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
Surgery for locoregionally advanced head and neck squamous cell carcinoma (HNSCC) results in 30-50% five-year overall survival. In IMCISION (NCT03003637), a non-randomized phase Ib/IIa trial, 32... Show moreSurgery for locoregionally advanced head and neck squamous cell carcinoma (HNSCC) results in 30-50% five-year overall survival. In IMCISION (NCT03003637), a non-randomized phase Ib/IIa trial, 32 HNSCC patients are treated with 2 doses (in weeks 1 and 3) of immune checkpoint blockade (ICB) using nivolumab (NIVO MONO, n = 6, phase Ib arm A) or nivolumab plus a single dose of ipilimumab (COMBO, n = 26, 6 in phase Ib arm B, and 20 in phase IIa) prior to surgery. Primary endpoints are feasibility to resect no later than week 6 (phase Ib) and primary tumor pathological response (phase IIa). Surgery is not delayed or suspended for any patient in phase Ib, meeting the primary endpoint. Grade 3-4 immune-related adverse events are seen in 2 of 6 (33%) NIVO MONO and 10 of 26 (38%) total COMBO patients. Pathological response, defined as the %-change in primary tumor viable tumor cell percentage from baseline biopsy to on-treatment resection, is evaluable in 17/20 phase IIa patients and 29/32 total trial patients (6/6 NIVO MONO, 23/26 COMBO). We observe a major pathological response (MPR, 90-100% response) in 35% of patients after COMBO ICB, both in phase IIa (6/17) and in the whole trial (8/23), meeting the phase IIa primary endpoint threshold of 10%. NIVO MONO's MPR rate is 17% (1/6). None of the MPR patients develop recurrent HSNCC during 24.0 months median postsurgical follow-up. FDG-PET-based total lesion glycolysis identifies MPR patients prior to surgery. A baseline AID/APOBEC-associated mutational profile and an on-treatment decrease in hypoxia RNA signature are observed in MPR patients. Our data indicate that neoadjuvant COMBO ICB is feasible and encouragingly efficacious in HNSCC.Immune checkpoint blockade has become standard care for patients with recurrent metastatic head and neck squamous cell carcinoma (HNSCC). Here the authors present the results of a non-randomized phase Ib/IIa trial, reporting safety and efficacy of neoadjuvant nivolumab monotherapy and nivolumab plus ipilimumab prior to standard-of-care surgery in patients with HNSCC. . Show less
Outeiral, R.R.; Bos, P.; Al-Mamgani, A.; Jasperse, B.; Simoes, R.; Heide, U.A. van der 2021
AbstractBackground and purpose: Segmentation of oropharyngeal squamous cell carcinoma (OPSCC) is needed for radiotherapy planning. We aimed to segment the primary tumor for OPSCC on MRI using... Show moreAbstractBackground and purpose: Segmentation of oropharyngeal squamous cell carcinoma (OPSCC) is needed for radiotherapy planning. We aimed to segment the primary tumor for OPSCC on MRI using convolutional neural networks (CNNs). We investigated the effect of multiple MRI sequences as input and we proposed a semi-automatic approach for tumor segmentation that is expected to save time in the clinic. Materials and methods: We included 171 OPSCC patients retrospectively from 2010 until 2015. For all patients the following MRI sequences were available: T1-weighted, T2-weighted and 3D T1-weighted after gadolinium injection. We trained a 3D UNet using the entire images and images with reduced context, considering only information within clipboxes around the tumor. We compared the performance using different combinations of MRI sequences as input. Finally, a semi-automatic approach by two human observers defining clipboxes around the tumor was tested. Segmentation performance was measured with Sørensen-Dice coefficient (Dice), 95th Hausdorff distance (HD) and Mean Surface Distance (MSD). Results: The 3D UNet trained with full context and all sequences as input yielded a median Dice of 0.55, HD of 8.7 mm and MSD of 2.7 mm. Combining all MRI sequences was better than using single sequences. The semi-automatic approach with all sequences as input yielded significantly better performance (p < 0.001): a median Dice of 0.74, HD of 4.6 mm and MSD of 1.2 mm. Conclusion: Reducing the amount of context around the tumor and combining multiple MRI sequences improved the segmentation performance. A semi-automatic approach was accurate and clinically feasible. Show less
Gahrmann, R.; Bent, M. van den; Holt, B. van der; Vernhout, R.; Taal, W.; Taphoorn, M.; ... ; Smits, M. 2016
