![]() ![]() ![]() Sarcopenia is associated with worse overall (OS) and progression-free survival (PFS), postoperative outcomes and chemotherapy toxicity in common cancer types. However, performance status is subjectively evaluated, resulting in inaccuracy and high inter-observer variability, so objectively assessable indicators of frailty/physical condition such as measures of sarcopenia and skeletal muscle mass may improve prognostic assessment and treatment stratification. Factors including age, performance status, tumour location, size, molecular and histological characteristics are known to be prognostic, with performance status particularly important. Glioblastoma multiforme (GBM) is an aggressive brain malignancy with <5% 5-year survival. We are the first to show that a head/neck muscle-derived sarcopenia metric generated using deep learning is associated with oncological outcomes and one of the first to show deep learning-based muscle quantification has prognostic value in cancer. Temporalis CSA is a prognostic marker in patients with glioblastoma, rapidly and accurately assessable with deep learning. Median age was 55 and 58 years and 75.6 and 64.7% were males in the in-house and TCGA-GBM data sets, respectively. The model achieved high segmentation accuracy (Dice coefficient 0.893). Association between temporalis CSA and survival was determined in 96 glioblastoma patients from internal and external data sets. MethodsĪ neural network for temporalis segmentation was trained with 366 MRI head images from 132 patients from 4 different glioblastoma data sets and used to quantify muscle cross-sectional area (CSA). We present a deep learning-based system for quantification of temporalis muscle, a surrogate for skeletal muscle mass, and assess its prognostic value in glioblastoma. Sarcopenia is associated with worse cancer survival, but manually quantifying muscle on imaging is time-consuming. Glioblastoma is the commonest malignant brain tumour.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |