ETISTP: An Enhanced Model for Brain Tumor Identification and Survival Time Prediction

Abstract

Technology-assisted diagnosis is increasingly important in healthcare systems. Brain tumors are a leading cause of death worldwide, and treatment plans rely heavily on accurate survival predictions. Gliomas, a type of brain tumor, have particularly high mortality rates and can be further classified as low- or high-grade, making survival prediction challenging. Existing literature provides several survival prediction models that use different parameters, such as patient age, gross total resection status, tumor size, or tumor grade. However, accuracy is often lacking in these models. The use of tumor volume instead of size may improve the accuracy of survival prediction. In response to this need, we propose a novel model, the enhanced brain tumor identification and survival time prediction (ETISTP), which computes tumor volume, classifies it into low- or high-grade glioma, and predicts survival time with greater accuracy. The ETISTP model integrates four parameters: patient age, survival days, gross total resection (GTR) status, and tumor volume. Notably, ETISTP is the first model to employ tumor volume for prediction. Furthermore, our model minimizes the computation time by allowing for parallel execution of tumor volume computation and classification. The simulation results demonstrate that ETISTP outperforms prominent survival prediction models.

Brain tumor segmentation and survival time prediction using graph momentum fully convolutional network with modified Elman spike neural network

“…In 2023, Hussain et al 37 had implemented a enhanced BT identification and survival time prediction (EBTISTP), it calculates the volume of tumor, divides it into high or low‐grade glioma, which provides the overall survival (OS) period. The only drawback was dependence on high‐quality MRIs.…”

Survival Prediction of Patients after Heart Attack and Breast Cancer Surgery with a Hybrid Model Built with Particle Swarm Optimization, Stacked AutoEncoders, and the Softmax Classifier

“…Hussain et al [5] proposed a model to predict the survival time of patients with brain tumors. This model was the first model to consider the volume of brain tumor in survival time calculation.…”

Advances in the Use of Deep Learning for the Analysis of Magnetic Resonance Image in Neuro-Oncology

“…Although brain MRIs inherently capture 3D data, a notable observation is that over 80% of the studies conducted their analyses within a 2D domain, focusing on 2D MRI slices. Nonetheless, some investigations have actively explored the significance of incorporating 3D volumetric information into the realm of brain tumor classification [56,58,59,74,97,98,100,112,117,[129][130][131][132]135,[140][141][142][143][144][145][146][147][148]. Although 3D volumes inherently capture information from the three anatomical planes, 2D slices are restricted to a specific view.…”

“…To further enhance the classification performance, they incorporated information from each source using an aggregation layer within the network architecture. Subsequently, similar ensemble learning approaches were adopted by Gutta et al [106], Hussain et al [148], Rui et al [149]. Notably, Guo et al [150] directly compared the performance of a modality-fusion approach, where the four MRI modalities were concatenated as a four-channel input, with a decision-fusion approach, where final predictions were derived through a linear weighted sum from the probabilities obtained through four independent pre-trained unimodal models.…”