Jonghyun Bae1,2,3,4, Zhengnan Huang1,2,3, Florian Knoll2,3, Krzysztof Geras2,3,5, Terlika Pandit Sood2,3, Li Feng6, Laura Heacock2,3, Linda Moy1,2,3, Sungheon Gene Kim4. 1. Vilcek Institute of Graduate Biomedical Science, New York University School of Medicine, New York, New York, USA. 2. Center for Biomedical Imaging, Radiology, New York University School of Medicine, New York, New York, USA. 3. Center for Advanced Imaging Innovation and Research, Radiology, New York University School of Medicine, New York, New York, USA. 4. Department of Radiology, Weill Cornell Medical College, New York, New York, USA. 5. Center for Data Science, New York University, New York, New York, USA. 6. Biomedical Engineering and Imaging Institute and Department of Radiology, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
Abstract
PURPOSE: To develop a deep learning approach to estimate the local capillary-level input function (CIF) for pharmacokinetic model analysis of DCE-MRI. METHODS: A deep convolutional network was trained with numerically simulated data to estimate the CIF. The trained network was tested using simulated lesion data and used to estimate voxel-wise CIF for pharmacokinetic model analysis of breast DCE-MRI data using an abbreviated protocol from women with malignant (n = 25) and benign (n = 28) lesions. The estimated parameters were used to build a logistic regression model to detect the malignancy. RESULT: The pharmacokinetic parameters estimated using the network-predicted CIF from our breast DCE data showed significant differences between the malignant and benign groups for all parameters. Testing the diagnostic performance with the estimated parameters, the conventional approach with arterial input function (AIF) showed an area under the curve (AUC) between 0.76 and 0.87, and the proposed approach with CIF demonstrated similar performance with an AUC between 0.79 and 0.81. CONCLUSION: This study shows the feasibility of estimating voxel-wise CIF using a deep neural network. The proposed approach could eliminate the need to measure AIF manually without compromising the diagnostic performance to detect the malignancy in the clinical setting.
PURPOSE: To develop a deep learning approach to estimate the local capillary-level input function (CIF) for pharmacokinetic model analysis of DCE-MRI. METHODS: A deep convolutional network was trained with numerically simulated data to estimate the CIF. The trained network was tested using simulated lesion data and used to estimate voxel-wise CIF for pharmacokinetic model analysis of breast DCE-MRI data using an abbreviated protocol from women with malignant (n = 25) and benign (n = 28) lesions. The estimated parameters were used to build a logistic regression model to detect the malignancy. RESULT: The pharmacokinetic parameters estimated using the network-predicted CIF from our breast DCE data showed significant differences between the malignant and benign groups for all parameters. Testing the diagnostic performance with the estimated parameters, the conventional approach with arterial input function (AIF) showed an area under the curve (AUC) between 0.76 and 0.87, and the proposed approach with CIF demonstrated similar performance with an AUC between 0.79 and 0.81. CONCLUSION: This study shows the feasibility of estimating voxel-wise CIF using a deep neural network. The proposed approach could eliminate the need to measure AIF manually without compromising the diagnostic performance to detect the malignancy in the clinical setting.
Authors: Siamak P Nejad-Davarani; Hassan Bagher-Ebadian; James R Ewing; Douglas C Noll; Tom Mikkelsen; Michael Chopp; Quan Jiang Journal: NMR Biomed Date: 2017-02-17 Impact factor: 4.044
Authors: Aytekin Oto; Cheng Yang; Arda Kayhan; Maria Tretiakova; Tatjana Antic; Christine Schmid-Tannwald; Scott Eggener; Gregory S Karczmar; Walter M Stadler Journal: AJR Am J Roentgenol Date: 2011-12 Impact factor: 3.959
Authors: P S Tofts; G Brix; D L Buckley; J L Evelhoch; E Henderson; M V Knopp; H B Larsson; T Y Lee; N A Mayr; G J Parker; R E Port; J Taylor; R M Weisskoff Journal: J Magn Reson Imaging Date: 1999-09 Impact factor: 4.813