Simple Summary Immunotherapy may induce early treatment response in head and neck squamous cell carcinoma (HNSCC) for some patients. Routine imaging parameters fail to diagnose these responses;... Show moreSimple Summary Immunotherapy may induce early treatment response in head and neck squamous cell carcinoma (HNSCC) for some patients. Routine imaging parameters fail to diagnose these responses; however, magnetic resonance (MR) diffusion-weighted imaging (DWI) may be able to do so. This study sought to correlate DWI parameters with treatment response early after immunotherapy treatment in HNSCC. We analyzed 24 patients with advanced HNSCC with imaging before and after the immunotherapy. We found that rounder tumors that were smaller in diameter before treatment were more likely to respond. A decrease in skewness of the tumor after treatment compared to before treatment, as well as an overall low skewness post-treatment, were linked to better treatment response. Though this study was explorative in nature, these results are promising for the predictive use of MR-DWI in HNSCC treated with immunotherapy. Background: Neoadjuvant immune checkpoint blockade (ICB) prior to surgery may induce early pathological responses in head and neck squamous cell carcinoma (HNSCC) patients. Routine imaging parameters fail to diagnose these responses early on. Magnetic resonance (MR) diffusion-weighted imaging (DWI) has proven to be useful for detecting HNSCC tumor mass after (chemo)radiation therapy. METHODS: 32 patients with stage II-IV, resectable HNSCC, treated at a phase Ib/IIa IMCISION trial (NCT03003637), were retrospectively analyzed using MR-imaging before and after two doses of single agent nivolumab (anti-PD-1) (n = 6) or nivolumab with ipilimumab (anti-CTLA-4) ICB (n = 26). The primary tumors were delineated pre- and post-treatment. A total of 32 features were derived from the delineation and correlated with the tumor regression percentage in the surgical specimen. Results: MR-DWI data was available for 24 of 32 patients. Smaller baseline tumor diameter (p = 0.01-0.04) and higher sphericity (p = 0.03) were predictive of having a good pathological response to ICB. Post-treatment skewness and the change in skewness between MRIs were negatively correlated with the tumor's regression (p = 0.04, p = 0.02). Conclusion: Pre-treatment DWI tumor diameter and sphericity may be quantitative biomarkers for the prediction of an early pathological response to ICB. Furthermore, our data indicate that ADC skewness could be a marker for individual response evaluation. Show less
Outeiral, R.R.; Bos, P.; Hulst, H.J. van der; Al-Mamgani, A.; Jasperse, B.; Simoes, R.; Heide, U.A. van der 2022
Background and purpose: Contouring oropharyngeal primary tumors in radiotherapy is currently done manually which is time-consuming. Autocontouring techniques based on deep learning methods are a... Show moreBackground and purpose: Contouring oropharyngeal primary tumors in radiotherapy is currently done manually which is time-consuming. Autocontouring techniques based on deep learning methods are a desirable alternative, but these methods can render suboptimal results when the structure to segment is considerably smaller than the rest of the image. The purpose of this work was to investigate different strategies to tackle the class imbalance problem in this tumor site.Materials and methods: A cohort of 230 oropharyngeal cancer patients treated between 2010 and 2018 was retrospectively collected. The following magnetic resonance imaging (MRI) sequences were available: T1 -weighted, T2-weighted, 3D T1-weighted after gadolinium injection. Two strategies to tackle the class imbal-ance problem were studied: training with different loss functions (namely: Dice loss, Generalized Dice loss, Focal Tversky loss and Unified Focal loss) and implementing a two-stage approach (i.e. splitting the task in detection and segmentation). Segmentation performance was measured with Sorensen-Dice coefficient (Dice), 95th Hausdorff distance (HD) and Mean Surface Distance (MSD). Results: The network trained with the Generalized Dice Loss yielded a median Dice of 0.54, median 95th HD of 10.6 mm and median MSD of 2.4 mm but no significant differences were observed among the different loss functions (p-value > 0.7). The two-stage approach resulted in a median Dice of 0.64, median HD of 8.7 mm and median MSD of 2.1 mm, significantly outperforming the end-to-end 3D U-Net (p-value < 0.05).Conclusion: No significant differences were observed when training with different loss functions. The two-stage approach outperformed the end-to-end 3D U-Net. Show less