TY - JOUR
AU - Starke, Sebastian
AU - Zwanenburg-Bezemer, Alexander Adriaan
AU - Leger, Karoline
AU - Lohaus, Fabian
AU - Linge, Annett
AU - Kalinauskaite, Goda
AU - Tinhofer, Inge
AU - Guberina, Nika
AU - Guberina, Maja
AU - Balermpas, Panagiotis
AU - Grün, Jens von der
AU - Ganswindt, Ute
AU - Belka, Claus
AU - Peeken, Jan C
AU - Combs, Stephanie E
AU - Boeke, Simon
AU - Zips, Daniel
AU - Richter, Christian
AU - Troost, Esther
AU - Krause, Mechthild
AU - Baumann, Michael
AU - Löck, Steffen
TI - Multitask Learning with Convolutional Neural Networks and Vision Transformers Can Improve Outcome Prediction for Head and Neck Cancer Patients.
JO - Cancers
VL - 15
IS - 19
SN - 2072-6694
CY - Basel
PB - MDPI
M1 - DKFZ-2023-02064
SP - 4897
PY - 2023
AB - 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
KW - Cox proportional hazards (Other)
KW - convolutional neural network (Other)
KW - discrete-time survival models (Other)
KW - head and neck cancer (Other)
KW - loco-regional control (Other)
KW - multitask learning (Other)
KW - progression-free survival (Other)
KW - survival analysis (Other)
KW - tumor segmentation (Other)
KW - vision transformer (Other)
LB - PUB:(DE-HGF)16
C6 - pmid:37835591
C2 - pmc:PMC10571894
DO - DOI:10.3390/cancers15194897
UR - https://inrepo02.dkfz.de/record/284753
ER -