Josef Vymazal
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Josef Vymazal has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Jiří Keller
Na Homolce Hospital
2 shared publications Libor Dujka
Department of Cardiology Na Homolce Hospital Prague Czech Republic
2 shared publications- Pavel Hala
Department of Cardiology Na Homolce Hospital Prague Czech Republic
2 shared publications Petr Moučka
Department of Cardiology Na Homolce Hospital Prague Czech Republic
2 shared publicationsRadovan Žáček
Department of Radiology Na Homolce Hospital Prague Czech Republic
2 shared publications- Vivek Y. Reddy
Mount Sinai Fuster Heart Hospital, Icahn School of Medicine at Mount Sinai, New York, New York
2 shared publications
Latest Publications
- Open Access
- 15 June 2022
- Published by American Association for Cancer Research (AACR) in Cancer Research
- Vol. 82 (12_Supplem) , 4138
Abstract 4138: Prediction of progression-free survival in patients with primary glioblastoma: MRI T2 relaxivity and deep learning
Introduction: We aimed to evaluate T2 relaxation times in the follow-up of patients with glioblastoma (GBM), the most common and aggressive primary brain tumor with nearly universal recurrence following standard therapy. Methods: In this partially retrospective study, 53 patients (mean age 45.05 years ± 12.6) with non-recurrent GBM followed at our department roughly every 2 months after surgery and combined chemo-radiotherapy were included (>180 days progression-free survival [PFS] as determined by RANO,1 ≥3 MRI examinations in the PFS interval [same scanner and protocol]). Thirty-six patients additionally received Tumor-Treating Fields (TTFields) therapy. All data used were prior to progression. T2 relaxation rates (1/T2) were calculated voxel-wise assuming mono-exponential decay. Whole-brain (WB) histogram values were extracted from 1/T2 maps including skewness, kurtosis, mean, median, 15 and 85 percentile values and variance. We additionally segmented 1/T2 maps using a 5 compartment Gaussian mixture model (Python v3.8.2), producing mean, variance and voxel percentage for each component. To evaluate predictive potential with respect to PFS, we used a deep recurrent neural network (long short-term memory [LSTM] model) in Tensorflow v2.3.1 (4 timesteps); the features used included the above metrics as well as TTFields treatment status and scanner. Twenty subjects were included in the predictive model, as inclusion criteria were stricter (progression, ≤120 days between all MRIs [mean 43.6 days], ≥4 PFS MRIs). Two models were tested: a regression model (days to progression) and a classification model (±18 months PFS; models differed in output layer). Both models were run 10 times; mean results are presented. Results: We found WB median 1/T2 correlated with PFS, as values decreased prior to progression. WB median 1/T2 linear regression slopes also differed in progression versus pseudo-progression, as values were relatively stable in pseudo-progression. The deep LSTM regression model achieved an R2 of 97%. The deep LSTM classification model achieved a mean macro precision of 86%, recall 85% and F1 accuracy of 85% in predicting progression within 18 months. Conclusions: We found very intriguing results with WB median 1/T2 measurements in distinguishing progression from pseudo-progression, and in suggesting progression despite otherwise unremarkable imaging. A more complex predictive model trained on pre-progression data, using a fully-automated segmentation method followed by deep learning, showed very promising results. The present results may find utility in the monitoring of GBM patients and may be advantageous to include in multimodal predictive models. Reference: 1. Wen PY et al. J Clin Oncol 2010;28:1963-1972. Citation Format: Aaron M. Rulseh, Josef Vymazal. Prediction of progression-free survival in patients with primary glioblastoma: MRI T2 relaxivity and deep learning [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 4138.
- 15 June 2022
- Published by American Association for Cancer Research (AACR) in Cancer Research
- Vol. 82 (12_Supplem) , 4138
Open AccessAbstract 4138: Prediction of progression-free survival in patients with primary glioblastoma: MRI T2 relaxivity and deep learning
Introduction: We aimed to evaluate T2 relaxation times in the follow-up of patients with glioblastoma (GBM), the most common and aggressive primary brain tumor with nearly universal recurrence following standard therapy. Methods: In this partially retrospective study, 53 patients (mean age 45.05 years ± 12.6) with non-recurrent GBM followed at our department roughly every 2 months after surgery and combined chemo-radiotherapy were included (>180 days progression-free survival [PFS] as determined by RANO,1 ≥3 MRI examinations in the PFS interval [same scanner and protocol]). Thirty-six patients additionally received Tumor-Treating Fields (TTFields) therapy. All data used were prior to progression. T2 relaxation rates (1/T2) were calculated voxel-wise assuming mono-exponential decay. Whole-brain (WB) histogram values were extracted from 1/T2 maps including skewness, kurtosis, mean, median, 15 and 85 percentile values and variance. We additionally segmented 1/T2 maps using a 5 compartment Gaussian mixture model (Python v3.8.2), producing mean, variance and voxel percentage for each component. To evaluate predictive potential with respect to PFS, we used a deep recurrent neural network (long short-term memory [LSTM] model) in Tensorflow v2.3.1 (4 timesteps); the features used included the above metrics as well as TTFields treatment status and scanner. Twenty subjects were included in the predictive model, as inclusion criteria were stricter (progression, ≤120 days between all MRIs [mean 43.6 days], ≥4 PFS MRIs). Two models were tested: a regression model (days to progression) and a classification model (±18 months PFS; models differed in output layer). Both models were run 10 times; mean results are presented. Results: We found WB median 1/T2 correlated with PFS, as values decreased prior to progression. WB median 1/T2 linear regression slopes also differed in progression versus pseudo-progression, as values were relatively stable in pseudo-progression. The deep LSTM regression model achieved an R2 of 97%. The deep LSTM classification model achieved a mean macro precision of 86%, recall 85% and F1 accuracy of 85% in predicting progression within 18 months. Conclusions: We found very intriguing results with WB median 1/T2 measurements in distinguishing progression from pseudo-progression, and in suggesting progression despite otherwise unremarkable imaging. A more complex predictive model trained on pre-progression data, using a fully-automated segmentation method followed by deep learning, showed very promising results. The present results may find utility in the monitoring of GBM patients and may be advantageous to include in multimodal predictive models. Reference: 1. Wen PY et al. J Clin Oncol 2010;28:1963-1972. Citation Format: Aaron M. Rulseh, Josef Vymazal. Prediction of progression-free survival in patients with primary glioblastoma: MRI T2 relaxivity and deep learning [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 4138.
- 11 May 2021
- Published by Wiley in Journal of Cardiovascular Electrophysiology
- Vol. 32 (5)
Cover Image, Volume 32, Issue 5
- 11 May 2021
- Published by Wiley in Journal of Cardiovascular Electrophysiology
- Vol. 32 (5)
Cover Image, Volume 32, Issue 5
- 8 March 2021
- Published by Wiley in Journal of Cardiovascular Electrophysiology
- Vol. 32 (5) , 1367-1375
Quantification of artifacts during cardiac magnetic resonance in patients with leadless Micra pacemakers
Introduction: When cardiac magnetic resonance (MR) is performed after previous leadless transcatheter pacemaker implantation, an image distortion has to be expected in the heart region and evaluation of myocardial tissue can be affected. In this clinical prospective study, we aim to assess the extent and impact of this artifact on individual ventricular segments and compare it to conventional pacing devices.Methods: Total of 20 patients with leadless pacemaker placed in the right ventricle underwent cardiac MR imaging in a 1.5 Tesla scanner. A multiplanar segmentation was used to demarcate the left and right ventricular myocardium as well as the pacemaker‐caused image artifact in systolic and diastolic time frames. Artifact size and its relative influence on myocardial segments were quantitatively assessed and expressed in AHA‐17 model.Results: Implanted leadless pacemaker caused an image artifact with a volume of 48 ± 5 ml. Most distorted were the apical septal (53 ± 23%), apical inferior (30 ± 18%), and midventricular inferoseptal (30 ± 20%) segments. The artifact intersection with basal and lateral segments was none or negligible (up to 2%). The portion of left ventricular (LV) myocardium affected by the artifact was significantly higher in systole (8 ± 4%) compared to diastole (10 ± 3%; p < .001).Conclusion: Implantation of leadless pacemaker represents no obstacle for cardiac MR imaging but causes an image artifact located mostly in septal, inferoseptal, and anteroseptal segments of apical and midventricular LV myocardium. With the exception of the apex, diastolic timing reduces the image distortion of all segments and improves global ventricular assessment.
- 8 March 2021
- Published by Wiley in Journal of Cardiovascular Electrophysiology
- Vol. 32 (5) , 1367-1375
Quantification of artifacts during cardiac magnetic resonance in patients with leadless Micra pacemakers
Introduction: When cardiac magnetic resonance (MR) is performed after previous leadless transcatheter pacemaker implantation, an image distortion has to be expected in the heart region and evaluation of myocardial tissue can be affected. In this clinical prospective study, we aim to assess the extent and impact of this artifact on individual ventricular segments and compare it to conventional pacing devices.Methods: Total of 20 patients with leadless pacemaker placed in the right ventricle underwent cardiac MR imaging in a 1.5 Tesla scanner. A multiplanar segmentation was used to demarcate the left and right ventricular myocardium as well as the pacemaker‐caused image artifact in systolic and diastolic time frames. Artifact size and its relative influence on myocardial segments were quantitatively assessed and expressed in AHA‐17 model.Results: Implanted leadless pacemaker caused an image artifact with a volume of 48 ± 5 ml. Most distorted were the apical septal (53 ± 23%), apical inferior (30 ± 18%), and midventricular inferoseptal (30 ± 20%) segments. The artifact intersection with basal and lateral segments was none or negligible (up to 2%). The portion of left ventricular (LV) myocardium affected by the artifact was significantly higher in systole (8 ± 4%) compared to diastole (10 ± 3%; p < .001).Conclusion: Implantation of leadless pacemaker represents no obstacle for cardiac MR imaging but causes an image artifact located mostly in septal, inferoseptal, and anteroseptal segments of apical and midventricular LV myocardium. With the exception of the apex, diastolic timing reduces the image distortion of all segments and improves global ventricular assessment.
- 1 February 2008
- Published by Elsevier in European Journal of Radiology
- Vol. 65 (2) , 316-325
A multi-center, comparative, phase 3 study to determine the efficacy of gadofosveset-enhanced magnetic resonance angiography for evaluation of renal artery disease
- 1 February 2008
- Published by Elsevier in European Journal of Radiology
- Vol. 65 (2) , 316-325
A multi-center, comparative, phase 3 study to determine the efficacy of gadofosveset-enhanced magnetic resonance angiography for evaluation of renal artery disease