Automated Contouring and Planning in Radiation Therapy: What Is ‘Clinically Acceptable’?

Baroudi, Hana; Brock, Kristy K.; Cao, Wenhua; Chen, Xinru; Chung, Caroline; Court, Laurence Edward; Basha, Mohammad D. El; Farhat, Maguy; Gay, Skylar; Gronberg, Mary; Gupta, Aashish C.; Hernandez, Soleil; Huang, Kai; Jaffray, David A.; Lim, Rebecca; Marquez, Barbara; Nealon, Kelly; Netherton, Tucker; Nguyen, Callistus; Reber, Brandon; Rhee, Dong Joo; Salazar, Ramon M.; Shanker, Manish; Sjogreen, Carlos; Woodland, McKell; Yang, Jinzhong; Yu, Cenji; Zhao, Yao

doi:10.3390/diagnostics13040667

Cited by 28 publications

(28 citation statements)

References 131 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our study was validated with physician evaluations of not only the entire process but also the contouring and planning steps separately. The results of this study reaffirmed that the values for DVH objectives do not fully describe the clinical acceptability of a plan, and so physician evaluations are essential in understanding the clinical usage of a given automated tool 16 …”

Section: Discussionmentioning

confidence: 51%

“…The results of this study reaffirmed that the values for DVH objectives do not fully describe the clinical acceptability of a plan, and so physician evaluations are essential in understanding the clinical usage of a given automated tool. 16 There were limitations in this study. First, we were unable to meaningfully compare the dosimetric results from the end-to-end plans with the clinical plans as the target volumes in the automatic plans were different from the clinical plans.…”

Section: Discussionmentioning

confidence: 87%

See 1 more Smart Citation

Automatic end‐to‐end VMAT treatment planning for rectal cancers

Huang,

Chung,

Ludmir

et al. 2024

J Applied Clin Med Phys

Self Cite

View full text Add to dashboard Cite

BackgroundThe treatment planning process from segmentation to producing a deliverable plan is time‐consuming and labor‐intensive. Existing solutions automate the segmentation and planning processes individually. The feasibility of combining auto‐segmentation and auto‐planning for volumetric modulated arc therapy (VMAT) for rectal cancers in an end‐to‐end process is not clear.PurposeTo create and clinically evaluate a complete end‐to‐end process for auto‐segmentation and auto‐planning of VMAT for rectal cancer requiring only the gross tumor volume contour and a CT scan as inputs.MethodsPatient scans and data were retrospectively selected from our institutional records for patients treated for malignant neoplasm of the rectum. We trained, validated, and tested deep learning auto‐segmentation models using nnU‐Net architecture for clinical target volume (CTV), bowel bag, large bowel, small bowel, total bowel, femurs, bladder, bone marrow, and female and male genitalia. For the CTV, we identified 174 patients with clinically drawn CTVs. We used data for 18 patients for all structures other than the CTV. The structures were contoured under the guidance of and reviewed by a gastrointestinal (GI) radiation oncologist. The predicted results for CTV in 35 patients and organs at risk (OAR) in six patients were scored by the GI radiation oncologist using a five‐point Likert scale. For auto‐planning, a RapidPlan knowledge‐based planning solution was modeled for VMAT delivery with a prescription of 25 Gy in five fractions. The model was trained and tested on 20 and 34 patients, respectively. The resulting plans were scored by two GI radiation oncologists using a five‐point Likert scale. Finally, the end‐to‐end pipeline was evaluated on 16 patients, and the resulting plans were scored by two GI radiation oncologists.ResultsIn 31 of 35 patients, CTV contours were clinically acceptable without necessary modifications. The CTV achieved a Dice similarity coefficient of 0.85 (±0.05) and 95% Hausdorff distance of 15.25 (±5.59) mm. All OAR contours were clinically acceptable without edits, except for large and small bowel which were challenging to differentiate. However, contours for total, large, and small bowel were clinically acceptable. The two physicians accepted 100% and 91% of the auto‐plans. For the end‐to‐end pipeline, the two physicians accepted 88% and 62% of the auto‐plans.ConclusionsThis study demonstrated that the VMAT treatment planning technique for rectal cancer can be automated to generate clinically acceptable and safe plans with minimal human interventions.

show abstract

Section: Discussionmentioning

confidence: 51%

Section: Discussionmentioning

confidence: 87%

Automatic end‐to‐end VMAT treatment planning for rectal cancers

Huang,

Chung,

Ludmir

et al. 2024

J Applied Clin Med Phys

Self Cite

View full text Add to dashboard Cite

show abstract

“…In routine radiotherapy workflow, the volume of the patient is obtained with the external contour, and it is usually created by automated tools of the TPSs, causing some fluctuations on the contour and consequently creating a volume that can be different compared to the real value. 17 The quantitative effects of these fluctuations on MC dose calculations were investigated in this study.…”

Section: Discussionmentioning

confidence: 99%

Evaluating the performance of automated external contouring tool on dose calculation of treatment planning system

Banaee,

Aeini,

Barough

2024

J Radiother Pract

View full text Add to dashboard Cite

Introduction The main goal of radiation therapy is to eradicate all cancer cells and minimize the damage to healthy tissues around the tumour. Treatment planning systems are used to predict the outcome of the treatment in terms of dose distribution prior to the treatment. One of the most reliable dose calculation algorithms is Monte Carlo. The aim of this study is to evaluate the performance of automated external contouring tool on dose calculation using Monte Carlo algorithm. Materials and methods The external contour of thorax phantom was created by automated tools of Monaco treatment planning system, and then, the IAEA-TECDOC-1583 quality assurance tests were created. Then, the treatment plans were delivered to the phantom, and the dose was measured by the Farmer ionization chamber at specific points. The external contour was corrected according to the source surface distances (SSD) which are mentioned in TECDOC-1583, and the dose was re-calculated. Finally, a comparison was made between the results. Results Dosimetric tests of TECDOC-1583 showed the errors ranged from −2·8% to +2·5%. In case of editing external contour and omitting fluctuations, the errors were decreased. The comparisons indicated that the most significant variation occurred in test 4 and the least changes were related to the tests 1 and 3. Conclusions The results of the study showed that the fluctuations of the external contour affect the calculated volume of the phantom and thus the dose. In order to obtain correct results, automated external contouring tools should be used with the correct instructions and re-checked before treatment planning.

show abstract

“…27 As a result, computational challenges were organized to evaluate the quality of auto-segmentation results, 28 and several datasets were made publicly available for benchmarking different auto-segmentation methodologies 20,[28][29][30][31] and evaluating their clinical acceptability. 32 However, even with sophisticated auto-segmentation approaches, manual contouring is still the method of choice for evaluating and benchmarking the performance of the developed algorithms.…”

Section: Introductionmentioning

confidence: 99%

“…On the other hand, automated contouring (i.e., automated segmentation, auto‐segmentation) performed by computer‐assisted algorithms 17 has witnessed a revival with the introduction and integration of artificial intelligence approaches, such as deep learning, 18–26 which has outperformed the previously established atlas‐based auto‐segmentation 27 . As a result, computational challenges were organized to evaluate the quality of auto‐segmentation results, 28 and several datasets were made publicly available for benchmarking different auto‐segmentation methodologies 20,28–31 and evaluating their clinical acceptability 32 . However, even with sophisticated auto‐segmentation approaches, manual contouring is still the method of choice for evaluating and benchmarking the performance of the developed algorithms.…”

Section: Introductionmentioning

confidence: 99%

vOARiability: Interobserver and intermodality variability analysis in OAR contouring from head and neck CT and MR images

Podobnik,

Ibragimov,

Peterlin

et al. 2024

Medical Physics

View full text Add to dashboard Cite

BackgroundAccurate and consistent contouring of organs‐at‐risk (OARs) from medical images is a key step of radiotherapy (RT) cancer treatment planning. Most contouring approaches rely on computed tomography (CT) images, but the integration of complementary magnetic resonance (MR) modality is highly recommended, especially from the perspective of OAR contouring, synthetic CT and MR image generation for MR‐only RT, and MR‐guided RT. Although MR has been recognized as valuable for contouring OARs in the head and neck (HaN) region, the accuracy and consistency of the resulting contours have not been yet objectively evaluated.PurposeTo analyze the interobserver and intermodality variability in contouring OARs in the HaN region, performed by observers with different level of experience from CT and MR images of the same patients.MethodsIn the final cohort of 27 CT and MR images of the same patients, contours of up to 31 OARs were obtained by a radiation oncology resident (junior observer, JO) and a board‐certified radiation oncologist (senior observer, SO). The resulting contours were then evaluated in terms of interobserver variability, characterized as the agreement among different observers (JO and SO) when contouring OARs in a selected modality (CT or MR), and intermodality variability, characterized as the agreement among different modalities (CT and MR) when OARs were contoured by a selected observer (JO or SO), both by the Dice coefficient (DC) and 95‐percentile Hausdorff distance (HD95).ResultsThe mean (±standard deviation) interobserver variability was 69.0 ± 20.2% and 5.1 ± 4.1 mm, while the mean intermodality variability was 61.6 ± 19.0% and 6.1 ± 4.3 mm in terms of DC and HD95, respectively, across all OARs. Statistically significant differences were only found for specific OARs. The performed MR to CT image registration resulted in a mean target registration error of 1.7 ± 0.5 mm, which was considered as valid for the analysis of intermodality variability.ConclusionsThe contouring variability was, in general, similar for both image modalities, and experience did not considerably affect the contouring performance. However, the results indicate that an OAR is difficult to contour regardless of whether it is contoured in the CT or MR image, and that observer experience may be an important factor for OARs that are deemed difficult to contour. Several of the differences in the resulting variability can be also attributed to adherence to guidelines, especially for OARs with poor visibility or without distinctive boundaries in either CT or MR images. Although considerable contouring differences were observed for specific OARs, it can be concluded that almost all OARs can be contoured with a similar degree of variability in either the CT or MR modality, which works in favor of MR images from the perspective of MR‐only and MR‐guided RT.

show abstract

Automated Contouring and Planning in Radiation Therapy: What Is ‘Clinically Acceptable’?

Cited by 28 publications

References 131 publications

Automatic end‐to‐end VMAT treatment planning for rectal cancers

Automatic end‐to‐end VMAT treatment planning for rectal cancers

Evaluating the performance of automated external contouring tool on dose calculation of treatment planning system

vOARiability: Interobserver and intermodality variability analysis in OAR contouring from head and neck CT and MR images

Contact Info

Product

Resources

About