Deep Learning Based Staging of Bone Lesions From Computed Tomography Scans.
Deep Learning Based Staging of Bone Lesions From Computed Tomography Scans.
复制标题
基于深度学习的计算机断层扫描骨病变分期。
DOI：
10.1109/access.2021.3074051
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Turkbey B
中科院分区：
文献类型：
--
作者：
Masoudi S;Mehralivand S;Harmon SA;Lay N;Lindenberg L;Mena E;Pinto PA;Citrin DE;Gulley JL;Wood BJ;Dahut WL;Madan RA;Bagci U;Choyke PL;Turkbey B
在这项研究中，我们制定了一种有效的基于深度学习的分类策略，用于使用前列腺癌患者的计算机断层扫描（CT）来表征转移性骨病变。为此，我们使用 114 名诊断为前列腺癌的患者的 CT 扫描中的 2,880 个带注释的骨病变进行训练、验证和最终评估。这些注释的形式是病变全分割、病变类型和良性或恶性标签。在这项工作中，我们提出了开发最先进的模型以将骨病变分类为良性或恶性的方法，其中（1）我们引入了一个有价值的数据集来解决临床上重要的问题，（2）我们通过在每次训练、验证和测试分组中遵循病变感知分布对数据集进行患者级分层来提高模型的可靠性，（3）我们探索病变纹理、形态、大小、位置和体积信息对分类性能的影响，（4）我们使用不同的算法研究病变分类的功能，包括基于病变的平均 2D ResNet-50、基于病变的平均 2D ResNeXt-50、3D ResNet-18、3D ResNet-50，以及 2D ResNet-50 和 3D ResNet-18 的集成。为此，我们采用了等于 75%/12%/13% 的训练/验证/测试分割，并对训练数据集应用了多种数据增强方法，以避免过度拟合并提高可靠性。我们使用基于病变的平均 2D ResNet-50 和 3D ResNet-18 的集合，在测试集中对良性与恶性骨病变进行正确分类，准确率达到 92.2%，其中纹理、体积信息和形态分别具有最大的区分能力。据我们所知，这是有史以来达到的最高的病变级别准确度，拥有针对此类临床重要问题的非常全面的数据集。转移发展早期阶段的这种分类表现水平预示着该策略的临床转化。
In this study, we formulated an efficient deep learning-based classification strategy for characterizing metastatic bone lesions using computed tomography scans (CTs) of prostate cancer patients. For this purpose, 2,880 annotated bone lesions from CT scans of 114 patients diagnosed with prostate cancer were used for training, validation, and final evaluation. These annotations were in the form of lesion full segmentation, lesion type and labels of either benign or malignant. In this work, we present our approach in developing the state-of-the-art model to classify bone lesions as benign or malignant, where (1) we introduce a valuable dataset to address a clinically important problem, (2) we increase the reliability of our model by patient-level stratification of our dataset following lesion-aware distribution at each of the training, validation, and test splits, (3) we explore the impact of lesion texture, morphology, size, location, and volumetric information on the classification performance, (4) we investigate the functionality of lesion classification using different algorithms including lesion-based average 2D ResNet-50, lesion-based average 2D ResNeXt-50, 3D ResNet-18, 3D ResNet-50, as well as the ensemble of 2D ResNet-50 and 3D ResNet-18. For this purpose, we employed a train/validation/test split equal to 75%/12%/13% with several data augmentation methods applied to the training dataset to avoid overfitting and to increase reliability. We achieved an accuracy of 92.2% for correct classification of benign vs. malignant bone lesions in the test set using an ensemble of lesion-based average 2D ResNet-50 and 3D ResNet-18 with texture, volumetric information, and morphology having the greatest discriminative power respectively. To the best of our knowledge, this is the highest ever achieved lesion-level accuracy having a very comprehensive data set for such a clinically important problem. This level of classification performance in the early stages of metastasis development bodes well for clinical translation of this strategy.
登录
查看更多内容
影响因子：
1.3
作者：
Dandil, Ali Aslantas Emre;Saglam, Semahat;Cakiroglu, Murat
通讯作者：
Cakiroglu, Murat
影响因子：
10.9
作者：
Chmelik, Jiri;Jakubicek, Roman;Gavelli, Giampaolo
通讯作者：
Gavelli, Giampaolo
影响因子：
19.5
作者：
Selvaraju, Ramprasaath R.;Cogswell, Michael;Batra, Dhruv
通讯作者：
Batra, Dhruv
影响因子：
3.7
作者：
Papandrianos, Nikolaos;Papageorgiou, Elpiniki;Papageorgiou, Konstantinos
通讯作者：
Papageorgiou, Konstantinos
基于PSMA的[（18）F] DCFPYL PET/CT优于传统成像，用于转移性前列腺癌患者的病变检测。
影响因子：
3.1
作者：
Rowe SP;Macura KJ;Mena E;Blackford AL;Nadal R;Antonarakis ES;Eisenberger M;Carducci M;Fan H;Dannals RF;Chen Y;Mease RC;Szabo Z;Pomper MG;Cho SY
通讯作者：
Cho SY