Breast imaging : 11th International Workshop, IWDM 2012, Philadelphia, PA, USA, July 8-11, 2012 : proceedings. International Workshop on Breast Imaging (11th : 2012 : Philadelphia, Pa.)最新文献

英文中文

Synthetic data of simulated microcalcification clusters to train and explain deep learning detection models in contrast-enhanced mammography 模拟微钙化簇的合成数据用于训练和解释对比增强乳房x光检查中的深度学习检测模型

Breast imaging : 11th International Workshop, IWDM 2012, Philadelphia, PA, USA, July 8-11, 2012 : proceedings. International Workshop on Breast Imaging (11th : 2012 : Philadelphia, Pa.)

Pub Date : 2022-07-13 DOI: 10.1117/12.2621195

A. Van Camp, M. Beuque, L. Cockmartin, H. Woodruff, N. Marshall, M. Lobbes, P. Lambin, H. Bosmans

Deep learning (DL) models can be trained on contrast-enhanced mammography (CEM) images to detect and classify lesions in the breast. As they often put more emphasis on the masses enhanced in the recombined image, they can fail in recognizing microcalcification clusters since these are hardly enhanced and are mainly visible in the (processed) lowenergy image. Therefore, we developed a method to create synthetic data with simulated microcalcification clusters to be used for data augmentation and explainability studies when training DL models. At first 3-dimensional voxel models of simulated microcalcification clusters based on descriptors of the shape and structure were constructed. In a set of 500 simulated microcalcification clusters the range of the size and of the number of microcalcifications per cluster followed the distribution of real clusters. The insertion of these clusters in real images of non-delineated CEM cases was evaluated by radiologists. The realism score was acceptable for single view applications. Radiologists could more easily categorize synthetic clusters into benign versus malignant than real clusters. In a second phase of the work, the role of synthetic data for training and/or explaining DL models was explored. A Mask R-CNN model was trained with synthetic CEM images containing microcalcification clusters. After a training run of 100 epochs the model was found to overfit on a training set of 192 images. In an evaluation with multiple test sets, it was found that this high level of sensitivity was due to the model being capable of recognizing the image rather than the cluster. Synthetic data could be applied for more tests, such as the impact of particular features in both background and lesion models.

深度学习(DL)模型可以在对比增强乳房x线摄影(CEM)图像上进行训练，以检测和分类乳房中的病变。由于它们往往更强调重组图像中增强的肿块，因此它们可能无法识别微钙化团簇，因为这些团簇几乎没有增强，主要在(处理过的)低能图像中可见。因此，我们开发了一种方法来创建具有模拟微钙化簇的合成数据，用于训练DL模型时的数据增强和可解释性研究。首先基于形状和结构描述符构建模拟微钙化团簇的三维体素模型;在一组500个模拟微钙化簇中，每个簇的大小和微钙化数量的范围遵循真实簇的分布。放射科医生评估了这些簇在未划定的CEM病例的真实图像中的插入。现实主义得分是可以接受的单一视图应用程序。放射科医生可以更容易地将合成的群集分为良性和恶性，而不是真正的群集。在第二阶段的工作中，研究了合成数据在训练和/或解释深度学习模型中的作用。用含有微钙化团簇的合成CEM图像训练Mask R-CNN模型。经过100次的训练后，该模型被发现在192张图像的训练集上过拟合。在多个测试集的评估中，发现这种高水平的灵敏度是由于模型能够识别图像而不是集群。合成数据可以应用于更多的测试，例如背景和病变模型中特定特征的影响。

{"title":"Synthetic data of simulated microcalcification clusters to train and explain deep learning detection models in contrast-enhanced mammography","authors":"A. Van Camp, M. Beuque, L. Cockmartin, H. Woodruff, N. Marshall, M. Lobbes, P. Lambin, H. Bosmans","doi":"10.1117/12.2621195","DOIUrl":"https://doi.org/10.1117/12.2621195","url":null,"abstract":"Deep learning (DL) models can be trained on contrast-enhanced mammography (CEM) images to detect and classify lesions in the breast. As they often put more emphasis on the masses enhanced in the recombined image, they can fail in recognizing microcalcification clusters since these are hardly enhanced and are mainly visible in the (processed) lowenergy image. Therefore, we developed a method to create synthetic data with simulated microcalcification clusters to be used for data augmentation and explainability studies when training DL models. At first 3-dimensional voxel models of simulated microcalcification clusters based on descriptors of the shape and structure were constructed. In a set of 500 simulated microcalcification clusters the range of the size and of the number of microcalcifications per cluster followed the distribution of real clusters. The insertion of these clusters in real images of non-delineated CEM cases was evaluated by radiologists. The realism score was acceptable for single view applications. Radiologists could more easily categorize synthetic clusters into benign versus malignant than real clusters. In a second phase of the work, the role of synthetic data for training and/or explaining DL models was explored. A Mask R-CNN model was trained with synthetic CEM images containing microcalcification clusters. After a training run of 100 epochs the model was found to overfit on a training set of 192 images. In an evaluation with multiple test sets, it was found that this high level of sensitivity was due to the model being capable of recognizing the image rather than the cluster. Synthetic data could be applied for more tests, such as the impact of particular features in both background and lesion models.","PeriodicalId":92005,"journal":{"name":"Breast imaging : 11th International Workshop, IWDM 2012, Philadelphia, PA, USA, July 8-11, 2012 : proceedings. International Workshop on Breast Imaging (11th : 2012 : Philadelphia, Pa.)","volume":"85 1","pages":"122860U - 122860U-8"},"PeriodicalIF":0.0,"publicationDate":"2022-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76853379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Correspondence between areas causing recall in breast cancer screening and artificial intelligence findings 乳腺癌筛查中引起回忆的区域与人工智能发现之间的对应关系

Breast imaging : 11th International Workshop, IWDM 2012, Philadelphia, PA, USA, July 8-11, 2012 : proceedings. International Workshop on Breast Imaging (11th : 2012 : Philadelphia, Pa.)

Pub Date : 2022-07-13 DOI: 10.1117/12.2625731

Victor Dahlblom, A. Tingberg, S. Zackrisson, M. Dustler

False positive recall is a major issue in breast cancer screening and the introduction of artificial intelligence (AI) might affect which women who are unnecessarily recalled. We have investigated how an AI system works on false positive recalls at screening and compared with radiologist findings. Two-view digital mammography (DM) examinations from 656 recalled women (136 with screening detected cancer), were analysed with a commercial AI system. The AI findings were matched with the areas on the images causing the recalls. The agreement was studied both at the examination level and for individual findings. Scores were compared between true positive and false positive recalls. ROC analysis was used to study the AI-system’s ability to distinguish between true and false positive recalls. It was also studied how the AI system performed on cases where there were discordant readings. AI identified the same areas as radiologists in 80% of the cases recalled on DM. For true positives both the proportion of matching areas and AI scores were higher than for false positive recalls. The AI system also had a relatively large AUC (0.83) for differentiating between false positive recalls and cancers. Further, the AI system identified most of the findings leading to recall in cases where only one of the readers had marked the case for discussion. There is a relatively large agreement between the AI system and radiologists. The AI system scores the false positives lower than true positives. AI complements a single reader in a way similar to a second reader.

假阳性召回是乳腺癌筛查中的一个主要问题，人工智能(AI)的引入可能会影响哪些女性被不必要地召回。我们研究了人工智能系统如何处理筛查时的假阳性回忆，并将其与放射科医生的发现进行了比较。通过商业人工智能系统分析了656名被召回女性(136名筛查出癌症)的双视图数字乳房x光检查(DM)。人工智能的发现与导致召回的图像上的区域相匹配。在审查一级和个别调查结果方面都对该协定进行了研究。比较真阳性和假阳性回忆的得分。使用ROC分析来研究人工智能系统区分真阳性和假阳性回忆的能力。研究人员还研究了人工智能系统在读数不一致的情况下的表现。人工智能识别出与放射科医生相同的区域，在80%的DM回忆病例中。对于真阳性，匹配区域的比例和人工智能得分都高于假阳性回忆。人工智能系统在区分假阳性回忆和癌症方面也有相对较大的AUC(0.83)。此外，在只有一位读者标记了讨论案例的情况下，人工智能系统识别了大多数导致召回的发现。人工智能系统和放射科医生之间有一个相对较大的共识。人工智能系统对假阳性的评分低于真阳性。AI以类似于第二个阅读器的方式补充单个阅读器。

{"title":"Correspondence between areas causing recall in breast cancer screening and artificial intelligence findings","authors":"Victor Dahlblom, A. Tingberg, S. Zackrisson, M. Dustler","doi":"10.1117/12.2625731","DOIUrl":"https://doi.org/10.1117/12.2625731","url":null,"abstract":"False positive recall is a major issue in breast cancer screening and the introduction of artificial intelligence (AI) might affect which women who are unnecessarily recalled. We have investigated how an AI system works on false positive recalls at screening and compared with radiologist findings. Two-view digital mammography (DM) examinations from 656 recalled women (136 with screening detected cancer), were analysed with a commercial AI system. The AI findings were matched with the areas on the images causing the recalls. The agreement was studied both at the examination level and for individual findings. Scores were compared between true positive and false positive recalls. ROC analysis was used to study the AI-system’s ability to distinguish between true and false positive recalls. It was also studied how the AI system performed on cases where there were discordant readings. AI identified the same areas as radiologists in 80% of the cases recalled on DM. For true positives both the proportion of matching areas and AI scores were higher than for false positive recalls. The AI system also had a relatively large AUC (0.83) for differentiating between false positive recalls and cancers. Further, the AI system identified most of the findings leading to recall in cases where only one of the readers had marked the case for discussion. There is a relatively large agreement between the AI system and radiologists. The AI system scores the false positives lower than true positives. AI complements a single reader in a way similar to a second reader.","PeriodicalId":92005,"journal":{"name":"Breast imaging : 11th International Workshop, IWDM 2012, Philadelphia, PA, USA, July 8-11, 2012 : proceedings. International Workshop on Breast Imaging (11th : 2012 : Philadelphia, Pa.)","volume":"7 1","pages":"122860K - 122860K-7"},"PeriodicalIF":0.0,"publicationDate":"2022-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74000425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Using deep learning for triple-negative breast cancer classification in DCE-MRI 在DCE-MRI中应用深度学习进行三阴性乳腺癌分类

Breast imaging : 11th International Workshop, IWDM 2012, Philadelphia, PA, USA, July 8-11, 2012 : proceedings. International Workshop on Breast Imaging (11th : 2012 : Philadelphia, Pa.)

Pub Date : 2022-07-13 DOI: 10.1117/12.2625780

Joel Vidal, R. Martí

Triple-negative is one of the most aggressive type of breast cancer for which is also difficult to find an effective treatment. An early diagnosis and a fast and specific treatment are shown to be key aspects for a better prognosis. Current diagnosis of these cases are based on performing a biopsy. This study proposes a non-invasive medical imaging predication method, based on a deep learning architecture, to automatically classify triple-negative tumors in DCE-MRI images. Results are evaluated on an extensive public dataset for different normalizations, data augmentations, learning rates and batch sizes, reaching a state-of-the-art AUC of 0.68.

三阴性乳腺癌是最具侵袭性的乳腺癌之一，也很难找到有效的治疗方法。早期诊断和快速特异性治疗是获得更好预后的关键。目前对这些病例的诊断是基于活检。本研究提出了一种基于深度学习架构的无创医学影像预测方法，对DCE-MRI图像中的三阴性肿瘤进行自动分类。结果在一个广泛的公共数据集上进行评估，用于不同的归一化，数据增强，学习率和批大小，达到最先进的AUC为0.68。

引用次数: 1

Simultaneous pectoral muscle and nipple location in MLO mammograms, considering image quality assumptions 同时胸肌和乳头的MLO乳房x线照片，考虑图像质量的假设

Breast imaging : 11th International Workshop, IWDM 2012, Philadelphia, PA, USA, July 8-11, 2012 : proceedings. International Workshop on Breast Imaging (11th : 2012 : Philadelphia, Pa.)

Pub Date : 2022-07-13 DOI: 10.1117/12.2625778

E. García, R. Martí, J. Martí, J. del Riego, Cecilia Aynes, A. Oliver, Oliver Díaz

Feature-based registration algorithms can be used to establish spatial correspondence between two image. Therefore, anatomical landmarks such as the breast boundary, pectoral muscle, nipple, duct and vessels need to be considered. The aim of this paper is to introduce a new approach which combine the pectoral muscle segmentation and nipple location, considering mammography quality assumptions. Pectoral muscle is initialized as a straight line from the top of the image to the nipple level. Afterwards, both pectoral muscle boundary and nipple position are optimized using an iterative approach. The results show that the nipple is localized on the contour of the corresponding area (error smaller than 10 mm) while the Dice’s coefficient of the pectoral muscle segmentation is equal to 0.84 ± 0.12 using a straight line which is improved using a Chan-Vese active contour approach, reaching 0.87 ± 0.13. Our algorithm is easily generalized and portable to a different mammographic system since it barely depends on images statistics -i.e. pixel intensity values-, and is just based on geometrical considerations.

基于特征的配准算法可用于建立两幅图像之间的空间对应关系。因此，需要考虑乳房边界、胸肌、乳头、导管、血管等解剖标志。本文的目的是介绍一种结合胸肌分割和乳头定位的新方法，考虑乳房x光检查质量的假设。胸肌初始化为从图像顶部到乳头水平的一条直线。然后，采用迭代法对胸肌边界和乳头位置进行优化。结果表明，乳头定位在相应区域的轮廓上(误差小于10 mm)，胸肌直线分割的Dice系数为0.84±0.12，经Chan-Vese主动轮廓法改进后达到0.87±0.13。我们的算法很容易推广和移植到不同的乳房x光检查系统，因为它几乎不依赖于图像统计-即像素强度值-而只是基于几何考虑。

{"title":"Simultaneous pectoral muscle and nipple location in MLO mammograms, considering image quality assumptions","authors":"E. García, R. Martí, J. Martí, J. del Riego, Cecilia Aynes, A. Oliver, Oliver Díaz","doi":"10.1117/12.2625778","DOIUrl":"https://doi.org/10.1117/12.2625778","url":null,"abstract":"Feature-based registration algorithms can be used to establish spatial correspondence between two image. Therefore, anatomical landmarks such as the breast boundary, pectoral muscle, nipple, duct and vessels need to be considered. The aim of this paper is to introduce a new approach which combine the pectoral muscle segmentation and nipple location, considering mammography quality assumptions. Pectoral muscle is initialized as a straight line from the top of the image to the nipple level. Afterwards, both pectoral muscle boundary and nipple position are optimized using an iterative approach. The results show that the nipple is localized on the contour of the corresponding area (error smaller than 10 mm) while the Dice’s coefficient of the pectoral muscle segmentation is equal to 0.84 ± 0.12 using a straight line which is improved using a Chan-Vese active contour approach, reaching 0.87 ± 0.13. Our algorithm is easily generalized and portable to a different mammographic system since it barely depends on images statistics -i.e. pixel intensity values-, and is just based on geometrical considerations.","PeriodicalId":92005,"journal":{"name":"Breast imaging : 11th International Workshop, IWDM 2012, Philadelphia, PA, USA, July 8-11, 2012 : proceedings. International Workshop on Breast Imaging (11th : 2012 : Philadelphia, Pa.)","volume":"13 1","pages":"122860E - 122860E-7"},"PeriodicalIF":0.0,"publicationDate":"2022-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89081581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Using virtual clinical trials to assess objective image quality metrics in the task of microcalcification localization in digital mammography 使用虚拟临床试验来评估数字乳房x线摄影中微钙化定位任务中的客观图像质量指标

Breast imaging : 11th International Workshop, IWDM 2012, Philadelphia, PA, USA, July 8-11, 2012 : proceedings. International Workshop on Breast Imaging (11th : 2012 : Philadelphia, Pa.)

Pub Date : 2022-07-13 DOI: 10.1117/12.2625745

L. E. Soares, L. Borges, B. Barufaldi, Andrew D. A. Maidment, M. Vieira

Many works have investigated methods to assess the quality of mammography images using objective image quality metrics. However, few studies have evaluated the ability of these metrics to predict the performance of human observers on specific tasks related to mammographic examination that are highly dependent on image quality. The propose of this work is to evaluate the quality of digital mammography acquired at a range of radiation doses through a set of objective metrics and to compare the results with the performance of human observers in the task of locating microcalcification clusters in these images. A dataset of 100 synthetic mammograms was simulated using a virtual clinical trials software. Microcalcification clusters of different sizes and contrasts were computationally inserted into the images. Acquisitions with five different radiation doses were simulated using a noise injection method proposed in a previous work. Four medical physicists with experience in analysis of mammographic images participated in the microcalcification cluster localization tests. The quality of digital mammography images was assessed considering nine well-known objective metrics. The metrics were calculated on both the raw data (DICOM ‘for processing’ tag) and the processed images (DICOM ‘for presentation’ tag). Finally, the association between readers performance and image quality index was conducted by calculating the percentage variation of all metrics as a function of radiation dose, taking the standard dose as a reference. Although the Structural Similarity Index Measure (SSIM) and Peak Signal-to-Noise Ratio (PSNR) are the most used in the literature, our results showed that Quality Index based on Local Variance (QILV) is the objective metric that best describes the behavior of human visual perception with the variation of radiation dose in digital mammography.

许多工作已经研究了使用客观图像质量指标评估乳房x线摄影图像质量的方法。然而，很少有研究评估这些指标在高度依赖图像质量的乳房x光检查相关的特定任务中预测人类观察者表现的能力。这项工作的建议是通过一组客观指标来评估在一系列辐射剂量下获得的数字乳房x线照相术的质量，并将结果与人类观察者在这些图像中定位微钙化团块的任务中的表现进行比较。使用虚拟临床试验软件模拟了100张合成乳房x光片的数据集。通过计算将不同大小和对比度的微钙化簇插入图像中。使用先前工作中提出的噪声注入方法模拟了五种不同辐射剂量的采集。四位具有乳房x线摄影图像分析经验的医学物理学家参与了微钙化簇定位测试。数字乳房x线摄影图像的质量是根据九个众所周知的客观指标来评估的。这些指标是根据原始数据(DICOM“用于处理”标签)和处理后的图像(DICOM“用于呈现”标签)计算的。最后，以标准剂量为参考，通过计算各指标随辐射剂量的变化百分比，得出阅读器性能与成像质量指标之间的关系。虽然文献中使用最多的是结构相似指数测量(SSIM)和峰值信噪比(PSNR)，但我们的研究结果表明，基于局部方差的质量指数(QILV)是最能描述数字乳房x线摄影中人类视觉感知随辐射剂量变化行为的客观指标。

{"title":"Using virtual clinical trials to assess objective image quality metrics in the task of microcalcification localization in digital mammography","authors":"L. E. Soares, L. Borges, B. Barufaldi, Andrew D. A. Maidment, M. Vieira","doi":"10.1117/12.2625745","DOIUrl":"https://doi.org/10.1117/12.2625745","url":null,"abstract":"Many works have investigated methods to assess the quality of mammography images using objective image quality metrics. However, few studies have evaluated the ability of these metrics to predict the performance of human observers on specific tasks related to mammographic examination that are highly dependent on image quality. The propose of this work is to evaluate the quality of digital mammography acquired at a range of radiation doses through a set of objective metrics and to compare the results with the performance of human observers in the task of locating microcalcification clusters in these images. A dataset of 100 synthetic mammograms was simulated using a virtual clinical trials software. Microcalcification clusters of different sizes and contrasts were computationally inserted into the images. Acquisitions with five different radiation doses were simulated using a noise injection method proposed in a previous work. Four medical physicists with experience in analysis of mammographic images participated in the microcalcification cluster localization tests. The quality of digital mammography images was assessed considering nine well-known objective metrics. The metrics were calculated on both the raw data (DICOM ‘for processing’ tag) and the processed images (DICOM ‘for presentation’ tag). Finally, the association between readers performance and image quality index was conducted by calculating the percentage variation of all metrics as a function of radiation dose, taking the standard dose as a reference. Although the Structural Similarity Index Measure (SSIM) and Peak Signal-to-Noise Ratio (PSNR) are the most used in the literature, our results showed that Quality Index based on Local Variance (QILV) is the objective metric that best describes the behavior of human visual perception with the variation of radiation dose in digital mammography.","PeriodicalId":92005,"journal":{"name":"Breast imaging : 11th International Workshop, IWDM 2012, Philadelphia, PA, USA, July 8-11, 2012 : proceedings. International Workshop on Breast Imaging (11th : 2012 : Philadelphia, Pa.)","volume":"26 1","pages":"1228603 - 1228603-8"},"PeriodicalIF":0.0,"publicationDate":"2022-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85352645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Sharing generative models instead of private data: a simulation study on mammography patch classification 共享生成模型代替私有数据:乳房x线照相术贴片分类的仿真研究

Breast imaging : 11th International Workshop, IWDM 2012, Philadelphia, PA, USA, July 8-11, 2012 : proceedings. International Workshop on Breast Imaging (11th : 2012 : Philadelphia, Pa.)

Pub Date : 2022-03-08 DOI: 10.1117/12.2625781

Zuzanna Szafranowska, Richard Osuala, Bennet Breier, Kaisar Kushibar, K. Lekadir, Oliver Díaz

Early detection of breast cancer in mammography screening via deep-learning based computer-aided detection systems shows promising potential in improving the curability and mortality rates of breast cancer. However, many clinical centres are restricted in the amount and heterogeneity of available data to train such models to (i) achieve promising performance and to (ii) generalise well across acquisition protocols and domains. As sharing data between centres is restricted due to patient privacy concerns, we propose a potential solution: sharing trained generative models between centres as substitute for real patient data. In this work, we use three well known mammography datasets to simulate three different centres, where one centre receives the trained generator of Generative Adversarial Networks (GANs) from the two remaining centres in order to augment the size and heterogeneity of its training dataset. We evaluate the utility of this approach on mammography patch classification on the test set of the GAN-receiving centre using two different classification models, (a) a convolutional neural network and (b) a transformer neural network. Our experiments demonstrate that shared GANs notably increase the performance of both transformer and convolutional classification models and highlight this approach as a viable alternative to inter-centre data sharing.

通过基于深度学习的计算机辅助检测系统在乳房x线摄影筛查中早期发现乳腺癌，在提高乳腺癌的治愈率和死亡率方面显示出巨大的潜力。然而，许多临床中心在可用数据的数量和异质性方面受到限制，无法训练这样的模型(i)实现有希望的性能，(ii)在采集协议和领域之间很好地推广。由于中心之间的数据共享受到患者隐私问题的限制，我们提出了一个潜在的解决方案:在中心之间共享经过训练的生成模型，以替代真实的患者数据。在这项工作中，我们使用三个众所周知的乳房x线摄影数据集来模拟三个不同的中心，其中一个中心接收来自其余两个中心的生成对抗网络(gan)训练生成器，以增加其训练数据集的大小和异质性。我们使用两种不同的分类模型(a)卷积神经网络和(b)变压器神经网络，评估了这种方法在gan接收中心测试集上乳腺摄影贴片分类上的效用。我们的实验表明，共享gan显著提高了变压器和卷积分类模型的性能，并突出了这种方法作为中心间数据共享的可行替代方案。

{"title":"Sharing generative models instead of private data: a simulation study on mammography patch classification","authors":"Zuzanna Szafranowska, Richard Osuala, Bennet Breier, Kaisar Kushibar, K. Lekadir, Oliver Díaz","doi":"10.1117/12.2625781","DOIUrl":"https://doi.org/10.1117/12.2625781","url":null,"abstract":"Early detection of breast cancer in mammography screening via deep-learning based computer-aided detection systems shows promising potential in improving the curability and mortality rates of breast cancer. However, many clinical centres are restricted in the amount and heterogeneity of available data to train such models to (i) achieve promising performance and to (ii) generalise well across acquisition protocols and domains. As sharing data between centres is restricted due to patient privacy concerns, we propose a potential solution: sharing trained generative models between centres as substitute for real patient data. In this work, we use three well known mammography datasets to simulate three different centres, where one centre receives the trained generator of Generative Adversarial Networks (GANs) from the two remaining centres in order to augment the size and heterogeneity of its training dataset. We evaluate the utility of this approach on mammography patch classification on the test set of the GAN-receiving centre using two different classification models, (a) a convolutional neural network and (b) a transformer neural network. Our experiments demonstrate that shared GANs notably increase the performance of both transformer and convolutional classification models and highlight this approach as a viable alternative to inter-centre data sharing.","PeriodicalId":92005,"journal":{"name":"Breast imaging : 11th International Workshop, IWDM 2012, Philadelphia, PA, USA, July 8-11, 2012 : proceedings. International Workshop on Breast Imaging (11th : 2012 : Philadelphia, Pa.)","volume":"70 1","pages":"122860Q - 122860Q-9"},"PeriodicalIF":0.0,"publicationDate":"2022-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82351545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

Front Matter: Volume 10718 前题:10718卷

Breast imaging : 11th International Workshop, IWDM 2012, Philadelphia, PA, USA, July 8-11, 2012 : proceedings. International Workshop on Breast Imaging (11th : 2012 : Philadelphia, Pa.)

Pub Date : 2018-07-06 DOI: 10.1117/12.2502754

Iwbi, E. Krupinski

引用次数: 0

The Impact of Reduced Injected Radioactivity on Image Quality of Molecular Breast Imaging Tomosynthesis. 降低注射放射性对乳腺分子成像断层合成成像质量的影响。

Breast imaging : 11th International Workshop, IWDM 2012, Philadelphia, PA, USA, July 8-11, 2012 : proceedings. International Workshop on Breast Imaging (11th : 2012 : Philadelphia, Pa.)

Pub Date : 2012-07-01 DOI: 10.1007/978-3-642-31271-7_39

Olivia Sullivan, Zongyi Gong, Kelly Klanian, Tushita Patel, Mark B Williams

This study's objective is to compare image quality in 3-D molecular breast imaging tomosynthesis (MBIT) with that in planar molecular breast imaging (MBI) over a range of breast radioactivity concentrations. Using gelatin and point source phantoms lesion contrast, lesion signal-to-noise ratio (SNR) and spatial resolution were compared for a range of lesion sizes and depths. For both MBI and MBIT, lesion contrast is essentially constant with changing activity while SNR decreases by a factor of 1.5 - 2 between 100% and 25% activity levels. For nearly all lesion sizes and locations contrast and SNR are significantly higher for MBIT than MBI, potentially permitting greater reductions in injected dose. Spatial resolution in MBI is dependent on lesion depth but independent of lesion location with MBIT. Reconstructed MBIT spatial resolution is substantially better than that in the projection images, suggesting future use of higher sensitivity collimators for even further reductions in injected activity.

本研究的目的是比较三维分子乳房成像断层合成(MBIT)与平面分子乳房成像(MBI)在乳房放射性浓度范围内的图像质量。利用明胶和点源图像对比病变，比较不同大小和深度的病变信噪比(SNR)和空间分辨率。对于MBI和mbbi，病变对比度随着活动的变化基本不变，而在100%和25%的活动水平之间，信噪比下降了1.5 - 2倍。对于几乎所有的病变大小和部位，MBI的对比度和信噪比都明显高于MBI，这可能使注射剂量的减少幅度更大。MBI的空间分辨率依赖于病灶深度，而与病灶位置无关。重建的MBIT空间分辨率明显优于投影图像，这表明未来使用更高灵敏度的准直器来进一步降低注入活度。

{"title":"The Impact of Reduced Injected Radioactivity on Image Quality of Molecular Breast Imaging Tomosynthesis.","authors":"Olivia Sullivan, Zongyi Gong, Kelly Klanian, Tushita Patel, Mark B Williams","doi":"10.1007/978-3-642-31271-7_39","DOIUrl":"https://doi.org/10.1007/978-3-642-31271-7_39","url":null,"abstract":"This study's objective is to compare image quality in 3-D molecular breast imaging tomosynthesis (MBIT) with that in planar molecular breast imaging (MBI) over a range of breast radioactivity concentrations. Using gelatin and point source phantoms lesion contrast, lesion signal-to-noise ratio (SNR) and spatial resolution were compared for a range of lesion sizes and depths. For both MBI and MBIT, lesion contrast is essentially constant with changing activity while SNR decreases by a factor of 1.5 - 2 between 100% and 25% activity levels. For nearly all lesion sizes and locations contrast and SNR are significantly higher for MBIT than MBI, potentially permitting greater reductions in injected dose. Spatial resolution in MBI is dependent on lesion depth but independent of lesion location with MBIT. Reconstructed MBIT spatial resolution is substantially better than that in the projection images, suggesting future use of higher sensitivity collimators for even further reductions in injected activity.","PeriodicalId":92005,"journal":{"name":"Breast imaging : 11th International Workshop, IWDM 2012, Philadelphia, PA, USA, July 8-11, 2012 : proceedings. International Workshop on Breast Imaging (11th : 2012 : Philadelphia, Pa.)","volume":"7361 ","pages":"300-307"},"PeriodicalIF":0.0,"publicationDate":"2012-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5565232/pdf/nihms424638.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"35441154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Detective Quantum Efficiency of a CsI-CMOS X-ray Detector for Breast Tomosynthesis Operating in High Dynamic Range and High Sensitivity Modes. 在高动态范围和高灵敏度模式下用于乳腺断层合成的cmos - cmos x射线探测器的探测量子效率。

Breast imaging : 11th International Workshop, IWDM 2012, Philadelphia, PA, USA, July 8-11, 2012 : proceedings. International Workshop on Breast Imaging (11th : 2012 : Philadelphia, Pa.)

Pub Date : 2012-07-01 DOI: 10.1007/978-3-642-31271-7_11

Tushita Patel, Kelly Klanian, Zongyi Gong, Mark B Williams

The spatial frequency dependent detective quantum efficiency (DQE) of a CsI-CMOS x-ray detector was measured in two operating modes: a high dynamic range (HDR) mode and a high sensitivity (HS) mode. DQE calculations were performed using the IEC-62220-1-2 Standard. For detector entrance air kerma values between ~7 µGy and 60 µGy the DQE is similar in either HDR mode or HS mode, with a value of ~0.7 at low frequency and ~ 0.15 - 0.20 at the Nyquist frequency f_N = 6.7 mm^-1. In HDR mode the DQE remains virtually constant for operation with K_a values between ~7 µGy and 119 µGy but decreases for K_a levels below ~ 7 µGy. In HS mode the DQE is approximately constant over the full range of entrance air kerma tested between 1.7 µGy and 60 µGy but kerma values above ~75 µGy produce hard saturation. Quantum limited operation in HS mode for entrance kerma as small as 1.7 µGy makes it possible to use a large number of low dose views to improve angular sampling and decrease acquisition time.

在高动态范围(HDR)和高灵敏度(HS)两种工作模式下，测量了cmos x射线探测器的空间频率相关探测量子效率(DQE)。DQE计算使用IEC-62220-1-2标准执行。在HDR模式和HS模式下，探测器入口空气kerma值在~7 ~ 60µGy之间时，DQE值在低频为~0.7，在奈奎斯特频率fN = 6.7 mm-1时为~ 0.15 ~ 0.20。在HDR模式下，当Ka值介于~7µGy和119µGy之间时，DQE几乎保持不变，但当Ka水平低于~7µGy时，DQE会下降。在HS模式下，DQE在1.7µGy到60µGy之间的整个测试入口空气kerma范围内近似恒定，但kerma值高于~75µGy会产生硬饱和。在HS模式下，入口kerma小至1.7µGy的量子限制操作使得使用大量低剂量视图来改善角度采样并减少采集时间成为可能。

{"title":"Detective Quantum Efficiency of a CsI-CMOS X-ray Detector for Breast Tomosynthesis Operating in High Dynamic Range and High Sensitivity Modes.","authors":"Tushita Patel, Kelly Klanian, Zongyi Gong, Mark B Williams","doi":"10.1007/978-3-642-31271-7_11","DOIUrl":"https://doi.org/10.1007/978-3-642-31271-7_11","url":null,"abstract":"The spatial frequency dependent detective quantum efficiency (DQE) of a CsI-CMOS x-ray detector was measured in two operating modes: a high dynamic range (HDR) mode and a high sensitivity (HS) mode. DQE calculations were performed using the IEC-62220-1-2 Standard. For detector entrance air kerma values between ~7 µGy and 60 µGy the DQE is similar in either HDR mode or HS mode, with a value of ~0.7 at low frequency and ~ 0.15 - 0.20 at the Nyquist frequency fN = 6.7 mm-1. In HDR mode the DQE remains virtually constant for operation with Ka values between ~7 µGy and 119 µGy but decreases for Ka levels below ~ 7 µGy. In HS mode the DQE is approximately constant over the full range of entrance air kerma tested between 1.7 µGy and 60 µGy but kerma values above ~75 µGy produce hard saturation. Quantum limited operation in HS mode for entrance kerma as small as 1.7 µGy makes it possible to use a large number of low dose views to improve angular sampling and decrease acquisition time.","PeriodicalId":92005,"journal":{"name":"Breast imaging : 11th International Workshop, IWDM 2012, Philadelphia, PA, USA, July 8-11, 2012 : proceedings. International Workshop on Breast Imaging (11th : 2012 : Philadelphia, Pa.)","volume":"7361 ","pages":"80-87"},"PeriodicalIF":0.0,"publicationDate":"2012-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1007/978-3-642-31271-7_11","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"35312074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 11

首页上一页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Breast imaging : 11th International Workshop, IWDM 2012, Philadelphia, PA, USA, July 8-11, 2012 : proceedings. International Workshop on Breast Imaging (11th : 2012 : Philadelphia, Pa.)

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀