Cortechs.ai | Deep Learning Segmentation Of Infiltrative And Enhancing Cellular Tumor In Post-Treatment Glioblastoma Patients With Multi-Shell Diffusion MRI

Deep Learning Segmentation Of Infiltrative And Enhancing Cellular Tumor In Post-Treatment Glioblastoma Patients With Multi-Shell Diffusion MRI

Louis Gagnon, Diviya Gupta, George Mastorakos, Nathan White, Vanessa Goodwill, Carrie McDonald, Thomas Beaumont, Christopher Conlin, Tyler Seibert, Jona Hattangandi-Gluth, Santosh Kesari, Jessica Schulte, David Piccioni, Anders Dale, Niky Farid, Jeffrey Rudie

Abstract

Multimodal MRI is used for the evaluation of tumor burden in glioblastoma (GBM) patients after surgical resection, radiation, and chemotherapy. However, it can be challenging to identify non-enhancing infiltrative tumor and differentiate recurrent enhancing tumor from post-treatment changes. Restriction spectrum imaging (RSI), an advanced multishell diffusion technique, has shown promise in distinguishing cellular tumor from edema and enhancing post-treatment changes including pseudoprogression and radiation necrosis. We developed a convolutional network (nnUNet) that incorporates traditional multimodal MRI with DSC perfusion and RSI to detect and quantify enhancing and nonenhancing cellular tumor in post-treatment glioblastoma patients. This cellular tumor segmentation network was evaluated in a cohort of 186 post-treatment GBM patients (55.5 +/- 13.7 years, 158 male) with 243 timepoints using 5-fold cross validation. Cellular tumor volumes were then used to predict overall survival (OS) and progression free survival (PFS) in 94 patients with imaging within 3 months of initial surgery. Accuracy for segmenting cellular tumor as measured by the Dice-similarity coefficient was 0.77 (IQR 0.55-0.87) and the AUC of the ROC curve for detecting residual/recurrent tumor compared to post-treatment changes was 0.86. The predicted cellular tumor volumes were an independent hazard over age, sex, GTR status and conventional enhancing residual tumor for both OS (p=0.0003) and PFS (p=0.0004). The tumor segmentation network was validated in an external dataset of 22 GBM patients (55 timepoints) with a median Dice of 0.73 and AUC of 0.91. Survival prediction was validated in a different external dataset of 70 post-treatment GBM patients, with cellular tumor volumes being an independent predictor of OS (p=0.03). In conclusion, deep learning models incorporating advanced imaging can accurately segment enhancing and nonenhancing cellular tumor, which can help distinguish recurrent/residual tumor from post-treatment changes and predict OS and PFS.

More Resources

05/18/2025

Cortechs.ai and ALZ-NET Announce Strategic Collaboration to Improve Alzheimer’s Disease Care Through AI-Driven Imaging

This new strategic collaboration aims to enhance the quality of care for people living with Alzheimer’s disease.

05/16/2025

Case Study: NeuroQuant® for ARIA: Monitoring ARIA Progression in Early Alzheimer’s Disease

Dr. Suzie Bash highlights how advanced imaging with NeuroQuant for ARIA supported detection and monitoring of ARIA-E and ARIA-H in an 81-year-old patient.

05/13/2025

Dr. Ana M. Franceschi Joins Cortechs.ai Medical Advisory Board

Neuroimaging thought leader to enhance PET/MRI and dementia research impact through AI-powered tools

05/10/2025

All the Ways to Use the NeuroQuant Custom Report

With the ability to select structures from NeuroQuant’s 70+ structure parcellation atlas, the user has the power to truly personalize patient care!

05/04/2025

Introducing NeuroQuant MS Lesion Dynamics Computation: A Clearer Path to Understanding Disease Progression

Discover how the latest NeuroQuant MS update offers a clearer, more intuitive way to track lesion changes and understand disease progression over time.

05/02/2025

4 Reasons Why Over 1500 Medical Centers Worldwide Trust Cortechs.ai

Trusted by 1500+ medical centers, Cortechs.ai delivers AI-powered imaging tools that enhance diagnostic accuracy and streamline workflows.
Scroll to Top