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

Abstract

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

Vision 20/20: Perspectives on automated image segmentation for radiotherapy

“…Among the methods which do not use prior-knowledge for segmentation, region based methods such as adaptive thresholding 1 and graph cuts 2 as well as edge detection based methods, e.g., watershed segmentation 3 have been used for radiotherapy planning. 4,5 Moreover, different types of deformable models 6 such as geodesic active contours 7 have been applied. 8 In order to take advantage of the flexibility of these methods and at the same time compensate their defi-ciency of using prior-knowledge, especially approaches based on graph cuts and deformable models are often used in combination with atlas-or model-based segmentation methods in hybrid approaches (see Sec.…”

Preprocessing of 18F-DMFP-PET Data Based on Hidden Markov Random Fields and the Gaussian Distribution

“…Segmentation is common in studies that use structural data but it has been also used for functional data. In Moussallem et al ( 2012 ) the authors used a threshold (adjusted by an ad hoc function) to segment 18 F-FDG-PET data in order to delimit tumors. A more sophisticated approach for the same purpose was demonstrated in Li et al ( 2017 ).…”

Radiotherapy Planning

“…77,78 Determining which threshold or segmentation method should be used for delineating the PET GTV for accurate target volume definition for lung cancer continues to be debated. 79 In a study by Biehl and colleagues, 80 using thresholds of 40% and 20% underestimated the CT-based GTV for 80% and 70% of lesions, respectively, such that they did not conclude that any single threshold criteria for delineating PET/GTV provided an accurate target volume definition.…”