TY - JOUR T1 - Evaluation of Deep Learning-based Approaches to Segment Bowel Air Pockets and Generate Pelvis Attenuation Maps from CAIPIRINHA-accelerated Dixon MR Images JF - Journal of Nuclear Medicine JO - J Nucl Med DO - 10.2967/jnumed.120.261032 SP - jnumed.120.261032 AU - Hasan Sari AU - Ja Reaungamornrat AU - Onofrio Catalano AU - Javier Vera-Olmos AU - David Izquierdo-Garcia AU - Manuel Antonio Morales AU - Angel Torrado-Carvajal AU - Sheung Chee Thomas Ng AU - Norberto Malpica AU - Ali Kamen AU - Ciprian Catana Y1 - 2021/07/01 UR - http://jnm.snmjournals.org/content/early/2021/07/22/jnumed.120.261032.abstract N2 - Attenuation correction (AC) remains a challenge in pelvis PET/MR imaging. In addition to the segmentation/model-based approaches, deep learning methods have shown promise in synthesizing accurate pelvis attenuation maps (μ-maps). However, these methods often misclassify air pockets in the digestive tract, which can introduce bias in the reconstructed PET images. The aims of this work were to develop deep learning-based methods to automatically segment air pockets and generate pseudo-CT images from CAIPIRINHA-accelerated MR Dixon images. Methods: A convolutional neural network (CNN) was trained to segment air pockets using 3D CAIPIRINHA-accelerated MR Dixon datasets from 35 subjects and was evaluated against semi-automated segmentations. A separate CNN was trained to synthesize pseudo-CT μ-maps from the Dixon images. Its accuracy was evaluated by comparing the deep learning-, model- and CT-based μ-maps using data from 30 of the subjects. Finally, the impact of different μ-maps and air pocket segmentation methods on the PET quantification was investigated. Results: Air pockets segmented using the CNN agreed well with semi-automated segmentations, with a mean Dice similarity coefficient of 0.75. Volumetric similarity score between two segmentations was 0.85 ± 0.14. The mean absolute relative change (RCs) with respect to the CT-based μ-maps were 2.6% and 5.1% in the whole pelvis for the deep learning and model-based μ-maps, respectively. The average RC between PET images reconstructed with deep learning and CT-based μ-maps was 2.6%. Conclusion: We presented a deep learning-based method to automatically segment air pockets from CAIPIRINHA-accelerated Dixon images with comparable accuracy to semi-automatic segmentations. We also showed that the μ-maps synthesized using a deep learning-based method from CAIPIRINHA-accelerated Dixon images are more accurate than those generated with the model-based approach available on integrated PET/MRI scanner. ER -