Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Feb 6;12(2):417.
doi: 10.3390/diagnostics12020417.

Deep Learning Approach to Automatize TMTV Calculations Regardless of Segmentation Methodology for Major FDG-Avid Lymphomas

Wendy Revailler  1   2 , Anne Ségolène Cottereau  3 , Cedric Rossi  4 , Rudy Noyelle  5 , Thomas Trouillard  1   2 , Franck Morschhauser  6 , Olivier Casasnovas  4 , Catherine Thieblemont  7 , Steven Le Gouill  8 , Marc André  9 , Herve Ghesquieres  10 , Romain Ricci  11 , Michel Meignan  12 , Salim Kanoun  1   2
Affiliations

Deep Learning Approach to Automatize TMTV Calculations Regardless of Segmentation Methodology for Major FDG-Avid Lymphomas

Wendy Revailler et al. Diagnostics (Basel). .

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.

Keywords: convolutional neural network; deep learning; lymphoma; total metabolic tumor volume.

PubMed Disclaimer

Conflict of interest statement

All authors have read and agreed to the published version of the manuscript.

Figures

Figure 1
Figure 1
Boxplot of TMTV distribution for predicted and manual TMTV for each methodology (A) 41%, (B) 2.5, (C) 4.0.
Figure 1
Figure 1
Boxplot of TMTV distribution for predicted and manual TMTV for each methodology (A) 41%, (B) 2.5, (C) 4.0.
Figure 2
Figure 2
Bland–Altman plots between manual and predicted TMTV for each methodology (A) 41%, (B) 2.5, (C) 4.0.
Figure 2
Figure 2
Bland–Altman plots between manual and predicted TMTV for each methodology (A) 41%, (B) 2.5, (C) 4.0.
Figure 3
Figure 3
Correlation coefficient between the manual and predicted TMTV for each methodology (A) 41%, (B) 2.5, (C) 4.0.
Figure 3
Figure 3
Correlation coefficient between the manual and predicted TMTV for each methodology (A) 41%, (B) 2.5, (C) 4.0.
Figure 4
Figure 4
Predictions with false positives at the left arm FDG injection site, dice =0.32 (A) vs. accurate predictions, dice = 0.84 (B) of two different patients from the AHL cohort (HL).
See this image and copyright information in PMC

References

    1. Cottereau A.-S., Versari A., Loft A., Casasnovas O., Bellei M., Ricci R., Bardet S., Castagnoli A., Brice P., Raemaekers J., et al. Prognostic Value of Baseline Metabolic Tumor Volume in Early-Stage Hodgkin Lymphoma in the Standard Arm of the H10 Trial. Blood. 2018;131:1456–1463. doi: 10.1182/blood-2017-07-795476. - DOI - PubMed
    1. Kanoun S., Rossi C., Berriolo-Riedinger A., Dygai-Cochet I., Cochet A., Humbert O., Toubeau M., Ferrant E., Brunotte F., Casasnovas R.-O. Baseline Metabolic Tumour Volume Is an Independent Prognostic Factor in Hodgkin Lymphoma. Eur. J. Nucl. Med. Mol. Imaging. 2014;41:1735–1743. doi: 10.1007/s00259-014-2783-x. - DOI - PubMed
    1. Thieblemont C., Howlett S., Casasnovas R.-O., Mounier N., Perrot A., Morschhauser F., Fruchart C., Daguindau N., van Eygen K., Obéric L., et al. Lenalidomide Maintenance for Diffuse Large B-Cell Lymphoma Patients Responding to R-CHOP: Quality of Life, Dosing, and Safety Results from the Randomised Controlled REMARC Study. Br. J. Haematol. 2020;189:84–96. doi: 10.1111/bjh.16300. - DOI - PMC - PubMed
    1. Meignan M., Cottereau A.S., Versari A., Chartier L., Dupuis J., Boussetta S., Grassi I., Casasnovas R.-O., Haioun C., Tilly H., et al. Baseline Metabolic Tumor Volume Predicts Outcome in High–Tumor-Burden Follicular Lymphoma: A Pooled Analysis of Three Multicenter Studies. J. Clin. Oncol. 2016;34:3618–3626. doi: 10.1200/JCO.2016.66.9440. - DOI - PubMed
    1. Grossiord E., Passat N., Talbot H., Naegel B., Kanoun S., Tal I., Tervé P., Ken S., Casasnovas O., Meignan M., et al. Shaping for PET Image Analysis. Pattern Recognit. Lett. 2020;131:307–313. doi: 10.1016/j.patrec.2020.01.017. - DOI

LinkOut - more resources