Three-step-guided visual prediction of glioblastoma recurrence from multimodality images.

Comput Med Imaging Graph

The School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China. Electronic address:

Published: September 2025


Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

Accurately predicting glioblastoma (GBM) recurrence is crucial for guiding the planning of target areas in subsequent radiotherapy and radiosurgery for glioma patients. Current prediction methods can determine the likelihood and type of recurrence but cannot identify the specific region or visually display location of the recurrence. To efficiently and accurately predict the recurrence of GBM, we proposed a three-step-guided prediction method consisting of feature extraction and segmentation (FES), radiomics analysis, and tag constraints to narrow the predicted region of GBM recurrence and standardize the shape of GBM recurrence prediction. Particularly in FES we developed an adaptive fusion module and a modality fusion module to fuse feature maps from different modalities. In the modality fusion module proposed, we designed different convolution modules (Conv-D and Conv-P) specifically for diffusion tensor imaging (DTI) and Positron Emission Computed Tomography (PET) images to extract recurrence-related features. Additionally, model fusion is proposed in the stable diffusion training process to learn and integrate the individual and typical properties of the recurrent tumors from different patients. Contrasted with existing segmentation and generation methods, our three-step-guided prediction method improves the ability to predict distant recurrence of GBM, achieving a 28.93 Fréchet Inception Distance (FID), and a 0.9113 Dice Similarity Coefficient (DSC). Quantitative results demonstrate the effectiveness of the proposed method in predicting the recurrence of GBM with the type and location. To the best of our knowledge, this is the first study combines the stable diffusion and multimodal images fusion with PET and DTI from different institutions to predict both distant and local recurrence of GBM in the form of images.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.compmedimag.2025.102585DOI Listing

Publication Analysis

Top Keywords

recurrence gbm
16
gbm recurrence
12
fusion module
12
recurrence
10
three-step-guided prediction
8
prediction method
8
modality fusion
8
stable diffusion
8
predict distant
8
gbm
7

Similar Publications

Preventing Glioblastoma Relapse by Igniting Innate Immunity through Mitochondrial Stress in the Surgical Cavity.

Adv Mater

September 2025

Department of Neurosurgery, Qilu Hospital and Shandong Key Laboratory of Brain Health and Function Remodeling, Institute of Brain and Brain-Inspired Science, Jinan Microecological Biomedicine Shandong Laboratory, Cheeloo College of Medicine, Shandong University, 107 Wenhua Xi Road, Jinan, Shandong,

Innate immunity is crucial in orchestrating the brain immune response, however, glioblastoma multiforme (GBM) has evolved sophisticated mechanisms to evade innate immune surveillance, posing significant challenges for current immunotherapies. Here, a therapeutic strategy is reported that aims at reactivating innate immune responses in GBM via targeted induction of mitochondrial stress, thereby enhancing tumor immunogenicity. Specifically, innate immune-stimulating nanoparticles (INSTNA) are developed, encapsulating positively charged iridium-based complexes (Ir-mito) and small interfering RNA against Methylation-Controlled J protein (si-MCJ) to attenuate mitochondrial respiration.

View Article and Find Full Text PDF

Background: Neoantigen-based vaccines show promising therapeutic potential in solid tumors such as melanoma, GBM, NSCLC, and CRC. However, clinical responses remain suboptimal in stage IV patients, due to ineffective T-cell function and high tumor burdens. To overcome these limitations, our study investigates a combination strategy using neoantigen peptide vaccines and precision critical lesion radiotherapy (CLERT), which delivers immunomodulatory doses to key tumor regions synergistically enhance immune activation and inhibit progression in multifocal stage IV patients.

View Article and Find Full Text PDF

Comparative efficacy and safety of therapeutic strategies for EGFRvIII positive recurrent glioblastoma.

iScience

September 2025

Beijing Institute of Brain Disorders, Laboratory of Brain Disorders, Ministry of Science and Technology, Collaborative Innovation Center for Brain Disorders, Capital Medical University, No.10 Xitoutiao You'anmenwai Fengtai District, Beijing 100069, P.R. China.

Glioblastoma multiforme (GBM) is the most aggressive primary brain tumor, and EGFRvIII mutation has been associated with treatment resistance and poor prognosis, highlighting the need for more effective therapeutic strategies. We conducted a random-effects Bayesian network meta-analysis to compare the efficacy and safety of treatments for EGFRvIII-positive recurrent GBM (rGBM), evaluating overall survival (OS), progression-free survival (PFS), and objective response rate (ORR). Seven clinical trials were included ( = 716).

View Article and Find Full Text PDF

Novel Thioredoxin reductase 1 inhibitor BS1801 relieves treatment resistance and triggers endoplasmic reticulum stress by elevating reactive oxygen species in glioma.

Redox Biol

August 2025

Department of Molecular Neuropathology, Beijing Neurosurgical Institute, Capital Medical University, No.119 South 4th Ring Road West, Beijing, China; Chinese Glioma Genome Atlas Network (CGGA) and Asian Glioma Genome Atlas Network (AGGA), Beijing, China; Beijing Engineering Research Center of Target

Glioma patients will inevitably develop resistance to temozolomide (TMZ) leading to tumor recurrence. By comparing genomic differences between primary and recurrent glioma patients, Thioredoxin reductase 1 (TrxR1) was identified as a crucial role in TMZ resistance. Glioma cells elevate the expression level of TXNRD1 to against TMZ-induced reactive oxygen species (ROS), thereby conferring TMZ resistance.

View Article and Find Full Text PDF

Purpose: Because of tumor heterogeneity and sampling error, next-generation sequencing (NGS) of glioblastoma (GBM) tumors may provide an incomplete picture of the somatic mutational landscape. We hypothesized that simultaneous targeted NGS of matched tumor tissue and cerebrospinal fluid (CSF), obtained during craniotomy for resection of GBM, would lead to identification of clinically relevant variants not detected by tissue NGS alone.

Methods: We enrolled 50 patients undergoing resection of newly diagnosed (n = 15) or recurrent (n = 35) GBM.

View Article and Find Full Text PDF