Deep Learning Based Attenuation Correction of PET/MRI in Pediatric Brain Tumor Patients: Evaluation in a Clinical Setting

Abstract

Aim: Positron emission tomography (PET) imaging is a useful tool for assisting in correct differentiation of tumor progression from reactive changes. O-(2-18F-fluoroethyl)-L-tyrosine (FET)-PET in combination with MRI can add valuable information for clinical decision making. Acquiring FET-PET/MRI simultaneously allows for a one-stop-shop that limits the need for a second sedation or anesthesia as with PET and MRI in sequence. PET/MRI is challenged by lack of a direct measure of photon attenuation. Accepted solutions for attenuation correction (AC) might not be applicable to pediatrics. The aim of this study was to evaluate the use of the subject-specific MR-derived AC method RESOLUTE, modified to a pediatric cohort, against the performance of an MR-AC technique based on deep learning in a pediatric brain tumor cohort.Methods: The modifications to RESOLUTE and the implementation of a deep learning method were performed using 79 pediatric patient examinations. We analyzed the 36 of these with active brain tumor area above 1 mL. We measured background (B), tumor mean and maximal activity (TMEAN, TMAX), biological tumor volume (BTV), and calculated the clinical metrics TMEAN/B and TMAX/B.Results: Overall, we found both RESOLUTE and our DeepUTE methodologies to accurately reproduce the CT-AC clinical metrics. Regardless of age, both methods were able to obtain AC maps similar to the CT-AC, albeit with DeepUTE producing the most similar based on both quantitative metrics and visual inspection. In the patient-by-patient analysis DeepUTE was the only technique with all patients inside the predefined acceptable clinical limits. It also had a higher precision with relative %-difference to the reference CT-AC (TMAX/B mean: -0.1%, CI: [-0.8%, 0.5%], p = 0.54) compared to RESOLUTE (TMAX/B mean: 0.3%, CI: [-0.6%, 1.2%], p = 0.67) and DIXON-AC (TMAX/B mean: 5.9%, CI: [4.5%, 7.4%], p < 0.0001).Conclusion: Overall, we found DeepUTE to be the AC method that most robustly reproduced the CT-AC clinical metrics per se, closely followed by RESOLUTE modified to pediatric cohorts. The added accuracy due to better noise handling of DeepUTE, ease of use, as well as the improved runtime makes DeepUTE the method of choice for PET/MRI attenuation correction.

Magnetic Resonance-Based Attenuation Correction and Scatter Correction in Neurological Positron Emission Tomography/Magnetic Resonance Imaging—Current Status With Emerging Applications

“…Similarly, a deep convolutional neural network that derived attenuation maps based on ZTE images was shown to outperform both ZTE and atlas-based method in Blanc-Durand et al [43]. Interestingly, while most evaluations have been performed with adults with normal anatomy, Ladefoged et al [103] evaluated deep learning methods in pediatric brain tumor patients, with robust performance. The preliminary results obtained with these methods are encouraging.…”

“…In regard to novel applications, a recent study showed the benefit of PET/MR in low activity imaging (14 MBq) of [ 15 O]-H2O PET for quantitative relative cerebral blood flow (rCBF) assessment in unsedated healthy newborn infants [209]. In this regard, applying and modifying existing MRAC methods to pediatric cohorts such as in Ladefoged et al [103] are encouraged.…”

Comparison of CBCT‐based dose calculation methods in head and neck cancer radiotherapy: from Hounsfield unit to density calibration curve to deep learning

“…[19][20][21][22][23][24][25] DLMs have been primarily proposed for pCT generation from magnetic resonance imaging (MRI). [26][27][28][29][30][31] They are particularly appealing owing to their fast computation time. One of the first DLMs for pCT generation was based on the U-Net architecture.…”

Brain Tumor Analysis Empowered with Deep Learning: A Review, Taxonomy, and Future Challenges

“…The Deep-UTE method produces more robust clinical metrics using CT-AC and overall patient survival time is increased. PET/MRIs' attenuation correction in the Deep-UTE method is reliable for brain tumor evaluation due to better noise handling capability and less runtime properties [81].…”