Abstract
BackgroundThe radiological differential diagnosis between tumor recurrence and radiation-induced necrosis (ie, pseudoprogression) is of paramount importance in the management of glioma patients.ObjectiveThis research aims to develop a deep learning methodology for automated differentiation of tumor recurrence from radiation necrosis based on routine magnetic resonance imaging (MRI) scans.MethodsIn this retrospective study, 146 patients who underwent radiation therapy after glioma resection and presented with suspected recurrent lesions at the follow-up MRI examination were selected for analysis. Routine MRI scans were acquired from each patient, including T1, T2, and gadolinium-contrast-enhanced T1 sequences. Of those cases, 96 (65.8%) were confirmed as glioma recurrence on postsurgical pathological examination, while 50 (34.2%) were diagnosed as necrosis. A light-weighted deep neural network (DNN) (ie, efficient radionecrosis neural network [ERN-Net]) was proposed to learn radiological features of gliomas and necrosis from MRI scans. Sensitivity, specificity, accuracy, and area under the curve (AUC) were used to evaluate performance of the model in both image-wise and subject-wise classifications. Preoperative diagnostic performance of the model was also compared to that of the state-of-the-art DNN models and five experienced neurosurgeons.ResultsDNN models based on multimodal MRI outperformed single-modal models. ERN-Net achieved the highest AUC in both image-wise (0.915) and subject-wise (0.958) classification tasks. The evaluated DNN models achieved an average sensitivity of 0.947 (SD 0.033), specificity of 0.817 (SD 0.075), and accuracy of 0.903 (SD 0.026), which were significantly better than the tested neurosurgeons (P=.02 in sensitivity and P<.001 in specificity and accuracy).ConclusionsDeep learning offers a useful computational tool for the differential diagnosis between recurrent gliomas and necrosis. The proposed ERN-Net model, a simple and effective DNN model, achieved excellent performance on routine MRI scans and showed a high clinical applicability.
Highlights
Brain radiation necrosis can be a consequence of radiation therapy, which is used for the treatment of brain tumors, with an incidence of 3%-24% [1,2,3,4]
For feature learning and classification, we proposed a light-weighted deep neural network (DNN) model to learn radiological features of gliomas and necrosis from magnetic resonance imaging (MRI) scans
Principal Findings To the best of our knowledge, this is the first research on the application of DNN models to routine MRI scans for the purposes of automated differentiation between radiation necrosis and recurrent tumors
Summary
Brain radiation necrosis (ie, pseudoprogression) can be a consequence of radiation therapy, which is used for the treatment of brain tumors, with an incidence of 3%-24% [1,2,3,4]. It is of paramount importance to distinguish radiation necrosis from tumor recurrence, as these two pathologies share similar appearances in neuroimaging yet have different treatments and outcomes [5,6]. Recent studies demonstrate that radiologists may not be able to systematically identify differences in the highly variable appearances of brain tumors and radionecrosis, handcrafted features extracted from routine magnetic resonance imaging (MRI) can effectively differentiate these two conditions [14,15,16]. The first limitation is that all these methods require manual segmentation of the lesion (ie, drawing regions of interest [ROIs] of the lesion on T1-weighted MRI [T1], gadolinium-contrast-enhanced T1 [T1c], and/or T2-weighted MRI [T2]/fluid-attenuated inversion recovery [FLAIR]), from which the texture or shape features can be extracted [17]. The radiological differential diagnosis between tumor recurrence and radiation-induced necrosis (ie, pseudoprogression) is of paramount importance in the management of glioma patients
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
