P10.22.B PREDICTING INTRAOPERATIVE 5-ALA-INDUCED TUMOR FLUORESCENCE VIA MRI AND DEEP LEARNING IN GLIOMAS WITH RADIOGRAPHIC LOWER-GRADE CHARACTERISTICS

Abstract BACKGROUND Lower-grade gliomas typically exhibit 5-aminolevulinic acid (5-ALA)-induced fluorescence in only 20-30% of cases, a rate that can be increased by doubling the administered dose of 5-ALA. Fluorescence can depict anaplastic foci, which can be precisely resected to avoid undergrading. We aimed to analyze whether a deep learning model can predict intraoperative fluorescence based on preoperative magnetic resonance imaging (MRI). Material and Methods: The MRI images of gliomas lacking high-grade characteristics (necrosis, extended contrast-enhancement, a.o.) consisted of T1, T1-post gadolinium, and FLAIR sequences. The preprocessed MRIs were fed into an encoder-decoder convolutional neural network (U-Net), pre-trained for tumor segmentation using those three MRI sequences. We used the outputs of the bottleneck layer of the U-Net in the Variational Autoencoder (VAE) as features for classification. We identified and utilized the most effective features in a Random Forest classifier using the principal component analysis (PCA) and the partial least square discriminant analysis (PLS-DA) algorithms. We evaluated the performance of the classifier using a 10-fold cross-validation procedure. RESULTS We evaluated a cohort of 163 glioma patients categorized as fluorescent (n=83) or non-fluorescent (n=80). Our proposed approach’s performance was evaluated using metrics such as mean balanced accuracy, mean sensitivity, and mean specificity. The optimal results were obtained by employing top-performing features selected by PCA, resulting in a mean balanced accuracy of 80% and mean sensitivity and specificity of 84% and 76%, respectively. CONCLUSION Our findings highlight the potential of a U-Net model, coupled with a random forest classifier, for intraoperative fluorescence prediction. We achieved good accuracy using advanced techniques such as deep learning-based tumor segmentation and Variational Autoencoder for radiomics feature extraction. While the model can still be improved, it has the potential for evaluating when to administer 5-ALA to gliomas lacking typical high-grade radiographic features.