Ensembles of Convolutional Neural Networks for Survival Time Estimation of High-Grade Glioma Patients from Multimodal MRI.
Kaoutar Ben AhmedLawrence O HallDmitry B GoldgofRobert GatenbyPublished in: Diagnostics (Basel, Switzerland) (2022)
Glioma is the most common type of primary malignant brain tumor. Accurate survival time prediction for glioma patients may positively impact treatment planning. In this paper, we develop an automatic survival time prediction tool for glioblastoma patients along with an effective solution to the limited availability of annotated medical imaging datasets. Ensembles of snapshots of three dimensional (3D) deep convolutional neural networks (CNN) are applied to Magnetic Resonance Image (MRI) data to predict survival time of high-grade glioma patients. Additionally, multi-sequence MRI images were used to enhance survival prediction performance. A novel way to leverage the potential of ensembles to overcome the limitation of labeled medical image availability is shown. This new classification method separates glioblastoma patients into long- and short-term survivors. The BraTS (Brain Tumor Image Segmentation) 2019 training dataset was used in this work. Each patient case consisted of three MRI sequences (T1CE, T2, and FLAIR). Our training set contained 163 cases while the test set included 46 cases. The best known prediction accuracy of 74% for this type of problem was achieved on the unseen test set.
Keyphrases
- end stage renal disease
- deep learning
- convolutional neural network
- magnetic resonance
- ejection fraction
- newly diagnosed
- chronic kidney disease
- high grade
- magnetic resonance imaging
- prognostic factors
- peritoneal dialysis
- machine learning
- patient reported outcomes
- contrast enhanced
- young adults
- high resolution
- computed tomography
- low grade
- big data
- case report
- risk assessment
- positron emission tomography