Fully automatic segmentation of diffuse large B cell lymphoma lesions on 3D FDG-PET/CT for total metabolic tumour volume
- PDF / 1,697,763 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 99 Downloads / 172 Views
ORIGINAL ARTICLE
Fully automatic segmentation of diffuse large B cell lymphoma lesions on 3D FDG-PET/CT for total metabolic tumour volume prediction using a convolutional neural network. Paul Blanc-Durand 1,2,3,4,5 & Simon Jégou 6 & Salim Kanoun 2,7 & Alina Berriolo-Riedinger 2,8 & Caroline Bodet-Milin 2,9,10 & Françoise Kraeber-Bodéré 2,9,10 & Thomas Carlier 2,9,10 & Steven Le Gouill 2,11 & René-Olivier Casasnovas 2,12 & Michel Meignan 2 & Emmanuel Itti 1,2,3 Received: 19 June 2020 / Accepted: 15 October 2020 # Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Purpose Lymphoma lesion detection and segmentation on whole-body FDG-PET/CT are a challenging task because of the diversity of involved nodes, organs or physiological uptakes. We sought to investigate the performances of a three-dimensional (3D) convolutional neural network (CNN) to automatically segment total metabolic tumour volume (TMTV) in large datasets of patients with diffuse large B cell lymphoma (DLBCL). Methods The dataset contained pre-therapy FDG-PET/CT from 733 DLBCL patients of 2 prospective LYmphoma Study Association (LYSA) trials. The first cohort (n = 639) was used for training using a 5-fold cross validation scheme. The second cohort (n = 94) was used for external validation of TMTV predictions. Ground truth masks were manually obtained after a 41% SUVmax adaptive thresholding of lymphoma lesions. A 3D U-net architecture with 2 input channels for PET and CT was trained on patches randomly sampled within PET/CTs with a summed cross entropy and Dice similarity coefficient (DSC) loss. Segmentation performance was assessed by the DSC and Jaccard coefficients. Finally, TMTV predictions were validated on the second independent cohort. Results Mean DSC and Jaccard coefficients (± standard deviation) in the validations set were 0.73 ± 0.20 and 0.68 ± 0.21, respectively. An underestimation of mean TMTV by − 12 mL (2.8%) ± 263 was found in the validation sets of the first cohort (P = 0.27). In the second cohort, an underestimation of mean TMTV by − 116 mL (20.8%) ± 425 was statistically significant (P = 0.01). Conclusion Our CNN is a promising tool for automatic detection and segmentation of lymphoma lesions, despite slight underestimation of TMTV. The fully automatic and open-source features of this CNN will allow to increase both dissemination in routine practice and reproducibility of TMTV assessment in lymphoma patients. Keywords Positron emission tomography . Lymphoma . Total metabolic tumour volume . Segmentation . Deep learning . U-net . Convolutional neural network
Introduction This article is part of the Topical Collection on Advanced Image Analyses (Radiomics and Artificial Intelligence). Electronic supplementary material The online version of this article (https://doi.org/10.1007/s00259-020-05080-7) contains supplementary material, which is available to authorized users. * Paul Blanc-Durand [email protected] Extended author information available on the last page of the article
Total metabolic tumour volume (TMT
Data Loading...
