Gradient-based delineation of the primary GTV on FDG-PET in non-small cell lung cancer: A comparison with threshold-based approaches, CT and surgical specimens

PurposeThe aim of this paper is to define the requirements and describe the design and implementation of a standard benchmark tool for evaluation and validation of PET‐auto‐segmentation (PET‐AS) algorithms. This work follows the recommendations of Task Group 211 (TG211) appointed by the American Association of Physicists in Medicine (AAPM).MethodsThe recommendations published in the AAPM TG211 report were used to derive a set of required features and to guide the design and structure of a benchmarking software tool. These items included the selection of appropriate representative data and reference contours obtained from established approaches and the description of available metrics. The benchmark was designed in a way that it could be extendable by inclusion of bespoke segmentation methods, while maintaining its main purpose of being a standard testing platform for newly developed PET‐AS methods. An example of implementation of the proposed framework, named PETASset, was built. In this work, a selection of PET‐AS methods representing common approaches to PET image segmentation was evaluated within PETASset for the purpose of testing and demonstrating the capabilities of the software as a benchmark platform.ResultsA selection of clinical, physical, and simulated phantom data, including “best estimates” reference contours from macroscopic specimens, simulation template, and CT scans was built into the PETASset application database. Specific metrics such as Dice Similarity Coefficient (DSC), Positive Predictive Value (PPV), and Sensitivity (S), were included to allow the user to compare the results of any given PET‐AS algorithm to the reference contours. In addition, a tool to generate structured reports on the evaluation of the performance of PET‐AS algorithms against the reference contours was built. The variation of the metric agreement values with the reference contours across the PET‐AS methods evaluated for demonstration were between 0.51 and 0.83, 0.44 and 0.86, and 0.61 and 1.00 for DSC, PPV, and the S metric, respectively. Examples of agreement limits were provided to show how the software could be used to evaluate a new algorithm against the existing state‐of‐the art.Conclusions PETASset provides a platform that allows standardizing the evaluation and comparison of different PET‐AS methods on a wide range of PET datasets. The developed platform will be available to users willing to evaluate their PET‐AS methods and contribute with more evaluation datasets.

show abstract

“…UCLPTLU11: 10 clinical PET/CT lung cases, with two PET scans corresponding to different spatial sampling, i.e., different voxel sizes.…”

Section: Resultsmentioning

confidence: 99%

Toward a standard for the evaluation of PET‐Auto‐Segmentation methods following the recommendations of AAPM task group No. 211: Requirements and implementation

et al. 2017

View full text Add to dashboard Cite

show abstract

“…In addition, deformations of lungs must also be better considered in histological measurements. Note that it is indeed possible to obtain more accurate measurements and significance by taking into account the microscopic spread, the entire histological volume (delineations on three dimensions), and better consideration of lung deformations through a manner similar to studies already cited 8 , 19 , 22 …”

Section: Discussionmentioning

confidence: 95%

“…Histological data are used only for validation and comparison of segmentation techniques 8 , 19 , 22 . Furthermore, there is no study that adjusts the threshold function by using histological data.…”

Section: Introductionmentioning

confidence: 99%

New strategy for automatic tumor segmentation by adaptive thresholding on PET/CT images

Moussallem

Valette

Traverse-Gléhen

et al. 2012

J Applied Clin Med Phys

View full text Add to dashboard Cite

Tumor delineation is a critical aspect in radiotherapy treatment planning and is usually performed with the anatomical images of a computed tomography (CT) scan. For non‐small cell lung cancer, it has been recommended to use functional positron emission tomography (PET) images to take into account the biological target characteristics. However, today, there is no satisfactory segmentation technique for PET images in clinical applications. In the present study, a solution to this problem is proposed. The development of the segmentation technique is based on the threshold's adjustment directly from patients, rather than from phantoms. To this end, two references were chosen: measurements performed on CT images of the selected lesions, and histological measurements of surgically removed tumors. The inclusion and exclusion criteria were chosen to produce references that are assumed to have measured tumor sizes equal to the true in vivo tumor sizes. In total, for the two references, 65 lung lesions of 54 patients referred for FDG‐PET/CT exams were selected. For validation, measurements of segmented lesions on PET images using this technique were also compared to CT and histological measurements. For lesions greater than 20 mm, our segmentation technique showed a good estimation of histological measurements (mean difference between measured and calculated data equal to −0.8±9.0%) and an acceptable estimation of CT measurements. For lesions smaller than or equal to 20 mm, the method showed disagreement with the measurements derived from histological or CT data. This novel segmentation technique shows high accuracy for the lesions with largest axes between 2 and 4.5 cm. However, it does not correctly evaluate smaller lesions, likely due to the partial volume effect and/or respiratory motions.PACS numbers: 87.53.Bn, 87.53.Kn, 87.55.D, 87.57.nm, 87.57.U

show abstract

“…On the other hand the number of reported prospective studies is limited. Wanet et al [52] reported on the study carried on to validate a gradient-based segmentation method for GTV delineation on FDG-PET in NSCLC through surgical specimen, and to compare the results to other PET threshold-based approaches and CT. They concluded that FDG-PET improved the GTV definition in NSCLC when the primary tumor was surrounded by modifications of the lung parenchyma.…”

Section: Head and Neck Patientsmentioning

confidence: 99%

Towards Biological Target Volumes Definition for Radiotherapy Treatment Planning: Quo Vadis PET/CT?

Dević¹

2013

J Nucl Med Radiat Ther

View full text Add to dashboard Cite

IntroductionRadiotherapy treatment planning (RTP) over the last few decades has been based on anatomical targets, namely gross tumor volume (GTV) and from it derived clinical target volume (CTV) as well as the planning target volume (PTV). Owing to its superb spatial reproducibility and the ability to provide the information on electron density (useful for heterogeneity corrections), computed tomography (CT) was, and it still represents, the backbone of modern/high technology radiotherapy treatment planning. The lack of sufficient soft tissue contrast in CT resulted in the incorporation of other imaging methods, such as the magnetic resonance imaging (MRI), into the target definition through the process of image co-registration (sometimes incorrectly termed as image fusion). Whereas the MRI has widely contributed to a better definition of the GTV, [1] which represents an anatomical volume, functional information has not been readily available in the framework of conformal 3D treatment planning and delivery in radiotherapy until recently. In addition, it has been widely accepted that a homogeneous dose delivery to the PTV is the standard of care one should pursue to achieve the best local tumor control.Integration of positron emission tomography (PET) and computed tomography (CT) scanners [2][3][4][5] introduced a new dimension in nuclear medicine by combining functional and anatomical imaging in one machine: the PET/CT scanner. Main advantages of PET/CT scanners are:9 Improved quality of reconstructed PET images with the use of a CT map for attenuation correction of emission PET scans 9 Decrease of about half of the PET acquisition time compared to the previous generation of PET scanners, which used an external radioactive source to acquire transmission scan for attenuation correction. In addition, new faster scintillation materials have also contributed to the shortening of the scanning time 9 The combined medical imaging modality is likely helping management of radiotherapy patients 9 Better understanding of tumor metabolic activity spatial localization by the ability to map the distribution of a specific radiopharmaceutical in co-registered PET/CT images, despite the relatively poor spatial resolution of PET image [6,7].With an increased access to PET/CT information and an apparent appreciation that different sections of the tumor functionally do not behave uniformly, radiation oncologists started to contemplate a change in the traditional concept of uniform dose to the PTV delivery. Instead, a notion of biological targeting and dose painting has come into the play. The first question that comes to our attention is how to define the biological target volumes (BTV) and what do they represent? Ten years after the introduction of the PET/CT scanners into the radiation oncology community, target delineation in radiotherapy treatment planning using FDG-PET/CT scans still has a lot of controversy. The aim of this article is to review the limitations of the current methods for the incorporation of FDG based PET/CT ...

show abstract

Gradient-based delineation of the primary GTV on FDG-PET in non-small cell lung cancer: A comparison with threshold-based approaches, CT and surgical specimens

Cited by 149 publications

References 65 publications

Toward a standard for the evaluation of PET‐Auto‐Segmentation methods following the recommendations of AAPM task group No. 211: Requirements and implementation

Toward a standard for the evaluation of PET‐Auto‐Segmentation methods following the recommendations of AAPM task group No. 211: Requirements and implementation

New strategy for automatic tumor segmentation by adaptive thresholding on PET/CT images

Towards Biological Target Volumes Definition for Radiotherapy Treatment Planning: Quo Vadis PET/CT?

Contact Info

Product

Resources

About