深度学习卷积神经网络（DLCNN）：释放F-FDG PET/CT在淋巴瘤诊断中的潜力
Deep learning convolutional neural network (DLCNN): unleashing the potential of F-FDG PET/CT in lymphoma.
作者信息
Li Ke, Zhang Ran, Cai Weibo
机构信息
Department of Medical Physics, University of Wisconsin-Madison 1111 Highland Avenue, Madison, WI, USA.
Department of Radiology, University of Wisconsin-Madison 600 Highland Avenue, Madison, WI, USA.
出版信息
Am J Nucl Med Mol Imaging. 2021 Aug 15;11(4):327-331. eCollection 2021.
Abstract
This perspective briefly reviewed the applications of F-FDG PET/CT in the clinical management of lymphoma and the need for lesion segmentation in those applications. It discussed the limitations of existing segmentation technologies and the great potential of using deep learning convolutional neural network (DLCNN) to accomplish automatic lymphoma segmentation and characterizations. Finally, the authors shared perspectives on the technical challenges that need to be addressed to fully unleash the potential of DLCNN and F-FDG PET/CT in the diagnosis, prognosis, and treatment of lymphoma.
摘要
本观点简要回顾了F-FDG PET/CT在淋巴瘤临床管理中的应用以及这些应用中病变分割的必要性。讨论了现有分割技术的局限性以及使用深度学习卷积神经网络（DLCNN）实现淋巴瘤自动分割和特征描述的巨大潜力。最后，作者就充分发挥DLCNN和F-FDG PET/CT在淋巴瘤诊断、预后和治疗方面的潜力所需解决的技术挑战分享了观点。
相似文献
1
Deep learning convolutional neural network (DLCNN): unleashing the potential of F-FDG PET/CT in lymphoma.深度学习卷积神经网络（DLCNN）：释放F-FDG PET/CT在淋巴瘤诊断中的潜力
Am J Nucl Med Mol Imaging. 2021 Aug 15;11(4):327-331. eCollection 2021.
2
Computer-aided detection of mantle cell lymphoma on F-FDG PET/CT using a deep learning convolutional neural network.使用深度学习卷积神经网络在F-FDG PET/CT上对套细胞淋巴瘤进行计算机辅助检测。
Am J Nucl Med Mol Imaging. 2021 Aug 15;11(4):260-270. eCollection 2021.
3
Fully automatic segmentation of diffuse large B cell lymphoma lesions on 3D FDG-PET/CT for total metabolic tumour volume prediction using a convolutional neural network.使用卷积神经网络对 3D FDG-PET/CT 上弥漫性大 B 细胞淋巴瘤病变进行全自动分割，以预测总代谢肿瘤体积。
Eur J Nucl Med Mol Imaging. 2021 May;48(5):1362-1370. doi: 10.1007/s00259-020-05080-7. Epub 2020 Oct 24.
4
Evaluation of Semiautomatic and Deep Learning-Based Fully Automatic Segmentation Methods on [F]FDG PET/CT Images from Patients with Lymphoma: Influence on Tumor Characterization.基于半自动和深度学习的全自动分割方法在淋巴瘤患者 [F]FDG PET/CT 图像上的评估：对肿瘤特征的影响。
J Digit Imaging. 2023 Aug;36(4):1864-1876. doi: 10.1007/s10278-023-00823-y. Epub 2023 Apr 14.
5
F-FDG PET/CT Uptake Classification in Lymphoma and Lung Cancer by Using Deep Convolutional Neural Networks.使用深度卷积神经网络对淋巴瘤和肺癌的 F-FDG PET/CT 摄取进行分类。
Radiology. 2020 Feb;294(2):445-452. doi: 10.1148/radiol.2019191114. Epub 2019 Dec 10.
6
Preliminary study of AI-assisted diagnosis using FDG-PET/CT for axillary lymph node metastasis in patients with breast cancer.利用氟代脱氧葡萄糖正电子发射断层显像/X线计算机体层成像（FDG-PET/CT）对乳腺癌患者腋窝淋巴结转移进行人工智能辅助诊断的初步研究。
EJNMMI Res. 2021 Jan 25;11(1):10. doi: 10.1186/s13550-021-00751-4.
7
Prediction of Neoadjuvant Chemotherapy Response in Osteosarcoma Using Convolutional Neural Network of Tumor Center F-FDG PET Images.利用肿瘤中心F-FDG PET图像的卷积神经网络预测骨肉瘤新辅助化疗反应
Diagnostics (Basel). 2021 Oct 25;11(11):1976. doi: 10.3390/diagnostics11111976.
8
Tumor co-segmentation in PET/CT using multi-modality fully convolutional neural network.基于多模态全卷积神经网络的 PET/CT 肿瘤共分割。
Phys Med Biol. 2018 Dec 21;64(1):015011. doi: 10.1088/1361-6560/aaf44b.
9
Validation of Deep Learning-based Augmentation for Reduced F-FDG Dose for PET/MRI in Children and Young Adults with Lymphoma.基于深度学习增强技术减少儿童和青年淋巴瘤患者PET/MRI中F-FDG剂量的验证
Radiol Artif Intell. 2021 Oct 6;3(6):e200232. doi: 10.1148/ryai.2021200232. eCollection 2021 Nov.
10
Classification of Pulmonary Nodules in 2-[F]FDG PET/CT Images with a 3D Convolutional Neural Network.基于三维卷积神经网络的2-[F]FDG PET/CT图像中肺结节的分类
Nucl Med Mol Imaging. 2024 Feb;58(1):9-24. doi: 10.1007/s13139-023-00821-6. Epub 2023 Aug 30.
引用本文的文献
1
Recent advances in imaging and artificial intelligence (AI) for quantitative assessment of multiple myeloma.用于多发性骨髓瘤定量评估的成像和人工智能（AI）的最新进展。
Am J Nucl Med Mol Imaging. 2024 Aug 25;14(4):208-229. doi: 10.62347/NLLV9295. eCollection 2024.
2
PET/CT based cross-modal deep learning signature to predict occult nodal metastasis in lung cancer.基于 PET/CT 的跨模态深度学习特征预测肺癌隐匿性淋巴结转移。
Nat Commun. 2023 Nov 18;14(1):7513. doi: 10.1038/s41467-023-42811-4.
3
Quantitative PET-based biomarkers in lymphoma: getting ready for primetime.基于定量 PET 的淋巴瘤生物标志物：准备迎接黄金时代。
Nat Rev Clin Oncol. 2023 Sep;20(9):640-657. doi: 10.1038/s41571-023-00799-2. Epub 2023 Jul 17.
4
Deep Neural Networks and Machine Learning Radiomics Modelling for Prediction of Relapse in Mantle Cell Lymphoma.用于预测套细胞淋巴瘤复发的深度神经网络和机器学习放射组学建模
Cancers (Basel). 2022 Apr 15;14(8):2008. doi: 10.3390/cancers14082008.
本文引用的文献
1
Computer-aided detection of mantle cell lymphoma on F-FDG PET/CT using a deep learning convolutional neural network.使用深度学习卷积神经网络在F-FDG PET/CT上对套细胞淋巴瘤进行计算机辅助检测。
Am J Nucl Med Mol Imaging. 2021 Aug 15;11(4):260-270. eCollection 2021.
2
Convolutional Neural Networks for Automated PET/CT Detection of Diseased Lymph Node Burden in Patients with Lymphoma.用于自动检测淋巴瘤患者病变淋巴结负荷的卷积神经网络在PET/CT中的应用
Radiol Artif Intell. 2020 Sep 2;2(5):e200016. doi: 10.1148/ryai.2020200016. eCollection 2020 Sep.
3
Checklist for Artificial Intelligence in Medical Imaging (CLAIM): A Guide for Authors and Reviewers.医学影像人工智能清单（CLAIM）：作者和审稿人指南
Radiol Artif Intell. 2020 Mar 25;2(2):e200029. doi: 10.1148/ryai.2020200029. eCollection 2020 Mar.
4
Diffuse large B-cell lymphoma segmentation in PET-CT images via hybrid learning for feature fusion.基于混合学习的特征融合进行 PET-CT 图像中弥漫性大 B 细胞淋巴瘤的分割。
Med Phys. 2021 Jul;48(7):3665-3678. doi: 10.1002/mp.14847. Epub 2021 Jun 22.
5
Weakly supervised deep learning for determining the prognostic value of F-FDG PET/CT in extranodal natural killer/T cell lymphoma, nasal type.基于弱监督学习的 F-FDG PET/CT 预测结外鼻型自然杀伤/T 细胞淋巴瘤预后的价值研究。
Eur J Nucl Med Mol Imaging. 2021 Sep;48(10):3151-3161. doi: 10.1007/s00259-021-05232-3. Epub 2021 Feb 20.
6
The role of PET in first-line treatment of Hodgkin lymphoma.正电子发射断层扫描在霍奇金淋巴瘤一线治疗中的作用。
Lancet Haematol. 2021 Jan;8(1):e67-e79. doi: 10.1016/S2352-3026(20)30357-4. Epub 2020 Dec 22.
7
A pilot study treatment of malignant tumors using low-dose F-fluorodeoxyglucose (F-FDG).一项使用低剂量氟脱氧葡萄糖（F-FDG）治疗恶性肿瘤的初步研究。
Am J Nucl Med Mol Imaging. 2020 Dec 15;10(6):334-341. eCollection 2020.
8
Quantitative parameters of MRI and F-FDG PET/CT in the prediction of breast cancer prognosis and molecular type: an original study.MRI和F-FDG PET/CT的定量参数在预测乳腺癌预后及分子类型中的应用：一项原创性研究
Am J Nucl Med Mol Imaging. 2020 Dec 15;10(6):279-292. eCollection 2020.
9
Correlation of whole-bone marrow dual-time-point F-FDG, as measured by a CT-based method of PET/CT quantification, with response to treatment in newly diagnosed multiple myeloma patients.通过基于CT的PET/CT定量方法测量的全骨髓双时间点F-FDG与新诊断的多发性骨髓瘤患者治疗反应的相关性。
Am J Nucl Med Mol Imaging. 2020 Oct 15;10(5):257-264. eCollection 2020.
10
Fully automatic segmentation of diffuse large B cell lymphoma lesions on 3D FDG-PET/CT for total metabolic tumour volume prediction using a convolutional neural network.使用卷积神经网络对 3D FDG-PET/CT 上弥漫性大 B 细胞淋巴瘤病变进行全自动分割，以预测总代谢肿瘤体积。
Eur J Nucl Med Mol Imaging. 2021 May;48(5):1362-1370. doi: 10.1007/s00259-020-05080-7. Epub 2020 Oct 24.
Zotero 插件