of 98.72%, AUC of 0.9989, sensitivity of 98.76%, and specificity of 98.16%, which outperforms than the state-of-the-art deep learning-based methods. A series of comprehensive ablation studies suggest the effectiveness of each proposed component and show great potential in clinical application.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"118 ","pages":"Article 102454"},"PeriodicalIF":5.4,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565040","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

MRI-based vector radiomics for predicting breast cancer HER2 status and its changes after neoadjuvant therapy 基于磁共振成像的载体放射组学用于预测乳腺癌 HER2 状态及其在新辅助治疗后的变化。

IF 5.4 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2024-10-17 DOI: 10.1016/j.compmedimag.2024.102443

Lan Zhang , Quan-Xiang Cui , Liang-Qin Zhou , Xin-Yi Wang , Hong-Xia Zhang , Yue-Min Zhu , Xi-Qiao Sang , Zi-Xiang Kuai

Purpose

: To develop a novel MRI-based vector radiomic approach to predict breast cancer (BC) human epidermal growth factor receptor 2 (HER2) status (zero, low, and positive; task 1) and its changes after neoadjuvant therapy (NAT) (positive-to-positive, positive-to-negative, and positive-to-pathologic complete response; task 2).

Materials and Methods

: Both dynamic contrast-enhanced (DCE) MRI data and multi-b-value (MBV) diffusion-weighted imaging (DWI) data were acquired in BC patients at two centers. Vector-radiomic and conventional-radiomic features were extracted from both DCE-MRI and MBV-DWI. After feature selection, the following models were built using the retained features and logistic regression: vector model, conventional model, and combined model that integrates the vector-radiomic and conventional-radiomic features. The models’ performances were quantified by the area under the receiver-operating characteristic curve (AUC).

Results:

The training/external test set (center 1/2) included 483/361 women. For task 1, the vector model (AUCs=0.73

\sim

0.86) was superior to (p

<

.05) the conventional model (AUCs=0.68

\sim

0.81), and the addition of vector-radiomic features to conventional-radiomic features yielded an incremental predictive value (AUCs=0.80

\sim

0.90,

p < . 05

). For task 2, the combined MBV-DWI model (AUCs=0.85

\sim

0.89) performed better than (

p < . 05

) the conventional MBV-DWI model (AUCs=0.73

\sim

0.82). In addition, for the combined DCE-MRI model and the combined MBV-DWI model, the former (AUCs=0.85

\sim

0.90) outperformed (

p < . 05

) the latter (AUCs=0.80

\sim

0.85) in task 1, whereas the latter (AUCs=0.85

\sim

0.89) outperformed (

p < . 05

) the former (AUCs=0.76

\sim

0.81) in task 2. The above results are true for the training and external test sets.

Conclusions:

MRI-based vector radiomics may predict BC HER2 status and its changes after NAT and provide significant incremental prediction over and above conventional radiomics.

目的：开发一种基于磁共振成像的新型矢量放射组学方法，用于预测乳腺癌（BC）人表皮生长因子受体2（HER2）状态（零、低和阳性；任务1）及其在新辅助治疗（NAT）后的变化（阳性到阳性、阳性到阴性、阳性到病理完全反应；任务2）：在两个中心采集了 BC 患者的动态对比增强（DCE）磁共振成像数据和多比值（MBV）弥散加权成像（DWI）数据。从 DCE-MRI 和 MBV-DWI 中提取了矢量放射学和传统放射学特征。经过特征选择后，利用保留的特征和逻辑回归建立了以下模型：矢量模型、传统模型以及整合了矢量放射体和传统放射体特征的组合模型。模型的性能通过接收者工作特征曲线下面积（AUC）进行量化：训练/外部测试集（中心 1/2）包括 483/361 名女性。在任务 1 中，矢量模型（AUCs=0.73∼0.86）优于矢量模型（pConclusions：基于 MRI 的矢量放射组学可预测 BC HER2 状态及其在 NAT 后的变化，其预测效果明显优于传统放射组学。

{"title":"MRI-based vector radiomics for predicting breast cancer HER2 status and its changes after neoadjuvant therapy","authors":"Lan Zhang , Quan-Xiang Cui , Liang-Qin Zhou , Xin-Yi Wang , Hong-Xia Zhang , Yue-Min Zhu , Xi-Qiao Sang , Zi-Xiang Kuai","doi":"10.1016/j.compmedimag.2024.102443","DOIUrl":"10.1016/j.compmedimag.2024.102443","url":null,"abstract":"<div><h3>Purpose</h3><div>: To develop a novel MRI-based vector radiomic approach to predict breast cancer (BC) human epidermal growth factor receptor 2 (HER2) status (zero, low, and positive; task 1) and its changes after neoadjuvant therapy (NAT) (positive-to-positive, positive-to-negative, and positive-to-pathologic complete response; task 2).</div></div><div><h3>Materials and Methods</h3><div>: Both dynamic contrast-enhanced (DCE) MRI data and multi-<em>b</em>-value (MBV) diffusion-weighted imaging (DWI) data were acquired in BC patients at two centers. Vector-radiomic and conventional-radiomic features were extracted from both DCE-MRI and MBV-DWI. After feature selection, the following models were built using the retained features and logistic regression: vector model, conventional model, and combined model that integrates the vector-radiomic and conventional-radiomic features. The models’ performances were quantified by the area under the receiver-operating characteristic curve (AUC).</div></div><div><h3>Results:</h3><div>The training/external test set (center 1/2) included 483/361 women. For task 1, the vector model (AUCs=0.73<span><math><mo>∼</mo></math></span>0.86) was superior to (<em>p</em><span><math><mo><</mo></math></span>.05) the conventional model (AUCs=0.68<span><math><mo>∼</mo></math></span>0.81), and the addition of vector-radiomic features to conventional-radiomic features yielded an incremental predictive value (AUCs=0.80<span><math><mo>∼</mo></math></span>0.90, <span><math><mrow><mi>p</mi><mo><</mo><mo>.</mo><mn>05</mn></mrow></math></span>). For task 2, the combined MBV-DWI model (AUCs=0.85<span><math><mo>∼</mo></math></span>0.89) performed better than (<span><math><mrow><mi>p</mi><mo><</mo><mo>.</mo><mn>05</mn></mrow></math></span>) the conventional MBV-DWI model (AUCs=0.73<span><math><mo>∼</mo></math></span>0.82). In addition, for the combined DCE-MRI model and the combined MBV-DWI model, the former (AUCs=0.85<span><math><mo>∼</mo></math></span>0.90) outperformed (<span><math><mrow><mi>p</mi><mo><</mo><mo>.</mo><mn>05</mn></mrow></math></span>) the latter (AUCs=0.80<span><math><mo>∼</mo></math></span>0.85) in task 1, whereas the latter (AUCs=0.85<span><math><mo>∼</mo></math></span>0.89) outperformed (<span><math><mrow><mi>p</mi><mo><</mo><mo>.</mo><mn>05</mn></mrow></math></span>) the former (AUCs=0.76<span><math><mo>∼</mo></math></span>0.81) in task 2. The above results are true for the training and external test sets.</div></div><div><h3>Conclusions:</h3><div>MRI-based vector radiomics may predict BC HER2 status and its changes after NAT and provide significant incremental prediction over and above conventional radiomics.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"118 ","pages":"Article 102443"},"PeriodicalIF":5.4,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142479837","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 review of AutoML optimization techniques for medical image applications 医学影像应用中的 AutoML 优化技术综述。

IF 5.4 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2024-10-16 DOI: 10.1016/j.compmedimag.2024.102441

Muhammad Junaid Ali, Mokhtar Essaid, Laurent Moalic, Lhassane Idoumghar

Automatic analysis of medical images using machine learning techniques has gained significant importance over the years. A large number of approaches have been proposed for solving different medical image analysis tasks using machine learning and deep learning approaches. These approaches are quite effective thanks to their ability to analyze large volume of medical imaging data. Moreover, they can also identify patterns that may be difficult for human experts to detect. Manually designing and tuning the parameters of these algorithms is a challenging and time-consuming task. Furthermore, designing a generalized model that can handle different imaging modalities is difficult, as each modality has specific characteristics. To solve these problems and automate the whole pipeline of different medical image analysis tasks, numerous Automatic Machine Learning (AutoML) techniques have been proposed. These techniques include Hyper-parameter Optimization (HPO), Neural Architecture Search (NAS), and Automatic Data Augmentation (ADA). This study provides an overview of several AutoML-based approaches for different medical imaging tasks in terms of optimization search strategies. The usage of optimization techniques (evolutionary, gradient-based, Bayesian optimization, etc.) is of significant importance for these AutoML approaches. We comprehensively reviewed existing AutoML approaches, categorized them, and performed a detailed analysis of different proposed approaches. Furthermore, current challenges and possible future research directions are also discussed.

多年来，利用机器学习技术自动分析医学影像的重要性日益凸显。人们提出了大量使用机器学习和深度学习方法解决不同医学图像分析任务的方法。由于这些方法能够分析大量医学影像数据，因此相当有效。此外，它们还能识别人类专家难以发现的模式。手动设计和调整这些算法的参数是一项具有挑战性且耗时的任务。此外，设计一个能处理不同成像模式的通用模型也很困难，因为每种模式都有特定的特征。为了解决这些问题并使不同医学图像分析任务的整个流程自动化，人们提出了许多自动机器学习（AutoML）技术。这些技术包括超参数优化（HPO）、神经架构搜索（NAS）和自动数据增强（ADA）。本研究从优化搜索策略的角度概述了几种基于 AutoML 的方法，用于不同的医学成像任务。优化技术（进化、梯度、贝叶斯优化等）的使用对这些 AutoML 方法至关重要。我们全面回顾了现有的 AutoML 方法，对其进行了分类，并对不同的建议方法进行了详细分析。此外，我们还讨论了当前面临的挑战和未来可能的研究方向。

{"title":"A review of AutoML optimization techniques for medical image applications","authors":"Muhammad Junaid Ali, Mokhtar Essaid, Laurent Moalic, Lhassane Idoumghar","doi":"10.1016/j.compmedimag.2024.102441","DOIUrl":"10.1016/j.compmedimag.2024.102441","url":null,"abstract":"<div><div>Automatic analysis of medical images using machine learning techniques has gained significant importance over the years. A large number of approaches have been proposed for solving different medical image analysis tasks using machine learning and deep learning approaches. These approaches are quite effective thanks to their ability to analyze large volume of medical imaging data. Moreover, they can also identify patterns that may be difficult for human experts to detect. Manually designing and tuning the parameters of these algorithms is a challenging and time-consuming task. Furthermore, designing a generalized model that can handle different imaging modalities is difficult, as each modality has specific characteristics. To solve these problems and automate the whole pipeline of different medical image analysis tasks, numerous Automatic Machine Learning (AutoML) techniques have been proposed. These techniques include Hyper-parameter Optimization (HPO), Neural Architecture Search (NAS), and Automatic Data Augmentation (ADA). This study provides an overview of several AutoML-based approaches for different medical imaging tasks in terms of optimization search strategies. The usage of optimization techniques (evolutionary, gradient-based, Bayesian optimization, etc.) is of significant importance for these AutoML approaches. We comprehensively reviewed existing AutoML approaches, categorized them, and performed a detailed analysis of different proposed approaches. Furthermore, current challenges and possible future research directions are also discussed.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"118 ","pages":"Article 102441"},"PeriodicalIF":5.4,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142570286","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

Prior knowledge-guided vision-transformer-based unsupervised domain adaptation for intubation prediction in lung disease at one week 以先验知识为指导，基于视觉变换器的无监督领域适配，用于肺病一周内的插管预测。

IF 5.4 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2024-10-15 DOI: 10.1016/j.compmedimag.2024.102442

Junlin Yang , John Anderson Garcia Henao , Nicha Dvornek , Jianchun He , Danielle V. Bower , Arno Depotter , Herkus Bajercius , Aurélie Pahud de Mortanges , Chenyu You , Christopher Gange , Roberta Eufrasia Ledda , Mario Silva , Charles S. Dela Cruz , Wolf Hautz , Harald M. Bonel , Mauricio Reyes , Lawrence H. Staib , Alexander Poellinger , James S. Duncan

Data-driven approaches have achieved great success in various medical image analysis tasks. However, fully-supervised data-driven approaches require unprecedentedly large amounts of labeled data and often suffer from poor generalization to unseen new data due to domain shifts. Various unsupervised domain adaptation (UDA) methods have been actively explored to solve these problems. Anatomical and spatial priors in medical imaging are common and have been incorporated into data-driven approaches to ease the need for labeled data as well as to achieve better generalization and interpretation. Inspired by the effectiveness of recent transformer-based methods in medical image analysis, the adaptability of transformer-based models has been investigated. How to incorporate prior knowledge for transformer-based UDA models remains under-explored. In this paper, we introduce a prior knowledge-guided and transformer-based unsupervised domain adaptation (PUDA) pipeline. It regularizes the vision transformer attention heads using anatomical and spatial prior information that is shared by both the source and target domain, which provides additional insight into the similarity between the underlying data distribution across domains. Besides the global alignment of class tokens, it assigns local weights to guide the token distribution alignment via adversarial training. We evaluate our proposed method on a clinical outcome prediction task, where Computed Tomography (CT) and Chest X-ray (CXR) data are collected and used to predict the intubation status of patients in a week. Abnormal lesions are regarded as anatomical and spatial prior information for this task and are annotated in the source domain scans. Extensive experiments show the effectiveness of the proposed PUDA method.

数据驱动方法在各种医学图像分析任务中取得了巨大成功。然而，完全监督的数据驱动方法需要前所未有的大量标注数据，而且由于领域转移，对未见过的新数据的泛化能力往往很差。为了解决这些问题，人们积极探索各种无监督领域适应（UDA）方法。解剖学和空间先验在医学成像中很常见，已被纳入数据驱动方法，以缓解对标记数据的需求，并实现更好的泛化和解释。受最近基于变换器的方法在医学图像分析中的有效性启发，人们对基于变换器的模型的适应性进行了研究。如何将先验知识纳入基于变压器的 UDA 模型仍未得到充分探讨。在本文中，我们介绍了一种以先验知识为指导、基于变换器的无监督域自适应（PUDA）管道。它利用源域和目标域共享的解剖学和空间先验信息对视觉变换器注意头进行正则化，从而提供了对跨域底层数据分布相似性的额外洞察。除了类标记的全局对齐外，它还通过对抗训练分配局部权重来指导标记分布的对齐。我们在一项临床结果预测任务中评估了我们提出的方法，该任务收集了计算机断层扫描（CT）和胸部 X 光片（CXR）数据，用于预测一周内患者的插管状态。异常病变被视为这项任务的解剖和空间先验信息，并在源域扫描中进行注释。广泛的实验表明了所提出的 PUDA 方法的有效性。

{"title":"Prior knowledge-guided vision-transformer-based unsupervised domain adaptation for intubation prediction in lung disease at one week","authors":"Junlin Yang , John Anderson Garcia Henao , Nicha Dvornek , Jianchun He , Danielle V. Bower , Arno Depotter , Herkus Bajercius , Aurélie Pahud de Mortanges , Chenyu You , Christopher Gange , Roberta Eufrasia Ledda , Mario Silva , Charles S. Dela Cruz , Wolf Hautz , Harald M. Bonel , Mauricio Reyes , Lawrence H. Staib , Alexander Poellinger , James S. Duncan","doi":"10.1016/j.compmedimag.2024.102442","DOIUrl":"10.1016/j.compmedimag.2024.102442","url":null,"abstract":"<div><div>Data-driven approaches have achieved great success in various medical image analysis tasks. However, fully-supervised data-driven approaches require unprecedentedly large amounts of labeled data and often suffer from poor generalization to unseen new data due to domain shifts. Various unsupervised domain adaptation (UDA) methods have been actively explored to solve these problems. Anatomical and spatial priors in medical imaging are common and have been incorporated into data-driven approaches to ease the need for labeled data as well as to achieve better generalization and interpretation. Inspired by the effectiveness of recent transformer-based methods in medical image analysis, the adaptability of transformer-based models has been investigated. How to incorporate prior knowledge for transformer-based UDA models remains under-explored. In this paper, we introduce a prior knowledge-guided and transformer-based unsupervised domain adaptation (PUDA) pipeline. It regularizes the vision transformer attention heads using anatomical and spatial prior information that is shared by both the source and target domain, which provides additional insight into the similarity between the underlying data distribution across domains. Besides the global alignment of class tokens, it assigns local weights to guide the token distribution alignment via adversarial training. We evaluate our proposed method on a clinical outcome prediction task, where Computed Tomography (CT) and Chest X-ray (CXR) data are collected and used to predict the intubation status of patients in a week. Abnormal lesions are regarded as anatomical and spatial prior information for this task and are annotated in the source domain scans. Extensive experiments show the effectiveness of the proposed PUDA method.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"118 ","pages":"Article 102442"},"PeriodicalIF":5.4,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142607466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Distance guided generative adversarial network for explainable medical image classifications 用于可解释医学图像分类的距离引导生成对抗网络。

IF 5.4 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2024-10-15 DOI: 10.1016/j.compmedimag.2024.102444

Xiangyu Xiong , Yue Sun , Xiaohong Liu , Wei Ke , Chan-Tong Lam , Jiangang Chen , Mingfeng Jiang , Mingwei Wang , Hui Xie , Tong Tong , Qinquan Gao , Hao Chen , Tao Tan

Despite the potential benefits of data augmentation for mitigating data insufficiency, traditional augmentation methods primarily rely on prior intra-domain knowledge. On the other hand, advanced generative adversarial networks (GANs) generate inter-domain samples with limited variety. These previous methods make limited contributions to describing the decision boundaries for binary classification. In this paper, we propose a distance-guided GAN (DisGAN) that controls the variation degrees of generated samples in the hyperplane space. Specifically, we instantiate the idea of DisGAN by combining two ways. The first way is vertical distance GAN (VerDisGAN) where the inter-domain generation is conditioned on the vertical distances. The second way is horizontal distance GAN (HorDisGAN) where the intra-domain generation is conditioned on the horizontal distances. Furthermore, VerDisGAN can produce the class-specific regions by mapping the source images to the hyperplane. Experimental results show that DisGAN consistently outperforms the GAN-based augmentation methods with explainable binary classification. The proposed method can apply to different classification architectures and has the potential to extend to multi-class classification. We provide the code in https://github.com/yXiangXiong/DisGAN.

尽管数据扩增在缓解数据不足方面具有潜在优势，但传统的扩增方法主要依赖于先前的域内知识。另一方面，先进的生成式对抗网络（GAN）生成的域间样本种类有限。这些方法对描述二元分类的决策边界贡献有限。在本文中，我们提出了一种距离引导生成式对抗网络（DisGAN），它能控制超平面空间中生成样本的变化度。具体来说，我们通过结合两种方式来实现 DisGAN 的想法。第一种方式是垂直距离 GAN（VerDisGAN），其中域间生成以垂直距离为条件。第二种方法是水平距离 GAN（HorDisGAN），域内生成以水平距离为条件。此外，VerDisGAN 可以通过将源图像映射到超平面来生成特定类别的区域。实验结果表明，DisGAN 在可解释的二元分类方面始终优于基于 GAN 的增强方法。所提出的方法可适用于不同的分类架构，并有可能扩展到多类分类。我们在 https://github.com/yXiangXiong/DisGAN 中提供了代码。

{"title":"Distance guided generative adversarial network for explainable medical image classifications","authors":"Xiangyu Xiong , Yue Sun , Xiaohong Liu , Wei Ke , Chan-Tong Lam , Jiangang Chen , Mingfeng Jiang , Mingwei Wang , Hui Xie , Tong Tong , Qinquan Gao , Hao Chen , Tao Tan","doi":"10.1016/j.compmedimag.2024.102444","DOIUrl":"10.1016/j.compmedimag.2024.102444","url":null,"abstract":"<div><div>Despite the potential benefits of data augmentation for mitigating data insufficiency, traditional augmentation methods primarily rely on prior intra-domain knowledge. On the other hand, advanced generative adversarial networks (GANs) generate inter-domain samples with limited variety. These previous methods make limited contributions to describing the decision boundaries for binary classification. In this paper, we propose a distance-guided GAN (DisGAN) that controls the variation degrees of generated samples in the hyperplane space. Specifically, we instantiate the idea of DisGAN by combining two ways. The first way is vertical distance GAN (VerDisGAN) where the inter-domain generation is conditioned on the vertical distances. The second way is horizontal distance GAN (HorDisGAN) where the intra-domain generation is conditioned on the horizontal distances. Furthermore, VerDisGAN can produce the class-specific regions by mapping the source images to the hyperplane. Experimental results show that DisGAN consistently outperforms the GAN-based augmentation methods with explainable binary classification. The proposed method can apply to different classification architectures and has the potential to extend to multi-class classification. We provide the code in <span><span>https://github.com/yXiangXiong/DisGAN</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"118 ","pages":"Article 102444"},"PeriodicalIF":5.4,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142479836","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

An anthropomorphic diagnosis system of pulmonary nodules using weak annotation-based deep learning 利用基于弱注释的深度学习的肺结节拟人化诊断系统。

IF 5.4 2区医学 Q1 ENGINEERING, BIOMEDICAL

Computerized Medical Imaging and Graphics

Pub Date : 2024-10-10 DOI: 10.1016/j.compmedimag.2024.102438

Lipeng Xie , Yongrui Xu , Mingfeng Zheng , Yundi Chen , Min Sun , Michael A. Archer , Wenjun Mao , Yubing Tong , Yuan Wan

The accurate categorization of lung nodules in CT scans is an essential aspect in the prompt detection and diagnosis of lung cancer. The categorization of grade and texture for nodules is particularly significant since it can aid radiologists and clinicians to make better-informed decisions concerning the management of nodules. However, currently existing nodule classification techniques have a singular function of nodule classification and rely on an extensive amount of high-quality annotation data, which does not meet the requirements of clinical practice. To address this issue, we develop an anthropomorphic diagnosis system of pulmonary nodules (PN) based on deep learning (DL) that is trained by weak annotation data and has comparable performance to full-annotation based diagnosis systems. The proposed system uses DL models to classify PNs (benign vs. malignant) with weak annotations, which eliminates the need for time-consuming and labor-intensive manual annotations of PNs. Moreover, the PN classification networks, augmented with handcrafted shape features acquired through the ball-scale transform technique, demonstrate capability to differentiate PNs with diverse labels, including pure ground-glass opacities, part-solid nodules, and solid nodules. Through 5-fold cross-validation on two datasets, the system achieved the following results: (1) an Area Under Curve (AUC) of 0.938 for PN localization and an AUC of 0.912 for PN differential diagnosis on the LIDC-IDRI dataset of 814 testing cases, (2) an AUC of 0.943 for PN localization and an AUC of 0.815 for PN differential diagnosis on the in-house dataset of 822 testing cases. In summary, our system demonstrates eﬀicient localization and differential diagnosis of PNs in a resource limited environment, and thus could be translated into clinical use in the future.

在 CT 扫描中对肺部结节进行准确分类是及时发现和诊断肺癌的一个重要方面。结节的等级和质地分类尤其重要，因为它可以帮助放射科医生和临床医生就结节的处理做出更明智的决定。然而，目前现有的结节分类技术只有单一的结节分类功能，并且依赖于大量高质量的注释数据，无法满足临床实践的要求。为解决这一问题，我们开发了一种基于深度学习（DL）的肺结节（PN）拟人诊断系统，该系统由弱注释数据训练而成，性能与基于全注释的诊断系统相当。该系统利用深度学习模型对弱注释的肺结节进行分类（良性与恶性），从而无需对肺结节进行耗时耗力的人工注释。此外，通过球尺度变换技术获得的手工形状特征增强了 PN 分类网络，证明它有能力区分不同标签的 PN，包括纯磨玻璃不透明、部分实性结节和实性结节。通过在两个数据集上进行 5 倍交叉验证，该系统取得了以下结果：（1）在由 814 个测试病例组成的 LIDC-IDRI 数据集上，PN 定位的曲线下面积（AUC）为 0.938，PN 鉴别诊断的曲线下面积（AUC）为 0.912；（2）在由 822 个测试病例组成的内部数据集上，PN 定位的曲线下面积（AUC）为 0.943，PN 鉴别诊断的曲线下面积（AUC）为 0.815。总之，我们的系统能在资源有限的环境下对 PN 进行有效的定位和鉴别诊断，因此将来可以应用于临床。

{"title":"An anthropomorphic diagnosis system of pulmonary nodules using weak annotation-based deep learning","authors":"Lipeng Xie , Yongrui Xu , Mingfeng Zheng , Yundi Chen , Min Sun , Michael A. Archer , Wenjun Mao , Yubing Tong , Yuan Wan","doi":"10.1016/j.compmedimag.2024.102438","DOIUrl":"10.1016/j.compmedimag.2024.102438","url":null,"abstract":"<div><div>The accurate categorization of lung nodules in CT scans is an essential aspect in the prompt detection and diagnosis of lung cancer. The categorization of grade and texture for nodules is particularly significant since it can aid radiologists and clinicians to make better-informed decisions concerning the management of nodules. However, currently existing nodule classification techniques have a singular function of nodule classification and rely on an extensive amount of high-quality annotation data, which does not meet the requirements of clinical practice. To address this issue, we develop an anthropomorphic diagnosis system of pulmonary nodules (PN) based on deep learning (DL) that is trained by weak annotation data and has comparable performance to full-annotation based diagnosis systems. The proposed system uses DL models to classify PNs (benign vs. malignant) with weak annotations, which eliminates the need for time-consuming and labor-intensive manual annotations of PNs. Moreover, the PN classification networks, augmented with handcrafted shape features acquired through the ball-scale transform technique, demonstrate capability to differentiate PNs with diverse labels, including pure ground-glass opacities, part-solid nodules, and solid nodules. Through 5-fold cross-validation on two datasets, the system achieved the following results: (1) an Area Under Curve (AUC) of 0.938 for PN localization and an AUC of 0.912 for PN differential diagnosis on the LIDC-IDRI dataset of 814 testing cases, (2) an AUC of 0.943 for PN localization and an AUC of 0.815 for PN differential diagnosis on the in-house dataset of 822 testing cases. In summary, our system demonstrates eﬀicient localization and differential diagnosis of PNs in a resource limited environment, and thus could be translated into clinical use in the future.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"118 ","pages":"Article 102438"},"PeriodicalIF":5.4,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142479835","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