Deep Learning for Per-Fraction Automatic Segmentation of Gross Tumor Volume (GTV) and Organs at Risk (OARs) in Adaptive Radiotherapy of Cervical Cancer

Breto, Adrian L.; Spieler, Benjamin; Zavala-Romero, Olmo; Alhusseini, Mohammad; Patel, Nirav; Asher, David; Xu, Isaac; Baikovitz, Jacqueline B.; Mellon, Eric A.; Ford, John C.; Stoyanova, Radka; Portelance, Lorraine

doi:10.3389/fonc.2022.854349

Cited by 12 publications

(22 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Commercial systems have become available to perform online magnetic resonance imaging–assisted or CBCT-assisted ART . To decrease adaptation time, automatic AI-based segmentation methods for organs at risk have been developed . However, data on the gain of ART in terms of the equivalent uniform dose and the accumulated dose distribution over the whole series in comparison with IGRT are lacking.…”

Section: Introductionmentioning

confidence: 99%

“… 12 , 13 To decrease adaptation time, automatic AI-based segmentation methods for organs at risk have been developed. 14 , 15 However, data on the gain of ART in terms of the equivalent uniform dose and the accumulated dose distribution over the whole series in comparison with IGRT are lacking. Furthermore, strategies to optimally select patients based on dosimetric criteria for ART are also not defined.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of Online-Onboard Adaptive Intensity-Modulated Radiation Therapy or Volumetric-Modulated Arc Radiotherapy With Image-Guided Radiotherapy for Patients With Gynecologic Tumors in Dependence on Fractionation and the Planning Target Volume Margin

et al. 2023

View full text Add to dashboard Cite

ImportancePatients with newly diagnosed locally advanced cervical carcinomas or recurrences after surgery undergoing radiochemotherapy whose tumor is unsuited for a brachytherapy boost need high-dose percutaneous radiotherapy with small margins to compensate for clinical target volume deformations and set-up errors. Cone-beam computed tomography–based online adaptive radiotherapy (ART) has the potential to reduce planning target volume (PTV) margins below 5 mm for these tumors.ObjectiveTo compare online ART technologies with image-guided radiotherapy (IGRT) for gynecologic tumors.Design, Setting, and ParticipantsThis comparative effectiveness study comprised all 7 consecutive patients with gynecologic tumors who were treated with ART with artificial intelligence segmentation from January to May 2022 at the West German Cancer Center. All adapted treatment plans were reviewed for the new scenario of organs at risk and target volume. Dose distributions of adapted and scheduled plans optimized on the initial planning computed tomography scan were compared.ExposureOnline ART for gynecologic tumors.Main Outcomes and MeasuresTarget dose coverage with ART compared with IGRT for PTV margins of 5 mm or less in terms of the generalized equivalent uniform dose (gEUD) without increasing the gEUD for the organs at risk (bladder and rectum).ResultsThe first 10 treatment series among 7 patients (mean [SD] age, 65.7 [16.5] years) with gynecologic tumors from a prospective observational trial performed with ART were compared with IGRT. For a clinical PTV margin of 5 mm, IGRT was associated with a median gEUD decrease in the interfractional clinical target volume of −1.5% (90% CI, −31.8% to 2.9%) for all fractions in comparison with the planned dose distribution. Online ART was associated with a decrease of −0.02% (90% CI, −3.2% to 1.5%), which was less than the decrease with IGRT (P &lt; .001). This was not associated with an increase in the gEUD for the bladder or rectum. For a PTV margin of 0 mm, the median gEUD deviation with IGRT was −13.1% (90% CI, −47.9% to 1.6%) compared with 0.1% (90% CI, −2.3% to 6.6%) with ART (P &lt; .001). The benefit associated with ART was larger for a PTV margin of 0 mm than of 5 mm (P = .004) due to spreading of the cold spot at the clinical target volume margin from fraction to fraction with a median SD of 2.4 cm (90% CI, 1.9-3.4 cm) for all patients.Conclusions and RelevanceThis study suggests that ART is associated with an improvement in the percentage deviation of gEUD for the interfractional clinical target volume compared with IGRT. As the gain of ART depends on fractionation and PTV margin, a strategy is proposed here to switch from IGRT to ART, if the delivered gEUD distribution becomes unfavorable in comparison with the expected distribution during the course of treatment.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Comparison of Online-Onboard Adaptive Intensity-Modulated Radiation Therapy or Volumetric-Modulated Arc Radiotherapy With Image-Guided Radiotherapy for Patients With Gynecologic Tumors in Dependence on Fractionation and the Planning Target Volume Margin

et al. 2023

View full text Add to dashboard Cite

show abstract

“…There is extensive literature demonstrating varying success in automatically delineating solid GTV volumes using MRI information or multi‐modality imaging information 16,17,22–24 . There is limited literature on automatically delineating post‐operative GTV volumes.…”

Section: Introductionmentioning

confidence: 99%

“…20,21 There is extensive literature demonstrating varying success in automatically delineating solid GTV volumes using MRI information or multi-modality imaging information. 16,17,[22][23][24] There is limited literature on automatically delineating post-operative GTV volumes. Previous post-operative autocontouring studies relied on multiple MRI sequences for training and achieved Dice Similarity Coefficients (DSCs) ranging from 0.75 to 0.89.…”

Section: Introductionmentioning

confidence: 99%

Resection cavity auto‐contouring for patients with pediatric medulloblastoma using only CT information

Hernandez

Nguyen

Gay

et al. 2023

J Applied Clin Med Phys

View full text Add to dashboard Cite

Target delineation for radiation therapy is a time-consuming and complex task. Autocontouring gross tumor volumes (GTVs) has been shown to increase efficiency. However, there is limited literature on post-operative target delineation,particularly for CT-based studies.To this end,we trained a CT-based autocontouring model to contour the post-operative GTV of pediatric patients with medulloblastoma. Methods: One hundred four retrospective pediatric CT scans were used to train a GTV auto-contouring model. Eighty patients were then preselected for contour visibility, continuity, and location to train an additional model. Each GTV was manually annotated with a visibility score based on the number of slices with a visible GTV (1 = < 25%, 2 = 25-50%, 3 = > 50-75%, and 4 = > 75-100%). Contrast and the contrast-to-noise ratio (CNR) were calculated for the GTV contour with respect to a cropped background image. Both models were tested on the original and pre-selected testing sets. The resulting surface and overlap metrics were calculated comparing the clinical and autocontoured GTVs and the corresponding clinical target volumes (CTVs). Results: Eighty patients were pre-selected to have a continuous GTV within the posterior fossa. Of these, 7, 41, 21, and 11 were visibly scored as 4, 3, 2, and 1, respectively. The contrast and CNR removed an additional 11 and 20 patients from the dataset, respectively. The Dice similarity coefficients (DSC) were 0.61 ± 0.29 and 0.67 ± 0.22 on the models without pre-selected training data and 0.55 ± 13.01 and 0.83 ± 0.17 on the models with pre-selected data, respectively. The DSC on the CTV expansions were 0.90 ± 0.13. Conclusion:We successfully automatically contoured continuous GTVs within the posterior fossa on scans that had contrast > ± 10 HU. CT-Based autocontouring algorithms have potential to positively impact centers with limited MRI access.

show abstract

“…Modern automatic multi‐organ segmentation models can be roughly classified into two categories: conventional learning and deep learning‐based segmentation 3,9–11 . In general, conventional learning‐based approaches for building segmentation models have two major components 12 : (a) extraction of hand‐crafted features to represent target organs, and (b) classification/regression model for segmentation.…”

Section: Introductionmentioning

confidence: 99%

A new architecture combining convolutional and transformer‐based networks for automatic 3D multi‐organ segmentation on CT images

Li,

Bagher‐Ebadian,

Sultan

et al. 2023

Medical Physics

View full text Add to dashboard Cite

PurposeDeep learning‐based networks have become increasingly popular in the field of medical image segmentation. The purpose of this research was to develop and optimize a new architecture for automatic segmentation of the prostate gland and normal organs in the pelvic, thoracic, and upper gastro‐intestinal (GI) regions.MethodsWe developed an architecture which combines a shifted‐window (Swin) transformer with a convolutional U‐Net. The network includes a parallel encoder, a cross‐fusion block, and a CNN‐based decoder to extract local and global information and merge related features on the same scale. A skip connection is applied between the cross‐fusion block and decoder to integrate low‐level semantic features. Attention gates (AGs) are integrated within the CNN to suppress features in image background regions. Our network is termed “SwinAttUNet.” We optimized the architecture for automatic image segmentation. Training datasets consisted of planning‐CT datasets from 300 prostate cancer patients from an institutional database and 100 CT datasets from a publicly available dataset (CT‐ORG). Images were linearly interpolated and resampled to a spatial resolution of (1.0 × 1.0× 1.5) mm3. A volume patch (192 × 192 × 96) was used for training and inference, and the dataset was split into training (75%), validation (10%), and test (15%) cohorts. Data augmentation transforms were applied consisting of random flip, rotation, and intensity scaling. The loss function comprised Dice and cross‐entropy equally weighted and summed. We evaluated Dice coefficients (DSC), 95th percentile Hausdorff Distances (HD95), and Average Surface Distances (ASD) between results of our network and ground truth data.ResultsSwinAttUNet, DSC values were 86.54 ± 1.21, 94.15 ± 1.17, and 87.15 ± 1.68% and HD95 values were 5.06 ± 1.42, 3.16 ± 0.93, and 5.54 ± 1.63 mm for the prostate, bladder, and rectum, respectively. Respective ASD values were 1.45 ± 0.57, 0.82 ± 0.12, and 1.42 ± 0.38 mm. For the lung, liver, kidneys and pelvic bones, respective DSC values were: 97.90 ± 0.80, 96.16 ± 0.76, 93.74 ± 2.25, and 89.31 ± 3.87%. Respective HD95 values were: 5.13 ± 4.11, 2.73 ± 1.19, 2.29 ± 1.47, and 5.31 ± 1.25 mm. Respective ASD values were: 1.88 ± 1.45, 1.78 ± 1.21, 0.71 ± 0.43, and 1.21 ± 1.11 mm. Our network outperformed several existing deep learning approaches using only attention‐based convolutional or Transformer‐based feature strategies, as detailed in the results section.ConclusionsWe have demonstrated that our new architecture combining Transformer‐ and convolution‐based features is able to better learn the local and global context for automatic segmentation of multi‐organ, CT‐based anatomy.

show abstract

Deep Learning for Per-Fraction Automatic Segmentation of Gross Tumor Volume (GTV) and Organs at Risk (OARs) in Adaptive Radiotherapy of Cervical Cancer

Cited by 12 publications

References 27 publications

Comparison of Online-Onboard Adaptive Intensity-Modulated Radiation Therapy or Volumetric-Modulated Arc Radiotherapy With Image-Guided Radiotherapy for Patients With Gynecologic Tumors in Dependence on Fractionation and the Planning Target Volume Margin

Comparison of Online-Onboard Adaptive Intensity-Modulated Radiation Therapy or Volumetric-Modulated Arc Radiotherapy With Image-Guided Radiotherapy for Patients With Gynecologic Tumors in Dependence on Fractionation and the Planning Target Volume Margin

Resection cavity auto‐contouring for patients with pediatric medulloblastoma using only CT information

A new architecture combining convolutional and transformer‐based networks for automatic 3D multi‐organ segmentation on CT images

Contact Info

Product

Resources

About