Deep Learning and Registration-Based Mapping for Analyzing the Distribution of Nodal Metastases in Head and Neck Cancer Cohorts: Informing Optimal Radiotherapy Target Volume Design

Weissmann T, Mansoorian S, May M, Lettmaier S, Höfler D, Deloch L, Speer S, Balk M, Frey B, Gaipl U, Bert C, Distel L, Walter F, Belka C, Semrau S, Iro H, Fietkau R, Huang Y, Putz F (2023)

Publication Type: Journal article

Publication year: 2023

Journal

Cancers MDPI

Book Volume: 15

Pages Range: 4620

Issue: 18

DOI: 10.3390/cancers15184620

Abstract

We introduce a deep-learning- and a registration-based method for automatically analyzing the spatial distribution of nodal metastases (LNs) in head and neck (H/N) cancer cohorts to inform radiotherapy (RT) target volume design. The two methods are evaluated in a cohort of 193 H/N patients/planning CTs with a total of 449 LNs. In the deep learning method, a previously developed nnU-Net 3D/2D ensemble model is used to autosegment 20 H/N levels, with each LN subsequently being algorithmically assigned to the closest-level autosegmentation. In the nonrigid-registration-based mapping method, LNs are mapped into a calculated template CT representing the cohort-average patient anatomy, and kernel density estimation is employed to estimate the underlying average 3D-LN probability distribution allowing for analysis and visualization without prespecified level definitions. Multireader assessment by three radio-oncologists with majority voting was used to evaluate the deep learning method and obtain the ground-truth distribution. For the mapping technique, the proportion of LNs predicted by the 3D probability distribution for each level was calculated and compared to the deep learning and ground-truth distributions. As determined by a multireader review with majority voting, the deep learning method correctly categorized all 449 LNs to their respective levels. Level 2 showed the highest LN involvement (59.0%). The level involvement predicted by the mapping technique was consistent with the ground-truth distribution (p for difference 0.915). Application of the proposed methods to multicenter cohorts with selected H/N tumor subtypes for informing optimal RT target volume design is promising.

Authors with CRIS profile

Thomas Weissmann Department of Radiation Oncology Matthias May Institute of Radiology Daniel Höfler Department of Radiation Oncology Lisa Deloch Department of Radiation Oncology Stefan Speer Department of Radiation Oncology Matthias Balk Department of Otorhinolaryngology – Head and Neck Surgery Benjamin Frey Department of Radiation Oncology Udo Gaipl Department of Radiation Oncology Christoph Bert Professur für Med. Strahlenphysik Luitpold Distel Department of Radiation Oncology Sabine Semrau Medizinische Fakultät Heinrich Iro Lehrstuhl für Hals-, Nasen- und Ohrenheilkunde Rainer Fietkau Lehrstuhl für Strahlentherapie Yixing Huang Department of Radiation Oncology Florian Putz Department of Radiation Oncology

Involved external institutions

LMU Klinikum DE Germany (DE)

How to cite

APA:

Weissmann, T., Mansoorian, S., May, M., Lettmaier, S., Höfler, D., Deloch, L.,... Putz, F. (2023). Deep Learning and Registration-Based Mapping for Analyzing the Distribution of Nodal Metastases in Head and Neck Cancer Cohorts: Informing Optimal Radiotherapy Target Volume Design. Cancers, 15, 4620. https://doi.org/10.3390/cancers15184620

MLA:

Weissmann, Thomas, et al. "Deep Learning and Registration-Based Mapping for Analyzing the Distribution of Nodal Metastases in Head and Neck Cancer Cohorts: Informing Optimal Radiotherapy Target Volume Design." Cancers 15 (2023): 4620.

BibTeX: Download