Comparison of atlas-based and deep learning methods for organs at risk delineation on head-and-neck CT images using an automated treatment planning system

Costea, Madalina; Zlate, Alexandra; Durand, Morgane; Baudier, Thomas; Grégoire, Vincent; Sarrut, David; Biston, Marie-Claude

doi:10.1016/j.radonc.2022.10.029

Cited by 16 publications

(20 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mean change in VDSC before and after the revisions was not significantly different from zero and there were no revisions resulting in an increase of VDSC greater than 0.06. This finding holds with SDCS-1mm and APL-1mm, which have been shown to have a strong correlation with time-savings ( 19 , 32 , 65 ), and HD95% which is often used to assess treatment planning impact. Importantly, the quality of the DL contours was evident by the fact that the ROs required less time to revise them compared to the MDA contours (an average reduction of 0.4 hours per patient, or 35%).…”

Section: Discussionsupporting

confidence: 53%

“…Providing adequate resources to produce a large, standardized, and high-quality dataset provided a strong foundation for both model training and validation. In addition, deep learning in general (and 3D U-Nets specifically) have been shown to have advantages over other reported approaches to HN autosegmentation ( 16 , 19 , 23 , 24 , 32 , 34 ). The architecture of this model is unique because of both the size of the 3D sub-volumes it uses and the depth of the network (six layers), which enabled the creation of a model of sufficient complexity to tackle this challenging problem.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Validation of clinical acceptability of deep-learning-based automated segmentation of organs-at-risk for head-and-neck radiotherapy treatment planning

et al. 2023

View full text Add to dashboard Cite

IntroductionOrgan-at-risk segmentation for head and neck cancer radiation therapy is a complex and time-consuming process (requiring up to 42 individual structure, and may delay start of treatment or even limit access to function-preserving care. Feasibility of using a deep learning (DL) based autosegmentation model to reduce contouring time without compromising contour accuracy is assessed through a blinded randomized trial of radiation oncologists (ROs) using retrospective, de-identified patient data.MethodsTwo head and neck expert ROs used dedicated time to create gold standard (GS) contours on computed tomography (CT) images. 445 CTs were used to train a custom 3D U-Net DL model covering 42 organs-at-risk, with an additional 20 CTs were held out for the randomized trial. For each held-out patient dataset, one of the eight participant ROs was randomly allocated to review and revise the contours produced by the DL model, while another reviewed contours produced by a medical dosimetry assistant (MDA), both blinded to their origin. Time required for MDAs and ROs to contour was recorded, and the unrevised DL contours, as well as the RO-revised contours by the MDAs and DL model were compared to the GS for that patient.ResultsMean time for initial MDA contouring was 2.3 hours (range 1.6-3.8 hours) and RO-revision took 1.1 hours (range, 0.4-4.4 hours), compared to 0.7 hours (range 0.1-2.0 hours) for the RO-revisions to DL contours. Total time reduced by 76% (95%-Confidence Interval: 65%-88%) and RO-revision time reduced by 35% (95%-CI,-39%-91%). All geometric and dosimetric metrics computed, agreement with GS was equivalent or significantly greater (p<0.05) for RO-revised DL contours compared to the RO-revised MDA contours, including volumetric Dice similarity coefficient (VDSC), surface DSC, added path length, and the 95%-Hausdorff distance. 32 OARs (76%) had mean VDSC greater than 0.8 for the RO-revised DL contours, compared to 20 (48%) for RO-revised MDA contours, and 34 (81%) for the unrevised DL OARs.ConclusionDL autosegmentation demonstrated significant time-savings for organ-at-risk contouring while improving agreement with the institutional GS, indicating comparable accuracy of DL model. Integration into the clinical practice with a prospective evaluation is currently underway.

show abstract

Section: Discussionsupporting

confidence: 53%

Section: Discussionmentioning

confidence: 99%

Validation of clinical acceptability of deep-learning-based automated segmentation of organs-at-risk for head-and-neck radiotherapy treatment planning

et al. 2023

View full text Add to dashboard Cite

show abstract

“…As deep learning-based auto-contouring methods for head-and-neck OARs have been shown to offer satisfactory geometric performance [10] , [6] , the next step is to evaluate their dose impact [11] . However, we observed that dose-based studies on auto-contours tend to use either smaller (

) [12] , [13] , [14] , [15] , [16] , [17] , [18] or medium-sized (

) [19] , rather than larger [20] datasets. Studies using larger datasets simply superimpose the automated contours on the clinical dose [20] which does not fully replicate the treatment planning process.…”

Section: Introductionmentioning

confidence: 82%

Large-scale dose evaluation of deep learning organ contours in head-and-neck radiotherapy by leveraging existing plans

Mody,

Huiskes,

Chaves-de-Plaza

et al. 2024

Physics and Imaging in Radiation Oncology

View full text Add to dashboard Cite

“…The main advantage is that this technique does not require a large training dataset. The disadvantage is that it requires at least one annotated scan per patient and that traditional techniques are slow compared to auto-contouring with CNNs (Klein et al 2009, Costea et al 2022. Furthermore, when anatomical changes occur, deformable image registration (DIR) is needed, which is an ill-posed problem requiring careful hyperparameter tuning and algorithm choice to achieve high performance (Brock et al 2017).…”

Section: Introductionmentioning

confidence: 99%

Patient-specific neural networks for contour propagation in online adaptive radiotherapy

et al. 2023

View full text Add to dashboard Cite

Objective: fast and accurate contouring of daily 3D images is a prerequisite for online adaptive radiotherapy. Current automatic techniques rely either on contour propagation with registration or deep learning (DL) based segmentation with convolutional neural networks (CNNs). Registration lacks general knowledge about the appearance of organs and traditional methods are slow. CNNs lack patient-specific details and do not leverage the known contours on the planning CT. This works aims to incorporate patient-specific information into CNNs to improve their segmentation accuracy.Approach: patient-specific information is incorporated into CNNs by retraining them solely on the planning CT. The resulting patient-specific CNNs are compared to general CNNs and rigid and deformable registration for contouring of organs-at-risk and target volumes in the thorax and head-and-neck regions.Results: patient-specific fine-tuning of CNNs significantly improves contour accuracy compared to standard CNNs. The method further outperforms rigid registration and a commercial DL segmentation software and yields similar contour quality as deformable registration (DIR). It is additionally 7-10 times faster than DIR.Significance: patient-specific CNNs are a fast and accurate contouring technique, enhancing the benefits of adaptive radiotherapy.

show abstract

Comparison of atlas-based and deep learning methods for organs at risk delineation on head-and-neck CT images using an automated treatment planning system

Cited by 16 publications

References 50 publications

Validation of clinical acceptability of deep-learning-based automated segmentation of organs-at-risk for head-and-neck radiotherapy treatment planning

Validation of clinical acceptability of deep-learning-based automated segmentation of organs-at-risk for head-and-neck radiotherapy treatment planning

Large-scale dose evaluation of deep learning organ contours in head-and-neck radiotherapy by leveraging existing plans

Patient-specific neural networks for contour propagation in online adaptive radiotherapy

Contact Info

Product

Resources

About