Comparative Study With New Accuracy Metrics for Target Volume Contouring in PET Image Guided Radiation Therapy

Abstract

The impact of positron emission tomography (PET) on radiation therapy is held back by poor methods of defining functional volumes of interest. Many new software tools are being proposed for contouring target volumes but the different approaches are not adequately compared and their accuracy is poorly evaluated due to the ill-definition of ground truth. This paper compares the largest cohort to date of established, emerging and proposed PET contouring methods, in terms of accuracy and variability. We emphasize spatial accuracy and present a new metric that addresses the lack of unique ground truth. Thirty methods are used at 13 different institutions to contour functional volumes of interest in clinical PET/CT and a custom-built PET phantom representing typical problems in image guided radiotherapy. Contouring methods are grouped according to algorithmic type, level of interactivity and how they exploit structural information in hybrid images. Experiments reveal benefits of high levels of user interaction, as well as simultaneous visualization of CT images and PET gradients to guide interactive procedures. Method-wise evaluation identifies the danger of over-automation and the value of prior knowledge built into an algorithm.

Hybrid positron emission tomography segmentation of heterogeneous lung tumors using 3D Slicer: improved GrowCut algorithm with threshold initialization

“…It has been argued that the clinicians usually outperform computer algorithms in the high-level task of tumor recognition. 35 This was our motivation to use manual segmentation as the gold standard to validate computerized image segmentation techniques in the absence of the surgical specimen of the tumor that serves as the gold standard. 36 Due to practical difficulties in finding more experienced clinicians in contouring lung lesions based on PET imaging, we had to use a single clinician-defined volume for validation.…”

Molecular Imaging to Plan Radiotherapy and Evaluate Its Efficacy

“…Numerous advanced automatic and semiautomatic PET segmentation algorithms have been developed (43,44). Broadly, these can be categorized as iterative/adaptive methods, statistical modeling methods, machine learning-based methods, and image filter-based methods (e.g., using gradients or texture features).…”

“…Currently, it remains unclear which methods perform best and how best to assess the performance of different algorithms. Various performance evaluation methods have been developed for testing segmentation algorithms (44,45). It is recommended that institutions thoroughly evaluate segmentation algorithms, including any tuning parameters, and benchmark their performance against both phantom and clinical images before clinical implementation.…”

Computerized PET/CT image analysis in the evaluation of tumour response to therapy

“…The Turku PET symposium organized a challenge to delineate tumours on PET images 35 (http://www.turkupetcentre.net/ PET_symposium_XII_software_session/ContouringChallengeResults/ index.php) using two phantoms and three head and neck tumours. 13 groups presented their methods that included manual contouring, thresholding, region growing, watershed, gradient based, pipeline (multistep) and graph based (multimodality).…”