Abstract
PurposeGlioma is the most common primary brain tumor, with varying degrees of aggressiveness and prognosis. Accurate glioma classification is very important for treatment planning and prognosis prediction. The main purpose of this study is to design a novel effective algorithm for further improving the performance of glioma subtype classification using multimodal MRI images.MethodMRI images of four modalities for 221 glioma patients were collected from Computational Precision Medicine: Radiology-Pathology 2020 challenge, including T1, T2, T1ce, and fluid-attenuated inversion recovery (FLAIR) MRI images, to classify astrocytoma, oligodendroglioma, and glioblastoma. We proposed a multimodal MRI image decision fusion-based network for improving the glioma classification accuracy. First, the MRI images of each modality were input into a pre-trained tumor segmentation model to delineate the regions of tumor lesions. Then, the whole tumor regions were centrally clipped from original MRI images followed by max–min normalization. Subsequently, a deep learning-based network was designed based on a unified DenseNet structure, which extracts features through a series of dense blocks. After that, two fully connected layers were used to map the features into three glioma subtypes. During the training stage, we used the images of each modality after tumor segmentation to train the network to obtain its best accuracy on our testing set. During the inferring stage, a linear weighted module based on a decision fusion strategy was applied to assemble the predicted probabilities of the pre-trained models obtained in the training stage. Finally, the performance of our method was evaluated in terms of accuracy, area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), etc.ResultsThe proposed method achieved an accuracy of 0.878, an AUC of 0.902, a sensitivity of 0.772, a specificity of 0.930, a PPV of 0.862, an NPV of 0.949, and a Cohen’s Kappa of 0.773, which showed a significantly higher performance than existing state-of-the-art methods.ConclusionCompared with current studies, this study demonstrated the effectiveness and superiority in the overall performance of our proposed multimodal MRI image decision fusion-based network method for glioma subtype classification, which would be of enormous potential value in clinical practice.
Highlights
Glioma is the most common primary tumor of the brain and spine, representing 80% of malignant brain tumors [1] and having varying degrees of aggressiveness and prognosis
Xue et al [24] trained a 3D residual convolutional network with MRI images for glioma classification, and the results showed that using tumor segmentation regions would get higher accuracy
We found that the prediction performance for each modality among different validation folds was not significantly different, which validates that the dataset selection has no significant influence on the prediction performance of our method
Summary
Glioma is the most common primary tumor of the brain and spine, representing 80% of malignant brain tumors [1] and having varying degrees of aggressiveness and prognosis. Low-grade glioma is welldifferentiated and presents an aggressive growth pattern in terms of biological characteristics, whereas high-grade glioma is a malignant brain tumor that is difficult to identify and has a poor prognosis [3]. MRI is the standard medical imaging technique for brain tumor diagnosis for its advantages of relative safety and noninvasiveness as compared to pathological biopsy examinations [6]. The low contrast between tumor masses and surrounding tissues as well as the varying levels of physicians’ experience may lead to misdiagnosis; more importantly, diagnosing based on manual analysis is a time-consuming procedure [7]. With the development of artificial intelligence and computing facilities, computer-aided diagnosis (CAD) technology based on computer vision has been applied to many medical fields and provides help for physicians in visualization and tumor identification to improve the subjective diagnosis manually [8]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.