A Fully Automated Post-Surgical Brain Tumor Segmentation Model for Radiation Treatment Planning and Longitudinal Tracking

Abstract

Glioblastoma (GBM) has a poor survival rate even with aggressive surgery, concomitant radiation therapy (RT), and adjuvant chemotherapy. Standard-of-care RT involves irradiating a lower dose to the hyperintense lesion in T2-weighted fluid-attenuated inversion recovery MRI (T2w/FLAIR) and a higher dose to the enhancing tumor on contrast-enhanced, T1-weighted MRI (CE-T1w). While there have been several attempts to segment pre-surgical brain tumors, there have been minimal efforts to segment post-surgical tumors, which are complicated by a resection cavity and postoperative blood products, and tools are needed to assist physicians in generating treatment contours and assessing treated patients on follow up. This report is one of the first to train and test multiple deep learning models for the purpose of post-surgical brain tumor segmentation for RT planning and longitudinal tracking. Post-surgical FLAIR and CE-T1w MRIs, as well as their corresponding RT targets (GTV1 and GTV2, respectively) from 225 GBM patients treated with standard RT were trained on multiple deep learning models including: Unet, ResUnet, Swin-Unet, 3D Unet, and Swin-UNETR. These models were tested on an independent dataset of 30 GBM patients with the Dice metric used to evaluate segmentation accuracy. Finally, the best-performing segmentation model was integrated into our longitudinal tracking web application to assign automated structured reporting scores using change in percent cutoffs of lesion volume. The 3D Unet was our best-performing model with mean Dice scores of 0.72 for GTV1 and 0.73 for GTV2 with a standard deviation of 0.17 for both in the test dataset. We have successfully developed a lightweight post-surgical segmentation model for RT planning and longitudinal tracking.

Improving the Generalizability of Deep Learning for T2-Lesion Segmentation of Gliomas in the Post-Treatment Setting

“…This study sheds light on the dichotomy between typical training sets utilized and utility for clinical implementation, offers insight into effectively leveraging the widespread availability of pre-treatment data with smaller amounts of post-treatment data, and demonstrates the benefit of incorporating relatively simple but effective modifications to training strategies to tailor T2-lesion segmentation of gliomas to effectively monitor response to treatment. Overall, our model achieved a performance that was on par with results from similar deep learning-based studies of segmenting gliomas post-treatment as shown in Table 4, while using a single MR contrast and minimal processing [10,[66][67][68][75][76][77][78].…”

“…The utility of deep learning models used in monitoring longitudinal tumor progression and treatment response [10,11] is directly dependent on the accuracy of these models to perform well on treated gliomas. Although a few more recent studies have achieved equivalent performance in segmenting treated gliomas [66][67][68][69], they still either require multiple (4) image contrasts as input to segment multiple tumor compartments simultaneously, necessitate multiple image preprocessing steps (i.e., co-registration/skull stripping), use very few post-operative patients for training and testing, neglect edema and infiltration seen on T2-weighted images, or report low Dice scores (<0.65).…”

Brain Tumor Detection Based on Deep Learning Approaches and Magnetic Resonance Imaging

“…In recent research, Ramesh et al [ 94 ] embarked on a pioneering endeavor, in which they developed multiple deep learning models designed for post-surgical brain tumor segmentation, tailored explicitly for radiation treatment planning and longitudinal tracking. Leveraging imaging data from an anonymized repository encompassing 225 glioblastoma multiforme (GBM) patients who underwent intensity-modulated radiation therapy at Emory University over the past decade, the segmentation model was carefully trained.…”