Comparing different CT, PET and MRI multi-modality image combinations for deep learning-based head and neck tumor segmentation

Ren, Jintao; Eriksen, Jesper Grau; Nijkamp, Jasper; Korreman, S.

doi:10.1080/0284186x.2021.1949034

Cited by 61 publications

(45 citation statements)

References 33 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main subsite of the challenge was the oropharyngeal tumor and the winner of the challenge achieved a mean Dice of 0.76, but the image modalities used were PET/CT. Additionally, Ren et al [31] compared the use of PET/CT/MRI as different input image combinations for the automatic segmentation of head and neck GTV and observed that, when including PET, the segmentation performance improved. Considering all the above, it is possible that PET is a useful modality for the task of head and neck tumor segmentation.…”

Section: Discussionmentioning

confidence: 99%

Strategies for tackling the class imbalance problem of oropharyngeal primary tumor segmentation on magnetic resonance imaging

Outeiral

Bos

Hulst

et al. 2022

Physics and Imaging in Radiation Oncology

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Strategies for tackling the class imbalance problem of oropharyngeal primary tumor segmentation on magnetic resonance imaging

Outeiral

Bos

Hulst

et al. 2022

Physics and Imaging in Radiation Oncology

View full text Add to dashboard Cite

“…Tissue changes from previous local therapies strongly impede target volume delineation in recurrent head and neck cancer. Combining multi-modality imaging including CT, diffusionweighted MRI and positron emission tomography (PET)/ CT can be crucial to mitigate uncertainties in contouring [32,33]. One patient with type E local failure developed tumor recurrence within 5 mm of the CTV.…”

Section: Discussionmentioning

confidence: 99%

Ways to unravel the clinical potential of carbon ions for head and neck cancer reirradiation: dosimetric comparison and local failure pattern analysis as part of the prospective randomized CARE trial

et al. 2022

View full text Add to dashboard Cite

Background Carbon ion radiotherapy (CIRT) yields biophysical advantages compared to photons but randomized studies for the reirradiation setting are pending. The aim of the current project was to evaluate potential clinical benefits and drawbacks of CIRT compared to volumetric modulated arc therapy (VMAT) in recurrent head and neck cancer. Methods Dose-volume parameters and local failure patterns of CIRT compared to VMAT were evaluate in 16 patients from the randomized CARE trial on head and neck cancer reirradiation. Results Despite an increased target dose, CIRT resulted in significantly reduced organ at risk (OAR) dose across all patients (− 8.7% Dmean). The dose-volume benefits were most pronounced in the brainstem (− 20.7% Dmax) and the optic chiasma (− 13.0% Dmax). The most frequent local failure was type E (extraneous; 50%), followed type B (peripheral; 33%) and type A (central; 17%). In one patient with type A biological and/or dosimetric failure after CIRT, mMKM dose recalculation revealed reduced target coverage. Conclusions CIRT resulted in highly improved critical OAR sparing compared to VMAT across all head and neck cancer reirradiation scenarios despite an increased prescription dose. Local failure pattern analysis revealed further potential CIRT specific clinical benefits and potential pitfalls with regard to image-guidance and biological dose-optimization.

show abstract

“…All models were trained using 5-fold cross-validation, with a train\test split of 48\12 cases every fold. To minimize the training variation, we used ensemble learning [ 9 , 21 , 22 , 23 ], where the highest cumulated in-class segmentation probability of 5 sequentially trained networks decided the final segmentation map. The training and evaluation times were saved.…”

Section: Methodsmentioning

confidence: 99%

Deep Learning for Automated Elective Lymph Node Level Segmentation for Head and Neck Cancer Radiotherapy

Strijbis

Dahele

Gurney‐Champion

et al. 2022

Cancers

View full text Add to dashboard Cite

Depending on the clinical situation, different combinations of lymph node (LN) levels define the elective LN target volume in head-and-neck cancer (HNC) radiotherapy. The accurate auto-contouring of individual LN levels could reduce the burden and variability of manual segmentation and be used regardless of the primary tumor location. We evaluated three deep learning approaches for the segmenting individual LN levels I–V, which were manually contoured on CT scans from 70 HNC patients. The networks were trained and evaluated using five-fold cross-validation and ensemble learning for 60 patients with (1) 3D patch-based UNets, (2) multi-view (MV) voxel classification networks and (3) sequential UNet+MV. The performances were evaluated using Dice similarity coefficients (DSC) for automated and manual segmentations for individual levels, and the planning target volumes were extrapolated from the combined levels I–V and II–IV, both for the cross-validation and for an independent test set of 10 patients. The median DSC were 0.80, 0.66 and 0.82 for UNet, MV and UNet+MV, respectively. Overall, UNet+MV significantly (p < 0.0001) outperformed other arrangements and yielded DSC = 0.87, 0.85, 0.86, 0.82, 0.77, 0.77 for the combined and individual level I–V structures, respectively. Both PTVs were also significantly (p < 0.0001) more accurate with UNet+MV, with DSC = 0.91 and 0.90, respectively. The accurate segmentation of individual LN levels I–V can be achieved using an ensemble of UNets. UNet+MV can further refine this result.

show abstract

Comparing different CT, PET and MRI multi-modality image combinations for deep learning-based head and neck tumor segmentation

Cited by 61 publications

References 33 publications

Strategies for tackling the class imbalance problem of oropharyngeal primary tumor segmentation on magnetic resonance imaging

Strategies for tackling the class imbalance problem of oropharyngeal primary tumor segmentation on magnetic resonance imaging

Ways to unravel the clinical potential of carbon ions for head and neck cancer reirradiation: dosimetric comparison and local failure pattern analysis as part of the prospective randomized CARE trial

Deep Learning for Automated Elective Lymph Node Level Segmentation for Head and Neck Cancer Radiotherapy

Contact Info

Product

Resources

About