Automatic Contour Refinement for Deep Learning Auto-segmentation of Complex Organs in MRI-guided Adaptive Radiation Therapy

Ding, Jie; Zhang, Ying; Amjad, A.; Xu, Jiaofeng; Thill, Daniel; Li, X Allen

doi:10.1016/j.adro.2022.100968

Cited by 12 publications

(13 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, study by Fu et al 19 . separated stomach and duodenum into two distinct structures but combined small and large bowel into one structure, whereas we combined stomach and duodenum as one structure but separated the small and large bowels into two distinct structures, consistent with the treatment planning requirements at our institution and others 8,42 . Consistent with the findings in a prior study by Zhang et al., 12 incorporating prior knowledge from multiple preceding fractions as an ensemble segmentation improved the accuracy for all organs including the small bowel in the later treatment fractions.…”

Section: Discussionsupporting

confidence: 85%

Progressively refined deep joint registration segmentation (ProRSeg) of gastrointestinal organs at risk: Application to MRI and cone‐beam CT

et al. 2023

View full text Add to dashboard Cite

BackgroundAdaptive radiation treatment (ART) for locally advanced pancreatic cancer (LAPC) requires consistently accurate segmentation of the extremely mobile gastrointestinal (GI) organs at risk (OAR) including the stomach, duodenum, large and small bowel. Also, due to lack of sufficiently accurate and fast deformable image registration (DIR), accumulated dose to the GI OARs is currently only approximated, further limiting the ability to more precisely adapt treatments.PurposeDevelop a 3‐D Progressively refined joint Registration‐Segmentation (ProRSeg) deep network to deformably align and segment treatment fraction magnetic resonance images (MRI)s, then evaluate segmentation accuracy, registration consistency, and feasibility for OAR dose accumulation.MethodProRSeg was trained using five‐fold cross‐validation with 110 T2‐weighted MRI acquired at five treatment fractions from 10 different patients, taking care that same patient scans were not placed in training and testing folds. Segmentation accuracy was measured using Dice similarity coefficient (DSC) and Hausdorff distance at 95th percentile (HD95). Registration consistency was measured using coefficient of variation (CV) in displacement of OARs. Statistical comparison to other deep learning and iterative registration methods were done using the Kruskal‐Wallis test, followed by pair‐wise comparisons with Bonferroni correction applied for multiple testing. Ablation tests and accuracy comparisons against multiple methods were done. Finally, applicability of ProRSeg to segment cone‐beam CT (CBCT) scans was evaluated on a publicly available dataset of 80 scans using five‐fold cross‐validation.ResultsProRSeg processed 3D volumes (128 × 192 × 128) in 3 s on a NVIDIA Tesla V100 GPU. It's segmentations were significantly more accurate () than compared methods, achieving a DSC of 0.94 ±0.02 for liver, 0.88±0.04 for large bowel, 0.78±0.03 for small bowel and 0.82±0.04 for stomach‐duodenum from MRI. ProRSeg achieved a DSC of 0.72±0.01 for small bowel and 0.76±0.03 for stomach‐duodenum from public CBCT dataset. ProRSeg registrations resulted in the lowest CV in displacement (stomach‐duodenum : 0.75%, : 0.73%, and : 0.81%; small bowel : 0.80%, : 0.80%, and : 0.68%; large bowel : 0.71%, : 0.81%, and : 0.75%). ProRSeg based dose accumulation accounting for intra‐fraction (pre‐treatment to post‐treatment MRI scan) and inter‐fraction motion showed that the organ dose constraints were violated in four patients for stomach‐duodenum and for three patients for small bowel. Study limitations include lack of independent testing and ground truth phantom datasets to measure dose accumulation accuracy.ConclusionsProRSeg produced more accurate and consistent GI OARs segmentation and DIR of MRI and CBCTs compared to multiple methods. Preliminary results indicates feasibility for OAR dose accumulation using ProRSeg.

show abstract

Section: Discussionsupporting

confidence: 85%

Progressively refined deep joint registration segmentation (ProRSeg) of gastrointestinal organs at risk: Application to MRI and cone‐beam CT

et al. 2023

View full text Add to dashboard Cite

show abstract

“…However, the application of baseline corrections can prevent such excursions and improve the GTV coverage as compared to treatments delivered without intra-fraction corrections. In the future, methods to reduce treatment session times such as more efficient contouring methods, faster dose optimization, and volumetric modulated arc therapy treatment deliveries are desirable as these will further reduce the number of intra-fraction adaptions needed ( 34 , 43 , 44 ).…”

Section: Discussionmentioning

confidence: 99%

Intra-fraction motion of pelvic oligometastases and feasibility of PTV margin reduction using MRI guided adaptive radiotherapy

et al. 2023

View full text Add to dashboard Cite

PurposeThis study assesses the impact of intra-fraction motion and PTV margin size on target coverage for patients undergoing radiation treatment of pelvic oligometastases. Dosimetric sparing of the bowel as a function of the PTV margin is also evaluated.Materials and methodsSeven patients with pelvic oligometastases previously treated on our MR-linac (35 Gy in 5 fractions) were included in this study. Retrospective adaptive plans were created for each fraction on the daily MRI datasets using PTV margins of 5 mm, 3 mm, and 2 mm. Dosimetric constraint violations and GTV coverage were measured as a function of PTV margin size. The impact of intra-fraction motion on GTV coverage was assessed by tracking the GTV position on the cine MR images acquired during treatment delivery and creating an intra-fraction dose distribution for each IMRT beam. The intra-fraction dose was accumulated for each fraction to determine the total dose delivered to the target for each PTV size.ResultsAll OAR constraints were achieved in 85.7%, 94.3%, and 100.0% of fractions when using 5 mm, 3 mm, and 2 mm PTV margins while scaling to 95% PTV coverage. Compared to plans with a 5 mm PTV margin, there was a 27.4 ± 12.3% (4.0 ± 2.2 Gy) and an 18.5 ± 7.3% (2.7 ± 1.4 Gy) reduction in the bowel D0.5cc dose for 2 mm and 3 mm PTV margins, respectively. The target dose (GTV V35 Gy) was on average 100.0 ± 0.1% (99.6 – 100%), 99.6 ± 1.0% (97.2 – 100%), and 99.0 ± 1.4% (95.0 – 100%), among all fractions for the 5 mm, 3 mm, and 2 mm PTV margins on the adaptive plans when accounting for intra-fraction motion, respectively.ConclusionA 2 mm PTV margin achieved a minimum of 95% GTV coverage while reducing the dose to the bowel for all patients.

show abstract

“…The DL model trained from popular data will not perform well when applied to new and unseen cases. [26][27][28][29] The existing DIR and DL methods are suboptimal, so the development of a reliable and efficient automatic segmentation algorithm is an urgent need of online MRI-guided prostate radiotherapy. Ding et al 27,28 developed a DL-based automatic contour refinement to correct the segmentation errors in regular method.…”

Section: Introductionmentioning

confidence: 99%

“…[26][27][28][29] The existing DIR and DL methods are suboptimal, so the development of a reliable and efficient automatic segmentation algorithm is an urgent need of online MRI-guided prostate radiotherapy. Ding et al 27,28 developed a DL-based automatic contour refinement to correct the segmentation errors in regular method. They focused on algorithmic enhancements, instead of using supplemental information.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Pretreatment information–aided automatic segmentation for online magnetic resonance imaging‐guided prostate radiotherapy

et al. 2023

View full text Add to dashboard Cite

BackgroundIt is necessary to contour regions of interest (ROIs) for online magnetic resonance imaging (MRI)‐guided adaptive radiotherapy (MRIgART). These updated contours are used for online replanning to obtain maximum dosimetric benefits. Contouring can be accomplished using deformable image registration (DIR) and deep learning (DL)‐based autosegmentation methods. However, these methods may require considerable manual editing and thus prolong treatment time.PurposeThe present study aimed to improve autosegmentation performance by integrating patients’ pretreatment information in a DL‐based segmentation algorithm. It is expected to improve the efficiency of current MRIgART process.MethodsForty patients with prostate cancer were enrolled retrospectively. The online adaptive MR images, patient‐specific planning computed tomography (CT), and contours in CT were used for segmentation. The deformable registration of planning CT and MR images was performed first to obtain a deformable CT and corresponding contours. A novel DL network, which can integrate such patient‐specific information (deformable CT and corresponding contours) into the segmentation task of MR images was designed. We performed a four‐fold cross‐validation for the DL models. The proposed method was compared with DIR and DL methods on segmentation of prostate cancer. The ROIs included the clinical target volume (CTV), bladder, rectum, left femur head, and right femur head. Dosimetric parameters of automatically generated ROIs were evaluated using a clinical treatment planning system.ResultsThe proposed method enhanced the segmentation accuracy of conventional procedures. Its mean value of the dice similarity coefficient (93.5%) over the five ROIs was higher than both DIR (87.5%) and DL (87.2%). The number of patients (n = 40) that required major editing using DIR, DL, and our method were 12, 18, and 7 (CTV); 17, 4, and 1 (bladder); 8, 11, and 5 (rectum); 2, 4, and 1 (left femur head); and 3, 7, and 1 (right femur head), respectively. The Spearman rank correlation coefficient of dosimetry parameters between the proposed method and ground truth was 0.972 ± 0.040, higher than that of DIR (0.897 ± 0.098) and DL (0.871 ± 0.134).ConclusionThis study proposed a novel method that integrates patient‐specific pretreatment information into DL‐based segmentation algorithm. It outperformed baseline methods, thereby improving the efficiency and segmentation accuracy in adaptive radiotherapy.

show abstract

Automatic Contour Refinement for Deep Learning Auto-segmentation of Complex Organs in MRI-guided Adaptive Radiation Therapy

Cited by 12 publications

References 30 publications

Progressively refined deep joint registration segmentation (ProRSeg) of gastrointestinal organs at risk: Application to MRI and cone‐beam CT

Progressively refined deep joint registration segmentation (ProRSeg) of gastrointestinal organs at risk: Application to MRI and cone‐beam CT

Intra-fraction motion of pelvic oligometastases and feasibility of PTV margin reduction using MRI guided adaptive radiotherapy

Pretreatment information–aided automatic segmentation for online magnetic resonance imaging‐guided prostate radiotherapy

Contact Info

Product

Resources

About