Abstract
The total metabolic tumor volume (TMTV) is a new prognostic factor in lymphomas that could benefit from automation with deep learning convolutional neural networks (CNN). Manual TMTV segmentations of 1218 baseline 18FDG-PET/CT have been used for training. A 3D V-NET model has been trained to generate segmentations with soft dice loss. Ground truth segmentation has been generated using a combination of different thresholds (TMTVprob), applied to the manual region of interest (Otsu, relative 41% and SUV 2.5 and 4 cutoffs). In total, 407 and 405 PET/CT were used for test and validation datasets, respectively. The training was completed in 93 h. In comparison with the TMTVprob, mean dice reached 0.84 in the training set, 0.84 in the validation set and 0.76 in the test set. The median dice scores for each TMTV methodology were 0.77, 0.70 and 0.90 for 41%, 2.5 and 4 cutoff, respectively. Differences in the median TMTV between manual and predicted TMTV were 32, 147 and 5 mL. Spearman’s correlations between manual and predicted TMTV were 0.92, 0.95 and 0.98. This generic deep learning model to compute TMTV in lymphomas can drastically reduce computation time of TMTV.
Highlights
The total metabolic tumor volume (TMTV) has recently been proposed as a tumor burden quantification method in various lymphoma subtypes, especially in Hodgkin lymphoma (HL) [1,2], diffuse large B cell lymphoma (DLBCL) [3] and follicular lymphoma (FL) [4]
PET/CT quality was checked for slice interval regularity and axial slice completeness, and attenuation-corrected PET/CT images were converted into standardized uptake value (SUV) units
We have shown a very strong correlation for each segmentation methodology (>0.9) and a relatively acceptable difference in median TMTV (CNN vs. manual)
Summary
The total metabolic tumor volume (TMTV) has recently been proposed as a tumor burden quantification method in various lymphoma subtypes, especially in Hodgkin lymphoma (HL) [1,2], diffuse large B cell lymphoma (DLBCL) [3] and follicular lymphoma (FL) [4] This evaluation requires whole-body segmentation of the tumor mass on the baseline 18FDG PET/CT imaging. To make TMTV acceptable in routine clinical practice, a high level of automation is needed to reduce the calculation time and to enhance the interobserver reproducibility Such automatization approaches have been proposed using a large range of algorithms, and more recently, using deep learning segmentation algorithms [5,6,7]. These CNN approaches can exploit numbers of imaging features to distinguish tumoral uptakes from physiological uptakes such as brain, kidney or brown fat uptakes, which are common pitfalls in segmentation automation
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.