Independent histological validation of MR-derived radio-pathomic maps of tumor cell density using image-guided biopsies in human brain tumors.
Authors
Affiliations (18)
Affiliations (18)
- UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision and Imaging Biomarkers, University of California Los Angeles, Los Angeles, CA, USA.
- Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA.
- University Vita-Salute San Raffaele, Milan, Italy.
- Neuroradiology Unit and CERMAC, IRCCS Ospedale San Raffaele, Milan, Italy.
- Department of Neurosurgery and Gamma Knife Radiosurgery, IRCCS Ospedale San Raffaele, Milan, Italy.
- Department of Diagnostic Imaging and Nuclear Medicine, Graduate School of Medicine, Kyoto University, Kyoto, Japan.
- Department of Radiology, Medical College of Wisconsin, Milwaukee, WI, USA.
- Department of Neurosurgery, David Geffen School of Medicine, University of California, Los Angeles, CA, USA.
- Department of Neurology, Medical College of Wisconsin, Milwaukee, WI, USA.
- Department of Neurology, Ronald Reagan UCLA Medical Center, University of California, Los Angeles, CA, USA.
- David Geffen School of Medicine, UCLA Neuro-Oncology Program, University of California, Los Angeles, CA, USA.
- Department of Biomedical Engineering, Medical College of Wisconsin, Milwaukee, WI, USA.
- UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision and Imaging Biomarkers, University of California Los Angeles, Los Angeles, CA, USA. [email protected].
- Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA. [email protected].
- Department of Neurosurgery, David Geffen School of Medicine, University of California, Los Angeles, CA, USA. [email protected].
- Department of Bioengineering, Henry Samueli School of Engineering and Applied Science, University of California Los Angeles, Los Angeles, CA, USA. [email protected].
- Department of Psychiatry and Biobehavioral Sciences, David Geffen School of Medicine, University of California, Los Angeles, CA, USA. [email protected].
- UCLA Radiology, UCLA Brain Tumor Imaging Laboratory, Los Angeles, USA. [email protected].
Abstract
In brain gliomas, non-invasive biomarkers reflecting tumor cellularity would be useful to guide supramarginal resections and to plan stereotactic biopsies. We aim to validate a previously-trained machine learning algorithm that generates cellularity prediction maps (CPM) from multiparametric MRI data to an independent, retrospective external cohort of gliomas undergoing image-guided biopsies, and to compare the performance of CPM and diffusion MRI apparent diffusion coefficient (ADC) in predicting cellularity. A cohort of patients with treatment-naïve or recurrent gliomas were prospectively studied. All patients underwent pre-surgical MRI according to the standardized brain tumor imaging protocol. The surgical sampling site was planned based on image-guided biopsy targets and tissue was stained with hematoxylin-eosin for cell density count. The correlation between MRI-derived CPM values and histological cellularity, and between ADC and histological cellularity, was evaluated both assuming independent observations and accounting for non-independent observations. Sixty-six samples from twenty-seven patients were collected. Thirteen patients had treatment-naïve tumors and fourteen had recurrent lesions. CPM value accurately predicted histological cellularity in treatment-naïve patients (b = 1.4, R<sup>2</sup> = 0.2, p = 0.009, rho = 0.41, p = 0.016, RMSE = 1503 cell/mm<sup>2</sup>), but not in the recurrent sub-cohort. Similarly, ADC values showed a significant association with histological cellularity only in treatment-naive patients (b = 1.3, R<sup>2</sup> = 0.22, p = 0.007; rho = -0.37, p = 0.03), not statistically different from the CPM correlation. These findings were confirmed with statistical tests accounting for non-independent observations. MRI-derived machine learning generated cellularity prediction maps (CPM) enabled a non-invasive evaluation of tumor cellularity in treatment-naïve glioma patients, although CPM did not clearly outperform ADC alone in this cohort.