View in EDS

Predicting intraoperative 5-ALA-induced tumor fluorescence via MRI and deep learning in gliomas with radiographic lower-grade characteristics

Saved in:
Bibliographic Details
Title: Predicting intraoperative 5-ALA-induced tumor fluorescence via MRI and deep learning in gliomas with radiographic lower-grade characteristics
Authors: Suero Molina, Eric, Azemi, Ghasem, Özdemir, Zeynep, Russo, Carlo, Krähling, Hermann, Valls Chavarria, Alexandra, Liu, Sidong, Stummer, Walter, Di Ieva, Antonio
Source: J Neurooncol
Publisher Information: Springer Science and Business Media LLC, 2024.
Publication Year: 2024
Subject Terms: Glioma/surgery [MeSH], Neoplasm Grading [MeSH], Aged [MeSH], Deep Learning [MeSH], Brain Neoplasms/surgery [MeSH], 5-ALA, Glioma/diagnostic imaging [MeSH], Autoencoder, Glioma/pathology [MeSH], Male [MeSH], Deep learning, Female [MeSH], Fluorescence [MeSH], Adult [MeSH], Humans [MeSH], Retrospective Studies [MeSH], Middle Aged [MeSH], Aminolevulinic Acid/administration, Lower-grade gliomas, Fluorescence-guided resection, Photosensitizing Agents/administration, Research, Magnetic Resonance Imaging/methods [MeSH], Brain Neoplasms/diagnostic imaging [MeSH], Brain Neoplasms/pathology [MeSH], 03 medical and health sciences, 0302 clinical medicine
Description: Purpose 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 sampled to avoid undergrading. We aimed to analyze whether a deep learning model could predict intraoperative fluorescence based on preoperative magnetic resonance imaging (MRI). Methods We evaluated a cohort of 163 glioma patients categorized intraoperatively as fluorescent (n = 83) or non-fluorescent (n = 80). The preoperative MR images of gliomas lacking high-grade characteristics (e.g., necrosis or irregular ring contrast-enhancement) 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 tenfold cross-validation procedure. Results Our proposed approach's performance was assessed using 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. Conclusions Our findings highlight the potential of a U-Net model, coupled with a Random Forest classifier, for pre-operative prediction of intraoperative fluorescence. We achieved high accuracy using the features extracted by the U-Net model pre-trained for brain tumor segmentation. 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. Graphical abstract
Document Type: Article
Other literature type
Language: English
ISSN: 1573-7373
0167-594X
DOI: 10.1007/s11060-024-04875-0
Access URL: https://pubmed.ncbi.nlm.nih.gov/39560696
https://repository.publisso.de/resource/frl:6498279
Rights: CC BY
Accession Number: edsair.doi.dedup.....544ac007daadad6c5e6b940202448c50
Database: OpenAIRE
Description
Abstract:Purpose 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 sampled to avoid undergrading. We aimed to analyze whether a deep learning model could predict intraoperative fluorescence based on preoperative magnetic resonance imaging (MRI). Methods We evaluated a cohort of 163 glioma patients categorized intraoperatively as fluorescent (n = 83) or non-fluorescent (n = 80). The preoperative MR images of gliomas lacking high-grade characteristics (e.g., necrosis or irregular ring contrast-enhancement) 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 tenfold cross-validation procedure. Results Our proposed approach's performance was assessed using 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. Conclusions Our findings highlight the potential of a U-Net model, coupled with a Random Forest classifier, for pre-operative prediction of intraoperative fluorescence. We achieved high accuracy using the features extracted by the U-Net model pre-trained for brain tumor segmentation. 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. Graphical abstract
ISSN:15737373
0167594X
DOI:10.1007/s11060-024-04875-0