Cortechs.ai | Segmentation Of Pre And Post-Treatment Glioma Tissue Types Including Resection Cavities

Segmentation Of Pre And Post-Treatment Glioma Tissue Types Including Resection Cavities

Nathan White, Saif Baig, Igor Vidic, George Mastorakos, Robert Smith, Anders Dale, Carrie McDonald, Thomas Beaumont, Tyler Seibert, Srinivas Peddi, Jona Hattangadi-Gluth, Nikdokht Farid, Santosh Kesari, Jeffrey Rudie

Abstract

Purpose

Measuring gliomas is a time-intensive process with significant inter-rater variability in post-surgical residual tumor and resection cavities. This likely contributes to the delayed assessment of progression and in-field recurrences from radiation. Automated segmentation of pre and post-treatment gliomas could reduce inter-rater variability and increase workflow efficiency for routine longitudinal radiographic assessment and treatment planning. We evaluated whether a 3D neural network is comparable to expert assessment of pre and post-treatment diffuse gliomas tissue types and resection cavities.

Methods

A retrospective cohort of 647 MRIs of patients with diffuse gliomas (average 55.1 years, 45% female, 396 pre-treatment and 251 post-treatment, median 237 days post-surgery) from The Cancer Imaging Archive were stratified by operation status and tumor grade and randomly split into training (536) and testing (111) samples. T1, T1-post-contrast, T2, and FLAIR images were registered, skull-stripped, and interpolated to 1x1x1. Four classes — edema/infiltrative/post-treatment changes (ED), enhancing tissue (ET), necrotic core (NCR), and resection cavities (RC) — were manually segmented by an expert neuroradiologist. Using these segmentations and the four input image modalities, a nnU-Net, a state-of-the-art 3D U-Net convolutional neural network, was trained to predict segmentations of the four classes.

Results

Segmentation performance in the test set for the ED, ET, and RC classes was at the level of inter-rater reliability with median Dice scores ranging from 0.85 to 1 and relative volume errors ranging from -0.05 to 0.02. There was a near-perfect correlation between manually segmented and predicted total lesion volumes (r2 values ranging from 0.95 to 0.98 among classes).

Conclusions

Accurate, automated volumetric quantification of diffuse glioma tissue volumes may improve response assessment in clinical trials and reduce provider burden and errors in measurement.

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