Search

Your search keyword '"DiCarlo, Julie C."' showing total 30 results
Start Over Author "DiCarlo, Julie C."
30 results on '"DiCarlo, Julie C."'

2. An untrained deep learning method for reconstructing dynamic magnetic resonance images from accelerated model-based data

Author

Slavkova, Kalina P., DiCarlo, Julie C., Wadhwa, Viraj, Wu, Chengyue, Virostko, John, Kumar, Sidharth, Yankeelov, Thomas E., and Tamir, Jonathan I.

Subjects
Electrical Engineering and Systems Science - Image and Video Processing
Abstract

The purpose of this work is to implement physics-based regularization as a stopping condition in tuning an untrained deep neural network for reconstructing MR images from accelerated data. The ConvDecoder neural network was trained with a physics-based regularization term incorporating the spoiled gradient echo equation that describes variable-flip angle (VFA) data. Fully-sampled VFA k-space data were retrospectively accelerated by factors of R={8,12,18,36} and reconstructed with ConvDecoder (CD), ConvDecoder with the proposed regularization (CD+r), locally low-rank (LR) reconstruction, and compressed sensing with L1-wavelet regularization (L1). Final images from CD+r training were evaluated at the \emph{argmin} of the regularization loss; whereas the CD, LR, and L1 reconstructions were chosen optimally based on ground truth data. The performance measures used were the normalized root-mean square error, the concordance correlation coefficient (CCC), and the structural similarity index (SSIM). The CD+r reconstructions, chosen using the stopping condition, yielded SSIMs that were similar to the CD (p=0.47) and LR SSIMs (p=0.95) across R and that were significantly higher than the L1 SSIMs (p=0.04). The CCC values for the CD+r T1 maps across all R and subjects were greater than those corresponding to the L1 (p=0.15) and LR (p=0.13) T1 maps, respectively. For R > 12 (<4.2 minutes scan time), L1 and LR T1 maps exhibit a loss of spatially refined details compared to CD+r. We conclude that the use of an untrained neural network together with a physics-based regularization loss shows promise as a measure for determining the optimal stopping point in training without relying on fully-sampled ground truth data., Comment: 45 pages, 7 figures, 2 Tables, supplementary material included (10 figures, 4 tables)

Published
2022
Full Text
View/download PDF

5. Breast Multiparametric MRI for Prediction of Neoadjuvant Chemotherapy Response in Breast Cancer: The BMMR2 Challenge

Author

Li, Wen, primary, Partridge, Savannah C., additional, Newitt, David C., additional, Steingrimsson, Jon, additional, Marques, Helga S., additional, Bolan, Patrick J., additional, Hirano, Michael, additional, Bearce, Benjamin Aaron, additional, Kalpathy-Cramer, Jayashree, additional, Boss, Michael A., additional, Teng, Xinzhi, additional, Zhang, Jiang, additional, Cai, Jing, additional, Kontos, Despina, additional, Cohen, Eric A., additional, Mankowski, Walter C., additional, Liu, Michael, additional, Ha, Richard, additional, Pellicer-Valero, Oscar J., additional, Maier-Hein, Klaus, additional, Rabinovici-Cohen, Simona, additional, Tlusty, Tal, additional, Ozery-Flato, Michal, additional, Parekh, Vishwa S., additional, Jacobs, Michael A., additional, Yan, Ran, additional, Sung, Kyunghyun, additional, Kazerouni, Anum S., additional, DiCarlo, Julie C., additional, Yankeelov, Thomas E., additional, Chenevert, Thomas L., additional, and Hylton, Nola M., additional

Published
2024
Full Text
View/download PDF

6. The ISMRM Open Science Initiative for Perfusion Imaging (OSIPI): Results from the OSIPI–Dynamic Contrast‐Enhanced challenge

Author

Shalom, Eve S., primary, Kim, Harrison, additional, van der Heijden, Rianne A., additional, Ahmed, Zaki, additional, Patel, Reyna, additional, Hormuth, David A., additional, DiCarlo, Julie C., additional, Yankeelov, Thomas E., additional, Sisco, Nicholas J., additional, Dortch, Richard D., additional, Stokes, Ashley M., additional, Inglese, Marianna, additional, Grech‐Sollars, Matthew, additional, Toschi, Nicola, additional, Sahoo, Prativa, additional, Singh, Anup, additional, Verma, Sanjay K., additional, Rathore, Divya K., additional, Kazerouni, Anum S., additional, Partridge, Savannah C., additional, LoCastro, Eve, additional, Paudyal, Ramesh, additional, Wolansky, Ivan A., additional, Shukla‐Dave, Amita, additional, Schouten, Pepijn, additional, Gurney‐Champion, Oliver J., additional, Jiřík, Radovan, additional, Macíček, Ondřej, additional, Bartoš, Michal, additional, Vitouš, Jiří, additional, Das, Ayesha Bharadwaj, additional, Kim, S. Gene, additional, Bokacheva, Louisa, additional, Mikheev, Artem, additional, Rusinek, Henry, additional, Berks, Michael, additional, Hubbard Cristinacce, Penny L., additional, Little, Ross A., additional, Cheung, Susan, additional, O'Connor, James P. B., additional, Parker, Geoff J. M., additional, Moloney, Brendan, additional, LaViolette, Peter S., additional, Bobholz, Samuel, additional, Duenweg, Savannah, additional, Virostko, John, additional, Laue, Hendrik O., additional, Sung, Kyunghyun, additional, Nabavizadeh, Ali, additional, Saligheh Rad, Hamidreza, additional, Hu, Leland S., additional, Sourbron, Steven, additional, Bell, Laura C., additional, and Fathi Kazerooni, Anahita, additional

Published
2023
Full Text
View/download PDF

8. The ISMRM Open Science Initiative for Perfusion Imaging (OSIPI): Results from the OSIPI–Dynamic Contrast‐Enhanced challenge.

Author

Shalom, Eve S., Kim, Harrison, van der Heijden, Rianne A., Ahmed, Zaki, Patel, Reyna, Hormuth, David A., DiCarlo, Julie C., Yankeelov, Thomas E., Sisco, Nicholas J., Dortch, Richard D., Stokes, Ashley M., Inglese, Marianna, Grech‐Sollars, Matthew, Toschi, Nicola, Sahoo, Prativa, Singh, Anup, Verma, Sanjay K., Rathore, Divya K., Kazerouni, Anum S., and Partridge, Savannah C.

Subjects
OPEN scholarship, PERFUSION imaging, STANDARD operating procedure, SOFTWARE development tools
Abstract

Purpose: Ktrans$$ {K}^{\mathrm{trans}} $$ has often been proposed as a quantitative imaging biomarker for diagnosis, prognosis, and treatment response assessment for various tumors. None of the many software tools for Ktrans$$ {K}^{\mathrm{trans}} $$ quantification are standardized. The ISMRM Open Science Initiative for Perfusion Imaging–Dynamic Contrast‐Enhanced (OSIPI‐DCE) challenge was designed to benchmark methods to better help the efforts to standardize Ktrans$$ {K}^{\mathrm{trans}} $$ measurement. Methods: A framework was created to evaluate Ktrans$$ {K}^{\mathrm{trans}} $$ values produced by DCE‐MRI analysis pipelines to enable benchmarking. The perfusion MRI community was invited to apply their pipelines for Ktrans$$ {K}^{\mathrm{trans}} $$ quantification in glioblastoma from clinical and synthetic patients. Submissions were required to include the entrants' Ktrans$$ {K}^{\mathrm{trans}} $$ values, the applied software, and a standard operating procedure. These were evaluated using the proposed OSIPIgold$$ \mathrm{OSIP}{\mathrm{I}}_{\mathrm{gold}} $$ score defined with accuracy, repeatability, and reproducibility components. Results: Across the 10 received submissions, the OSIPIgold$$ \mathrm{OSIP}{\mathrm{I}}_{\mathrm{gold}} $$ score ranged from 28% to 78% with a 59% median. The accuracy, repeatability, and reproducibility scores ranged from 0.54 to 0.92, 0.64 to 0.86, and 0.65 to 1.00, respectively (0–1 = lowest–highest). Manual arterial input function selection markedly affected the reproducibility and showed greater variability in Ktrans$$ {K}^{\mathrm{trans}} $$ analysis than automated methods. Furthermore, provision of a detailed standard operating procedure was critical for higher reproducibility. Conclusions: This study reports results from the OSIPI‐DCE challenge and highlights the high inter‐software variability within Ktrans$$ {K}^{\mathrm{trans}} $$ estimation, providing a framework for ongoing benchmarking against the scores presented. Through this challenge, the participating teams were ranked based on the performance of their software tools in the particular setting of this challenge. In a real‐world clinical setting, many of these tools may perform differently with different benchmarking methodology. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

12. Integrating mechanism-based modeling with biomedical imaging to build practical digital twins for clinical oncology

Author

Wu, Chengyue, primary, Lorenzo, Guillermo, additional, Hormuth, David A., additional, Lima, Ernesto A. B. F., additional, Slavkova, Kalina P., additional, DiCarlo, Julie C., additional, Virostko, John, additional, Phillips, Caleb M., additional, Patt, Debra, additional, Chung, Caroline, additional, and Yankeelov, Thomas E., additional

Published
2022
Full Text
View/download PDF

13. An untrained deep learning method for reconstructing dynamic MR images from accelerated model‐based data.

Author

Slavkova, Kalina P., DiCarlo, Julie C., Wadhwa, Viraj, Kumar, Sidharth, Wu, Chengyue, Virostko, John, Yankeelov, Thomas E., and Tamir, Jonathan I.

Subjects
DEEP learning, MAGNETIC resonance imaging, SIGNAL convolution
Abstract

Purpose: To implement physics‐based regularization as a stopping condition in tuning an untrained deep neural network for reconstructing MR images from accelerated data. Methods: The ConvDecoder (CD) neural network was trained with a physics‐based regularization term incorporating the spoiled gradient echo equation that describes variable‐flip angle data. Fully‐sampled variable‐flip angle k‐space data were retrospectively accelerated by factors of R = {8, 12, 18, 36} and reconstructed with CD, CD with the proposed regularization (CD + r), locally low‐rank (LR) reconstruction, and compressed sensing with L1‐wavelet regularization (L1). Final images from CD + r training were evaluated at the "argmin" of the regularization loss; whereas the CD, LR, and L1 reconstructions were chosen optimally based on ground truth data. The performance measures used were the normalized RMS error, the concordance correlation coefficient, and the structural similarity index. Results: The CD + r reconstructions, chosen using the stopping condition, yielded structural similarity indexs that were similar to the CD (p = 0.47) and LR structural similarity indexs (p = 0.95) across R and that were significantly higher than the L1 structural similarity indexs (p = 0.04). The concordance correlation coefficient values for the CD + r T1 maps across all R and subjects were greater than those corresponding to the L1 (p = 0.15) and LR (p = 0.13) T1 maps, respectively. For R ≥ 12 (≤4.2 min scan time), L1 and LR T1 maps exhibit a loss of spatially refined details compared to CD + r. Conclusion: The use of an untrained neural network together with a physics‐based regularization loss shows promise as a measure for determining the optimal stopping point in training without relying on fully‐sampled ground truth data. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

14. Analysis of simplicial complexes to determine when to sample for quantitative DCE MRI of the breast.

Author

DiCarlo, Julie C., Jarrett, Angela M., Kazerouni, Anum S., Virostko, John, Sorace, Anna, Slavkova, Kalina P., Woodard, Stefanie, Avery, Sarah, Patt, Debra, Goodgame, Boone, and Yankeelov, Thomas E.

Subjects
FIX-point estimation, BREAST cancer, CONTRAST media, BREAST exams, MAGNETIC resonance imaging
Abstract

Purpose: A method is presented to select the optimal time points at which to measure DCE‐MRI signal intensities, leaving time in the MR exam for high‐spatial resolution image acquisition. Theory: Simplicial complexes are generated from the Kety‐Tofts model pharmacokinetic parameters Ktrans and ve. A geometric search selects optimal time points for accurate estimation of perfusion parameters. Methods: The DCE‐MRI data acquired in women with invasive breast cancer (N = 27) were used to retrospectively compare parameter maps fit to full and subsampled time courses. Simplicial complexes were generated for a fixed range of Kety‐Tofts model parameters and for the parameter ranges weighted by estimates from the fully sampled data. The largest‐area manifolds determined the optimal three time points for each case. Simulations were performed along with retrospectively subsampled data fits. The agreement was computed between the model parameters fit to three points and those fit to all points. Results: The optimal three‐point sample times were from the data‐informed simplicial complex analysis and determined to be 65, 204, and 393 s after arrival of the contrast agent to breast tissue. In the patient data, tumor‐median parameter values fit using all points and the three selected time points agreed with concordance correlation coefficients of 0.97 for Ktrans and 0.67 for ve. Conclusion: It is possible to accurately estimate pharmacokinetic parameters from three properly selected time points inserted into a clinical DCE‐MRI breast exam. This technique can provide guidance on when to capture images for quantitative data between high‐spatial‐resolution DCE‐MRI images. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

19. Additional file 2 of Quantitative multiparametric MRI predicts response to neoadjuvant therapy in the community setting

Author

Virostko, John, Sorace, Anna G., Slavkova, Kalina P., Kazerouni, Anum S., Jarrett, Angela M., DiCarlo, Julie C., Woodard, Stefanie, Avery, Sarah, Goodgame, Boone, Patt, Debra, and Yankeelov, Thomas E.

Subjects
sense organs, skin and connective tissue diseases
Abstract

Additional file 2: Figure S1. Receiver operating characteristic curves for each MRI parameter for predicting pCR from the relative change from baseline at each serial MRI.

Published
2021
Full Text
View/download PDF

22. Abstract PS13-18: Predicting breast cancer response to neoadjuvant therapies using a mathematical model individualized with patient-specific magnetic resonance imaging data: Preliminary Results

Author

Jarrett, Angela M, primary, Hormuth, David A., additional, Syed, Anum K, additional, Wu, Chengyue, additional, Virostko, John, additional, Sorace, Anna G, additional, DiCarlo, Julie C, additional, Kowalski, Jeanne, additional, Patt, Debra, additional, Goodgame, Boone, additional, Avery, Sarah, additional, and Yankeelov, Thomas E, additional

Published
2021
Full Text
View/download PDF

25. Abstract P2-16-17: Optimizing neoadjuvant regimens for individual breast cancer patients generated by a mathematical model utilizing quantitative magnetic resonance imaging data: Preliminary results

Author

Jarrett, Angela M, primary, Hormuth, David A, additional, Wu, Chengyue, additional, Virostko, John, additional, Sorace, Anna G, additional, DiCarlo, Julie C, additional, Patt, Debra, additional, Goodgame, Boone, additional, Avery, Sarah, additional, and Yankeelov, Thomas E, additional

Published
2020
Full Text
View/download PDF

27. Sustained improvements in MRI outcomes with abatacept following the withdrawal of all treatments in patients with early, progressive rheumatoid arthritis

Author

Peterfy, Charles, primary, Burmester, Gerd R, additional, Bykerk, Vivian P, additional, Combe, Bernard G, additional, DiCarlo, Julie C, additional, Furst, Daniel E, additional, Huizinga, Tom W J, additional, Wong, Dennis A, additional, Conaghan, Philip G, additional, and Emery, Paul, additional

Published
2016
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results