文章基本信息

标题：2D and 3D convolutional neural networks for outcome modelling of locally advanced head and neck squamous cell carcinoma
本地全文：下载
作者：Sebastian Starke ; Stefan Leger ; Alex Zwanenburg 等
期刊名称：Scientific Reports
电子版ISSN：2045-2322
出版年度：2020
卷号：10
期号：1
页码：1-13
DOI：10.1038/s41598-020-70542-9
出版社：Springer Nature
摘要：For treatment individualisation of patients with locally advanced head and neck squamous cell carcinoma (HNSCC) treated with primary radiochemotherapy, we explored the capabilities of different deep learning approaches for predicting loco-regional tumour control (LRC) from treatment-planning computed tomography images. Based on multicentre cohorts for exploration (206 patients) and independent validation (85 patients), multiple deep learning strategies including training of 3D- and 2D-convolutional neural networks (CNN) from scratch, transfer learning and extraction of deep autoencoder features were assessed and compared to a clinical model. Analyses were based on Cox proportional hazards regression and model performances were assessed by the concordance index (C-index) and the model’s ability to stratify patients based on predicted hazards of LRC. Among all models, an ensemble of 3D-CNNs achieved the best performance (C-index 0.31) with a significant association to LRC on the independent validation cohort. It performed better than the clinical model including the tumour volume (C-index 0.39). Significant differences in LRC were observed between patient groups at low or high risk of tumour recurrence as predicted by the model ( $$p=0.001$$ ). This 3D-CNN ensemble will be further evaluated in a currently ongoing prospective validation study once follow-up is complete.
其他摘要：Abstract For treatment individualisation of patients with locally advanced head and neck squamous cell carcinoma (HNSCC) treated with primary radiochemotherapy, we explored the capabilities of different deep learning approaches for predicting loco-regional tumour control (LRC) from treatment-planning computed tomography images. Based on multicentre cohorts for exploration (206 patients) and independent validation (85 patients), multiple deep learning strategies including training of 3D- and 2D-convolutional neural networks (CNN) from scratch, transfer learning and extraction of deep autoencoder features were assessed and compared to a clinical model. Analyses were based on Cox proportional hazards regression and model performances were assessed by the concordance index (C-index) and the model’s ability to stratify patients based on predicted hazards of LRC. Among all models, an ensemble of 3D-CNNs achieved the best performance (C-index 0.31) with a significant association to LRC on the independent validation cohort. It performed better than the clinical model including the tumour volume (C-index 0.39). Significant differences in LRC were observed between patient groups at low or high risk of tumour recurrence as predicted by the model ( $$p=0.001$$ p = 0.001 ). This 3D-CNN ensemble will be further evaluated in a currently ongoing prospective validation study once follow-up is complete.