Fig. 2From: Deep learning for Dixon MRI-based attenuation correction in PET/MRI of head and neck cancer patientsJoint histograms of PET voxels within the patient volumes for (A) PETDeep and PETCT (R2 = 0.997), and (B) PETAtlas and PETCT (R2 = 0.975). Notice, that the axes are clamped to SUV of 5 even though there are higher values in the PET imagesBack to article page