Paul Blanc-Durand1,2,3, Luca Campedel4, Sébastien Mule5,6, Simon Jegou7, Alain Luciani5,6, Frédéric Pigneur6, Emmanuel Itti8,9,5. 1. Department of Nuclear Medicine, Henri Mondor Hospital/AP-HP, Créteil, F-94010, France. paul.blancdurand@aphp.fr. 2. INSERM IMRB, Team 8, U-PEC, Créteil, F-94000, France. paul.blancdurand@aphp.fr. 3. Université Paris-Est Créteil (U-PEC), F-94000, Créteil, France. paul.blancdurand@aphp.fr. 4. Department of Oncology, Groupe Hospitalier Pitié Salpêtrière C. Foix/AP-HP, Paris, F-75013, France. 5. Université Paris-Est Créteil (U-PEC), F-94000, Créteil, France. 6. Department of Radiology, Henri Mondor Hospital/AP-HP, Créteil, F-94010, France. 7. Owkin, F-75010, Paris, France. 8. Department of Nuclear Medicine, Henri Mondor Hospital/AP-HP, Créteil, F-94010, France. 9. INSERM IMRB, Team 8, U-PEC, Créteil, F-94000, France.
Abstract
INTRODUCTION: The aim of the study was to extract anthropometric measures from CT by deep learning and to evaluate their prognostic value in patients with non-small-cell lung cancer (NSCLC). METHODS: A convolutional neural network was trained to perform automatic segmentation of subcutaneous adipose tissue (SAT), visceral adipose tissue (VAT), and muscular body mass (MBM) from low-dose CT images in 189 patients with NSCLC who underwent pretherapy PET/CT. After a fivefold cross-validation in a subset of 35 patients, anthropometric measures extracted by deep learning were normalized to the body surface area (BSA) to control the various patient morphologies. VAT/SAT ratio and clinical parameters were included in a Cox proportional-hazards model for progression-free survival (PFS) and overall survival (OS). RESULTS: Inference time for a whole volume was about 3 s. Mean Dice similarity coefficients in the validation set were 0.95, 0.93, and 0.91 for SAT, VAT, and MBM, respectively. For PFS prediction, T-stage, N-stage, chemotherapy, radiation therapy, and VAT/SAT ratio were associated with disease progression on univariate analysis. On multivariate analysis, only N-stage (HR = 1.7 [1.2-2.4]; p = 0.006), radiation therapy (HR = 2.4 [1.0-5.4]; p = 0.04), and VAT/SAT ratio (HR = 10.0 [2.7-37.9]; p < 0.001) remained significant prognosticators. For OS, male gender, smoking status, N-stage, a lower SAT/BSA ratio, and a higher VAT/SAT ratio were associated with mortality on univariate analysis. On multivariate analysis, male gender (HR = 2.8 [1.2-6.7]; p = 0.02), N-stage (HR = 2.1 [1.5-2.9]; p < 0.001), and the VAT/SAT ratio (HR = 7.9 [1.7-37.1]; p < 0.001) remained significant prognosticators. CONCLUSION: The BSA-normalized VAT/SAT ratio is an independent predictor of both PFS and OS in NSCLC patients. KEY POINTS: • Deep learning will make CT-derived anthropometric measures clinically usable as they are currently too time-consuming to calculate in routine practice. • Whole-body CT-derived anthropometrics in non-small-cell lung cancer are associated with progression-free survival and overall survival. • A priori medical knowledge can be implemented in the neural network loss function calculation.
INTRODUCTION: The aim of the study was to extract anthropometric measures from CT by deep learning and to evaluate their prognostic value in patients with non-small-cell lung cancer (NSCLC). METHODS: A convolutional neural network was trained to perform automatic segmentation of subcutaneous adipose tissue (SAT), visceral adipose tissue (VAT), and muscular body mass (MBM) from low-dose CT images in 189 patients with NSCLC who underwent pretherapy PET/CT. After a fivefold cross-validation in a subset of 35 patients, anthropometric measures extracted by deep learning were normalized to the body surface area (BSA) to control the various patient morphologies. VAT/SAT ratio and clinical parameters were included in a Cox proportional-hazards model for progression-free survival (PFS) and overall survival (OS). RESULTS: Inference time for a whole volume was about 3 s. Mean Dice similarity coefficients in the validation set were 0.95, 0.93, and 0.91 for SAT, VAT, and MBM, respectively. For PFS prediction, T-stage, N-stage, chemotherapy, radiation therapy, and VAT/SAT ratio were associated with disease progression on univariate analysis. On multivariate analysis, only N-stage (HR = 1.7 [1.2-2.4]; p = 0.006), radiation therapy (HR = 2.4 [1.0-5.4]; p = 0.04), and VAT/SAT ratio (HR = 10.0 [2.7-37.9]; p < 0.001) remained significant prognosticators. For OS, male gender, smoking status, N-stage, a lower SAT/BSA ratio, and a higher VAT/SAT ratio were associated with mortality on univariate analysis. On multivariate analysis, male gender (HR = 2.8 [1.2-6.7]; p = 0.02), N-stage (HR = 2.1 [1.5-2.9]; p < 0.001), and the VAT/SAT ratio (HR = 7.9 [1.7-37.1]; p < 0.001) remained significant prognosticators. CONCLUSION: The BSA-normalized VAT/SAT ratio is an independent predictor of both PFS and OS in NSCLCpatients. KEY POINTS: • Deep learning will make CT-derived anthropometric measures clinically usable as they are currently too time-consuming to calculate in routine practice. • Whole-body CT-derived anthropometrics in non-small-cell lung cancer are associated with progression-free survival and overall survival. • A priori medical knowledge can be implemented in the neural network loss function calculation.
Authors: Martina Sollini; Francesco Bartoli; Andrea Marciano; Roberta Zanca; Riemer H J A Slart; Paola A Erba Journal: Eur J Hybrid Imaging Date: 2020-12-09
Authors: J Peter Marquardt; Eric J Roeland; Emily E Van Seventer; Till D Best; Nora K Horick; Ryan D Nipp; Florian J Fintelmann Journal: J Cachexia Sarcopenia Muscle Date: 2021-11-02 Impact factor: 12.910