%0 Journal Article
%A Starke, Sebastian
%A Zwanenburg-Bezemer, Alexander Adriaan
%A Leger, Karoline
%A Lohaus, Fabian
%A Linge, Annett
%A Kalinauskaite, Goda
%A Tinhofer, Inge
%A Guberina, Nika
%A Guberina, Maja
%A Balermpas, Panagiotis
%A Grün, Jens von der
%A Ganswindt, Ute
%A Belka, Claus
%A Peeken, Jan C
%A Combs, Stephanie E
%A Boeke, Simon
%A Zips, Daniel
%A Richter, Christian
%A Troost, Esther
%A Krause, Mechthild
%A Baumann, Michael
%A Löck, Steffen
%T Multitask Learning with Convolutional Neural Networks and Vision Transformers Can Improve Outcome Prediction for Head and Neck Cancer Patients.
%J Cancers
%V 15
%N 19
%@ 2072-6694
%C Basel
%I MDPI
%M DKFZ-2023-02064
%P 4897
%D 2023
%X Neural-network-based outcome predictions may enable further treatment personalization of patients with head and neck cancer. The development of neural networks can prove challenging when a limited number of cases is available. Therefore, we investigated whether multitask learning strategies, implemented through the simultaneous optimization of two distinct outcome objectives (multi-outcome) and combined with a tumor segmentation task, can lead to improved performance of convolutional neural networks (CNNs) and vision transformers (ViTs). Model training was conducted on two distinct multicenter datasets for the endpoints loco-regional control (LRC) and progression-free survival (PFS), respectively. The first dataset consisted of pre-treatment computed tomography (CT) imaging for 290 patients and the second dataset contained combined positron emission tomography (PET)/CT data of 224 patients. Discriminative performance was assessed by the concordance index (C-index). Risk stratification was evaluated using log-rank tests. Across both datasets, CNN and ViT model ensembles achieved similar results. Multitask approaches showed favorable performance in most investigations. Multi-outcome CNN models trained with segmentation loss were identified as the optimal strategy across cohorts. On the PET/CT dataset, an ensemble of multi-outcome CNNs trained with segmentation loss achieved the best discrimination (C-index: 0.29, 95
%K Cox proportional hazards (Other)
%K convolutional neural network (Other)
%K discrete-time survival models (Other)
%K head and neck cancer (Other)
%K loco-regional control (Other)
%K multitask learning (Other)
%K progression-free survival (Other)
%K survival analysis (Other)
%K tumor segmentation (Other)
%K vision transformer (Other)
%F PUB:(DE-HGF)16
%9 Journal Article
%$ pmid:37835591
%2 pmc:PMC10571894
%R 10.3390/cancers15194897
%U https://inrepo02.dkfz.de/record/284753