Fully automatic and robust segmentation of the clinical target volume for radiotherapy of breast cancer using big data and deep learning

Men, Kuo; Zhang, Tao; Chen, Xinyuan; Chen, Bin; Tang, Yu; Wang, Shulian; Li, Yexiong; Dai, Jianrong

doi:10.1016/j.ejmp.2018.05.006

Cited by 127 publications

(112 citation statements)

References 27 publications

Supporting

Mentioning

107

Contrasting

Unclassified

Order By: Relevance

“…A significant shorter time for each fraction is possible if further improvement in the deformable registration step of the original contours is achieved. However, other alternatives are also possible for the generation of new contours for both tumor and OARs at each fraction, such as the use of atlas based methods [34] or convolutional neural networks [35,36]. The time spent in recontouring and generating a new treatment plan could also be used to acquire additional MR sequences for offline evaluation of treatment response (for instance, diffusion weighted MR [37]).…”

Section: Discussionmentioning

confidence: 99%

Clinical implementation of magnetic resonance imaging guided adaptive radiotherapy for localized prostate cancer

Tetar

Bruynzeel

Lagerwaard

et al. 2019

Physics and Imaging in Radiation Oncology

134

127

View full text Add to dashboard Cite

A B S T R A C TBackground and purpose: Magnetic resonance-guided radiation therapy (MRgRT) has recently become available in clinical practice and is expected to expand significantly in coming years. MRgRT offers marker-less continuous imaging during treatment delivery, use of small clinical target volume (CTV) to planning target volume (PTV) margins, and finally the option to perform daily plan re-optimization. Materials and methods: A total of 140 patients (700 fractions) have been treated with MRgRT and online plan adaptation for localized prostate cancer since early 2016. Clinical workflow for MRgRT of prostate cancer consisted of patient selection, simulation on both MR-and computed tomography (CT) scan, inverse intensitymodulated radiotherapy (IMRT) treatment planning and daily plan re-optimization prior to treatment delivery with partial organs at risk (OAR) recontouring within the first 2 cm outside the PTV. For each adapted plan online patient-specific quality assurance (QA) was performed by means of a secondary Monte Carlo 3D dose calculation and gamma analysis comparison. Patient experiences with MRgRT were assessed using a patientreported outcome questionnaire (PRO-Q) after the last fraction. Results: In 97% of fractions, MRgRT was delivered using the online adapted plan. Intrafractional prostate drifts necessitated 2D-corrections during treatment in approximately 20% of fractions. The average duration of an uneventful fraction of MRgRT was 45 min. showed that MRgRT was generally well tolerated, with disturbing noise sensations being most commonly reported. Conclusions: MRgRT with daily online plan adaptation constitutes an innovative approach for delivering SBRT for prostate cancer and appears to be feasible, although necessitating extended timeslots and logistical challenges.

show abstract

Section: Discussionmentioning

confidence: 99%

Clinical implementation of magnetic resonance imaging guided adaptive radiotherapy for localized prostate cancer

Tetar

Bruynzeel

Lagerwaard

et al. 2019

Physics and Imaging in Radiation Oncology

134

127

View full text Add to dashboard Cite

show abstract

“…To date, automated workflow has been developed and implemented in various businesses but the pace of applying automation into health care is not as fast as expected. In the recent two decades, the rapid progress in computerized radiotherapy treatment planning systems has led to great interest in the possibility of automating radiotherapy workflow, which includes automated target delineation (auto-segmentation), automated treatment planning, automated real-time adaptive radiotherapy and automated quality assurance [20][21][22][23][24][25]. This study presents a well-designed fully automated planning algorithm for standardized whole-breast radiotherapy treatment plan generation with a large cohort of 99 patients.…”

Section: Discussionmentioning

confidence: 99%

Automated Hypofractionated IMRT treatment planning for early-stage breast Cancer

Lin

et al. 2020

Radiat Oncol

View full text Add to dashboard Cite

Background: Hypofractionated whole-breast irradiation is a standard adjuvant therapy for early-stage breast cancer. This study evaluates the plan quality and efficacy of an in-house-developed automated radiotherapy treatment planning algorithm for hypofractionated whole-breast radiotherapy. Methods: A cohort of 99 node-negative left-sided breast cancer patients completed hypofractionated whole-breast irradiation with six-field IMRT for 42.56 Gy in 16 daily fractions from year 2016 to 2018 at a tertiary center were replanned with an in-house-developed algorithm. The automated plan-generating C#-based program is developed in a Varian ESAPI research mode. The dose-volume histogram (DVH) and other dosimetric parameters of the automated and manual plans were directly compared. Results: The average time for generating an autoplan was 5 to 6 min, while the manual planning time ranged from 1 to 1.5 h. There was only a small difference in both the gantry angles and the collimator angles between the autoplans and the manual plans (ranging from 2.2 to 5.3 degrees). Autoplans and manual plans performed similarly well in hotspot volume and PTV coverage, with the autoplans performing slightly better in the ipsilateral-lungsparing dose parameters but were inferior in contralateral-breast-sparing. The autoplan dosimetric quality did not vary with different breast sizes, but for manual plans, there was worse ipsilateral-lung-sparing (V 4Gy ) in larger or medium-sized breasts than in smaller breasts. Autoplans were generally superior than manual plans in CI (1.24 ± 0.06 vs. 1.30 ± 0.09, p < 0.01) and MU (1010 ± 46 vs. 1205 ± 187, p < 0.01). Conclusions:Our study presents a well-designed standardized fully automated planning algorithm for optimized whole-breast radiotherapy treatment plan generation. A large cohort of 99 patients were re-planned and retrospectively analyzed. The automated plans demonstrated similar or even better dosimetric quality and efficacy in comparison with the manual plans. Our result suggested that the autoplanning algorithm has great clinical applicability potential.

show abstract

“…Comparison setup and metrics: We use 3-fold cross-validation, separated at the patient level, to evaluate performance of our approach and the competitor methods. We compare against setups using only the CT appearance information [14,15] and setups using the CT with binary GTV/LN masks [3]. Finally, we also compare against setups using the CT + GTV/LN SDMs, which does not consider the OARs.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…However, to the best of our knowledge, no prior work, CNN-based or not, has addressed esophageal cancer CTV segmentation. Works on CTV segmentation of other cancer types mostly operate based on the RTCT appearance alone [14,15]. As shown in Fig.…”

Section: Introductionmentioning

confidence: 99%

“…Since we are the first to tackle automated esophageal cancer CTV delineation, we compare against previous CTV delineation methods for other cancers [3,15], using the 3D PHNN as the delineation model. When comparing against pure appearance-based [15] and binary-mask-based [3] solutions, we show that our approach provides improvements of 10% and 3.8% in Dice score, respectively, with analogous improvements in Hausdorff distance (HD) and average surface distance (ASD). Moreover, we also show that PHNN is responsible for providing improvements of 1% in Dice score and 0.4mm reduction in ASD over a 3D U-Net model [4].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Esophageal Clinical Target Volume Delineation Using Encoded 3D Spatial Context of Tumors, Lymph Nodes, and Organs At Risk

Jin¹,

Guo²,

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Clinical target volume (CTV) delineation from radiotherapy computed tomography (RTCT) images is used to define the treatment areas containing the gross tumor volume (GTV) and/or sub-clinical malignant disease for radiotherapy (RT). High intra-and inter-user variability makes this a particularly difficult task for esophageal cancer. This motivates automated solutions, which is the aim of our work. Because CTV delineation is highly context-dependent-it must encompass the GTV and regional lymph nodes (LNs) while also avoiding excessive exposure to the organs at risk (OARs)-we formulate it as a deep contextual appearance-based problem using encoded spatial contexts of these anatomical structures. This allows the deep network to better learn from and emulate the margin-and appearance-based delineation performed by human physicians. Additionally, we develop domain-specific data augmentation to inject robustness to our system. Finally, we show that a simple 3D progressive holistically nested network (PHNN), which avoids computationally heavy decoding paths while still aggregating features at different levels of context, can outperform more complicated networks. Cross-validated experiments on a dataset of 135 esophageal cancer patients demonstrate that our encoded spatial context approach can produce concrete performance improvements, with an average Dice score of 83.9 ± 5.4% and an average surface distance of 4.2 ± 2.7 mm, representing improvements of 3.8% and 2.4mm, respectively, over the state-of-the-art approach.

show abstract

Fully automatic and robust segmentation of the clinical target volume for radiotherapy of breast cancer using big data and deep learning

Cited by 127 publications

References 27 publications

Clinical implementation of magnetic resonance imaging guided adaptive radiotherapy for localized prostate cancer

Clinical implementation of magnetic resonance imaging guided adaptive radiotherapy for localized prostate cancer

Automated Hypofractionated IMRT treatment planning for early-stage breast Cancer

Deep Esophageal Clinical Target Volume Delineation Using Encoded 3D Spatial Context of Tumors, Lymph Nodes, and Organs At Risk

Contact Info

Product

Resources

About