A convolutional neural network with self-attention for fully automated metabolic tumor volume delineation of head and neck cancer in [Formula: see text]F]FDG PET/CT.
Pavel NikulinSebastian ZschaeckJens MausPaulina CeglaElia LombardoChristian FurthJoanna KaźmierskaJulian M M RogaschAdrien HolzgreveNathalie L AlbertKonstantinos FerentinosIosif StrouthosMarina HajiyianniSebastian N MarschnerClaus BelkaGuillaume LandryWitold CholewinskiJörg KotzerkeFrank HofheinzJörg van den HoffPublished in: European journal of nuclear medicine and molecular imaging (2023)
To the best of our knowledge, this work presents the first CNN model for successful MTV delineation and lesion classification in HNC. In the vast majority of patients, the network performs satisfactory delineation and classification of primary tumor and lymph node metastases and only rarely requires more than minimal manual correction. It is thus able to massively facilitate study data evaluation in large patient groups and also does have clear potential for supervised clinical application.
Keyphrases
- deep learning
- convolutional neural network
- machine learning
- lymph node
- end stage renal disease
- artificial intelligence
- ejection fraction
- chronic kidney disease
- newly diagnosed
- healthcare
- big data
- case report
- patient reported outcomes
- radiation therapy
- smoking cessation
- electronic health record
- single cell
- locally advanced
- preterm birth
- human milk