A deep learning model for distinguishing pseudoprogression and tumor progression in glioblastoma based on pre- and post-operative contrast-enhanced T1 imaging.
Authors
Affiliations (5)
Affiliations (5)
- Department of Blood Transfusion, Key Laboratory of Cancer Prevention and Therapy in Tianjin, National Clinical Research Center for Cancer, Tianjin's Clinical Research Center for Cancer, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, Tianjin 300060, China.
- School of Microelectronics, Tianjin University, Tianjin 300060, China.
- Department of Epidemiology and Biostatistics, Key Laboratory of Molecular Cancer Epidemiology, Key Laboratory of Prevention and Control of Human Major Diseases, Ministry of Education, National Clinical Research Center for Cancer, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, Tianjin 300060, China.
- Department of Neurosurgery and Neuro-oncology, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Clinical Research Center for Cancer, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, Tianjin 300060, China.
- Department of Molecular Imaging and Nuclear Medicine, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Clinical Research Center for Cancer, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, Tianjin 300060, China. Electronic address: [email protected].
Abstract
Accurately predicting pseudoprogression (PsP) from tumor progression (TuP) in patients with glioblastoma (GBM) is crucial for treatment and prognosis. This study develops a deep learning (DL) prognostic model using pre- and post-operative contrast-enhanced T1-weighted (CET1) magnetic resonance imaging (MRI) to forecast the likelihood of PsP or TuP following standard GBM treatment. Brain MRI data and clinical characteristics from 110 GBM patients were divided into a training set (n = 68) and a validation set (n = 42). Pre-operative and post-operative CET1 images were used individually and combined. A Vision Transformer (ViT) model was built using expert-segmented tumor images to extract DL features. Several mainstream convolutional neural network (CNN) models (DenseNet121, Inception_v3, MobileNet_v2, ResNet18, ResNet50, and VGG16) were built for comparative evaluation. Principal Component Analysis (PCA) and Least Absolute Shrinkage and Selection Operator (LASSO) regression selected the significant features, classified using a Multi-Layer Perceptron (MLP). Model performance was evaluated with Receiver Operating Characteristic (ROC) curves. A multimodal model also incorporated DL features and clinical characteristics. The optimal input for predicting TuP versus PsP was the combination of pre- and post-operative CET1 tumor regions. The CET1-ViT model achieved an area under the curve (AUC) of 95.5% and accuracy of 90.7% on the training set, and an AUC of 95.2% and accuracy of 96.7% on the validation set. This model outperformed the mainstream CNN models. The multimodal model showed superior performance, with AUCs of 98.6% and 99.3% on the training and validation sets, respectively. We developed a DL model based on pre- and post-operative CET1 imaging that can effectively forecast PsP versus TuP in GBM patients, offering potential for evaluating treatment responses and early indications of tumor progression.