2020
Mouraviev, Andrei; Detsky, Jay; Sahgal, Arjun; Ruschin, Mark; Lee, Young K; Karam, Irene; Heyn, Chris; Stanisz, Greg J; Martel, Anne L
Use of Radiomics for the Prediction of Local Control of Brain Metastases After Stereotactic Radiosurgery Journal Article
In: Neuro-Oncology, 2020.
Abstract | BibTeX | Tags: Brain
@article{Mouraviev2020,
title = {Use of Radiomics for the Prediction of Local Control of Brain Metastases After Stereotactic Radiosurgery},
author = {Mouraviev, Andrei and Detsky, Jay and Sahgal, Arjun and Ruschin, Mark and Lee, Young K and Karam, Irene and Heyn, Chris and Stanisz, Greg J and Martel, Anne L},
year = {2020},
date = {2020-01-20},
journal = {Neuro-Oncology},
abstract = {Background
Local response prediction for brain metastases (BM) after stereotactic radiosurgery (SRS) is challenging, particularly for smaller BM, as existing criteria are based solely on unidimensional measurements. This investigation sought to determine whether radiomic features provide additional value to routinely available clinical and dosimetric variables to predict local recurrence following SRS.
Methods
408 BM in 87 patients treated with SRS were analyzed. A total of 440 radiomic features were extracted from the tumor core, and the peritumoral regions, using the baseline pre-treatment volumetric post-contrast T1 (T1c) and volumetric T2 fluid-attenuated inversion recovery (FLAIR) MRI sequences. Local tumor progression was determined based on RANO-BM criteria, with a maximum axial diameter growth of >20% on the follow-up T1c indicating local failure. The top radiomic features were determined based on resampled Random Forest (RF) feature importance. An RF classifier was trained using each set of features and evaluated using the area under the receiver operating characteristic curve (AUC).
Results
The addition of any one of the top ten radiomic features to the set of clinical features resulted in a statistically significant (p<0.001) increase in the AUC. An optimized combination of radiomic and clinical features resulted in a 19% higher resampled AUC (mean = 0.793, 95% C.I. = 0.792-0.795) than clinical features alone (0.669, 0.668-0.671).
Conclusions
The increase in AUC of the RF classifier, after incorporating radiomic features, suggests that quantitative characterization of tumor appearance on pretreatment T1c and FLAIR adds value to known clinical and dosimetric variables for predicting local failure.},
keywords = {Brain},
pubstate = {published},
tppubtype = {article}
}
Local response prediction for brain metastases (BM) after stereotactic radiosurgery (SRS) is challenging, particularly for smaller BM, as existing criteria are based solely on unidimensional measurements. This investigation sought to determine whether radiomic features provide additional value to routinely available clinical and dosimetric variables to predict local recurrence following SRS.
Methods
408 BM in 87 patients treated with SRS were analyzed. A total of 440 radiomic features were extracted from the tumor core, and the peritumoral regions, using the baseline pre-treatment volumetric post-contrast T1 (T1c) and volumetric T2 fluid-attenuated inversion recovery (FLAIR) MRI sequences. Local tumor progression was determined based on RANO-BM criteria, with a maximum axial diameter growth of >20% on the follow-up T1c indicating local failure. The top radiomic features were determined based on resampled Random Forest (RF) feature importance. An RF classifier was trained using each set of features and evaluated using the area under the receiver operating characteristic curve (AUC).
Results
The addition of any one of the top ten radiomic features to the set of clinical features resulted in a statistically significant (p<0.001) increase in the AUC. An optimized combination of radiomic and clinical features resulted in a 19% higher resampled AUC (mean = 0.793, 95% C.I. = 0.792-0.795) than clinical features alone (0.669, 0.668-0.671).
Conclusions
The increase in AUC of the RF classifier, after incorporating radiomic features, suggests that quantitative characterization of tumor appearance on pretreatment T1c and FLAIR adds value to known clinical and dosimetric variables for predicting local failure.
2019
Emmanuel Edward Ntiri Maged Goubran, Hassan Akhavein; Martel, Anne L; Mario Masellis Walter Swardfager, Richard Swartz
Hippocampal segmentation for brains with extensive atrophy using three‐dimensional convolutional neural networks Journal Article
In: Human brain mapping, 2019.
Abstract | BibTeX | Tags: Brain
@article{Goubran2019,
title = {Hippocampal segmentation for brains with extensive atrophy using three‐dimensional convolutional neural networks},
author = {Maged Goubran, Emmanuel Edward Ntiri, Hassan Akhavein, Melissa Holmes, Sean Nestor, Joel Ramirez, Sabrina Adamo, Miracle Ozzoude, Christopher Scott, Fuqiang Gao and Anne L Martel and Walter Swardfager, Mario Masellis, Richard Swartz, Bradley MacIntosh, Sandra E Black},
year = {2019},
date = {2019-10-14},
urldate = {2019-10-14},
journal = {Human brain mapping},
abstract = {Hippocampal volumetry is a critical biomarker of aging and dementia, and it is widely used as a predictor of cognitive performance; however, automated hippocampal segmentation methods are limited because the algorithms are (a) not publicly available, (b) subject to error with significant brain atrophy, cerebrovascular disease and lesions, and/or (c) computationally expensive or require parameter tuning. In this study, we trained a 3D convolutional neural network using 259 bilateral manually delineated segmentations collected from three studies, acquired at multiple sites on different scanners with variable protocols. Our training dataset consisted of elderly cases difficult to segment due to extensive atrophy, vascular disease, and lesions. Our algorithm, (HippMapp3r), was validated against four other publicly available state‐of‐the‐art techniques (HippoDeep, FreeSurfer, SBHV, volBrain, and FIRST). HippMapp3r outperformed the other techniques on all three metrics, generating an average Dice of 0.89 and a correlation coefficient of 0.95. It was two orders of magnitude faster than some of the tested techniques. Further validation was performed on 200 subjects from two other disease populations (frontotemporal dementia and vascular cognitive impairment), highlighting our method's low outlier rate. We finally tested the methods on real and simulated “clinical adversarial” cases to study their robustness to corrupt, low‐quality scans. The pipeline and models are available at: https://hippmapp3r.readthedocs.ioto facilitate the study of the hippocampus in large multisite studies.},
keywords = {Brain},
pubstate = {published},
tppubtype = {article}
}
Mouraviev, A; Detsky, J; Ruschin, ME; Sahgal, A; Lee, Y; Heyn, C; Karam, I; Martel, Anne L
Use of Radiomics in the Prediction of Brain Metastases Local Control Post-Stereotactic Radiosurgery Journal Article
In: International Journal of Radiation Oncology• Biology• Physics, vol. 105, no. 1, pp. E82-E83, 2019.
Abstract | BibTeX | Tags: Brain
@article{Mouraviev2019,
title = {Use of Radiomics in the Prediction of Brain Metastases Local Control Post-Stereotactic Radiosurgery},
author = {A Mouraviev and J Detsky and ME Ruschin and A Sahgal and Y Lee and C Heyn and I Karam and Anne L Martel},
year = {2019},
date = {2019-09-01},
urldate = {2019-09-01},
journal = {International Journal of Radiation Oncology• Biology• Physics},
volume = {105},
number = {1},
pages = {E82-E83},
abstract = {Results
Top 10 highest ranked radiomic features were combined, one at a time, with the clinical features, resulting in a very significant (p< 0.001) increase in AUC from the addition of the top 9 radiomic features, and no increase from adding the 10 th best radiomic feature. An optimized combination of radiomic and clinical features resulted in a dramatically higher performance (resampled AUC: mean= 0.792, 95% CI of mean= 0.790-0.793) compared to clinical features alone (0.676, 0.674-0.678).
Conclusion
The increase in performance from incorporating radiomic features suggests that quantitative characterization of tumor structure through the use of radiomics adds complementary information to what is typically available in the clinical workflow.},
keywords = {Brain},
pubstate = {published},
tppubtype = {article}
}
Top 10 highest ranked radiomic features were combined, one at a time, with the clinical features, resulting in a very significant (p< 0.001) increase in AUC from the addition of the top 9 radiomic features, and no increase from adding the 10 th best radiomic feature. An optimized combination of radiomic and clinical features resulted in a dramatically higher performance (resampled AUC: mean= 0.792, 95% CI of mean= 0.790-0.793) compared to clinical features alone (0.676, 0.674-0.678).
Conclusion
The increase in performance from incorporating radiomic features suggests that quantitative characterization of tumor structure through the use of radiomics adds complementary information to what is typically available in the clinical workflow.