Suero Molina Eric, Tabassum Mehnaz, Azemi Ghasem, Özdemir Zeynep, Roll Wolfgang, Backhaus Philipp, Schindler Philipp, Valls Chavarria Alex, Russo Carlo, Liu Sidong, Stummer Walter, Di Ieva Antonio
Macquarie Neurosurgery & Spine, Macquarie University Hospital, Sydney, NSW, Australia.
Computational NeuroSurgery (CNS) Lab, Macquarie Medical School, Macquarie University, Sydney, NSW, Australia.
Neurooncol Adv. 2025 Jan 16;7(1):vdaf001. doi: 10.1093/noajnl/vdaf001. eCollection 2025 Jan-Dec.
Limited amino acid availability for positron emission tomography (PET) imaging hinders therapeutic decision-making for gliomas without typical high-grade imaging features. To address this gap, we evaluated a generative artificial intelligence (AI) approach for creating synthetic O-(2-F-fluoroethyl)-l-tyrosine ([F]FET)-PET and predicting high [F]FET uptake from magnetic resonance imaging (MRI).
We trained a deep learning (DL)-based model to segment tumors in MRI, extracted radiomic features using the Python PyRadiomics package, and utilized a Random Forest classifier to predict high [F]FET uptake. To generate [F]FET-PET images, we employed a generative adversarial network framework and utilized a split-input fusion module for processing different MRI sequences through feature extraction, concatenation, and self-attention.
We included magnetic resonance imaging (MRI) and PET images from 215 studies for the hotspot classification and 211 studies for the synthetic PET generation task. The top-performing radiomic features achieved 80% accuracy for hotspot prediction. From the synthetic [F]FET-PET, 85% were classified as clinically useful by senior physicians. Peak signal-to-noise ratio analysis indicated high signal fidelity with a peak at 40 dB, while structural similarity index values showed structural congruence. Root mean square error analysis demonstrated lower values below 5.6. Most visual information fidelity scores ranged between 0.6 and 0.7. This indicates that synthetic PET images retain the essential information required for clinical assessment and diagnosis.
For the first time, we demonstrate that predicting high [F]FET uptake and generating synthetic PET images from preoperative MRI in lower-grade and high-grade glioma are feasible. Advanced MRI modalities and other generative AI models will be used to improve the algorithm further in future studies.
正电子发射断层扫描（PET）成像中有限的氨基酸可用性阻碍了对没有典型高级别成像特征的胶质瘤进行治疗决策。为了弥补这一差距，我们评估了一种生成式人工智能（AI）方法，用于创建合成的O-(2-氟乙基)-L-酪氨酸（[F]FET）-PET，并从磁共振成像（MRI）预测高[F]FET摄取。
我们训练了一个基于深度学习（DL）的模型来分割MRI中的肿瘤，使用Python的PyRadiomics包提取放射组学特征，并利用随机森林分类器预测高[F]FET摄取。为了生成[F]FET-PET图像，我们采用了生成对抗网络框架，并利用一个分割输入融合模块通过特征提取、拼接和自注意力来处理不同的MRI序列。
我们纳入了215项研究的磁共振成像（MRI）和PET图像用于热点分类，以及211项研究用于合成PET生成任务。表现最佳的放射组学特征在热点预测中达到了80%的准确率。对于合成的[F]FET-PET，85%被高级医师分类为具有临床实用性。峰值信噪比分析表明信号保真度高，峰值为40 dB，而结构相似性指数值显示结构一致性。均方根误差分析表明值低于5.6。大多数视觉信息保真度分数在0.6至0.7之间。这表明合成PET图像保留了临床评估和诊断所需的基本信息。
我们首次证明，在低级别和高级别胶质瘤中，从术前MRI预测高[F]FET摄取并生成合成PET图像是可行的。未来的研究将使用先进的MRI模态和其他生成式AI模型进一步改进该算法。
