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

SIMPLE SUMMARY: This study presents two novel methods for automatically analyzing the distribution of nodal metastases in head and neck (H/N) cancer cohorts. The proposed deep learning method uses lymph node level autosegmentation to automatically assign lymph node metastases to 20 H/N nodal levels. The second, registration-based method maps lymph nodes into a calculated average-anatomy template CT, allowing for the analysis and visualization of the 3D probability distribution of metastases without predefined level boundaries. Both methods were evaluated on a cohort of 193 H/N cancer patients, with the deep learning method being able to correctly categorize all 449 lymph nodes to their respective levels as determined by a multireader expert review. Level 2 was by far the most frequently involved level (59% of lymph nodes). The mapping technique showed clustering in high-risk regions and proved to be consistent with the ground-truth distribution. Both methods could contribute to the refinement of H/N radiotherapy target volume design. 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.