Deep learning for elective neck delineation: More consistent and time efficient

Veen, Julie van der; Willems, Siri; Bollen, Heleen; Maes, Frederik; Nuyts, Sandra

doi:10.1016/j.radonc.2020.10.007

Cited by 21 publications

(25 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cardenas et al reported an accurate segmentation performance of the combined LN level I–V and II-IV clinical target volumes (CTV; both DSC = 0.90) [ 9 ], but it should be noted that an inspection of example segmentations suggested that these structures more closely resembled PTV structures from our institute. We believe that our finding of PTV overlap of UNet and UNet+MV (PTV I–V and II–IV DSCs = 0.91, 0.90, respectively) is in line with, if not better than, the segmented structures reported by Cardenas et al To the best of our knowledge, the work of Van der Veen et al [ 14 ] was the first to involve the automated segmentation of individual levels I and V and reported segmentation accuracies (without expert intervention) of DSC = 0.73, 0.61 and 0.79 for levels I and V and the combined II–IV structure, respectively. Interestingly, however, these results seem to more closely resemble the results obtained with our second configuration (level I, V DSCs = 0.70, 0.61, respectively).…”

Section: Discussionsupporting

confidence: 91%

“…First, since UNet is a widely established CNN that is used for a variety of imaging-related problems [ 12 ] and since it was used in two other studies for combined lymph structure segmentation [ 9 , 13 ], we included a patch-based UNet variant as a baseline model configuration. Other works have suggested the use of voxel-classification methods for individual LN level segmentation using a 3D multi-scale network [ 14 ], as well as 2.5D (multi-view; MV) networks for several segmentation challenges (multiple sclerosis [ 15 ], ocular structures [ 16 ], abdominal lymph structures [ 17 ], head-and-neck tumors [ 18 ]). Because 2.5D networks may more effectively learn features in the presence of little data [ 19 ] and because voxel classification may better resolve local ambiguities near level transitions, a multi-view convolutional neural network (MV-CNN) was included as our second configuration.…”

Section: Introductionmentioning

confidence: 99%

“…This work expands the existing literature by demonstrating the feasibility of deep learning for auto-segmentation for the target definition of individual LN levels I–V towards a flexible RT planning for locally advanced HNC. Based on earlier work, we estimate that accurate performance levels are attained for the segmentation of individual LN levels I–V with Dice similarity coefficient (DSC) of at least 0.8 [ 9 , 13 , 14 ] and we hypothesize that the contours can be obtained with such accuracy levels for the majority of patients, using one or more of the proposed deep learning configurations.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Section: Discussionsupporting

confidence: 91%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

show abstract

“…Manual contouring of H&N lymph node levels is a highly laborious and time-consuming task requiring around 50 minutes of an expert’s time per patient case ( 7 ). These burdening time requirements limit the extent to which optimal H&N lymph node level delineation can be performed in clinical practice, increasing waiting time for patients, limiting frequent adaption of radiotherapy treatment plans and taking away clinical experts from other tasks ( 8 ).…”

Section: Introductionmentioning

confidence: 99%

“…Van der Veen et al. trained a 3D convolutional neural network (3D-CNN) based on the DeepMedic architecture ( 26 ) on a clinical dataset of 69 H&N cases to autosegment a selection of 17 individual nodal levels combining level II, III and IV on each side ( 7 ). The authors focused on a semiautomatic workflow with a subsequent manual expert-based correction step and were able to show a shortening of manual time required and a reduction in interobserver variability with upfront deep learning autosegmentation.…”

Section: Introductionmentioning

confidence: 99%

Deep learning for automatic head and neck lymph node level delineation provides expert-level accuracy

et al. 2023

View full text Add to dashboard Cite

BackgroundDeep learning-based head and neck lymph node level (HN_LNL) autodelineation is of high relevance to radiotherapy research and clinical treatment planning but still underinvestigated in academic literature. In particular, there is no publicly available open-source solution for large-scale autosegmentation of HN_LNL in the research setting.MethodsAn expert-delineated cohort of 35 planning CTs was used for training of an nnU-net 3D-fullres/2D-ensemble model for autosegmentation of 20 different HN_LNL. A second cohort acquired at the same institution later in time served as the test set (n = 20). In a completely blinded evaluation, 3 clinical experts rated the quality of deep learning autosegmentations in a head-to-head comparison with expert-created contours. For a subgroup of 10 cases, intraobserver variability was compared to the average deep learning autosegmentation accuracy on the original and recontoured set of expert segmentations. A postprocessing step to adjust craniocaudal boundaries of level autosegmentations to the CT slice plane was introduced and the effect of autocontour consistency with CT slice plane orientation on geometric accuracy and expert rating was investigated.ResultsBlinded expert ratings for deep learning segmentations and expert-created contours were not significantly different. Deep learning segmentations with slice plane adjustment were rated numerically higher (mean, 81.0 vs. 79.6, p = 0.185) and deep learning segmentations without slice plane adjustment were rated numerically lower (77.2 vs. 79.6, p = 0.167) than manually drawn contours. In a head-to-head comparison, deep learning segmentations with CT slice plane adjustment were rated significantly better than deep learning contours without slice plane adjustment (81.0 vs. 77.2, p = 0.004). Geometric accuracy of deep learning segmentations was not different from intraobserver variability (mean Dice per level, 0.76 vs. 0.77, p = 0.307). Clinical significance of contour consistency with CT slice plane orientation was not represented by geometric accuracy metrics (volumetric Dice, 0.78 vs. 0.78, p = 0.703).ConclusionsWe show that a nnU-net 3D-fullres/2D-ensemble model can be used for highly accurate autodelineation of HN_LNL using only a limited training dataset that is ideally suited for large-scale standardized autodelineation of HN_LNL in the research setting. Geometric accuracy metrics are only an imperfect surrogate for blinded expert rating.

show abstract

Auto‐segmentation of important centers of growth in the pediatric skeleton to consider during radiation therapy based on deep learning

Qiu

Zhang²,

et al. 2022

Medical Physics

View full text Add to dashboard Cite

Background Routinely delineating of important skeletal growth centers is imperative to mitigate radiation‐induced growth abnormalities for pediatric cancer patients treated with radiotherapy. However, it is hindered by several practical problems, including difficult identification, time consumption, and inter‐practitioner variability. Purpose The goal of this study was to construct and evaluate a novel Triplet‐Attention U‐Net (TAU‐Net)‐based auto‐segmentation model for important skeletal growth centers in childhood cancer radiotherapy, concentrating on the accuracy and time efficiency. Methods A total of 107 childhood cancer patients fulfilled the eligibility criteria were enrolled in the training cohort (N = 80) and test cohort (N = 27). The craniofacial growth plates, shoulder growth centers, and pelvic ossification centers, with a total of 19 structures in the three groups, were manually delineated by two experienced radiation oncologists on axial, coronal, and sagittal computed tomography images. Modified from U‐Net, the proposed TAU‐Net has one main branch and two bypass branches, receiving semantic information of three adjacent slices to predict the target structure. With supervised deep learning, the skeletal growth centers contouring of each group was generated by three different auto‐segmentation models: U‐Net, V‐Net, and the proposed TAU‐Net. Dice similarity coefficient (DSC) and Hausdorff distance 95% (HD95) were used to evaluate the accuracy of three auto‐segmentation models. The time spent on performing manual tasks and manually correcting auto‐contouring generated by TAU‐Net was recorded. The paired t‐test was used to compare the statistical differences in delineation quality and time efficiency. Results Among the three groups, including craniofacial growth plates, shoulder growth centers, and pelvic ossification centers groups, TAU‐Net had demonstrated highly acceptable performance (the average DSC = 0.77, 0.87, and 0.83 for each group; the average HD95 = 2.28, 2.07, and 2.86 mm for each group). In the overall evaluation of 19 regions of interest (ROIs) in the test cohort, TAU‐Net had an overwhelming advantage over U‐Net (63.2% ROIs in DSC and 31.6% ROIs in HD95, p = 0.001–0.042) and V‐Net (94.7% ROIs in DSC and 36.8% ROIs in HD95, p = 0.001–0.040). With an average time of 52.2 min for manual delineation, the average time saved to adjust TAU‐Net‐generated contours was 37.6 min (p < 0.001), a 72% reduction. Conclusions Deep learning–based models have presented enormous potential for the auto‐segmentation of important growth centers in pediatric skeleton, where the proposed TAU‐Net outperformed the U‐Net and V‐Net in geometrical precision for the majority status.

show abstract

Deep learning for elective neck delineation: More consistent and time efficient

Cited by 21 publications

References 26 publications

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

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

Deep learning for automatic head and neck lymph node level delineation provides expert-level accuracy

Auto‐segmentation of important centers of growth in the pediatric skeleton to consider during radiation therapy based on deep learning

Contact Info

Product

Resources

About