Geometric and dosimetric evaluation of atlas based auto-segmentation of cardiac structures in breast cancer patients

Kaderka, Robert; Gillespie, Erin F.; Mundt, R.; Bryant, Alex K.; Sanudo-Thomas, Camila B.; Harrison, Anna L.; Wouters, Emilie L.; Moiseenko, Vitali; Moore, Kevin L.; Atwood, Todd; Murphy, James D.

doi:10.1016/j.radonc.2018.07.013

Cited by 75 publications

(70 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address this, recent atlas‐based methods have standardized the size of the LADA to 4 mm throughout its entire length . Nevertheless, our DL pipeline performed well for coronary artery contours on non‐contrast CTs (DSC ~ 0.50, MDA < 2.0 mm), particularly as compared to recent atlas results where coronary artery (LADA, RCA, and LMCA) DSCs ranged from 0.09 to 0.27 and had MDAs > 4 mm . Coronary artery segmentations may be improved through the use of high resolution (0.78 × 0.78 × 1.6 mm 3 ) CTCA that use contrast and yield DSCs ~ 60% .…”

Section: Discussionmentioning

confidence: 59%

“…While cardiac substructure segmentation has been explored previously, to our knowledge, none have included paired MR/CT multi-channel data inputs to yield robust segmentations on non-contrast CT inputs. Several atlas segmentation methods have been recently published [13][14][15] and report cardiac chamber DSCs > 0.75. However, these methods have had limited success segmenting coronary arteries as atlas methods rely on image registration quality and are unable to consider large amounts of patient data due to computational demands.…”

Section: Discussionmentioning

confidence: 99%

“…16 However, most atlases fail in segmenting the coronary arteries, with Dice similarity coefficients (DSCs) between ground truth and auto-segmentation of the LADA ranging from 0.09 to 0.27. [13][14][15]17 Incorporating multiple imaging modalities (i.e., contrast enhanced CT and magnetic resonance imaging (MRI)) has improved visualization and yielded successful chamber and great vessel segmentation, yet coronary artery segmentation remains an unmet need. 13,14 Recently, deep neural networks (DNNs), such as U-Net, 18 have shown great promise for generating accurate and rapid delineations for RT.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Cardiac substructure segmentation with deep learning for improved cardiac sparing

et al. 2019

View full text Add to dashboard Cite

Purpose Radiation dose to cardiac substructures is related to radiation‐induced heart disease. However, substructures are not considered in radiation therapy planning (RTP) due to poor visualization on CT. Therefore, we developed a novel deep learning (DL) pipeline leveraging MRI’s soft tissue contrast coupled with CT for state‐of‐the‐art cardiac substructure segmentation requiring a single, non‐contrast CT input. Materials/methods Thirty‐two left‐sided whole‐breast cancer patients underwent cardiac T2 MRI and CT‐simulation. A rigid cardiac‐confined MR/CT registration enabled ground truth delineations of 12 substructures (chambers, great vessels (GVs), coronary arteries (CAs), etc.). Paired MRI/CT data (25 patients) were placed into separate image channels to train a three‐dimensional (3D) neural network using the entire 3D image. Deep supervision and a Dice‐weighted multi‐class loss function were applied. Results were assessed pre/post augmentation and post‐processing (3D conditional random field (CRF)). Results for 11 test CTs (seven unique patients) were compared to ground truth and a multi‐atlas method (MA) via Dice similarity coefficient (DSC), mean distance to agreement (MDA), and Wilcoxon signed‐ranks tests. Three physicians evaluated clinical acceptance via consensus scoring (5‐point scale). Results The model stabilized in ~19 h (200 epochs, training error <0.001). Augmentation and CRF increased DSC 5.0 ± 7.9% and 1.2 ± 2.5%, across substructures, respectively. DL provided accurate segmentations for chambers (DSC = 0.88 ± 0.03), GVs (DSC = 0.85 ± 0.03), and pulmonary veins (DSC = 0.77 ± 0.04). Combined DSC for CAs was 0.50 ± 0.14. MDA across substructures was <2.0 mm (GV MDA = 1.24 ± 0.31 mm). No substructures had statistical volume differences (P > 0.05) to ground truth. In four cases, DL yielded left main CA contours, whereas MA segmentation failed, and provided improved consensus scores in 44/60 comparisons to MA. DL provided clinically acceptable segmentations for all graded patients for 3/4 chambers. DL contour generation took ~14 s per patient. Conclusions These promising results suggest DL poses major efficiency and accuracy gains for cardiac substructure segmentation offering high potential for rapid implementation into RTP for improved cardiac sparing.

show abstract

Section: Discussionmentioning

confidence: 59%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cardiac substructure segmentation with deep learning for improved cardiac sparing

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Hausdorff distances (HD95)) and volumetric geometric indices (e.g., DSC and Jaccard) [9]. Although these indices are easy to calculate, they do not consider the clinical effect and may lack clinical relevance [10,11]. In addition, there is considerable variability between them, and different auto-segmentation studies use different geometric indices to evaluate the contouring results; further, different indices have different properties [12][13][14].…”

Section: Introductionmentioning

confidence: 99%

“…The relationships between geometric indices and dosimetric indices are yet to be further studied. At present, the research on the evaluation of geometric indices and dose parameters of auto-segmentation results is carried out under the condition of unknown contouring error [10,11,16]. The purpose of our study is to explore the evaluation accuracy of the geometric indices for evaluating the contours under the known errors.…”

Section: Introductionmentioning

confidence: 99%

Clinically oriented contour evaluation using geometric and dosimetric indices based on simple geometric transformations

Xian

Xiao

et al. 2020

Preprint

View full text Add to dashboard Cite

Abstract Background: In radiotherapy, geometric indices are often used to evaluate the accuracy of contouring; however, the ability of geometric indices to identify the error of contouring results is limited, and they do not consider any clinical background. Based on the reference contouring, we systematically introduced the known geometric errors to study the relationship between geometric indices and dosimetric indices and evaluated the clinical feasibility of assessing the accuracy of contouring based on geometric indices alone.Materials and Methods: A C-shaped target, organ at risk (Core), and intensity-modulated radiotherapy (IMRT) plan outlined in the American Association of Physicists in Medicine (AAPM) TG-119 report (The report of Task Group 119 of the AAPM) were used as references. Translation, scaling, rotation (except for the Core), and sine function transformation were performed to simulate the test contours. The corresponding dosimetric indices were obtained from the original dose distribution of the radiotherapy plan, and correlations (R²) between geometric and dosimetric indices were quantified through linear regression. The Wilcoxon signed rank test was used to compare the differences between the geometric indices of three different directions of translation transformations.Results: The correlations between the geometric and dosimetric indices were inconsistent for the contouring of the target and Core after the geometric transformation. Except for the sine function transformation (R²: 0.04–0.023, P > 0.05), the other geometric transformations of the planning target volume (PTV) had correlations with the dosimetric indices D98% and Dmean (R²: 0.689–0.988), 80% of which were strongly correlated. The correlation results for the other geometric transformations in the Core were similar to those in the PTV except for the posterior direction transformation. The results of Wilcoxon signed rank test showed that only the P-values of volumetric geometric indices of PTV were less than 0.05.Conclusions: The dosimetric indices are heavily influenced by the contour differences, thus highlighting their importance in the evaluation process. Clinically, an assessment of the contour accuracy of the region of interest is not feasible based on geometric indices alone, and should be combined with dosimetric indices.

show abstract

Technical note: Atlas‐based Auto‐segmentation of masticatory muscles for head and neck cancer radiotherapy

Zhang

Chen

et al. 2020

J Applied Clin Med Phys

View full text Add to dashboard Cite

Purpose The study aimed to use quantitative geometric and dosimetric metrics to assess the accuracy of atlas‐based auto‐segmentation of masticatory muscles (MMs) compared to manual drawn contours for head and neck cancer (HNC) radiotherapy (RT). Materials and methods Fifty‐eight patients with HNC treated with RT were analyzed. Paired MMs (masseter, temporalis, and medial and lateral pterygoids) were manually delineated on planning computed tomography (CT) images for all patients. Twenty‐nine patients were used to generate the MM atlas. Using this atlas, automatic segmentation of the MMs was performed for the remaining 29 patients without manual correction. Auto‐segmentation accuracy for MMs was compared using dice similarity coefficients (DSCs), Hausdorff distance (HD), HD95, and variation in the center of mass (∆COM). The dosimetric impact on MMs was calculated (∆dose) using dosimetric parameters (D99%, D95%, D50%, and D1%), and compared with the geometric indices to test correlation. Results DSC mean ranges from 0.79 ± 0.04 to 0.85 ± 0.04, HD mean from 0.43 ± 0.08 to 0.82 ± 0.26 cm, HD95 mean from 0.32 ± 0.08 to 0.42 ± 0.16 cm, and ∆COM mean from 0.18 ± 0.11 to 0.33 ± 0.23 cm. The mean MM volume difference was < 15%. The correlation coefficient (r) of geometric and dosimetric indices for the four MMs ranges between −0.456 and 0.300. Conclusions Atlas‐based auto‐segmentation for masticatory muscles provides geometrically accurate contours compared to manual drawn contours. Dose obtained from those auto‐segmented contours is comparable to that from manual drawn contours. Atlas‐based auto‐segmentation strategy for MM in HN radiotherapy is readily availalbe for clinical implementation.

show abstract

Geometric and dosimetric evaluation of atlas based auto-segmentation of cardiac structures in breast cancer patients

Cited by 75 publications

References 19 publications

Cardiac substructure segmentation with deep learning for improved cardiac sparing

Cardiac substructure segmentation with deep learning for improved cardiac sparing

Clinically oriented contour evaluation using geometric and dosimetric indices based on simple geometric transformations

Technical note: Atlas‐based Auto‐segmentation of masticatory muscles for head and neck cancer radiotherapy

Contact Info

Product

Resources

About